Compare Biotech Products

1849 bio designs microbes enabling cheap metal extraction allowing miners to unlock value from low quality copper and gold ores. Surprisingly, the mining industry is one of the largest scale users of biotech in the world with biomining processes accounting for ~1% of global copper production. Biomining is ultra-low cost, running around ~$1/ton of ore vs ~$7/ton for conventional processes. Unfortunately, while biomining is cheap, it can’t be applied to over 80% of copper ores, leaving vast resources without profitable extraction methods. An estimated ~$800B of copper sit today in waste materials and stockpiles with negative unit economics. While a great deal of effort has been spent on optimizing microbial metal extraction processes, very little effort has been spent on optimizing the microbes themselves. To change that, we’re creating new biotech tools and platforms applied directly to the types of biology most relevant to miners. This enables us to develop new microbes and tackle some of the most difficult problems in biomining, unlocking billions in value from unprofitable resources while being more environmentally friendly than conventional processes. We’re world class microbial engineers. We met while doing our PhDs in synthetic biology, where we spent our time applying and developing the most advanced bioengineering technologies to engineer living cells. 

SynsoryBio is creating next generation, protein therapeutics that sense where they are in the body and only activate at diseased tissue. This technology platform has the potential to expand the therapeutic window of highly potent drugs and apply to many diseases such as cancer and autoimmune disorders.

1849 bio designs microbes enabling cheap metal extraction allowing miners to unlock value from low quality copper and gold ores. Surprisingly, the mining industry is one of the largest scale users of biotech in the world with biomining processes accounting for ~1% of global copper production. Biomining is ultra-low cost, running around ~$1/ton of ore vs ~$7/ton for conventional processes. Unfortunately, while biomining is cheap, it can’t be applied to over 80% of copper ores, leaving vast resources without profitable extraction methods. An estimated ~$800B of copper sit today in waste materials and stockpiles with negative unit economics. While a great deal of effort has been spent on optimizing microbial metal extraction processes, very little effort has been spent on optimizing the microbes themselves. To change that, we’re creating new biotech tools and platforms applied directly to the types of biology most relevant to miners. This enables us to develop new microbes and tackle some of the most difficult problems in biomining, unlocking billions in value from unprofitable resources while being more environmentally friendly than conventional processes. We’re world class microbial engineers. We met while doing our PhDs in synthetic biology, where we spent our time applying and developing the most advanced bioengineering technologies to engineer living cells. 

Angstrom AI builds GenAI-based molecular simulations to substitute wet lab experiments in the pre-clinical drug development pipeline. We are a team of 2 PhD's and 2 Professors from the University of Cambridge who decided to start a company together after we realised how to combine breakthoughs in our research in quantum-accurate models of physics and generative AI models. Our Biotech/Pharma clients can verify the efficacy and safety of new drug candidates using our computer simulations, which match the accuracy of wet lab experiments, but are over 100x faster. We achieve this accuracy by constraining our genAI-based simulations to obey the laws of physics, avoiding the hallucinations seen in other GenAI technologies. Since joining YC, Angstrom AI has developed the first physically accurate gen-AI based simulation of multiple molecules interacting. We have published the first molecule water solubility results with accuracy within the error range of wet lab experiments. We have also kicked-off a 150K pilot project with a pharma company to apply our tech to estimating solubility in their drug development pipeline.

1849 bio designs microbes enabling cheap metal extraction allowing miners to unlock value from low quality copper and gold ores. Surprisingly, the mining industry is one of the largest scale users of biotech in the world with biomining processes accounting for ~1% of global copper production. Biomining is ultra-low cost, running around ~$1/ton of ore vs ~$7/ton for conventional processes. Unfortunately, while biomining is cheap, it can’t be applied to over 80% of copper ores, leaving vast resources without profitable extraction methods. An estimated ~$800B of copper sit today in waste materials and stockpiles with negative unit economics. While a great deal of effort has been spent on optimizing microbial metal extraction processes, very little effort has been spent on optimizing the microbes themselves. To change that, we’re creating new biotech tools and platforms applied directly to the types of biology most relevant to miners. This enables us to develop new microbes and tackle some of the most difficult problems in biomining, unlocking billions in value from unprofitable resources while being more environmentally friendly than conventional processes. We’re world class microbial engineers. We met while doing our PhDs in synthetic biology, where we spent our time applying and developing the most advanced bioengineering technologies to engineer living cells. 

Yoneda Labs provides software to help chemists optimise reactions. When chemists make a drug or a material, we help them figure out the best reaction parameters such as temperature, concentration and catalyst. When Jan was working at chemical labs, he experienced the struggle of spending weeks guessing reaction conditions. We then started experimenting with ML to speed up the process. Now, as a team of three friends from the University of Cambridge, we’ve spent the last month combining our domain expertise in Computer Science, Machine Learning and Chemistry to develop state of the art models for reaction optimisation. Although ML is becoming well established in other fields, current chemical models generalise poorly and require lots of programming experience. We make our models easily accessible to chemists in the lab. Finding the right conditions quickly allows pharmaceutical companies to test more drugs, and finding better optima makes manufacturing process cheaper and more environmentally friendly.

1849 bio designs microbes enabling cheap metal extraction allowing miners to unlock value from low quality copper and gold ores. Surprisingly, the mining industry is one of the largest scale users of biotech in the world with biomining processes accounting for ~1% of global copper production. Biomining is ultra-low cost, running around ~$1/ton of ore vs ~$7/ton for conventional processes. Unfortunately, while biomining is cheap, it can’t be applied to over 80% of copper ores, leaving vast resources without profitable extraction methods. An estimated ~$800B of copper sit today in waste materials and stockpiles with negative unit economics. While a great deal of effort has been spent on optimizing microbial metal extraction processes, very little effort has been spent on optimizing the microbes themselves. To change that, we’re creating new biotech tools and platforms applied directly to the types of biology most relevant to miners. This enables us to develop new microbes and tackle some of the most difficult problems in biomining, unlocking billions in value from unprofitable resources while being more environmentally friendly than conventional processes. We’re world class microbial engineers. We met while doing our PhDs in synthetic biology, where we spent our time applying and developing the most advanced bioengineering technologies to engineer living cells. 

You can think of Stempad as a Notion for science. It is the world's first true pen-and-paper alternative to fast scientific writing and collaborating. Quickly switch between different forms of technical visualization with the ease of a whiteboard and the convenience of your keyboard. Stempad allows you to share your work, collaborate in real time, store your data, annotate, write papers, plan, takes notes, create presentations, and so much more. Our vision is to make it easier and faster for students and scientists to digitize and share their scientific ideas.

1849 bio designs microbes enabling cheap metal extraction allowing miners to unlock value from low quality copper and gold ores. Surprisingly, the mining industry is one of the largest scale users of biotech in the world with biomining processes accounting for ~1% of global copper production. Biomining is ultra-low cost, running around ~$1/ton of ore vs ~$7/ton for conventional processes. Unfortunately, while biomining is cheap, it can’t be applied to over 80% of copper ores, leaving vast resources without profitable extraction methods. An estimated ~$800B of copper sit today in waste materials and stockpiles with negative unit economics. While a great deal of effort has been spent on optimizing microbial metal extraction processes, very little effort has been spent on optimizing the microbes themselves. To change that, we’re creating new biotech tools and platforms applied directly to the types of biology most relevant to miners. This enables us to develop new microbes and tackle some of the most difficult problems in biomining, unlocking billions in value from unprofitable resources while being more environmentally friendly than conventional processes. We’re world class microbial engineers. We met while doing our PhDs in synthetic biology, where we spent our time applying and developing the most advanced bioengineering technologies to engineer living cells. 

Artos is an AI-based document-drafting platform that helps life sciences companies turn their data into critical documents in minutes. These submissions currently take months and are the final hurdle before life sciences companies are allowed to sell their product.

1849 bio designs microbes enabling cheap metal extraction allowing miners to unlock value from low quality copper and gold ores. Surprisingly, the mining industry is one of the largest scale users of biotech in the world with biomining processes accounting for ~1% of global copper production. Biomining is ultra-low cost, running around ~$1/ton of ore vs ~$7/ton for conventional processes. Unfortunately, while biomining is cheap, it can’t be applied to over 80% of copper ores, leaving vast resources without profitable extraction methods. An estimated ~$800B of copper sit today in waste materials and stockpiles with negative unit economics. While a great deal of effort has been spent on optimizing microbial metal extraction processes, very little effort has been spent on optimizing the microbes themselves. To change that, we’re creating new biotech tools and platforms applied directly to the types of biology most relevant to miners. This enables us to develop new microbes and tackle some of the most difficult problems in biomining, unlocking billions in value from unprofitable resources while being more environmentally friendly than conventional processes. We’re world class microbial engineers. We met while doing our PhDs in synthetic biology, where we spent our time applying and developing the most advanced bioengineering technologies to engineer living cells. 

We are developing cancer therapeutics using small molecules that inhibit immune suppression. Our drugs engage the immune system to aggressively fight tumors. Our therapeutic portfolio addresses a range of solid tumors, starting with mesothelioma.

1849 bio designs microbes enabling cheap metal extraction allowing miners to unlock value from low quality copper and gold ores. Surprisingly, the mining industry is one of the largest scale users of biotech in the world with biomining processes accounting for ~1% of global copper production. Biomining is ultra-low cost, running around ~$1/ton of ore vs ~$7/ton for conventional processes. Unfortunately, while biomining is cheap, it can’t be applied to over 80% of copper ores, leaving vast resources without profitable extraction methods. An estimated ~$800B of copper sit today in waste materials and stockpiles with negative unit economics. While a great deal of effort has been spent on optimizing microbial metal extraction processes, very little effort has been spent on optimizing the microbes themselves. To change that, we’re creating new biotech tools and platforms applied directly to the types of biology most relevant to miners. This enables us to develop new microbes and tackle some of the most difficult problems in biomining, unlocking billions in value from unprofitable resources while being more environmentally friendly than conventional processes. We’re world class microbial engineers. We met while doing our PhDs in synthetic biology, where we spent our time applying and developing the most advanced bioengineering technologies to engineer living cells. 

We are building the next generation of deep-learning models for enzyme design to slash the cost of chemical manufacturing. The $6 trillion chemical industry is flawed: It produces 20% of industrial greenhouse gases, and is responsible for 15% of global energy usage. Enzymes offer a far more sustainable alternative to chemical synthesis and have already revolutionised how a select few chemicals are produced. The problem is each enzyme takes years of trial and error to develop. Our enzyme models learn the principles of catalysis, allowing us to design enzymes for each reaction, in days not years. We currently have $4.3M of LOIs and have completed our first $20k contract.

1849 bio designs microbes enabling cheap metal extraction allowing miners to unlock value from low quality copper and gold ores. Surprisingly, the mining industry is one of the largest scale users of biotech in the world with biomining processes accounting for ~1% of global copper production. Biomining is ultra-low cost, running around ~$1/ton of ore vs ~$7/ton for conventional processes. Unfortunately, while biomining is cheap, it can’t be applied to over 80% of copper ores, leaving vast resources without profitable extraction methods. An estimated ~$800B of copper sit today in waste materials and stockpiles with negative unit economics. While a great deal of effort has been spent on optimizing microbial metal extraction processes, very little effort has been spent on optimizing the microbes themselves. To change that, we’re creating new biotech tools and platforms applied directly to the types of biology most relevant to miners. This enables us to develop new microbes and tackle some of the most difficult problems in biomining, unlocking billions in value from unprofitable resources while being more environmentally friendly than conventional processes. We’re world class microbial engineers. We met while doing our PhDs in synthetic biology, where we spent our time applying and developing the most advanced bioengineering technologies to engineer living cells. 

Finding new cures requires seeing what and where the abnormal molecules are in a diseased tissue, but current tools see less than 1% of those molecules. Biocartesian combines microscopy and new chemistries to see 50X more, offering unprecedented insights into disease biology and new therapies.

1849 bio designs microbes enabling cheap metal extraction allowing miners to unlock value from low quality copper and gold ores. Surprisingly, the mining industry is one of the largest scale users of biotech in the world with biomining processes accounting for ~1% of global copper production. Biomining is ultra-low cost, running around ~$1/ton of ore vs ~$7/ton for conventional processes. Unfortunately, while biomining is cheap, it can’t be applied to over 80% of copper ores, leaving vast resources without profitable extraction methods. An estimated ~$800B of copper sit today in waste materials and stockpiles with negative unit economics. While a great deal of effort has been spent on optimizing microbial metal extraction processes, very little effort has been spent on optimizing the microbes themselves. To change that, we’re creating new biotech tools and platforms applied directly to the types of biology most relevant to miners. This enables us to develop new microbes and tackle some of the most difficult problems in biomining, unlocking billions in value from unprofitable resources while being more environmentally friendly than conventional processes. We’re world class microbial engineers. We met while doing our PhDs in synthetic biology, where we spent our time applying and developing the most advanced bioengineering technologies to engineer living cells. 

🦠🤖 We use our computational models to make next-generation antibiotics that outcompete bacterial evolution and precisely target pathogenic bacteria, without harming good microbes or human cells. ☠️ Current antibiotics stop working because bacteria evolve resistance to them. This makes drug-resistant bacteria a looming global health crisis - already killing more people than malaria and AIDS and it is getting exponentially worse 📈. 🧬 Our approach leverages co-evolutionary protein-protein interaction datasets combined with AI to forecast bacterial mutations and create ‘future-proof’ antibiotics, addressing antibiotic resistance before it develops. This changes the game for how frequently society will need to make new antibiotics and how long our new antibiotics will be able to treat patients 👩‍⚕️. We are a team of biochemists and evolutionary biologists who met at the University of Oxford.

1849 bio designs microbes enabling cheap metal extraction allowing miners to unlock value from low quality copper and gold ores. Surprisingly, the mining industry is one of the largest scale users of biotech in the world with biomining processes accounting for ~1% of global copper production. Biomining is ultra-low cost, running around ~$1/ton of ore vs ~$7/ton for conventional processes. Unfortunately, while biomining is cheap, it can’t be applied to over 80% of copper ores, leaving vast resources without profitable extraction methods. An estimated ~$800B of copper sit today in waste materials and stockpiles with negative unit economics. While a great deal of effort has been spent on optimizing microbial metal extraction processes, very little effort has been spent on optimizing the microbes themselves. To change that, we’re creating new biotech tools and platforms applied directly to the types of biology most relevant to miners. This enables us to develop new microbes and tackle some of the most difficult problems in biomining, unlocking billions in value from unprofitable resources while being more environmentally friendly than conventional processes. We’re world class microbial engineers. We met while doing our PhDs in synthetic biology, where we spent our time applying and developing the most advanced bioengineering technologies to engineer living cells. 

Metofico provides a no-code data analysis tool tailored for the life sciences. Our platform enables life scientists to analyse complex/massive datasets and extract necessary insights without needing advanced programming skills. This accessibility helps both researchers new to data science and experts save months of work. Metofico aims to be the leading centralized platform for data analysis in life science research, covering a wide range of applications from brain activity analysis (like photometry and EEG) to AI-powered detection and tracking of research animals. Our vision is to accelerate research processes and enhance the quality of research outputs across the board. By streamlining complex data analysis and making it more accessible, we’re committed to driving forward scientific discoveries and innovation.

1849 bio designs microbes enabling cheap metal extraction allowing miners to unlock value from low quality copper and gold ores. Surprisingly, the mining industry is one of the largest scale users of biotech in the world with biomining processes accounting for ~1% of global copper production. Biomining is ultra-low cost, running around ~$1/ton of ore vs ~$7/ton for conventional processes. Unfortunately, while biomining is cheap, it can’t be applied to over 80% of copper ores, leaving vast resources without profitable extraction methods. An estimated ~$800B of copper sit today in waste materials and stockpiles with negative unit economics. While a great deal of effort has been spent on optimizing microbial metal extraction processes, very little effort has been spent on optimizing the microbes themselves. To change that, we’re creating new biotech tools and platforms applied directly to the types of biology most relevant to miners. This enables us to develop new microbes and tackle some of the most difficult problems in biomining, unlocking billions in value from unprofitable resources while being more environmentally friendly than conventional processes. We’re world class microbial engineers. We met while doing our PhDs in synthetic biology, where we spent our time applying and developing the most advanced bioengineering technologies to engineer living cells. 

Proteins power everything from the cells in your body to creating materials you rely on every day, but until now, we’ve been forced to discover their functions by trial and error. Designing a new therapeutic can take decades and billions of dollars, and even our best industrial catalysts work at a snail’s pace compared to their theoretical optimums. Anthrogen is changing that. By training massive AI foundation models on protein sequences and structures, we’ve unlocked the ability to generate, on demand, completely novel molecular machines with atomic-level precision. Simply describe the function you need, and our platform imagines the peptide or protein that will deliver it. We're building models to speed up billions of years of evolution into the span of an afternoon's worth of compute. The result? New-to-nature therapies, ultra-efficient catalysts for sustainable manufacturing, and a whole new frontier of molecular innovation, designed as precisely as any cutting-edge aircraft or microchip.

1849 bio designs microbes enabling cheap metal extraction allowing miners to unlock value from low quality copper and gold ores. Surprisingly, the mining industry is one of the largest scale users of biotech in the world with biomining processes accounting for ~1% of global copper production. Biomining is ultra-low cost, running around ~$1/ton of ore vs ~$7/ton for conventional processes. Unfortunately, while biomining is cheap, it can’t be applied to over 80% of copper ores, leaving vast resources without profitable extraction methods. An estimated ~$800B of copper sit today in waste materials and stockpiles with negative unit economics. While a great deal of effort has been spent on optimizing microbial metal extraction processes, very little effort has been spent on optimizing the microbes themselves. To change that, we’re creating new biotech tools and platforms applied directly to the types of biology most relevant to miners. This enables us to develop new microbes and tackle some of the most difficult problems in biomining, unlocking billions in value from unprofitable resources while being more environmentally friendly than conventional processes. We’re world class microbial engineers. We met while doing our PhDs in synthetic biology, where we spent our time applying and developing the most advanced bioengineering technologies to engineer living cells. 

Reticular helps pharma companies discover drugs with AI models like AlphaFold by making them steerable, just like you can prompt LLMs. Today, limited validation data means companies spend millions on failed experiments trying to steer these models through trial and error. We’re piloting our AI interpretability technology with early-stage biotechs and scaling rapidly. Just a week after our pivot, we identified the first interpretable features ever found in protein models, allowing precise control over biological functions. Nithin and John met competing in Biology Olympiads before spending 4 years as roommates at MIT publishing ML/bio research in NeurIPS and Nature. We believe biological models encode far more information than anyone is currently using - our goal is to unlock this potential.

1849 bio designs microbes enabling cheap metal extraction allowing miners to unlock value from low quality copper and gold ores. Surprisingly, the mining industry is one of the largest scale users of biotech in the world with biomining processes accounting for ~1% of global copper production. Biomining is ultra-low cost, running around ~$1/ton of ore vs ~$7/ton for conventional processes. Unfortunately, while biomining is cheap, it can’t be applied to over 80% of copper ores, leaving vast resources without profitable extraction methods. An estimated ~$800B of copper sit today in waste materials and stockpiles with negative unit economics. While a great deal of effort has been spent on optimizing microbial metal extraction processes, very little effort has been spent on optimizing the microbes themselves. To change that, we’re creating new biotech tools and platforms applied directly to the types of biology most relevant to miners. This enables us to develop new microbes and tackle some of the most difficult problems in biomining, unlocking billions in value from unprofitable resources while being more environmentally friendly than conventional processes. We’re world class microbial engineers. We met while doing our PhDs in synthetic biology, where we spent our time applying and developing the most advanced bioengineering technologies to engineer living cells. 

The main document in a clinical trial is the study protocol. At large companies, floors of people use the protocol to create the study data collection forms, clinical database design, error checks, analysis code, and data transformation mappings. We use AI to automate the process of creating everything from the protocol, saving not only spend on headcount but also months of time which can translate to up to $27M in direct costs + lost revenue saved for a single phase 3 trial.

1849 bio designs microbes enabling cheap metal extraction allowing miners to unlock value from low quality copper and gold ores. Surprisingly, the mining industry is one of the largest scale users of biotech in the world with biomining processes accounting for ~1% of global copper production. Biomining is ultra-low cost, running around ~$1/ton of ore vs ~$7/ton for conventional processes. Unfortunately, while biomining is cheap, it can’t be applied to over 80% of copper ores, leaving vast resources without profitable extraction methods. An estimated ~$800B of copper sit today in waste materials and stockpiles with negative unit economics. While a great deal of effort has been spent on optimizing microbial metal extraction processes, very little effort has been spent on optimizing the microbes themselves. To change that, we’re creating new biotech tools and platforms applied directly to the types of biology most relevant to miners. This enables us to develop new microbes and tackle some of the most difficult problems in biomining, unlocking billions in value from unprofitable resources while being more environmentally friendly than conventional processes. We’re world class microbial engineers. We met while doing our PhDs in synthetic biology, where we spent our time applying and developing the most advanced bioengineering technologies to engineer living cells. 

Junction Bioscience is building an autonomous AI scientist to navigate the discovery of transformative medicines. Our scientific hypothesis engine iterates upon breakthrough chemistry from the laboratory to achieve clarity and control over the molecular basis of disease. We focus on the intersection of neuroinflammation and immunology where uncommon molecular insights position us to develop best-in-class therapies for millions of patients in need.

1849 bio designs microbes enabling cheap metal extraction allowing miners to unlock value from low quality copper and gold ores. Surprisingly, the mining industry is one of the largest scale users of biotech in the world with biomining processes accounting for ~1% of global copper production. Biomining is ultra-low cost, running around ~$1/ton of ore vs ~$7/ton for conventional processes. Unfortunately, while biomining is cheap, it can’t be applied to over 80% of copper ores, leaving vast resources without profitable extraction methods. An estimated ~$800B of copper sit today in waste materials and stockpiles with negative unit economics. While a great deal of effort has been spent on optimizing microbial metal extraction processes, very little effort has been spent on optimizing the microbes themselves. To change that, we’re creating new biotech tools and platforms applied directly to the types of biology most relevant to miners. This enables us to develop new microbes and tackle some of the most difficult problems in biomining, unlocking billions in value from unprofitable resources while being more environmentally friendly than conventional processes. We’re world class microbial engineers. We met while doing our PhDs in synthetic biology, where we spent our time applying and developing the most advanced bioengineering technologies to engineer living cells. 

Our Mission: We aim to accelerate and automate chemical process development by equipping wet-lab chemists with the power of data-driven optimization and robotic execution of experiments. The Problem: The discovery of novel pharmaceuticals is one of our most important weapons in fighting disease. However, the drug development pipeline is often held up for many months during the design of chemical processes to manufacture these drugs at scale, delaying FDA trials and lengthening the time until drug launch. Designing chemical processes involves the identification of suitable parameters such as catalyst/temperature/solvent. Currently process development is often done via tedious trial-and-error experimentation (slow) or exhaustive screening (expensive and wasteful). Our Approach: In our research, we have developed algorithms for chemical process optimization, which leverage transfer learning and Bayesian optimization. We validated the algorithms in the wet lab, showing an up to 95% reduction in required experiments and cost compared to exhaustive screening. We have made our approaches accessible to chemists through our user-friendly no-code software platform and to automated laboratory equipment with our API.

1849 bio designs microbes enabling cheap metal extraction allowing miners to unlock value from low quality copper and gold ores. Surprisingly, the mining industry is one of the largest scale users of biotech in the world with biomining processes accounting for ~1% of global copper production. Biomining is ultra-low cost, running around ~$1/ton of ore vs ~$7/ton for conventional processes. Unfortunately, while biomining is cheap, it can’t be applied to over 80% of copper ores, leaving vast resources without profitable extraction methods. An estimated ~$800B of copper sit today in waste materials and stockpiles with negative unit economics. While a great deal of effort has been spent on optimizing microbial metal extraction processes, very little effort has been spent on optimizing the microbes themselves. To change that, we’re creating new biotech tools and platforms applied directly to the types of biology most relevant to miners. This enables us to develop new microbes and tackle some of the most difficult problems in biomining, unlocking billions in value from unprofitable resources while being more environmentally friendly than conventional processes. We’re world class microbial engineers. We met while doing our PhDs in synthetic biology, where we spent our time applying and developing the most advanced bioengineering technologies to engineer living cells. 

Argon AI is a platform where biopharma and life sciences professionals can execute complex and data driven workflows using natural language. We help professionals get thorough answers to questions about clinical trials, existing treatments, healthcare landscape, and the competitive market in minutes rather than months. Prior to starting Argon, Samy was responsible for Flatiron Health’s (Roche) first data analytics project which eventually led to the start of the Flatiron Services business unit. There, he saw first-hand the heavily manual process that biopharma companies struggle through to get the insights they need to drive forward their drug development programs. He also helped close over $6M+ in ARR and is an expert in enterprise pharma sales. Cyrus previously led engineering teams and built 0 to 1 across pre-seed and unicorn startups, managed mission-critical trade generation systems at Bridgewater, and held AI advisory roles at various startups. Cyrus has a duel degree in EE and CS from USC. Breakthroughs in AI present an opportunity to reinvent biopharma and life science workflows to reduce the time and cost of bringing treatments to patients where delays in bringing a drug to market can cost a pharma company $3M / day.

1849 bio designs microbes enabling cheap metal extraction allowing miners to unlock value from low quality copper and gold ores. Surprisingly, the mining industry is one of the largest scale users of biotech in the world with biomining processes accounting for ~1% of global copper production. Biomining is ultra-low cost, running around ~$1/ton of ore vs ~$7/ton for conventional processes. Unfortunately, while biomining is cheap, it can’t be applied to over 80% of copper ores, leaving vast resources without profitable extraction methods. An estimated ~$800B of copper sit today in waste materials and stockpiles with negative unit economics. While a great deal of effort has been spent on optimizing microbial metal extraction processes, very little effort has been spent on optimizing the microbes themselves. To change that, we’re creating new biotech tools and platforms applied directly to the types of biology most relevant to miners. This enables us to develop new microbes and tackle some of the most difficult problems in biomining, unlocking billions in value from unprofitable resources while being more environmentally friendly than conventional processes. We’re world class microbial engineers. We met while doing our PhDs in synthetic biology, where we spent our time applying and developing the most advanced bioengineering technologies to engineer living cells. 

Design, simulate, and test your proteins 100x faster with the end-to-end no-code platform for protein engineering. Powered by Amina, our AI agent. With Amina, one protein engineer can do the work of 10. Describe what you want to achieve and Amina will handle everything else, from research and design to simulation, folding, docking, and protein characterization. It asks clarifying questions if needed, intelligently understands and performs the task, and analyzes your results within the context of your project.

1849 bio designs microbes enabling cheap metal extraction allowing miners to unlock value from low quality copper and gold ores. Surprisingly, the mining industry is one of the largest scale users of biotech in the world with biomining processes accounting for ~1% of global copper production. Biomining is ultra-low cost, running around ~$1/ton of ore vs ~$7/ton for conventional processes. Unfortunately, while biomining is cheap, it can’t be applied to over 80% of copper ores, leaving vast resources without profitable extraction methods. An estimated ~$800B of copper sit today in waste materials and stockpiles with negative unit economics. While a great deal of effort has been spent on optimizing microbial metal extraction processes, very little effort has been spent on optimizing the microbes themselves. To change that, we’re creating new biotech tools and platforms applied directly to the types of biology most relevant to miners. This enables us to develop new microbes and tackle some of the most difficult problems in biomining, unlocking billions in value from unprofitable resources while being more environmentally friendly than conventional processes. We’re world class microbial engineers. We met while doing our PhDs in synthetic biology, where we spent our time applying and developing the most advanced bioengineering technologies to engineer living cells. 

Tamarind Bio is a website and API which allows scientists to use computational biology tools at scale using a simple interface. On Tamarind, scientists can use ML models like AlphaFold to design and simulate molecules by simply selecting inputs instead of or setting up a high performance computing environment or dealing with DevOps. Our tools are used by thousands researchers in large pharma companies, top biotechs, and academic institutions. We currently focus on models in protein design and engineering, including for antibodies/therapeutics and enzymes. Get in touch at [email protected]

1849 bio designs microbes enabling cheap metal extraction allowing miners to unlock value from low quality copper and gold ores. Surprisingly, the mining industry is one of the largest scale users of biotech in the world with biomining processes accounting for ~1% of global copper production. Biomining is ultra-low cost, running around ~$1/ton of ore vs ~$7/ton for conventional processes. Unfortunately, while biomining is cheap, it can’t be applied to over 80% of copper ores, leaving vast resources without profitable extraction methods. An estimated ~$800B of copper sit today in waste materials and stockpiles with negative unit economics. While a great deal of effort has been spent on optimizing microbial metal extraction processes, very little effort has been spent on optimizing the microbes themselves. To change that, we’re creating new biotech tools and platforms applied directly to the types of biology most relevant to miners. This enables us to develop new microbes and tackle some of the most difficult problems in biomining, unlocking billions in value from unprofitable resources while being more environmentally friendly than conventional processes. We’re world class microbial engineers. We met while doing our PhDs in synthetic biology, where we spent our time applying and developing the most advanced bioengineering technologies to engineer living cells. 

Raycaster is the enterprise AI engine for life sciences. From speeding up regulatory approval and manufacturing tech transfer, Raycaster advances the Industry 4.0 initiatives with world's leading life sciences companies.

1849 bio designs microbes enabling cheap metal extraction allowing miners to unlock value from low quality copper and gold ores. Surprisingly, the mining industry is one of the largest scale users of biotech in the world with biomining processes accounting for ~1% of global copper production. Biomining is ultra-low cost, running around ~$1/ton of ore vs ~$7/ton for conventional processes. Unfortunately, while biomining is cheap, it can’t be applied to over 80% of copper ores, leaving vast resources without profitable extraction methods. An estimated ~$800B of copper sit today in waste materials and stockpiles with negative unit economics. While a great deal of effort has been spent on optimizing microbial metal extraction processes, very little effort has been spent on optimizing the microbes themselves. To change that, we’re creating new biotech tools and platforms applied directly to the types of biology most relevant to miners. This enables us to develop new microbes and tackle some of the most difficult problems in biomining, unlocking billions in value from unprofitable resources while being more environmentally friendly than conventional processes. We’re world class microbial engineers. We met while doing our PhDs in synthetic biology, where we spent our time applying and developing the most advanced bioengineering technologies to engineer living cells. 

Kopra Bio makes genetically engineered viruses that teach your immune system to kill cancer using tech we developed at UCSF. We’re making the next Keytruda ($25B/yr cancer drug blockbuster) starting with the most aggressive form of brain cancer, glioblastoma. In the most challenging brain cancer model, we improve survival from 0% with the current FDA approved treatment to 90% with our treatment.

SynsoryBio is creating next generation, protein therapeutics that sense where they are in the body and only activate at diseased tissue. This technology platform has the potential to expand the therapeutic window of highly potent drugs and apply to many diseases such as cancer and autoimmune disorders.

Angstrom AI builds GenAI-based molecular simulations to substitute wet lab experiments in the pre-clinical drug development pipeline. We are a team of 2 PhD's and 2 Professors from the University of Cambridge who decided to start a company together after we realised how to combine breakthoughs in our research in quantum-accurate models of physics and generative AI models. Our Biotech/Pharma clients can verify the efficacy and safety of new drug candidates using our computer simulations, which match the accuracy of wet lab experiments, but are over 100x faster. We achieve this accuracy by constraining our genAI-based simulations to obey the laws of physics, avoiding the hallucinations seen in other GenAI technologies. Since joining YC, Angstrom AI has developed the first physically accurate gen-AI based simulation of multiple molecules interacting. We have published the first molecule water solubility results with accuracy within the error range of wet lab experiments. We have also kicked-off a 150K pilot project with a pharma company to apply our tech to estimating solubility in their drug development pipeline.

SynsoryBio is creating next generation, protein therapeutics that sense where they are in the body and only activate at diseased tissue. This technology platform has the potential to expand the therapeutic window of highly potent drugs and apply to many diseases such as cancer and autoimmune disorders.

Yoneda Labs provides software to help chemists optimise reactions. When chemists make a drug or a material, we help them figure out the best reaction parameters such as temperature, concentration and catalyst. When Jan was working at chemical labs, he experienced the struggle of spending weeks guessing reaction conditions. We then started experimenting with ML to speed up the process. Now, as a team of three friends from the University of Cambridge, we’ve spent the last month combining our domain expertise in Computer Science, Machine Learning and Chemistry to develop state of the art models for reaction optimisation. Although ML is becoming well established in other fields, current chemical models generalise poorly and require lots of programming experience. We make our models easily accessible to chemists in the lab. Finding the right conditions quickly allows pharmaceutical companies to test more drugs, and finding better optima makes manufacturing process cheaper and more environmentally friendly.

SynsoryBio is creating next generation, protein therapeutics that sense where they are in the body and only activate at diseased tissue. This technology platform has the potential to expand the therapeutic window of highly potent drugs and apply to many diseases such as cancer and autoimmune disorders.

You can think of Stempad as a Notion for science. It is the world's first true pen-and-paper alternative to fast scientific writing and collaborating. Quickly switch between different forms of technical visualization with the ease of a whiteboard and the convenience of your keyboard. Stempad allows you to share your work, collaborate in real time, store your data, annotate, write papers, plan, takes notes, create presentations, and so much more. Our vision is to make it easier and faster for students and scientists to digitize and share their scientific ideas.

SynsoryBio is creating next generation, protein therapeutics that sense where they are in the body and only activate at diseased tissue. This technology platform has the potential to expand the therapeutic window of highly potent drugs and apply to many diseases such as cancer and autoimmune disorders.

Artos is an AI-based document-drafting platform that helps life sciences companies turn their data into critical documents in minutes. These submissions currently take months and are the final hurdle before life sciences companies are allowed to sell their product.

SynsoryBio is creating next generation, protein therapeutics that sense where they are in the body and only activate at diseased tissue. This technology platform has the potential to expand the therapeutic window of highly potent drugs and apply to many diseases such as cancer and autoimmune disorders.

We are developing cancer therapeutics using small molecules that inhibit immune suppression. Our drugs engage the immune system to aggressively fight tumors. Our therapeutic portfolio addresses a range of solid tumors, starting with mesothelioma.

SynsoryBio is creating next generation, protein therapeutics that sense where they are in the body and only activate at diseased tissue. This technology platform has the potential to expand the therapeutic window of highly potent drugs and apply to many diseases such as cancer and autoimmune disorders.

We are building the next generation of deep-learning models for enzyme design to slash the cost of chemical manufacturing. The $6 trillion chemical industry is flawed: It produces 20% of industrial greenhouse gases, and is responsible for 15% of global energy usage. Enzymes offer a far more sustainable alternative to chemical synthesis and have already revolutionised how a select few chemicals are produced. The problem is each enzyme takes years of trial and error to develop. Our enzyme models learn the principles of catalysis, allowing us to design enzymes for each reaction, in days not years. We currently have $4.3M of LOIs and have completed our first $20k contract.

SynsoryBio is creating next generation, protein therapeutics that sense where they are in the body and only activate at diseased tissue. This technology platform has the potential to expand the therapeutic window of highly potent drugs and apply to many diseases such as cancer and autoimmune disorders.

Finding new cures requires seeing what and where the abnormal molecules are in a diseased tissue, but current tools see less than 1% of those molecules. Biocartesian combines microscopy and new chemistries to see 50X more, offering unprecedented insights into disease biology and new therapies.

SynsoryBio is creating next generation, protein therapeutics that sense where they are in the body and only activate at diseased tissue. This technology platform has the potential to expand the therapeutic window of highly potent drugs and apply to many diseases such as cancer and autoimmune disorders.

🦠🤖 We use our computational models to make next-generation antibiotics that outcompete bacterial evolution and precisely target pathogenic bacteria, without harming good microbes or human cells. ☠️ Current antibiotics stop working because bacteria evolve resistance to them. This makes drug-resistant bacteria a looming global health crisis - already killing more people than malaria and AIDS and it is getting exponentially worse 📈. 🧬 Our approach leverages co-evolutionary protein-protein interaction datasets combined with AI to forecast bacterial mutations and create ‘future-proof’ antibiotics, addressing antibiotic resistance before it develops. This changes the game for how frequently society will need to make new antibiotics and how long our new antibiotics will be able to treat patients 👩‍⚕️. We are a team of biochemists and evolutionary biologists who met at the University of Oxford.

SynsoryBio is creating next generation, protein therapeutics that sense where they are in the body and only activate at diseased tissue. This technology platform has the potential to expand the therapeutic window of highly potent drugs and apply to many diseases such as cancer and autoimmune disorders.

Metofico provides a no-code data analysis tool tailored for the life sciences. Our platform enables life scientists to analyse complex/massive datasets and extract necessary insights without needing advanced programming skills. This accessibility helps both researchers new to data science and experts save months of work. Metofico aims to be the leading centralized platform for data analysis in life science research, covering a wide range of applications from brain activity analysis (like photometry and EEG) to AI-powered detection and tracking of research animals. Our vision is to accelerate research processes and enhance the quality of research outputs across the board. By streamlining complex data analysis and making it more accessible, we’re committed to driving forward scientific discoveries and innovation.

SynsoryBio is creating next generation, protein therapeutics that sense where they are in the body and only activate at diseased tissue. This technology platform has the potential to expand the therapeutic window of highly potent drugs and apply to many diseases such as cancer and autoimmune disorders.

Proteins power everything from the cells in your body to creating materials you rely on every day, but until now, we’ve been forced to discover their functions by trial and error. Designing a new therapeutic can take decades and billions of dollars, and even our best industrial catalysts work at a snail’s pace compared to their theoretical optimums. Anthrogen is changing that. By training massive AI foundation models on protein sequences and structures, we’ve unlocked the ability to generate, on demand, completely novel molecular machines with atomic-level precision. Simply describe the function you need, and our platform imagines the peptide or protein that will deliver it. We're building models to speed up billions of years of evolution into the span of an afternoon's worth of compute. The result? New-to-nature therapies, ultra-efficient catalysts for sustainable manufacturing, and a whole new frontier of molecular innovation, designed as precisely as any cutting-edge aircraft or microchip.

SynsoryBio is creating next generation, protein therapeutics that sense where they are in the body and only activate at diseased tissue. This technology platform has the potential to expand the therapeutic window of highly potent drugs and apply to many diseases such as cancer and autoimmune disorders.

Reticular helps pharma companies discover drugs with AI models like AlphaFold by making them steerable, just like you can prompt LLMs. Today, limited validation data means companies spend millions on failed experiments trying to steer these models through trial and error. We’re piloting our AI interpretability technology with early-stage biotechs and scaling rapidly. Just a week after our pivot, we identified the first interpretable features ever found in protein models, allowing precise control over biological functions. Nithin and John met competing in Biology Olympiads before spending 4 years as roommates at MIT publishing ML/bio research in NeurIPS and Nature. We believe biological models encode far more information than anyone is currently using - our goal is to unlock this potential.

SynsoryBio is creating next generation, protein therapeutics that sense where they are in the body and only activate at diseased tissue. This technology platform has the potential to expand the therapeutic window of highly potent drugs and apply to many diseases such as cancer and autoimmune disorders.

The main document in a clinical trial is the study protocol. At large companies, floors of people use the protocol to create the study data collection forms, clinical database design, error checks, analysis code, and data transformation mappings. We use AI to automate the process of creating everything from the protocol, saving not only spend on headcount but also months of time which can translate to up to $27M in direct costs + lost revenue saved for a single phase 3 trial.

SynsoryBio is creating next generation, protein therapeutics that sense where they are in the body and only activate at diseased tissue. This technology platform has the potential to expand the therapeutic window of highly potent drugs and apply to many diseases such as cancer and autoimmune disorders.

Junction Bioscience is building an autonomous AI scientist to navigate the discovery of transformative medicines. Our scientific hypothesis engine iterates upon breakthrough chemistry from the laboratory to achieve clarity and control over the molecular basis of disease. We focus on the intersection of neuroinflammation and immunology where uncommon molecular insights position us to develop best-in-class therapies for millions of patients in need.

SynsoryBio is creating next generation, protein therapeutics that sense where they are in the body and only activate at diseased tissue. This technology platform has the potential to expand the therapeutic window of highly potent drugs and apply to many diseases such as cancer and autoimmune disorders.

Our Mission: We aim to accelerate and automate chemical process development by equipping wet-lab chemists with the power of data-driven optimization and robotic execution of experiments. The Problem: The discovery of novel pharmaceuticals is one of our most important weapons in fighting disease. However, the drug development pipeline is often held up for many months during the design of chemical processes to manufacture these drugs at scale, delaying FDA trials and lengthening the time until drug launch. Designing chemical processes involves the identification of suitable parameters such as catalyst/temperature/solvent. Currently process development is often done via tedious trial-and-error experimentation (slow) or exhaustive screening (expensive and wasteful). Our Approach: In our research, we have developed algorithms for chemical process optimization, which leverage transfer learning and Bayesian optimization. We validated the algorithms in the wet lab, showing an up to 95% reduction in required experiments and cost compared to exhaustive screening. We have made our approaches accessible to chemists through our user-friendly no-code software platform and to automated laboratory equipment with our API.

SynsoryBio is creating next generation, protein therapeutics that sense where they are in the body and only activate at diseased tissue. This technology platform has the potential to expand the therapeutic window of highly potent drugs and apply to many diseases such as cancer and autoimmune disorders.

Argon AI is a platform where biopharma and life sciences professionals can execute complex and data driven workflows using natural language. We help professionals get thorough answers to questions about clinical trials, existing treatments, healthcare landscape, and the competitive market in minutes rather than months. Prior to starting Argon, Samy was responsible for Flatiron Health’s (Roche) first data analytics project which eventually led to the start of the Flatiron Services business unit. There, he saw first-hand the heavily manual process that biopharma companies struggle through to get the insights they need to drive forward their drug development programs. He also helped close over $6M+ in ARR and is an expert in enterprise pharma sales. Cyrus previously led engineering teams and built 0 to 1 across pre-seed and unicorn startups, managed mission-critical trade generation systems at Bridgewater, and held AI advisory roles at various startups. Cyrus has a duel degree in EE and CS from USC. Breakthroughs in AI present an opportunity to reinvent biopharma and life science workflows to reduce the time and cost of bringing treatments to patients where delays in bringing a drug to market can cost a pharma company $3M / day.

SynsoryBio is creating next generation, protein therapeutics that sense where they are in the body and only activate at diseased tissue. This technology platform has the potential to expand the therapeutic window of highly potent drugs and apply to many diseases such as cancer and autoimmune disorders.

Design, simulate, and test your proteins 100x faster with the end-to-end no-code platform for protein engineering. Powered by Amina, our AI agent. With Amina, one protein engineer can do the work of 10. Describe what you want to achieve and Amina will handle everything else, from research and design to simulation, folding, docking, and protein characterization. It asks clarifying questions if needed, intelligently understands and performs the task, and analyzes your results within the context of your project.

SynsoryBio is creating next generation, protein therapeutics that sense where they are in the body and only activate at diseased tissue. This technology platform has the potential to expand the therapeutic window of highly potent drugs and apply to many diseases such as cancer and autoimmune disorders.

Tamarind Bio is a website and API which allows scientists to use computational biology tools at scale using a simple interface. On Tamarind, scientists can use ML models like AlphaFold to design and simulate molecules by simply selecting inputs instead of or setting up a high performance computing environment or dealing with DevOps. Our tools are used by thousands researchers in large pharma companies, top biotechs, and academic institutions. We currently focus on models in protein design and engineering, including for antibodies/therapeutics and enzymes. Get in touch at [email protected]

SynsoryBio is creating next generation, protein therapeutics that sense where they are in the body and only activate at diseased tissue. This technology platform has the potential to expand the therapeutic window of highly potent drugs and apply to many diseases such as cancer and autoimmune disorders.

Raycaster is the enterprise AI engine for life sciences. From speeding up regulatory approval and manufacturing tech transfer, Raycaster advances the Industry 4.0 initiatives with world's leading life sciences companies.

SynsoryBio is creating next generation, protein therapeutics that sense where they are in the body and only activate at diseased tissue. This technology platform has the potential to expand the therapeutic window of highly potent drugs and apply to many diseases such as cancer and autoimmune disorders.

Kopra Bio makes genetically engineered viruses that teach your immune system to kill cancer using tech we developed at UCSF. We’re making the next Keytruda ($25B/yr cancer drug blockbuster) starting with the most aggressive form of brain cancer, glioblastoma. In the most challenging brain cancer model, we improve survival from 0% with the current FDA approved treatment to 90% with our treatment.

Angstrom AI builds GenAI-based molecular simulations to substitute wet lab experiments in the pre-clinical drug development pipeline. We are a team of 2 PhD's and 2 Professors from the University of Cambridge who decided to start a company together after we realised how to combine breakthoughs in our research in quantum-accurate models of physics and generative AI models. Our Biotech/Pharma clients can verify the efficacy and safety of new drug candidates using our computer simulations, which match the accuracy of wet lab experiments, but are over 100x faster. We achieve this accuracy by constraining our genAI-based simulations to obey the laws of physics, avoiding the hallucinations seen in other GenAI technologies. Since joining YC, Angstrom AI has developed the first physically accurate gen-AI based simulation of multiple molecules interacting. We have published the first molecule water solubility results with accuracy within the error range of wet lab experiments. We have also kicked-off a 150K pilot project with a pharma company to apply our tech to estimating solubility in their drug development pipeline.

Yoneda Labs provides software to help chemists optimise reactions. When chemists make a drug or a material, we help them figure out the best reaction parameters such as temperature, concentration and catalyst. When Jan was working at chemical labs, he experienced the struggle of spending weeks guessing reaction conditions. We then started experimenting with ML to speed up the process. Now, as a team of three friends from the University of Cambridge, we’ve spent the last month combining our domain expertise in Computer Science, Machine Learning and Chemistry to develop state of the art models for reaction optimisation. Although ML is becoming well established in other fields, current chemical models generalise poorly and require lots of programming experience. We make our models easily accessible to chemists in the lab. Finding the right conditions quickly allows pharmaceutical companies to test more drugs, and finding better optima makes manufacturing process cheaper and more environmentally friendly.

Angstrom AI builds GenAI-based molecular simulations to substitute wet lab experiments in the pre-clinical drug development pipeline. We are a team of 2 PhD's and 2 Professors from the University of Cambridge who decided to start a company together after we realised how to combine breakthoughs in our research in quantum-accurate models of physics and generative AI models. Our Biotech/Pharma clients can verify the efficacy and safety of new drug candidates using our computer simulations, which match the accuracy of wet lab experiments, but are over 100x faster. We achieve this accuracy by constraining our genAI-based simulations to obey the laws of physics, avoiding the hallucinations seen in other GenAI technologies. Since joining YC, Angstrom AI has developed the first physically accurate gen-AI based simulation of multiple molecules interacting. We have published the first molecule water solubility results with accuracy within the error range of wet lab experiments. We have also kicked-off a 150K pilot project with a pharma company to apply our tech to estimating solubility in their drug development pipeline.

You can think of Stempad as a Notion for science. It is the world's first true pen-and-paper alternative to fast scientific writing and collaborating. Quickly switch between different forms of technical visualization with the ease of a whiteboard and the convenience of your keyboard. Stempad allows you to share your work, collaborate in real time, store your data, annotate, write papers, plan, takes notes, create presentations, and so much more. Our vision is to make it easier and faster for students and scientists to digitize and share their scientific ideas.

Angstrom AI builds GenAI-based molecular simulations to substitute wet lab experiments in the pre-clinical drug development pipeline. We are a team of 2 PhD's and 2 Professors from the University of Cambridge who decided to start a company together after we realised how to combine breakthoughs in our research in quantum-accurate models of physics and generative AI models. Our Biotech/Pharma clients can verify the efficacy and safety of new drug candidates using our computer simulations, which match the accuracy of wet lab experiments, but are over 100x faster. We achieve this accuracy by constraining our genAI-based simulations to obey the laws of physics, avoiding the hallucinations seen in other GenAI technologies. Since joining YC, Angstrom AI has developed the first physically accurate gen-AI based simulation of multiple molecules interacting. We have published the first molecule water solubility results with accuracy within the error range of wet lab experiments. We have also kicked-off a 150K pilot project with a pharma company to apply our tech to estimating solubility in their drug development pipeline.

Artos is an AI-based document-drafting platform that helps life sciences companies turn their data into critical documents in minutes. These submissions currently take months and are the final hurdle before life sciences companies are allowed to sell their product.

Angstrom AI builds GenAI-based molecular simulations to substitute wet lab experiments in the pre-clinical drug development pipeline. We are a team of 2 PhD's and 2 Professors from the University of Cambridge who decided to start a company together after we realised how to combine breakthoughs in our research in quantum-accurate models of physics and generative AI models. Our Biotech/Pharma clients can verify the efficacy and safety of new drug candidates using our computer simulations, which match the accuracy of wet lab experiments, but are over 100x faster. We achieve this accuracy by constraining our genAI-based simulations to obey the laws of physics, avoiding the hallucinations seen in other GenAI technologies. Since joining YC, Angstrom AI has developed the first physically accurate gen-AI based simulation of multiple molecules interacting. We have published the first molecule water solubility results with accuracy within the error range of wet lab experiments. We have also kicked-off a 150K pilot project with a pharma company to apply our tech to estimating solubility in their drug development pipeline.

We are developing cancer therapeutics using small molecules that inhibit immune suppression. Our drugs engage the immune system to aggressively fight tumors. Our therapeutic portfolio addresses a range of solid tumors, starting with mesothelioma.

Angstrom AI builds GenAI-based molecular simulations to substitute wet lab experiments in the pre-clinical drug development pipeline. We are a team of 2 PhD's and 2 Professors from the University of Cambridge who decided to start a company together after we realised how to combine breakthoughs in our research in quantum-accurate models of physics and generative AI models. Our Biotech/Pharma clients can verify the efficacy and safety of new drug candidates using our computer simulations, which match the accuracy of wet lab experiments, but are over 100x faster. We achieve this accuracy by constraining our genAI-based simulations to obey the laws of physics, avoiding the hallucinations seen in other GenAI technologies. Since joining YC, Angstrom AI has developed the first physically accurate gen-AI based simulation of multiple molecules interacting. We have published the first molecule water solubility results with accuracy within the error range of wet lab experiments. We have also kicked-off a 150K pilot project with a pharma company to apply our tech to estimating solubility in their drug development pipeline.

We are building the next generation of deep-learning models for enzyme design to slash the cost of chemical manufacturing. The $6 trillion chemical industry is flawed: It produces 20% of industrial greenhouse gases, and is responsible for 15% of global energy usage. Enzymes offer a far more sustainable alternative to chemical synthesis and have already revolutionised how a select few chemicals are produced. The problem is each enzyme takes years of trial and error to develop. Our enzyme models learn the principles of catalysis, allowing us to design enzymes for each reaction, in days not years. We currently have $4.3M of LOIs and have completed our first $20k contract.

Angstrom AI builds GenAI-based molecular simulations to substitute wet lab experiments in the pre-clinical drug development pipeline. We are a team of 2 PhD's and 2 Professors from the University of Cambridge who decided to start a company together after we realised how to combine breakthoughs in our research in quantum-accurate models of physics and generative AI models. Our Biotech/Pharma clients can verify the efficacy and safety of new drug candidates using our computer simulations, which match the accuracy of wet lab experiments, but are over 100x faster. We achieve this accuracy by constraining our genAI-based simulations to obey the laws of physics, avoiding the hallucinations seen in other GenAI technologies. Since joining YC, Angstrom AI has developed the first physically accurate gen-AI based simulation of multiple molecules interacting. We have published the first molecule water solubility results with accuracy within the error range of wet lab experiments. We have also kicked-off a 150K pilot project with a pharma company to apply our tech to estimating solubility in their drug development pipeline.

Finding new cures requires seeing what and where the abnormal molecules are in a diseased tissue, but current tools see less than 1% of those molecules. Biocartesian combines microscopy and new chemistries to see 50X more, offering unprecedented insights into disease biology and new therapies.

Angstrom AI builds GenAI-based molecular simulations to substitute wet lab experiments in the pre-clinical drug development pipeline. We are a team of 2 PhD's and 2 Professors from the University of Cambridge who decided to start a company together after we realised how to combine breakthoughs in our research in quantum-accurate models of physics and generative AI models. Our Biotech/Pharma clients can verify the efficacy and safety of new drug candidates using our computer simulations, which match the accuracy of wet lab experiments, but are over 100x faster. We achieve this accuracy by constraining our genAI-based simulations to obey the laws of physics, avoiding the hallucinations seen in other GenAI technologies. Since joining YC, Angstrom AI has developed the first physically accurate gen-AI based simulation of multiple molecules interacting. We have published the first molecule water solubility results with accuracy within the error range of wet lab experiments. We have also kicked-off a 150K pilot project with a pharma company to apply our tech to estimating solubility in their drug development pipeline.

🦠🤖 We use our computational models to make next-generation antibiotics that outcompete bacterial evolution and precisely target pathogenic bacteria, without harming good microbes or human cells. ☠️ Current antibiotics stop working because bacteria evolve resistance to them. This makes drug-resistant bacteria a looming global health crisis - already killing more people than malaria and AIDS and it is getting exponentially worse 📈. 🧬 Our approach leverages co-evolutionary protein-protein interaction datasets combined with AI to forecast bacterial mutations and create ‘future-proof’ antibiotics, addressing antibiotic resistance before it develops. This changes the game for how frequently society will need to make new antibiotics and how long our new antibiotics will be able to treat patients 👩‍⚕️. We are a team of biochemists and evolutionary biologists who met at the University of Oxford.

Angstrom AI builds GenAI-based molecular simulations to substitute wet lab experiments in the pre-clinical drug development pipeline. We are a team of 2 PhD's and 2 Professors from the University of Cambridge who decided to start a company together after we realised how to combine breakthoughs in our research in quantum-accurate models of physics and generative AI models. Our Biotech/Pharma clients can verify the efficacy and safety of new drug candidates using our computer simulations, which match the accuracy of wet lab experiments, but are over 100x faster. We achieve this accuracy by constraining our genAI-based simulations to obey the laws of physics, avoiding the hallucinations seen in other GenAI technologies. Since joining YC, Angstrom AI has developed the first physically accurate gen-AI based simulation of multiple molecules interacting. We have published the first molecule water solubility results with accuracy within the error range of wet lab experiments. We have also kicked-off a 150K pilot project with a pharma company to apply our tech to estimating solubility in their drug development pipeline.

Metofico provides a no-code data analysis tool tailored for the life sciences. Our platform enables life scientists to analyse complex/massive datasets and extract necessary insights without needing advanced programming skills. This accessibility helps both researchers new to data science and experts save months of work. Metofico aims to be the leading centralized platform for data analysis in life science research, covering a wide range of applications from brain activity analysis (like photometry and EEG) to AI-powered detection and tracking of research animals. Our vision is to accelerate research processes and enhance the quality of research outputs across the board. By streamlining complex data analysis and making it more accessible, we’re committed to driving forward scientific discoveries and innovation.

Angstrom AI builds GenAI-based molecular simulations to substitute wet lab experiments in the pre-clinical drug development pipeline. We are a team of 2 PhD's and 2 Professors from the University of Cambridge who decided to start a company together after we realised how to combine breakthoughs in our research in quantum-accurate models of physics and generative AI models. Our Biotech/Pharma clients can verify the efficacy and safety of new drug candidates using our computer simulations, which match the accuracy of wet lab experiments, but are over 100x faster. We achieve this accuracy by constraining our genAI-based simulations to obey the laws of physics, avoiding the hallucinations seen in other GenAI technologies. Since joining YC, Angstrom AI has developed the first physically accurate gen-AI based simulation of multiple molecules interacting. We have published the first molecule water solubility results with accuracy within the error range of wet lab experiments. We have also kicked-off a 150K pilot project with a pharma company to apply our tech to estimating solubility in their drug development pipeline.

Proteins power everything from the cells in your body to creating materials you rely on every day, but until now, we’ve been forced to discover their functions by trial and error. Designing a new therapeutic can take decades and billions of dollars, and even our best industrial catalysts work at a snail’s pace compared to their theoretical optimums. Anthrogen is changing that. By training massive AI foundation models on protein sequences and structures, we’ve unlocked the ability to generate, on demand, completely novel molecular machines with atomic-level precision. Simply describe the function you need, and our platform imagines the peptide or protein that will deliver it. We're building models to speed up billions of years of evolution into the span of an afternoon's worth of compute. The result? New-to-nature therapies, ultra-efficient catalysts for sustainable manufacturing, and a whole new frontier of molecular innovation, designed as precisely as any cutting-edge aircraft or microchip.

Angstrom AI builds GenAI-based molecular simulations to substitute wet lab experiments in the pre-clinical drug development pipeline. We are a team of 2 PhD's and 2 Professors from the University of Cambridge who decided to start a company together after we realised how to combine breakthoughs in our research in quantum-accurate models of physics and generative AI models. Our Biotech/Pharma clients can verify the efficacy and safety of new drug candidates using our computer simulations, which match the accuracy of wet lab experiments, but are over 100x faster. We achieve this accuracy by constraining our genAI-based simulations to obey the laws of physics, avoiding the hallucinations seen in other GenAI technologies. Since joining YC, Angstrom AI has developed the first physically accurate gen-AI based simulation of multiple molecules interacting. We have published the first molecule water solubility results with accuracy within the error range of wet lab experiments. We have also kicked-off a 150K pilot project with a pharma company to apply our tech to estimating solubility in their drug development pipeline.

Reticular helps pharma companies discover drugs with AI models like AlphaFold by making them steerable, just like you can prompt LLMs. Today, limited validation data means companies spend millions on failed experiments trying to steer these models through trial and error. We’re piloting our AI interpretability technology with early-stage biotechs and scaling rapidly. Just a week after our pivot, we identified the first interpretable features ever found in protein models, allowing precise control over biological functions. Nithin and John met competing in Biology Olympiads before spending 4 years as roommates at MIT publishing ML/bio research in NeurIPS and Nature. We believe biological models encode far more information than anyone is currently using - our goal is to unlock this potential.

Angstrom AI builds GenAI-based molecular simulations to substitute wet lab experiments in the pre-clinical drug development pipeline. We are a team of 2 PhD's and 2 Professors from the University of Cambridge who decided to start a company together after we realised how to combine breakthoughs in our research in quantum-accurate models of physics and generative AI models. Our Biotech/Pharma clients can verify the efficacy and safety of new drug candidates using our computer simulations, which match the accuracy of wet lab experiments, but are over 100x faster. We achieve this accuracy by constraining our genAI-based simulations to obey the laws of physics, avoiding the hallucinations seen in other GenAI technologies. Since joining YC, Angstrom AI has developed the first physically accurate gen-AI based simulation of multiple molecules interacting. We have published the first molecule water solubility results with accuracy within the error range of wet lab experiments. We have also kicked-off a 150K pilot project with a pharma company to apply our tech to estimating solubility in their drug development pipeline.

The main document in a clinical trial is the study protocol. At large companies, floors of people use the protocol to create the study data collection forms, clinical database design, error checks, analysis code, and data transformation mappings. We use AI to automate the process of creating everything from the protocol, saving not only spend on headcount but also months of time which can translate to up to $27M in direct costs + lost revenue saved for a single phase 3 trial.

Angstrom AI builds GenAI-based molecular simulations to substitute wet lab experiments in the pre-clinical drug development pipeline. We are a team of 2 PhD's and 2 Professors from the University of Cambridge who decided to start a company together after we realised how to combine breakthoughs in our research in quantum-accurate models of physics and generative AI models. Our Biotech/Pharma clients can verify the efficacy and safety of new drug candidates using our computer simulations, which match the accuracy of wet lab experiments, but are over 100x faster. We achieve this accuracy by constraining our genAI-based simulations to obey the laws of physics, avoiding the hallucinations seen in other GenAI technologies. Since joining YC, Angstrom AI has developed the first physically accurate gen-AI based simulation of multiple molecules interacting. We have published the first molecule water solubility results with accuracy within the error range of wet lab experiments. We have also kicked-off a 150K pilot project with a pharma company to apply our tech to estimating solubility in their drug development pipeline.

Junction Bioscience is building an autonomous AI scientist to navigate the discovery of transformative medicines. Our scientific hypothesis engine iterates upon breakthrough chemistry from the laboratory to achieve clarity and control over the molecular basis of disease. We focus on the intersection of neuroinflammation and immunology where uncommon molecular insights position us to develop best-in-class therapies for millions of patients in need.

Angstrom AI builds GenAI-based molecular simulations to substitute wet lab experiments in the pre-clinical drug development pipeline. We are a team of 2 PhD's and 2 Professors from the University of Cambridge who decided to start a company together after we realised how to combine breakthoughs in our research in quantum-accurate models of physics and generative AI models. Our Biotech/Pharma clients can verify the efficacy and safety of new drug candidates using our computer simulations, which match the accuracy of wet lab experiments, but are over 100x faster. We achieve this accuracy by constraining our genAI-based simulations to obey the laws of physics, avoiding the hallucinations seen in other GenAI technologies. Since joining YC, Angstrom AI has developed the first physically accurate gen-AI based simulation of multiple molecules interacting. We have published the first molecule water solubility results with accuracy within the error range of wet lab experiments. We have also kicked-off a 150K pilot project with a pharma company to apply our tech to estimating solubility in their drug development pipeline.

Our Mission: We aim to accelerate and automate chemical process development by equipping wet-lab chemists with the power of data-driven optimization and robotic execution of experiments. The Problem: The discovery of novel pharmaceuticals is one of our most important weapons in fighting disease. However, the drug development pipeline is often held up for many months during the design of chemical processes to manufacture these drugs at scale, delaying FDA trials and lengthening the time until drug launch. Designing chemical processes involves the identification of suitable parameters such as catalyst/temperature/solvent. Currently process development is often done via tedious trial-and-error experimentation (slow) or exhaustive screening (expensive and wasteful). Our Approach: In our research, we have developed algorithms for chemical process optimization, which leverage transfer learning and Bayesian optimization. We validated the algorithms in the wet lab, showing an up to 95% reduction in required experiments and cost compared to exhaustive screening. We have made our approaches accessible to chemists through our user-friendly no-code software platform and to automated laboratory equipment with our API.

Angstrom AI builds GenAI-based molecular simulations to substitute wet lab experiments in the pre-clinical drug development pipeline. We are a team of 2 PhD's and 2 Professors from the University of Cambridge who decided to start a company together after we realised how to combine breakthoughs in our research in quantum-accurate models of physics and generative AI models. Our Biotech/Pharma clients can verify the efficacy and safety of new drug candidates using our computer simulations, which match the accuracy of wet lab experiments, but are over 100x faster. We achieve this accuracy by constraining our genAI-based simulations to obey the laws of physics, avoiding the hallucinations seen in other GenAI technologies. Since joining YC, Angstrom AI has developed the first physically accurate gen-AI based simulation of multiple molecules interacting. We have published the first molecule water solubility results with accuracy within the error range of wet lab experiments. We have also kicked-off a 150K pilot project with a pharma company to apply our tech to estimating solubility in their drug development pipeline.

Argon AI is a platform where biopharma and life sciences professionals can execute complex and data driven workflows using natural language. We help professionals get thorough answers to questions about clinical trials, existing treatments, healthcare landscape, and the competitive market in minutes rather than months. Prior to starting Argon, Samy was responsible for Flatiron Health’s (Roche) first data analytics project which eventually led to the start of the Flatiron Services business unit. There, he saw first-hand the heavily manual process that biopharma companies struggle through to get the insights they need to drive forward their drug development programs. He also helped close over $6M+ in ARR and is an expert in enterprise pharma sales. Cyrus previously led engineering teams and built 0 to 1 across pre-seed and unicorn startups, managed mission-critical trade generation systems at Bridgewater, and held AI advisory roles at various startups. Cyrus has a duel degree in EE and CS from USC. Breakthroughs in AI present an opportunity to reinvent biopharma and life science workflows to reduce the time and cost of bringing treatments to patients where delays in bringing a drug to market can cost a pharma company $3M / day.

Angstrom AI builds GenAI-based molecular simulations to substitute wet lab experiments in the pre-clinical drug development pipeline. We are a team of 2 PhD's and 2 Professors from the University of Cambridge who decided to start a company together after we realised how to combine breakthoughs in our research in quantum-accurate models of physics and generative AI models. Our Biotech/Pharma clients can verify the efficacy and safety of new drug candidates using our computer simulations, which match the accuracy of wet lab experiments, but are over 100x faster. We achieve this accuracy by constraining our genAI-based simulations to obey the laws of physics, avoiding the hallucinations seen in other GenAI technologies. Since joining YC, Angstrom AI has developed the first physically accurate gen-AI based simulation of multiple molecules interacting. We have published the first molecule water solubility results with accuracy within the error range of wet lab experiments. We have also kicked-off a 150K pilot project with a pharma company to apply our tech to estimating solubility in their drug development pipeline.

Design, simulate, and test your proteins 100x faster with the end-to-end no-code platform for protein engineering. Powered by Amina, our AI agent. With Amina, one protein engineer can do the work of 10. Describe what you want to achieve and Amina will handle everything else, from research and design to simulation, folding, docking, and protein characterization. It asks clarifying questions if needed, intelligently understands and performs the task, and analyzes your results within the context of your project.

Angstrom AI builds GenAI-based molecular simulations to substitute wet lab experiments in the pre-clinical drug development pipeline. We are a team of 2 PhD's and 2 Professors from the University of Cambridge who decided to start a company together after we realised how to combine breakthoughs in our research in quantum-accurate models of physics and generative AI models. Our Biotech/Pharma clients can verify the efficacy and safety of new drug candidates using our computer simulations, which match the accuracy of wet lab experiments, but are over 100x faster. We achieve this accuracy by constraining our genAI-based simulations to obey the laws of physics, avoiding the hallucinations seen in other GenAI technologies. Since joining YC, Angstrom AI has developed the first physically accurate gen-AI based simulation of multiple molecules interacting. We have published the first molecule water solubility results with accuracy within the error range of wet lab experiments. We have also kicked-off a 150K pilot project with a pharma company to apply our tech to estimating solubility in their drug development pipeline.

Tamarind Bio is a website and API which allows scientists to use computational biology tools at scale using a simple interface. On Tamarind, scientists can use ML models like AlphaFold to design and simulate molecules by simply selecting inputs instead of or setting up a high performance computing environment or dealing with DevOps. Our tools are used by thousands researchers in large pharma companies, top biotechs, and academic institutions. We currently focus on models in protein design and engineering, including for antibodies/therapeutics and enzymes. Get in touch at [email protected]

Angstrom AI builds GenAI-based molecular simulations to substitute wet lab experiments in the pre-clinical drug development pipeline. We are a team of 2 PhD's and 2 Professors from the University of Cambridge who decided to start a company together after we realised how to combine breakthoughs in our research in quantum-accurate models of physics and generative AI models. Our Biotech/Pharma clients can verify the efficacy and safety of new drug candidates using our computer simulations, which match the accuracy of wet lab experiments, but are over 100x faster. We achieve this accuracy by constraining our genAI-based simulations to obey the laws of physics, avoiding the hallucinations seen in other GenAI technologies. Since joining YC, Angstrom AI has developed the first physically accurate gen-AI based simulation of multiple molecules interacting. We have published the first molecule water solubility results with accuracy within the error range of wet lab experiments. We have also kicked-off a 150K pilot project with a pharma company to apply our tech to estimating solubility in their drug development pipeline.

Raycaster is the enterprise AI engine for life sciences. From speeding up regulatory approval and manufacturing tech transfer, Raycaster advances the Industry 4.0 initiatives with world's leading life sciences companies.

Angstrom AI builds GenAI-based molecular simulations to substitute wet lab experiments in the pre-clinical drug development pipeline. We are a team of 2 PhD's and 2 Professors from the University of Cambridge who decided to start a company together after we realised how to combine breakthoughs in our research in quantum-accurate models of physics and generative AI models. Our Biotech/Pharma clients can verify the efficacy and safety of new drug candidates using our computer simulations, which match the accuracy of wet lab experiments, but are over 100x faster. We achieve this accuracy by constraining our genAI-based simulations to obey the laws of physics, avoiding the hallucinations seen in other GenAI technologies. Since joining YC, Angstrom AI has developed the first physically accurate gen-AI based simulation of multiple molecules interacting. We have published the first molecule water solubility results with accuracy within the error range of wet lab experiments. We have also kicked-off a 150K pilot project with a pharma company to apply our tech to estimating solubility in their drug development pipeline.

Kopra Bio makes genetically engineered viruses that teach your immune system to kill cancer using tech we developed at UCSF. We’re making the next Keytruda ($25B/yr cancer drug blockbuster) starting with the most aggressive form of brain cancer, glioblastoma. In the most challenging brain cancer model, we improve survival from 0% with the current FDA approved treatment to 90% with our treatment.

Yoneda Labs provides software to help chemists optimise reactions. When chemists make a drug or a material, we help them figure out the best reaction parameters such as temperature, concentration and catalyst. When Jan was working at chemical labs, he experienced the struggle of spending weeks guessing reaction conditions. We then started experimenting with ML to speed up the process. Now, as a team of three friends from the University of Cambridge, we’ve spent the last month combining our domain expertise in Computer Science, Machine Learning and Chemistry to develop state of the art models for reaction optimisation. Although ML is becoming well established in other fields, current chemical models generalise poorly and require lots of programming experience. We make our models easily accessible to chemists in the lab. Finding the right conditions quickly allows pharmaceutical companies to test more drugs, and finding better optima makes manufacturing process cheaper and more environmentally friendly.

You can think of Stempad as a Notion for science. It is the world's first true pen-and-paper alternative to fast scientific writing and collaborating. Quickly switch between different forms of technical visualization with the ease of a whiteboard and the convenience of your keyboard. Stempad allows you to share your work, collaborate in real time, store your data, annotate, write papers, plan, takes notes, create presentations, and so much more. Our vision is to make it easier and faster for students and scientists to digitize and share their scientific ideas.

Yoneda Labs provides software to help chemists optimise reactions. When chemists make a drug or a material, we help them figure out the best reaction parameters such as temperature, concentration and catalyst. When Jan was working at chemical labs, he experienced the struggle of spending weeks guessing reaction conditions. We then started experimenting with ML to speed up the process. Now, as a team of three friends from the University of Cambridge, we’ve spent the last month combining our domain expertise in Computer Science, Machine Learning and Chemistry to develop state of the art models for reaction optimisation. Although ML is becoming well established in other fields, current chemical models generalise poorly and require lots of programming experience. We make our models easily accessible to chemists in the lab. Finding the right conditions quickly allows pharmaceutical companies to test more drugs, and finding better optima makes manufacturing process cheaper and more environmentally friendly.

Artos is an AI-based document-drafting platform that helps life sciences companies turn their data into critical documents in minutes. These submissions currently take months and are the final hurdle before life sciences companies are allowed to sell their product.

Yoneda Labs provides software to help chemists optimise reactions. When chemists make a drug or a material, we help them figure out the best reaction parameters such as temperature, concentration and catalyst. When Jan was working at chemical labs, he experienced the struggle of spending weeks guessing reaction conditions. We then started experimenting with ML to speed up the process. Now, as a team of three friends from the University of Cambridge, we’ve spent the last month combining our domain expertise in Computer Science, Machine Learning and Chemistry to develop state of the art models for reaction optimisation. Although ML is becoming well established in other fields, current chemical models generalise poorly and require lots of programming experience. We make our models easily accessible to chemists in the lab. Finding the right conditions quickly allows pharmaceutical companies to test more drugs, and finding better optima makes manufacturing process cheaper and more environmentally friendly.

We are developing cancer therapeutics using small molecules that inhibit immune suppression. Our drugs engage the immune system to aggressively fight tumors. Our therapeutic portfolio addresses a range of solid tumors, starting with mesothelioma.

Yoneda Labs provides software to help chemists optimise reactions. When chemists make a drug or a material, we help them figure out the best reaction parameters such as temperature, concentration and catalyst. When Jan was working at chemical labs, he experienced the struggle of spending weeks guessing reaction conditions. We then started experimenting with ML to speed up the process. Now, as a team of three friends from the University of Cambridge, we’ve spent the last month combining our domain expertise in Computer Science, Machine Learning and Chemistry to develop state of the art models for reaction optimisation. Although ML is becoming well established in other fields, current chemical models generalise poorly and require lots of programming experience. We make our models easily accessible to chemists in the lab. Finding the right conditions quickly allows pharmaceutical companies to test more drugs, and finding better optima makes manufacturing process cheaper and more environmentally friendly.

We are building the next generation of deep-learning models for enzyme design to slash the cost of chemical manufacturing. The $6 trillion chemical industry is flawed: It produces 20% of industrial greenhouse gases, and is responsible for 15% of global energy usage. Enzymes offer a far more sustainable alternative to chemical synthesis and have already revolutionised how a select few chemicals are produced. The problem is each enzyme takes years of trial and error to develop. Our enzyme models learn the principles of catalysis, allowing us to design enzymes for each reaction, in days not years. We currently have $4.3M of LOIs and have completed our first $20k contract.

Yoneda Labs provides software to help chemists optimise reactions. When chemists make a drug or a material, we help them figure out the best reaction parameters such as temperature, concentration and catalyst. When Jan was working at chemical labs, he experienced the struggle of spending weeks guessing reaction conditions. We then started experimenting with ML to speed up the process. Now, as a team of three friends from the University of Cambridge, we’ve spent the last month combining our domain expertise in Computer Science, Machine Learning and Chemistry to develop state of the art models for reaction optimisation. Although ML is becoming well established in other fields, current chemical models generalise poorly and require lots of programming experience. We make our models easily accessible to chemists in the lab. Finding the right conditions quickly allows pharmaceutical companies to test more drugs, and finding better optima makes manufacturing process cheaper and more environmentally friendly.

Finding new cures requires seeing what and where the abnormal molecules are in a diseased tissue, but current tools see less than 1% of those molecules. Biocartesian combines microscopy and new chemistries to see 50X more, offering unprecedented insights into disease biology and new therapies.

Yoneda Labs provides software to help chemists optimise reactions. When chemists make a drug or a material, we help them figure out the best reaction parameters such as temperature, concentration and catalyst. When Jan was working at chemical labs, he experienced the struggle of spending weeks guessing reaction conditions. We then started experimenting with ML to speed up the process. Now, as a team of three friends from the University of Cambridge, we’ve spent the last month combining our domain expertise in Computer Science, Machine Learning and Chemistry to develop state of the art models for reaction optimisation. Although ML is becoming well established in other fields, current chemical models generalise poorly and require lots of programming experience. We make our models easily accessible to chemists in the lab. Finding the right conditions quickly allows pharmaceutical companies to test more drugs, and finding better optima makes manufacturing process cheaper and more environmentally friendly.

🦠🤖 We use our computational models to make next-generation antibiotics that outcompete bacterial evolution and precisely target pathogenic bacteria, without harming good microbes or human cells. ☠️ Current antibiotics stop working because bacteria evolve resistance to them. This makes drug-resistant bacteria a looming global health crisis - already killing more people than malaria and AIDS and it is getting exponentially worse 📈. 🧬 Our approach leverages co-evolutionary protein-protein interaction datasets combined with AI to forecast bacterial mutations and create ‘future-proof’ antibiotics, addressing antibiotic resistance before it develops. This changes the game for how frequently society will need to make new antibiotics and how long our new antibiotics will be able to treat patients 👩‍⚕️. We are a team of biochemists and evolutionary biologists who met at the University of Oxford.

Yoneda Labs provides software to help chemists optimise reactions. When chemists make a drug or a material, we help them figure out the best reaction parameters such as temperature, concentration and catalyst. When Jan was working at chemical labs, he experienced the struggle of spending weeks guessing reaction conditions. We then started experimenting with ML to speed up the process. Now, as a team of three friends from the University of Cambridge, we’ve spent the last month combining our domain expertise in Computer Science, Machine Learning and Chemistry to develop state of the art models for reaction optimisation. Although ML is becoming well established in other fields, current chemical models generalise poorly and require lots of programming experience. We make our models easily accessible to chemists in the lab. Finding the right conditions quickly allows pharmaceutical companies to test more drugs, and finding better optima makes manufacturing process cheaper and more environmentally friendly.

Metofico provides a no-code data analysis tool tailored for the life sciences. Our platform enables life scientists to analyse complex/massive datasets and extract necessary insights without needing advanced programming skills. This accessibility helps both researchers new to data science and experts save months of work. Metofico aims to be the leading centralized platform for data analysis in life science research, covering a wide range of applications from brain activity analysis (like photometry and EEG) to AI-powered detection and tracking of research animals. Our vision is to accelerate research processes and enhance the quality of research outputs across the board. By streamlining complex data analysis and making it more accessible, we’re committed to driving forward scientific discoveries and innovation.

Yoneda Labs provides software to help chemists optimise reactions. When chemists make a drug or a material, we help them figure out the best reaction parameters such as temperature, concentration and catalyst. When Jan was working at chemical labs, he experienced the struggle of spending weeks guessing reaction conditions. We then started experimenting with ML to speed up the process. Now, as a team of three friends from the University of Cambridge, we’ve spent the last month combining our domain expertise in Computer Science, Machine Learning and Chemistry to develop state of the art models for reaction optimisation. Although ML is becoming well established in other fields, current chemical models generalise poorly and require lots of programming experience. We make our models easily accessible to chemists in the lab. Finding the right conditions quickly allows pharmaceutical companies to test more drugs, and finding better optima makes manufacturing process cheaper and more environmentally friendly.

Proteins power everything from the cells in your body to creating materials you rely on every day, but until now, we’ve been forced to discover their functions by trial and error. Designing a new therapeutic can take decades and billions of dollars, and even our best industrial catalysts work at a snail’s pace compared to their theoretical optimums. Anthrogen is changing that. By training massive AI foundation models on protein sequences and structures, we’ve unlocked the ability to generate, on demand, completely novel molecular machines with atomic-level precision. Simply describe the function you need, and our platform imagines the peptide or protein that will deliver it. We're building models to speed up billions of years of evolution into the span of an afternoon's worth of compute. The result? New-to-nature therapies, ultra-efficient catalysts for sustainable manufacturing, and a whole new frontier of molecular innovation, designed as precisely as any cutting-edge aircraft or microchip.

Yoneda Labs provides software to help chemists optimise reactions. When chemists make a drug or a material, we help them figure out the best reaction parameters such as temperature, concentration and catalyst. When Jan was working at chemical labs, he experienced the struggle of spending weeks guessing reaction conditions. We then started experimenting with ML to speed up the process. Now, as a team of three friends from the University of Cambridge, we’ve spent the last month combining our domain expertise in Computer Science, Machine Learning and Chemistry to develop state of the art models for reaction optimisation. Although ML is becoming well established in other fields, current chemical models generalise poorly and require lots of programming experience. We make our models easily accessible to chemists in the lab. Finding the right conditions quickly allows pharmaceutical companies to test more drugs, and finding better optima makes manufacturing process cheaper and more environmentally friendly.

Reticular helps pharma companies discover drugs with AI models like AlphaFold by making them steerable, just like you can prompt LLMs. Today, limited validation data means companies spend millions on failed experiments trying to steer these models through trial and error. We’re piloting our AI interpretability technology with early-stage biotechs and scaling rapidly. Just a week after our pivot, we identified the first interpretable features ever found in protein models, allowing precise control over biological functions. Nithin and John met competing in Biology Olympiads before spending 4 years as roommates at MIT publishing ML/bio research in NeurIPS and Nature. We believe biological models encode far more information than anyone is currently using - our goal is to unlock this potential.

Yoneda Labs provides software to help chemists optimise reactions. When chemists make a drug or a material, we help them figure out the best reaction parameters such as temperature, concentration and catalyst. When Jan was working at chemical labs, he experienced the struggle of spending weeks guessing reaction conditions. We then started experimenting with ML to speed up the process. Now, as a team of three friends from the University of Cambridge, we’ve spent the last month combining our domain expertise in Computer Science, Machine Learning and Chemistry to develop state of the art models for reaction optimisation. Although ML is becoming well established in other fields, current chemical models generalise poorly and require lots of programming experience. We make our models easily accessible to chemists in the lab. Finding the right conditions quickly allows pharmaceutical companies to test more drugs, and finding better optima makes manufacturing process cheaper and more environmentally friendly.

The main document in a clinical trial is the study protocol. At large companies, floors of people use the protocol to create the study data collection forms, clinical database design, error checks, analysis code, and data transformation mappings. We use AI to automate the process of creating everything from the protocol, saving not only spend on headcount but also months of time which can translate to up to $27M in direct costs + lost revenue saved for a single phase 3 trial.

Yoneda Labs provides software to help chemists optimise reactions. When chemists make a drug or a material, we help them figure out the best reaction parameters such as temperature, concentration and catalyst. When Jan was working at chemical labs, he experienced the struggle of spending weeks guessing reaction conditions. We then started experimenting with ML to speed up the process. Now, as a team of three friends from the University of Cambridge, we’ve spent the last month combining our domain expertise in Computer Science, Machine Learning and Chemistry to develop state of the art models for reaction optimisation. Although ML is becoming well established in other fields, current chemical models generalise poorly and require lots of programming experience. We make our models easily accessible to chemists in the lab. Finding the right conditions quickly allows pharmaceutical companies to test more drugs, and finding better optima makes manufacturing process cheaper and more environmentally friendly.

Junction Bioscience is building an autonomous AI scientist to navigate the discovery of transformative medicines. Our scientific hypothesis engine iterates upon breakthrough chemistry from the laboratory to achieve clarity and control over the molecular basis of disease. We focus on the intersection of neuroinflammation and immunology where uncommon molecular insights position us to develop best-in-class therapies for millions of patients in need.

Yoneda Labs provides software to help chemists optimise reactions. When chemists make a drug or a material, we help them figure out the best reaction parameters such as temperature, concentration and catalyst. When Jan was working at chemical labs, he experienced the struggle of spending weeks guessing reaction conditions. We then started experimenting with ML to speed up the process. Now, as a team of three friends from the University of Cambridge, we’ve spent the last month combining our domain expertise in Computer Science, Machine Learning and Chemistry to develop state of the art models for reaction optimisation. Although ML is becoming well established in other fields, current chemical models generalise poorly and require lots of programming experience. We make our models easily accessible to chemists in the lab. Finding the right conditions quickly allows pharmaceutical companies to test more drugs, and finding better optima makes manufacturing process cheaper and more environmentally friendly.

Our Mission: We aim to accelerate and automate chemical process development by equipping wet-lab chemists with the power of data-driven optimization and robotic execution of experiments. The Problem: The discovery of novel pharmaceuticals is one of our most important weapons in fighting disease. However, the drug development pipeline is often held up for many months during the design of chemical processes to manufacture these drugs at scale, delaying FDA trials and lengthening the time until drug launch. Designing chemical processes involves the identification of suitable parameters such as catalyst/temperature/solvent. Currently process development is often done via tedious trial-and-error experimentation (slow) or exhaustive screening (expensive and wasteful). Our Approach: In our research, we have developed algorithms for chemical process optimization, which leverage transfer learning and Bayesian optimization. We validated the algorithms in the wet lab, showing an up to 95% reduction in required experiments and cost compared to exhaustive screening. We have made our approaches accessible to chemists through our user-friendly no-code software platform and to automated laboratory equipment with our API.

Yoneda Labs provides software to help chemists optimise reactions. When chemists make a drug or a material, we help them figure out the best reaction parameters such as temperature, concentration and catalyst. When Jan was working at chemical labs, he experienced the struggle of spending weeks guessing reaction conditions. We then started experimenting with ML to speed up the process. Now, as a team of three friends from the University of Cambridge, we’ve spent the last month combining our domain expertise in Computer Science, Machine Learning and Chemistry to develop state of the art models for reaction optimisation. Although ML is becoming well established in other fields, current chemical models generalise poorly and require lots of programming experience. We make our models easily accessible to chemists in the lab. Finding the right conditions quickly allows pharmaceutical companies to test more drugs, and finding better optima makes manufacturing process cheaper and more environmentally friendly.

Argon AI is a platform where biopharma and life sciences professionals can execute complex and data driven workflows using natural language. We help professionals get thorough answers to questions about clinical trials, existing treatments, healthcare landscape, and the competitive market in minutes rather than months. Prior to starting Argon, Samy was responsible for Flatiron Health’s (Roche) first data analytics project which eventually led to the start of the Flatiron Services business unit. There, he saw first-hand the heavily manual process that biopharma companies struggle through to get the insights they need to drive forward their drug development programs. He also helped close over $6M+ in ARR and is an expert in enterprise pharma sales. Cyrus previously led engineering teams and built 0 to 1 across pre-seed and unicorn startups, managed mission-critical trade generation systems at Bridgewater, and held AI advisory roles at various startups. Cyrus has a duel degree in EE and CS from USC. Breakthroughs in AI present an opportunity to reinvent biopharma and life science workflows to reduce the time and cost of bringing treatments to patients where delays in bringing a drug to market can cost a pharma company $3M / day.

Yoneda Labs provides software to help chemists optimise reactions. When chemists make a drug or a material, we help them figure out the best reaction parameters such as temperature, concentration and catalyst. When Jan was working at chemical labs, he experienced the struggle of spending weeks guessing reaction conditions. We then started experimenting with ML to speed up the process. Now, as a team of three friends from the University of Cambridge, we’ve spent the last month combining our domain expertise in Computer Science, Machine Learning and Chemistry to develop state of the art models for reaction optimisation. Although ML is becoming well established in other fields, current chemical models generalise poorly and require lots of programming experience. We make our models easily accessible to chemists in the lab. Finding the right conditions quickly allows pharmaceutical companies to test more drugs, and finding better optima makes manufacturing process cheaper and more environmentally friendly.

Design, simulate, and test your proteins 100x faster with the end-to-end no-code platform for protein engineering. Powered by Amina, our AI agent. With Amina, one protein engineer can do the work of 10. Describe what you want to achieve and Amina will handle everything else, from research and design to simulation, folding, docking, and protein characterization. It asks clarifying questions if needed, intelligently understands and performs the task, and analyzes your results within the context of your project.

Yoneda Labs provides software to help chemists optimise reactions. When chemists make a drug or a material, we help them figure out the best reaction parameters such as temperature, concentration and catalyst. When Jan was working at chemical labs, he experienced the struggle of spending weeks guessing reaction conditions. We then started experimenting with ML to speed up the process. Now, as a team of three friends from the University of Cambridge, we’ve spent the last month combining our domain expertise in Computer Science, Machine Learning and Chemistry to develop state of the art models for reaction optimisation. Although ML is becoming well established in other fields, current chemical models generalise poorly and require lots of programming experience. We make our models easily accessible to chemists in the lab. Finding the right conditions quickly allows pharmaceutical companies to test more drugs, and finding better optima makes manufacturing process cheaper and more environmentally friendly.

Tamarind Bio is a website and API which allows scientists to use computational biology tools at scale using a simple interface. On Tamarind, scientists can use ML models like AlphaFold to design and simulate molecules by simply selecting inputs instead of or setting up a high performance computing environment or dealing with DevOps. Our tools are used by thousands researchers in large pharma companies, top biotechs, and academic institutions. We currently focus on models in protein design and engineering, including for antibodies/therapeutics and enzymes. Get in touch at [email protected]

Yoneda Labs provides software to help chemists optimise reactions. When chemists make a drug or a material, we help them figure out the best reaction parameters such as temperature, concentration and catalyst. When Jan was working at chemical labs, he experienced the struggle of spending weeks guessing reaction conditions. We then started experimenting with ML to speed up the process. Now, as a team of three friends from the University of Cambridge, we’ve spent the last month combining our domain expertise in Computer Science, Machine Learning and Chemistry to develop state of the art models for reaction optimisation. Although ML is becoming well established in other fields, current chemical models generalise poorly and require lots of programming experience. We make our models easily accessible to chemists in the lab. Finding the right conditions quickly allows pharmaceutical companies to test more drugs, and finding better optima makes manufacturing process cheaper and more environmentally friendly.

Raycaster is the enterprise AI engine for life sciences. From speeding up regulatory approval and manufacturing tech transfer, Raycaster advances the Industry 4.0 initiatives with world's leading life sciences companies.

Yoneda Labs provides software to help chemists optimise reactions. When chemists make a drug or a material, we help them figure out the best reaction parameters such as temperature, concentration and catalyst. When Jan was working at chemical labs, he experienced the struggle of spending weeks guessing reaction conditions. We then started experimenting with ML to speed up the process. Now, as a team of three friends from the University of Cambridge, we’ve spent the last month combining our domain expertise in Computer Science, Machine Learning and Chemistry to develop state of the art models for reaction optimisation. Although ML is becoming well established in other fields, current chemical models generalise poorly and require lots of programming experience. We make our models easily accessible to chemists in the lab. Finding the right conditions quickly allows pharmaceutical companies to test more drugs, and finding better optima makes manufacturing process cheaper and more environmentally friendly.

Kopra Bio makes genetically engineered viruses that teach your immune system to kill cancer using tech we developed at UCSF. We’re making the next Keytruda ($25B/yr cancer drug blockbuster) starting with the most aggressive form of brain cancer, glioblastoma. In the most challenging brain cancer model, we improve survival from 0% with the current FDA approved treatment to 90% with our treatment.

You can think of Stempad as a Notion for science. It is the world's first true pen-and-paper alternative to fast scientific writing and collaborating. Quickly switch between different forms of technical visualization with the ease of a whiteboard and the convenience of your keyboard. Stempad allows you to share your work, collaborate in real time, store your data, annotate, write papers, plan, takes notes, create presentations, and so much more. Our vision is to make it easier and faster for students and scientists to digitize and share their scientific ideas.

Artos is an AI-based document-drafting platform that helps life sciences companies turn their data into critical documents in minutes. These submissions currently take months and are the final hurdle before life sciences companies are allowed to sell their product.

You can think of Stempad as a Notion for science. It is the world's first true pen-and-paper alternative to fast scientific writing and collaborating. Quickly switch between different forms of technical visualization with the ease of a whiteboard and the convenience of your keyboard. Stempad allows you to share your work, collaborate in real time, store your data, annotate, write papers, plan, takes notes, create presentations, and so much more. Our vision is to make it easier and faster for students and scientists to digitize and share their scientific ideas.

We are developing cancer therapeutics using small molecules that inhibit immune suppression. Our drugs engage the immune system to aggressively fight tumors. Our therapeutic portfolio addresses a range of solid tumors, starting with mesothelioma.

You can think of Stempad as a Notion for science. It is the world's first true pen-and-paper alternative to fast scientific writing and collaborating. Quickly switch between different forms of technical visualization with the ease of a whiteboard and the convenience of your keyboard. Stempad allows you to share your work, collaborate in real time, store your data, annotate, write papers, plan, takes notes, create presentations, and so much more. Our vision is to make it easier and faster for students and scientists to digitize and share their scientific ideas.

We are building the next generation of deep-learning models for enzyme design to slash the cost of chemical manufacturing. The $6 trillion chemical industry is flawed: It produces 20% of industrial greenhouse gases, and is responsible for 15% of global energy usage. Enzymes offer a far more sustainable alternative to chemical synthesis and have already revolutionised how a select few chemicals are produced. The problem is each enzyme takes years of trial and error to develop. Our enzyme models learn the principles of catalysis, allowing us to design enzymes for each reaction, in days not years. We currently have $4.3M of LOIs and have completed our first $20k contract.

You can think of Stempad as a Notion for science. It is the world's first true pen-and-paper alternative to fast scientific writing and collaborating. Quickly switch between different forms of technical visualization with the ease of a whiteboard and the convenience of your keyboard. Stempad allows you to share your work, collaborate in real time, store your data, annotate, write papers, plan, takes notes, create presentations, and so much more. Our vision is to make it easier and faster for students and scientists to digitize and share their scientific ideas.

Finding new cures requires seeing what and where the abnormal molecules are in a diseased tissue, but current tools see less than 1% of those molecules. Biocartesian combines microscopy and new chemistries to see 50X more, offering unprecedented insights into disease biology and new therapies.

You can think of Stempad as a Notion for science. It is the world's first true pen-and-paper alternative to fast scientific writing and collaborating. Quickly switch between different forms of technical visualization with the ease of a whiteboard and the convenience of your keyboard. Stempad allows you to share your work, collaborate in real time, store your data, annotate, write papers, plan, takes notes, create presentations, and so much more. Our vision is to make it easier and faster for students and scientists to digitize and share their scientific ideas.

🦠🤖 We use our computational models to make next-generation antibiotics that outcompete bacterial evolution and precisely target pathogenic bacteria, without harming good microbes or human cells. ☠️ Current antibiotics stop working because bacteria evolve resistance to them. This makes drug-resistant bacteria a looming global health crisis - already killing more people than malaria and AIDS and it is getting exponentially worse 📈. 🧬 Our approach leverages co-evolutionary protein-protein interaction datasets combined with AI to forecast bacterial mutations and create ‘future-proof’ antibiotics, addressing antibiotic resistance before it develops. This changes the game for how frequently society will need to make new antibiotics and how long our new antibiotics will be able to treat patients 👩‍⚕️. We are a team of biochemists and evolutionary biologists who met at the University of Oxford.

You can think of Stempad as a Notion for science. It is the world's first true pen-and-paper alternative to fast scientific writing and collaborating. Quickly switch between different forms of technical visualization with the ease of a whiteboard and the convenience of your keyboard. Stempad allows you to share your work, collaborate in real time, store your data, annotate, write papers, plan, takes notes, create presentations, and so much more. Our vision is to make it easier and faster for students and scientists to digitize and share their scientific ideas.

Metofico provides a no-code data analysis tool tailored for the life sciences. Our platform enables life scientists to analyse complex/massive datasets and extract necessary insights without needing advanced programming skills. This accessibility helps both researchers new to data science and experts save months of work. Metofico aims to be the leading centralized platform for data analysis in life science research, covering a wide range of applications from brain activity analysis (like photometry and EEG) to AI-powered detection and tracking of research animals. Our vision is to accelerate research processes and enhance the quality of research outputs across the board. By streamlining complex data analysis and making it more accessible, we’re committed to driving forward scientific discoveries and innovation.

You can think of Stempad as a Notion for science. It is the world's first true pen-and-paper alternative to fast scientific writing and collaborating. Quickly switch between different forms of technical visualization with the ease of a whiteboard and the convenience of your keyboard. Stempad allows you to share your work, collaborate in real time, store your data, annotate, write papers, plan, takes notes, create presentations, and so much more. Our vision is to make it easier and faster for students and scientists to digitize and share their scientific ideas.

Proteins power everything from the cells in your body to creating materials you rely on every day, but until now, we’ve been forced to discover their functions by trial and error. Designing a new therapeutic can take decades and billions of dollars, and even our best industrial catalysts work at a snail’s pace compared to their theoretical optimums. Anthrogen is changing that. By training massive AI foundation models on protein sequences and structures, we’ve unlocked the ability to generate, on demand, completely novel molecular machines with atomic-level precision. Simply describe the function you need, and our platform imagines the peptide or protein that will deliver it. We're building models to speed up billions of years of evolution into the span of an afternoon's worth of compute. The result? New-to-nature therapies, ultra-efficient catalysts for sustainable manufacturing, and a whole new frontier of molecular innovation, designed as precisely as any cutting-edge aircraft or microchip.

You can think of Stempad as a Notion for science. It is the world's first true pen-and-paper alternative to fast scientific writing and collaborating. Quickly switch between different forms of technical visualization with the ease of a whiteboard and the convenience of your keyboard. Stempad allows you to share your work, collaborate in real time, store your data, annotate, write papers, plan, takes notes, create presentations, and so much more. Our vision is to make it easier and faster for students and scientists to digitize and share their scientific ideas.

Reticular helps pharma companies discover drugs with AI models like AlphaFold by making them steerable, just like you can prompt LLMs. Today, limited validation data means companies spend millions on failed experiments trying to steer these models through trial and error. We’re piloting our AI interpretability technology with early-stage biotechs and scaling rapidly. Just a week after our pivot, we identified the first interpretable features ever found in protein models, allowing precise control over biological functions. Nithin and John met competing in Biology Olympiads before spending 4 years as roommates at MIT publishing ML/bio research in NeurIPS and Nature. We believe biological models encode far more information than anyone is currently using - our goal is to unlock this potential.