Latest news with #MikaelDolsten
Yahoo
3 days ago
- Business
- Yahoo
Chai Discovery Unveils Chai-2 Breakthrough, Achieving Fully De Novo Antibody Design With AI
SAN FRANCISCO, June 30, 2025--(BUSINESS WIRE)--Chai Discovery, which builds frontier artificial intelligence to predict and reprogram the interactions between biochemical molecules, today announced a breakthrough in the de novo design of antibodies. The company's latest model, Chai-2, demonstrates a remarkable antibody design hit rate close to 20%. Prompted with just the target and epitope, Chai-2 successfully designs all complementarity-determining regions (CDRs) entirely from scratch—a breakthrough in a field where traditional techniques, including those based on AI, consistently show hit rates below 0.1%. Extensive lab validation of roughly 50 antibody targets showed that almost half yielded validated hits, when testing fewer than 20 designs experimentally for each. Designed antibodies exhibited desirable drug-like properties, such as nanomolar-range affinities, specificity for intended targets, and strong developability profiles, enabling rapid translation into therapeutic applications. Chai-2 also produced validated binders for 5 out of 5 miniprotein targets, with hit rates several times higher than previous state-of-the-art. "I've been impressed by the scale of Chai Discovery's ambition since our early conversations a while ago—when such progress scarcely seemed possible—and it's incredible to see this breakthrough come so quickly," said Mikael Dolsten, who served as Chief Scientific Officer of Pfizer for over 15 years. "Chai-2 holds high potential for de novo design of medicines with short turnaround times." Antibodies are essential to our immune systems and critical to biomedical research and therapeutic discovery. However, traditional methods of developing antibodies—like immunization, directed evolution, or yeast-surface display—can be slow, expensive, and imprecise. Computational approaches offer a faster, more precise alternative, but until now have struggled with low success rates and often required significant and expensive experimental screening to refine initial designs. Chai-2 is the first AI system capable of reliably generating novel antibodies from scratch, based solely on target epitopes, without any need for extensive lab screening or optimization rounds. It supports a wide range of formats and has already shown robust success across both nanobodies (VHHs) and VH-VL format. Researchers can go from in silico generation to lab validation in under two weeks, enabling rapid iteration and accelerated development timelines. "Chai-2 is like Photoshop for proteins—it enables precise, rapid, and intuitive creation of biologic therapeutics, which can enable previously intractable targets," said Joshua Meier, co-founder at Chai. "We built Chai to enable outcomes that were previously impossible, and we're thrilled by these results. This marks a turning point in science." In one case, Chai-2 solved an antibody challenge that had previously consumed over $5 million in traditional R&D spend—in just a few hours. The result was validated in the lab within two weeks. With the biopharma industry under pressure from patent cliffs, cost-cutting mandates, and the growing need to pursue differentiated R&D, Chai offers a platform to not only improve productivity but to unlock entirely new therapeutic spaces. Chai Discovery also announced that they will be opening early access to Chai-2 to select partners. For more details, visit or read ABOUT CHAI DISCOVERY Chai Discovery builds frontier artificial intelligence to predict and reprogram the interactions between biochemical molecules, the fundamental building blocks of life. Its mission is to transform biology from science into engineering. The team hails from pioneering research and applied AI companies such as OpenAI, Meta FAIR, Stripe, and Google X, and is backed by top investors including OpenAI, Thrive Capital and Dimension. View source version on Contacts press@
Business Wire
3 days ago
- Business
- Business Wire
Chai Discovery Unveils Chai-2 Breakthrough, Achieving Fully De Novo Antibody Design With AI
SAN FRANCISCO--(BUSINESS WIRE)-- Chai Discovery, which builds frontier artificial intelligence to predict and reprogram the interactions between biochemical molecules, today announced a breakthrough in the de novo design of antibodies. The company's latest model, Chai-2, demonstrates a remarkable antibody design hit rate close to 20%. Prompted with just the target and epitope, Chai-2 successfully designs all complementarity-determining regions (CDRs) entirely from scratch—a breakthrough in a field where traditional techniques, including those based on AI, consistently show hit rates below 0.1%. Extensive lab validation of roughly 50 antibody targets showed that almost half yielded validated hits, when testing fewer than 20 designs experimentally for each. Designed antibodies exhibited desirable drug-like properties, such as nanomolar-range affinities, specificity for intended targets, and strong developability profiles, enabling rapid translation into therapeutic applications. Chai-2 also produced validated binders for 5 out of 5 miniprotein targets, with hit rates several times higher than previous state-of-the-art. 'I've been impressed by the scale of Chai Discovery's ambition since our early conversations a while ago—when such progress scarcely seemed possible—and it's incredible to see this breakthrough come so quickly,' said Mikael Dolsten, who served as Chief Scientific Officer of Pfizer for over 15 years. 'Chai-2 holds high potential for de novo design of medicines with short turnaround times.' Antibodies are essential to our immune systems and critical to biomedical research and therapeutic discovery. However, traditional methods of developing antibodies—like immunization, directed evolution, or yeast-surface display—can be slow, expensive, and imprecise. Computational approaches offer a faster, more precise alternative, but until now have struggled with low success rates and often required significant and expensive experimental screening to refine initial designs. Chai-2 is the first AI system capable of reliably generating novel antibodies from scratch, based solely on target epitopes, without any need for extensive lab screening or optimization rounds. It supports a wide range of formats and has already shown robust success across both nanobodies (VHHs) and VH-VL format. Researchers can go from in silico generation to lab validation in under two weeks, enabling rapid iteration and accelerated development timelines. 'Chai-2 is like Photoshop for proteins—it enables precise, rapid, and intuitive creation of biologic therapeutics, which can enable previously intractable targets,' said Joshua Meier, co-founder at Chai. 'We built Chai to enable outcomes that were previously impossible, and we're thrilled by these results. This marks a turning point in science.' In one case, Chai-2 solved an antibody challenge that had previously consumed over $5 million in traditional R&D spend—in just a few hours. The result was validated in the lab within two weeks. With the biopharma industry under pressure from patent cliffs, cost-cutting mandates, and the growing need to pursue differentiated R&D, Chai offers a platform to not only improve productivity but to unlock entirely new therapeutic spaces. Chai Discovery also announced that they will be opening early access to Chai-2 to select partners. For more details, visit or read Chai Discovery builds frontier artificial intelligence to predict and reprogram the interactions between biochemical molecules, the fundamental building blocks of life. Its mission is to transform biology from science into engineering. The team hails from pioneering research and applied AI companies such as OpenAI, Meta FAIR, Stripe, and Google X, and is backed by top investors including OpenAI, Thrive Capital and Dimension.
Yahoo
03-06-2025
- Health
- Yahoo
Orbis Medicines Accelerates Next-Generation Oral Macrocycle Platform with Enhanced Artificial Intelligence Capabilities of Gefion Supercomputer
Orbis begins using Gefion, Denmark's first AI supercomputer Composed of 1,528 NVIDIA H100 Tensor Core GPUs, system is optimized for large-scale, AI-driven projects Enables significant expansion of macrocycle chemical space exploration by Orbis' nGen platform New AI/ML capacity will leverage large proprietary datasets and generative AI to design novel orally available macrocycle alternatives to existing biologics COPENHAGEN, Denmark, June 03, 2025--(BUSINESS WIRE)--Orbis Medicines, a leader in oral macrocycle drug discovery, and the Danish Center for AI Innovation (DCAI) today announced that Orbis has begun using Denmark's first AI supercomputer, Gefion, which is owned and operated by DCAI. Gefion will allow the company to accelerate its mission of developing oral alternatives to widely used biologics and targeting important intra- and extracellular proteins that are currently difficult or impossible to drug with orally bioavailable compounds. Orbis is pioneering the systematic discovery and development of targeted, orally available macrocycles for diseases and targets traditionally treated with biologics. The company develops compounds known as nCycles, which can address a wide range of validated protein targets with unique oral bioavailability and membrane permeability features. "Our advanced nGen platform helps us quickly create large numbers of custom-designed macrocycles with unique properties and broad medical applicability," said Orbis CEO Morten Graugaard. "By combining this platform with Gefion's computing power, we can extend beyond the nearly 140 billion compounds in our existing libraries to design entirely new collections of these molecules. This means we can explore an even broader range of chemical possibilities and more fully unlock the potential of macrocycles to improve healthcare." "Orbis' nGen platform, which has already been used to design, synthesize and test more than 700,000 individual nCycles, is an ideal application for Gefion's capabilities," said Orbis Medicines Board Chair Mikael Dolsten, M.D., Ph.D. "Combining the power of this supercomputer with our in-house target nCycle data collection, generative AI, and nCycle synthesis capabilities will accelerate the development of orally available macrocycles that have the potential to disrupt the current biologics market and provide new treatment options for patients." "Gefion is designed to deliver AI innovation at scale through immense computing power applied to the most challenging problems," said Dr. Nadia Carlsten, CEO of DCAI. "As a biomedical start-up with its own internal AI technology applied to drug design and the ability to generate vast data sets, Orbis is an ideal partner to demonstrate what Gefion can unlock when matched with specialist expertise." DCAI's Gefion supercomputer contains 1,528 NVIDIA GPUs and is optimized for large-scale AI-driven projects. Gefion enables innovators to utilize advanced computation to accelerate discovery in various fields, including biotechnology and drug discovery. Gefion has previously been used by researchers, start-ups, and large enterprises to develop new AI models and perform simulations in weather modeling, quantum computing, and business automation. About Orbis Medicines Orbis Medicines is pioneering a new era for oral macrocycle drug discovery. Its nGen platform systematically delivers macrocycle candidates, termed nCycles. These are optimized for oral bioavailability, which has historically hindered therapeutic development of this versatile class of molecules. Orbis' pipeline is initially focused on nCycle candidates against targets validated by blockbuster biologic drugs delivered by injection. Proof-of-concept of Orbis' work has been published in Nature Communications and Nature Chemical Biology. The company has raised €116 million in venture funding to date, including a €90 million series A round led by NEA with new investors Lilly Ventures, Cormorant, EIFO and existing investors Forbion and Novo Holdings. Orbis is located in Copenhagen, Denmark and Lausanne, Switzerland. For more information, please visit: About nGen nGen is Orbis Medicines' technology platform for generating nCycles, a new class of fully synthetic macrocycle compounds optimized for oral bioavailability and membrane permeability. It consists of multiple proprietary integrated elements in a "lab in a loop" system starting with hit finding libraries of 100 billion compounds and target specific libraries designed by generative AI. The highly automated chemistry-based nGen platform can synthesize and screen up to 100,000 distinct synthetic macrocycles in weeks, allowing the company to discover candidates with the right properties to enable oral dosing and intracellular targeting. The scale and quality of the data produced from these real compounds, paired with machine learning and generative AI, creates an industry-leading platform that de-risks and accelerates development. About DCAI The Danish Centre for AI Innovation (DCAI) owns and operates Gefion, Denmark's flagship AI supercomputer, designed specifically for large-scale AI projects. Gefion ranks among the most powerful supercomputers globally powered by 1.528 NVIDIA H100 Tensor Core GPUs. DCAI's mission is to lower the barrier for accessing advanced computing capabilities, enabling customers to innovate and fostering ecosystem growth. DCAI customers include academic researchers, startups, government institutions, and enterprise customers doing large scale innovation. DCAI was formed as a company and funded by the Novo Nordisk Foundation and EIFO in 2024. View source version on Contacts Media: Matt CrensonTen Bridge Communications(917) 640-7930mcrenson@ General enquiries for DCAI & Gefion hello@ (+45) 35 27 66 00 Sign in to access your portfolio
Business Wire
03-06-2025
- Business
- Business Wire
Orbis Medicines Accelerates Next-Generation Oral Macrocycle Platform with Enhanced Artificial Intelligence Capabilities of Gefion Supercomputer
COPENHAGEN, Denmark--(BUSINESS WIRE)--Orbis Medicines, a leader in oral macrocycle drug discovery, and the Danish Center for AI Innovation (DCAI) today announced that Orbis has begun using Denmark's first AI supercomputer, Gefion, which is owned and operated by DCAI. Gefion will allow the company to accelerate its mission of developing oral alternatives to widely used biologics and targeting important intra- and extracellular proteins that are currently difficult or impossible to drug with orally bioavailable compounds. Orbis is pioneering the systematic discovery and development of targeted, orally available macrocycles for diseases and targets traditionally treated with biologics. The company develops compounds known as n Cycles, which can address a wide range of validated protein targets with unique oral bioavailability and membrane permeability features. 'Our advanced n Gen platform helps us quickly create large numbers of custom-designed macrocycles with unique properties and broad medical applicability,' said Orbis CEO Morten Graugaard. 'By combining this platform with Gefion's computing power, we can extend beyond the nearly 140 billion compounds in our existing libraries to design entirely new collections of these molecules. This means we can explore an even broader range of chemical possibilities and more fully unlock the potential of macrocycles to improve healthcare.' 'Orbis' n Gen platform, which has already been used to design, synthesize and test more than 700,000 individual n Cycles, is an ideal application for Gefion's capabilities,' said Orbis Medicines Board Chair Mikael Dolsten, M.D., Ph.D. 'Combining the power of this supercomputer with our in-house target n Cycle data collection, generative AI, and n Cycle synthesis capabilities will accelerate the development of orally available macrocycles that have the potential to disrupt the current biologics market and provide new treatment options for patients.' 'Gefion is designed to deliver AI innovation at scale through immense computing power applied to the most challenging problems,' said Dr. Nadia Carlsten, CEO of DCAI. 'As a biomedical start-up with its own internal AI technology applied to drug design and the ability to generate vast data sets, Orbis is an ideal partner to demonstrate what Gefion can unlock when matched with specialist expertise.' DCAI's Gefion supercomputer contains 1,528 NVIDIA GPUs and is optimized for large-scale AI-driven projects. Gefion enables innovators to utilize advanced computation to accelerate discovery in various fields, including biotechnology and drug discovery. Gefion has previously been used by researchers, start-ups, and large enterprises to develop new AI models and perform simulations in weather modeling, quantum computing, and business automation. About Orbis Medicines Orbis Medicines is pioneering a new era for oral macrocycle drug discovery. Its n Gen platform systematically delivers macrocycle candidates, termed n Cycles. These are optimized for oral bioavailability, which has historically hindered therapeutic development of this versatile class of molecules. Orbis' pipeline is initially focused on n Cycle candidates against targets validated by blockbuster biologic drugs delivered by injection. Proof-of-concept of Orbis' work has been published in Nature Communications and Nature Chemical Biology. The company has raised €116 million in venture funding to date, including a €90 million series A round led by NEA with new investors Lilly Ventures, Cormorant, EIFO and existing investors Forbion and Novo Holdings. Orbis is located in Copenhagen, Denmark and Lausanne, Switzerland. For more information, please visit: About n Gen n Gen is Orbis Medicines' technology platform for generating n Cycles, a new class of fully synthetic macrocycle compounds optimized for oral bioavailability and membrane permeability. It consists of multiple proprietary integrated elements in a 'lab in a loop' system starting with hit finding libraries of 100 billion compounds and target specific libraries designed by generative AI. The highly automated chemistry-based n Gen platform can synthesize and screen up to 100,000 distinct synthetic macrocycles in weeks, allowing the company to discover candidates with the right properties to enable oral dosing and intracellular targeting. The scale and quality of the data produced from these real compounds, paired with machine learning and generative AI, creates an industry-leading platform that de-risks and accelerates development. About DCAI The Danish Centre for AI Innovation (DCAI) owns and operates Gefion, Denmark's flagship AI supercomputer, designed specifically for large-scale AI projects. Gefion ranks among the most powerful supercomputers globally powered by 1.528 NVIDIA H100 Tensor Core GPUs. DCAI's mission is to lower the barrier for accessing advanced computing capabilities, enabling customers to innovate and fostering ecosystem growth. DCAI customers include academic researchers, startups, government institutions, and enterprise customers doing large scale innovation. DCAI was formed as a company and funded by the Novo Nordisk Foundation and EIFO in 2024.
