Computational Chemist

Nvidia unveils science reasoning AI suite with BioNeMo Agent Toolkit. June 23, 2026 Nvidia has announced the NVIDIA BioNeMo Agent Toolkit, which turns complex scientific workflows into agent-executable tasks, including model selection, input preparation, workflow execution, output inspection, and results explanation. The toolkit includes NVIDIA BioNeMo and is powered by NVIDIA NIM microservices, NVIDIA Parabricks, NVIDIA NeMo, and NVIDIA Nemotron and has applications across protein structure prediction, molecular docking, generative chemistry, genomic analysis, protein design, and biomarker discovery. "For the first time, researchers can build AI agents that understand scientific knowledge, use scientific tools, and execute scientific workflows," said Jensen Huang, founder and CEO of Nvidia, in a press release. "This is a new way to do science - one that can dramatically accelerate discovery across biology, chemistry, genomics, and medicine." Nvidia has entered collaborations with research organizations, including the Arc Institute, Open Molecular Software Foundation, and the University of Washington's Institute for Protein Design (IPD). The partnership with IPD has accelerated runtimes for the biomolecular complex prediction tool, RosettaFold3, resulting in two times faster performance than the prior generation model. "Every tool we've built for protein design is only as powerful as the scientists who can efficiently access it," said David Baker, PhD, professor of biochemistry at the University of Washington and director of the Institute for Protein Design, in a public release. "The next leap in science won't come from a single discovery; it will come from the speed of iterative designs and agents that can repeatedly reason through the complexity of biology at a speed humans never could." The toolkit's applications include virtual screening, where agents identify promising small-molecule drug candidates by generating compound designs, docking them to a target, predicting binding strength, and filtering for developability properties. The agent can then output which candidates should be prioritized to compress timelines. In genomic analysis and target discovery, agents can identify genetic insights and biological targets from raw sequencing data. Agents can also connect real-world data to reasoning models for biomedical research, improving the efficiency and accuracy of clinical development processes, including literature review, protocol generation, clinical trial screening, and pharmacovigilance. In medical imaging analysis, agents can process, segment, synthesize, and reason over medical imaging data to support biomarker discovery. AI-native biology companies, including Boltz, Basecamp Research, Chai Discovery, PerturbAI, Dyno, and Proxima, have collaborated with NVIDIA to develop tools to accelerate therapeutic design workflows. Diagnostics and pharmaceutical companies, including Lilly and Natera, are using BioNeMo Agent Toolkit to scale agentic workflows across discovery, translational research, and clinical insight.

Proxima appoints Dr. Raymond Deshaies, Dr. Lyn Jones, and Dr. Juri Rappsilber to Scientific Advisory Board. New advisors bring decades of industry drug discovery leadership and foundational scientific expertise across Proxima's proximity therapeutics engine and structural proteomics data platform From left to right: Dr. Raymond Deshaies, Dr. Lyn Jones, and Dr. Juri Rappsilber, newly appointed members of Proxima's Scientific Advisory Board. NEW YORK-(BUSINESS WIRE)-Proxima (formerly VantAI), a frontier AI and data generation company discovering the next generation of proximity therapeutics, today announced three appointments to its Scientific Advisory Board: Dr. Raymond Deshaies, co-inventor of the PROTAC concept and widely recognized as one of the founding members of the field of targeted protein degradation; Dr. Lyn Jones, a leader in molecular glue development and chemical biology; and Dr. Juri Rappsilber, who established and continues to pioneer cross-linking mass spectrometry as a foundational tool for structural and systems biology. Proxima's platform is built to develop proximity-based medicines, molecules that unlock new possibilities against disease through co-opting the cell's own biological machinery. "Some of the most powerful drugs ever discovered, such as lenalidomide and thalidomide, turned out to work by hijacking the cell's own protein disposal machinery. Viruses do the same thing: they commandeer ubiquitin ligases to trick the cell into trashing its own antiviral defenses. The principle of induced proximity is using small molecules to leverage tools from nature's playbook, and we've barely scratched the surface of what's therapeutically possible with it," said Dr. Raymond Deshaies, member of the National Academy of Sciences and former SVP of Global Research at Amgen. "What we've lacked is the structural and systems biology data to systematically exploit this principle, and Proxima generates exactly that data at proteome scale." Even where the biology is well characterized, expanding the druggable proteome demands new chemistry that can precisely engage protein interfaces more broadly. "The human genome encodes more than 600 E3 ubiquitin ligases, and thousands of other proteins with potential in proximity applications, but we've built almost everything so far on just two of them," said Dr. Lyn Jones, Principal Investigator at Dana-Farber Cancer Institute and former Chief Scientist of its Center for Protein Degradation. "If we want to expand the druggable proteome, we need to understand the protein interfaces of new effector proteins in detail. To get there, you need structural data on these interfaces at a scale that hasn't yet existed." Pursuing proximity therapeutics rationally, as Deshaies and Jones describe, requires structural data at full cellular interactome scale - a scale that demands rethinking experimental methods themselves. Cross-linking mass spectrometry (XL-MS) has long held promise as a technique that can map native protein interactions, but leveraging it to create data at the scale required by frontier ML methods has not yet been possible. "The limiting factor in cross-linking mass spectrometry has historically been throughput: generating enough distance restraints, across enough of the interactome, to move from validating individual structures to building comprehensive structural models," said Dr. Juri Rappsilber. "Proxima's platform represents an important step in this direction. By industrializing cross-linking mass spectrometry as a critical data modality and pairing it directly with computational structure prediction, Proxima is demonstrating what becomes possible when this data is generated at a depth and scale the field has long envisioned but that has remained elusive until now." Together, these pioneering data modalities form a self-reinforcing flywheel with Proxima's leading frontier ML methods: structural data focused on interfaces deepens understanding of biology and pathways behind disease, helping to direct where small molecule adaptors that modify interactions stand to impact disease in powerful ways. Proxima is already putting this cycle to work alongside leading big pharma partners and advancing new proximity modalities like transcription factor relocalization, epigenetic modifiers, and RIPTACs through programs with innovative partners like Halda Therapeutics (acquired by Johnson & Johnson). About the New Advisors Dr. Raymond Deshaies is a member of the National Academy of Sciences and former Distinguished Fellow and Senior Vice President of Global Research at Amgen. Prior to Amgen, he was a Howard Hughes Medical Institute Investigator (HHMI) at the California Institute of Technology. He co-conceived the PROTAC (proteolysis-targeting chimera) concept with Craig Crews and is widely recognized as one of the founding members and most important voices across the field of targeted protein degradation and proximity therapeutics more broadly. Dr. Lyn Jones is a Principal Investigator and Faculty Member at Dana-Farber Cancer Institute, former Head of Chemical Biology at Pfizer, and Chief Scientist at Dana-Farber's Center for Protein Degradation. His laboratory focuses on next-generation covalent approaches to modulate protein function, with the objective of expanding the druggable proteome. Dr. Juri Rappsilber is Full Professor and Chair of Bioanalytics at Technische Universität Berlin and former Professor of Proteomics at the University of Edinburgh. He has pioneered both the computational and experimental methods that established cross-linking mass spectrometry (XL-MS) as a tool for mapping protein structures and interactions at systems scale, including in native cellular environments. About Proxima Proxima is pioneering a transformative approach to therapeutics by illuminating the dynamic networks of protein interactions that drive biological function. Leveraging a groundbreaking structural proteomics platform and frontier AI models, Proxima generates unprecedented interactomics data, revealing how proteins and small molecules interact and shape cellular behavior at proteome-wide scale. Alongside a robust and mechanistically differentiated internal pipeline, Proxima collaborates extensively with external partners to accelerate the delivery of innovative proximity therapeutics, applying its technology to make previously undruggable targets accessible and provide powerful new ways to target diseases by rewiring cellular circuitry. For more information, please visit www.proximabio.com.