Matteo Aldeghi

Excited to share that the Broad Institute of MIT and Harvard Machine Learning in Drug Discovery Symposium is coming up. Join for a gathering of leaders pushing the boundaries at the intersection of AI in drug discovery. The full agenda is now live: https://lnkd.in/eKZmPwnZ I am happy to be presenting work from Psivant Therapeutics that leverages AI/ML, physics, and wet lab experiments to drug challenging I&I targets. While the AI/ML field continues to gain momentum, we are beginning to learn more about the true value and limitations of AI/ML. In short, AI/ML approaches are great for interpolation but quite poor for extrapolation. When you have the appropriate training data, use AI/ML and you will generally get good predictions, fast. However, much of drug discovery involves finding novel drugs for undrugged targets (i.e. not great data). For those scenarios, proceed with caution when using AI/ML methods. It is easy to fool yourself into thinking your method can extrapolate when in reality you have data in your training set that looks a lot like your test set (which does not look like the novel drugs you want to design). For example, see recent publications on protein co-folding from Eva Nittinger et al. at AZ https://lnkd.in/eWmw8-w3, Pat Walters https://lnkd.in/ekEjhhnA and the SIB Swiss Institute of Bioinformatics https://lnkd.in/eG5puMUd At the same time, we are also familiar with the limitations of physics-based approaches (complex setup; computationally intensive; sampling local/global minima; force fields; tautomers; stereochemistry; waters; expert knowledge; and more). Yet physics-based methods can truly extrapolate and in fact do not need any training data when embarking on a new target or class of ligands. Our philosophy: * Build a computational ecosystem that fully leverages state-of-the-art methods in both AI/ML and physics. * Run at scale. * Automate as appropriate. * Keep humans in the loop. * Design an intuitive data-centric user interface for experienced drug hunters. * Hire expert developers who understand the strengths and limits along with a firm grasp of drug discovery such that the focus is on the highest value problems within the project. This might sound obvious, but for all the people at the interface of in silico and wet lab approaches, you know how hard it can be. The magic happens when you combine the speed of AI/ML, the extrapolative power of physics, the right experiments, and the judgment of experienced drug hunters. Registration is open, but this one tends to sell out, so sign up now: https://lnkd.in/epuJfyNT Looking forward to joining great speakers, such as Thomas Miller, Marinka Zitnik, and more.

303

6 Comments

🚀 Introducing Boltz-ABFE – accelerating accurate predictions without crystal structures in AI drug discovery. 🔹 A new paper from the research team at Recursion and Valence Labs demonstrates how we’ve combined the open-source model we developed with Massachusetts Institute of Technology, Boltz-2, with our own absolute binding free energy protocol to create Boltz-ABFE – a pipeline that makes gold-standard protein-ligand binding affinity predictions possible without the need for experimental crystal structures. 🔹 Key takeaways: ▪️ No Crystal Structure Needed: Traditionally, the most accurate physics-based methods for predicting drug binding affinity (FEP) required a high-quality 3D crystal structure of the protein-drug complex, which is often unavailable in the early stages of discovery. ▪️ Accurate AI-Predicted Structures: We demonstrate that AI models like Boltz-2 can generate protein-ligand structures that are accurate enough to be used as a starting point for these high-precision simulations. ▪️ A Robust New Pipeline: We developed Boltz-ABFE, a method that combines AI structure prediction with an automated protocol to correct common errors and prepare the structures for absolute binding free energy (ABFE) calculations. ▪️ Accelerating Discovery: By enabling accurate, structure-based affinity estimation much earlier in the process, this work paves the way for faster and more efficient identification and optimization of new drug candidates. 💥 This paper represents another important step for early-stage drug discovery. Congrats to the team! Stephan Thaler, William (Zhiyi) Wu, William G., Richard T. Bradshaw, Gail Bartlett, Prudencio Tossou, and Geoffrey Wood. *Link to the paper in comments! #DrugDiscovery #AI #FEP #TechBio 

721

10 Comments

#AI is changing how society functions, including in drug discovery. We prioritize continuous learning and development, ensuring our team remains well-rounded and informed within the ever-evolving #biotech ecosystem. Team members Robert Policastro, PhD, Cory Dunn and Alexey Seregin hosted a session on AI and its applications in protein and #DNA engineering at Ensoma. As technology evolves, so do we!

104

2 Comments

🧠 Cortex Conversations: Episode 3 – Digital Endpoints in Neuroscience Today Digital biomarkers are no longer a future concept—they’re shaping neuroscience trials right now. In this episode, Amber Burg is joined by Leone Atkinson, Executive Medical Director of Neuroscience and Ophthalmology at Fortrea, and Alicia Baker McDowell, DRSc, MS, EMBA, Vice President and Head of Global Regulatory Strategy at Fortrea, to explore how these tools are being used, what regulators are saying, and how biotech leaders can confidently integrate them into development strategies. 💡 Real-world wins, AI, and hybrid models—this episode lays the groundwork for smarter, more precise trials. 🎧Listen in: https://lnkd.in/eb2ArTjP #Fortrea #Neuroscience #DigitalEndpoints #ClinicalTrials

83

🌐 The #cellatlas community holds the potential to unlock critical new insights to tackle urgent global challenges, but bringing together vast #datasets and multiple studies from across the globe come with inherent challenges. In a new article, Prof Irene Papatheodorou Head of Data Science at the Earlham Institute, explains the importance of cell atlases in interrogating complex cellular mechanics, and the challenges currently faced by the community in integrating and sharing datasets. 💽 Read more here ➡️ https://okt.to/xErU0q #CellAtlas #CellularGenomics #Genomics

125

1 Comment

AI Innovation in Drug Discovery: Researchers at Duke have introduced PATH (Predicting Affinity Through Homology), a new algorithm that predicts how molecules bind to proteins — a crucial step in designing effective treatments. This breakthrough, developed by Bruce Donald, PhD, James B. Duke Distinguished Professor of Computer Science and professor of biochemistry, could accelerate the development of cancer drugs and HIV antibodies. Read more ⤵️

33

Xavier Godron, Co-founder & CTO at DNA Script, has been featured in The Scientist. Researchers today face long turnaround times, supply chain disruptions, and data security concerns when outsourcing #DNAsynthesis. Waiting weeks for sequences slows discovery, delays vaccine development, and adds risks around sensitive IP. With DNA Script’s enzymatic DNA synthesis (EDS) powered SYNTAX™ platform, labs can print DNA on demand, right at the bench. This means: - Faster “design/build/test” cycles to accelerate innovation - Greater control over timelines and supply chains - Enhanced security for valuable or sensitive sequences - More agility in responding to global health threats By putting DNA synthesis directly in scientists’ hands, we’re helping unlock a new era of faster, more secure, and more decentralized biology. 👉 Read more about Xavier’s perspective and get new insight : https://lnkd.in/dY97VptY

66

1 Comment

💊 What if failed experiments were the key to smarter drug discovery? Lot Fourteen-based QUBIGEN, is unlocking the hidden value of failed chemical reactions to improve the accuracy of AI in drug development. By using Federated AI to securely train models on real-world failure data (without compromising privacy) Qubigen is helping pharmaceutical companies cut costs, reduce false positives, and accelerate innovation. It's a powerful example of how South Australian critical tech is transforming global industries. 🔗 Discover more: https://lnkd.in/gq-nu63W 📸 Dr Jonathan Hall Founder & CEO, Qubigen. #SouthAusInnovationPlaces #SouthAusInnovation #DrugDiscovery #FederatedAI #HealthTech #SouthAustralia #CriticalTech

37