Benchling’s Post

All the buzz of AI/ML impact on R&D requires the infrastructure and solutions to ingest and process the data. Benchling is ready to support advanced analytics against the data model within our solutions. Are you ready for AI/ML? Benchling is!!! How can we help you?

An interesting article in today's Globe and Mail. AI hasn't lived up to the hype when it comes to pharmaceutical discovery. Bottom line: the problems are still too hard for current foundation models. https://lnkd.in/gBpTdiS7 Maybe the AI teams should start collaborating with the quantum teams working on the same problem: https://lnkd.in/gfm32ZHE

Exciting Developments in AI-Based Drug Discovery! This week i would like to share our newsletter highlighting innovations at the intersection of artificial intelligence and drug discovery. AI-Based Drug Discovery Tools Ver 1.0 https://lnkd.in/eVdcy_Z5

Who is next? Generative AI platforms drive recent drug discovery dealmaking - check out this article. The potential of generative AI models to accelerate the design of drug candidates looks set to boost the funding raised in recent years by AI-focused companies and is driving dealmaking by major biopharma companies seeking to enhance their pipelines. Will this trend continue? https://lnkd.in/gp65xGhS #biopharma #biotech #lifesciences #generativeai #artificialintelligence #genAI

Last year ended on news of some major AI - Pharma collaborations, and 2024 is starting strong on this front too, with 2 major deals announced with Alphabet Isomorphic partnering with both Eli Lilly and Novartis. Alphabets AI platform is able to predict protein structure and so could potentially speed up target discovery and compound construction. These deals are worth almost $ 3 billion combined, showing huge confidence in the positive effect AI could have on drug discovery. https://lnkd.in/eesvnfAu

Dr Reddy's arm rolls AI&ML assisted drug discovery platform Aurigene.AI The platform is an end-to-end solution for small molecule drug discovery that will combine AI & ML capabilities with Aurigene's core expertise in synthesising and testing molecules in vitro and in vivo. It has been rolled out with an eye on accelerating drug discovery projects, from hit identification to candidate nomination, Dr Reddy's said on Wednesday. #DrReddys | #DrugDiscoveryProjects | #Aurigenecoreexpertise | #TestingMolecules | #Healthnews Read more:

We are pleased to announce the publication of our latest article, "AI Hit Rates and Novelty,” by Tyler Umansky, the first article in our #AIDDCode series. This comprehensive study addresses the critical need for standardized evaluation metrics in AI-driven drug discovery, focusing on hit identification campaigns. Our work proposes a rigorous framework for assessing AI model performance, emphasizing both hit rates and chemical novelty. Criteria for hit identification: 1. Minimum Sample Size: A minimum of 10 compounds must be tested in vitro for each target. This ensures a robust sample size for meaningful comparison across studies. 2. Exact Compound Prediction Testing: Only the exact compounds predicted by the AI models are tested, without any intermediate or high-similarity synthetically accessible alternatives. 3. Therapeutic Relevance: Compounds must demonstrate biological activity against the target protein at or below a concentration of 20 μM, not just binding affinity (Kd). 4. Chemical Novelty (Training Set): An average nearest neighbor Tanimoto similarity score (ECFP4 2048) to the training data must be less than 0.4, to ensure exploration of novel chemical space. 5. Chemical Novelty (Public Data): An average nearest neighbor Tanimoto similarity score (ECFP4 2048) to public data (e.g., ChEMBL database) must also be less than 0.4, reinforcing the discovery of truly novel compounds. 6. Diversity Among Hits: An average pairwise Tanimoto diversity score (ECFP4 2048) must be less than 0.2, ensuring diversity among the identified hits. Our findings underscore the importance of considering chemical novelty and diversity alongside traditional hit rates, potentially reshaping how the scientific community evaluates AI models in drug discovery and inspiring further research in this area. We urge colleagues in medicinal chemistry, cheminformatics, and AI research to adopt these standards for a more transparent and rigorous evaluation of AI drug discovery models. Let's work together to accelerate innovation and improve the efficiency of drug discovery processes. Full article here: https://buff.ly/47fmZOJ #AIDD #DrugDiscovery Daniel Haders II, Ph.D. Sean Russell Tyler Umansky Virgil Woods Patrick ONeill Lani O. Tushar Menon, PhD JD Davey Smith, MD, MAS, FACP, FIDSA Karl Karlsson Kip Quackenbush Marlon Evans Irving Investors Christopher Chism Jeremy Abelson Andrew Kalmar ParticleX Jeffrey Friedman Clayton E. Hartman Philip Treick Kevin Whalen Cameron Akers Greg Young Wayne Schellhammer Doug Vander Weide, CFP® Tim Lugo  Annette Grimaldi Jennifer Schmitke, PhD Sam Howard Launa Aspeslet Delilah Panio Greg Goldner Brendan Hussey, Ph.D Fan Zhang, PhD David Smolensky Megan Wilson Launa Aspeslet 8VC James A Weber

Revolutionizing Drug Discovery: 15 AI Companies to Watch in 2024 #pharma #AI #drugs 1. Atomwise: Revolutionizing Virtual Screening 2. BenevolentAI: AI-Driven Drug Discovery 3. Insilico Medicine: Aging Research and Drug Discovery 4. Recursion Pharmaceuticals: AI-Powered Drug Repurposing 5. Molecule AI: AI-Powered Drug Design Platform 6. Numerate: Precision Chemistry with AI 7. TwoXAR ( ARIA ): Accelerating Preclinical Development 8. Deep Genomics: AI for Genomic Medicine 9. Recce Pharmaceuticals: AI-Enhanced Antibiotics  10. Biosymetrics: Integrated Data Analytics  11. Ardigen: Immunotherapy Advancements with AI 12. Cyclica: Polypharmacology and Network Pharmacology 13. Healx: Rare Disease Drug Discovery 14. BioXcel Therapeutics: Pharma AI for Drug Development 15. Strateos: Robotic Cloud Labs for Drug Discovery

AI-driven drug discovery and development represents a future where new medicines could become more precise and effective, better tolerated, and better tailored to an individual. UCB's Roger Palframan shares an overview of how #AI can help in this, and how can we work in a more active way toward this future. https://lnkd.in/emxibqes #drugdiscovery #drugdevelopment