Next time you need property-matched decoys to benchmark your molecular docking project, we suggest you try DUDEZ.docking.org, the new version of DUDE.docking.org. DUDEZ also offers "goldilocks" and "extrema" sets as described in Stein et al JCIM. 2021, 61, 2, 699–714

Check out our (Frank Noe) new paper where we improve the prediction of protein complexes by 'hacking' AlphaFold-multimer (AFM). Starting from an MSA, we use AFM to update what knowledge to sample from the MSA with gradient descent through the network. (1/2)

Established software predict ternary complex structures induced by #PROTACs with ~ 5Å accuracy, but can't distinguish these "close-miss" from 100s of "far-off" predictions. MD shows that structures beyond those captured by Xray may be valid. bit.ly/3ykCtnK Structural Genomics Consortium (SGC)

We couldn't be prouder of Rachel Harding who joined Leslie Dan Faculty of Pharmacy as an Assistant Professor! Please join us in congratulating Dr. Harding on this remarkable achievement! 📲 thesgc.org/news/dr-rachel…

Machine Learning vs Chemical Intuition

PDF position in Toronto at the interface of deep learning with Chris J. Maddison at Vector Institute and #compchem in my group at Structural Genomics Consortium (SGC). Develop novel approaches in hit-finding and hit-to-lead opt. Predictions are tested at the bench at Structural Genomics Consortium (SGC) bit.ly/3SvHXCU

I'm also recruiting PhD/MSc students this coming cycle, with an eye towards applications in drug discovery. cs.toronto.edu/~cmaddis/ DM me or email me if you have any questions at all!

Get ready for the 4th Probe Hackathon! Graduate students will get the chance to collaborate with experts and assess chemical probes to identify the most and least effective compounds for use in biological research. Merck Chemical Probes Portal chemicalprobes.org/hackathons/mer…

Can AlphaFold be useful in drug discovery? Hell yes! In our paper, structure-based virtual screens using AlphaFold models identify potent GPCR ligands with antipsychotic effects in vivo (science.org/doi/10.1126/sc…). KAW Uppsala University Karolinska Institutet SciLifeLab

And we're off! The design stage of the BioML Challenge 2024: Bits to Binders began this past Saturday 62 teams will be using AI methods to design ~300 de novo antigen binders for human CD20. We will be screening a total of *18,000* unique designs with the help of LEAHLabsInc

Our recent AI drug design paper pubs.acs.org/doi/10.1021/ac… led by USC USC Dornsife College of Letters, Arts & Sciences student Jesse Weller now published with an American Chemical Society journal cover in JCIM & JCTC Journals. If you work on drug targets with exp or AF structure, we invite ideas for collaboration ACS for Authors #MyACSCover

My seminar on ML in Structure-Based Drug Discovery at the MoML Summer School is now on YouTube youtube.com/watch?v=0EmYfN… Giving this class had a particular significance for me as MoML is dedicated to the memory of Octavian Ganea an amazing friend who introduced me to this topic 🙏

Join the virtual, two-day 𝐼𝑛 𝑠𝑖𝑙𝑖𝑐𝑜 #DrugDiscovery Workshop with top experts in the field. Learn cutting-edge techniques, network with professionals & enhance your skills for free! Register today: ncats.corsizio.com/event/6628253b… #AI #MachineLearning

I’m really excited about our preprint on the development of AVI-4206, an inhibitor of the SARS-CoV-2 Macrodomain (Mac1)! AVI-4206 pharmacologically validates Mac1 as a novel target that works by restoring our immune system’s fight against COVID. biorxiv.org/content/10.110…

Join us in Toronto for an exciting program in chemical biology. Submit your abstract now for a chance to present your research. AI in drug discovery. Targeted Protein Degradation and molecular glues. Systems level analysis of drug action and more!

Structure prediction of alternative protein conformations | Nature Communications - Cfold, a structure prediction model designed to predict alternative protein conformations. - Train AF2 without the Template Track and focus on MSAs and coevolutionary signals - Predict different

Thrilled to announce a preprint describing collaborative work between our group and James Fraser (A$AP J), Brian Shoichet, and Adam Renslo. The paper shows a practical application of the Thompson Sampling method we published earlier this year. biorxiv.org/content/10.110…

Optimal Molecular Design: Generative Active Learning Combining REINVENT with Precise Binding Free Energy Ranking Simulations #machinelearning #compchem pubs.acs.org/doi/abs/10.102…

Benchmarking Methods for PROTAC Ternary Complex Structure Prediction #MolecularDynamics pubs.acs.org/doi/10.1021/ac… Matthieu Schapira #JCIM Vol64 Issue15 #PharamceuticalModeling

Chemical tools from Structural Genomics Consortium (SGC) Boehringer Ingelheim 's Opnme @eubopen Target 2035 cover only 3% of the human proteome but already 50% of the Reactome! Great tool set to explore human biology ... and a pleasure to collab. with friends at SGC and Jark Boettcher. bit.ly/3XiHFRy