David Ryan Koes @dkoes.compstruct.org · 09/12/2025Had an informative and enjoyable time at NeurIPS and MLSB. It was great to see my students present their work and catch up with other CPCB students, both past and present. 080
David Ryan Koes @dkoes.compstruct.org · 07/12/2025Excited to be at the first independent @workshopmlsb.bsky.social 061
David Ryan Koes @dkoes.compstruct.org · 05/12/2025If you like to sample from the Boltzmann distribution and are in San Diego for NeurIPS, be sure to check out Rishal's (@rishalchich.bsky.social) poster (#2110). Great work with Nick Boffi (@nmboffi.bsky.social) and Jacky Chen. neurips.cc/virtual/2025... arxiv.org/abs/2507.00846 0123
David Ryan Koes @dkoes.compstruct.org · 23/09/2025Not true - random number generators aren't biased by molecular weight... 140
Reposted by David Ryan KoesMLSB (in San Diego + Copenhagen) @workshopmlsb.bsky.social · 17/09/2025🚨To accommodate the addition of EuroMLSB, we have extended the submission deadline to October 1, 2025 11:59pm AoE. Find information on paper guidelines at mlsb.io. Submissions will be made through CMT. 033
Reposted by David Ryan KoesOlexandr Isayev 🇺🇦 🇺🇸 @olexandr.bsky.social · 04/08/2025Most of MLIPs dont distinguish between spin states, making them unsuitable for open-shell chemistry. We present AIMNet2-NSE (Neural Spin-charge Equilibration), MLIP that incorporates spin-charge equilibration for systems with arbitrary charge and spin. #compchem #skychem chemrxiv.org/engage/chemr... 5264
Reposted by David Ryan KoesGina El Nesr @ginaelnesr.bsky.social · 20/03/2025Protein function often depends on protein dynamics. To design proteins that function like natural ones, how do we predict their dynamics? @hkws.bsky.social and I are thrilled to share the first big, experimental datasets on protein dynamics and our new model: Dyna-1! 🧵 610538
Reposted by David Ryan KoesEmma Flynn @emmaflynn.bsky.social · 27/05/2025Our new preprint PharmacoForge: Pharmacophore Generation with Diffusion Models is out now! PharmacoForge quickly generates pharmacophores for a given protein pocket that identify key binding features and find useful compounds in a pharmacophore search. Check it out! 🧪 doi.org/10.26434/che... 1209
David Ryan Koes @dkoes.compstruct.org · 19/05/2025Was proud and honored to hood Dr. Drew McNutt at the Pitt School of Medicine Diploma Ceremony. Here we are rocking both the blue and gold and tartan colors representing our joint Pitt-CMU CompBio PhD program. Congratulations to Drew and the other @cmupittcompbio.bsky.social graduates! 0203
Reposted by David Ryan KoesDr Javier Sánchez Utgés @javierutges.bsky.social · 19/05/2025I am #exhilarated to share that our new paper "LIGYSIS-web: a resource for the analysis of protein-ligand binding sites" is now published in @narjournal.bsky.social! After almost two years of development and more than 600 commits, LIGYSIS-web is out! 📜 : tinyurl.com/utges-LIGYSI... 22911
Reposted by David Ryan KoesComputational & Systems Biology Dept. at Pitt @csbpitt.bsky.social · 08/05/2025Two students in the Joint Carnegie Mellon-University of Pittsburgh PhD Program in Computational Biology have received honorable mentions from the National Science Foundation’s Graduate Research Fellowship Program. Congratulations to Anamarie Martinez and Emma Flynn! Read more: tinyurl.com/GRFPPitttinyurl.comPhD students earn recognition from National Science Foundation fellowship - Department of Computational and Systems BiologyTwo students in the Joint Carnegie Mellon-University of Pittsburgh PhD Program in Computational Biology have received honorable mentions from the National Science Foundation’s Graduate Research Fellow... 041
Reposted by David Ryan KoesOxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 08/04/2025We're recruiting a 3-year postdoc for the Novo Nordisk - Oxford Fellowship programme! Develop machine learning approaches for fragment library design and experimental optimisation With @fergusimrie.bsky.social and Charlotte Deane Job advert: shorturl.at/3l47e Further details: shorturl.at/u4UkKshorturl.atJob Details 045
David Ryan Koes @dkoes.compstruct.org · 31/03/2025Everything is easy in 2D.. - @franknoe.bsky.social 030
Reposted by David Ryan KoesConscience @conscience-network.bsky.social · 25/03/2025🚀One week left to register for our Symposium on Open Drug Discovery! Join us in Montreal April 7-8 for an exciting program showcasing how open science and AI are driving drug discovery. Some sessions are already sold out, so register now! Register by April 2nd: conscience.ca/symposium2025conscience.caConscience Symposium on Open Drug Discovery - Submission and registration are open! - ConscienceRegistration is now open for the second annual Conscience Symposium on Open Drug Discovery! Join us at the Society for Arts and Technology in Montreal on April 7-8, 2025, for two days of insightful ta... 012
David Ryan Koes @dkoes.compstruct.org · 25/03/2025Interested in generative modeling and pharmacophores search for SBDD? Check out our talks at #ACSSpring2025 041
Reposted by David Ryan KoesAlexey Amunts @amunts.bsky.social · 23/03/2025www.vant.ai/neo-1vant.aiThe world's most general-purpose atomistic foundation model, unifying structure prediction and de novo generation for the atoms of life 112
Reposted by David Ryan KoesEric Topol @erictopol.bsky.social · 23/03/2025A pie graph worth keeping in mind as the NIH budget plummets jamanetwork.com/journals/jam... for 356 new FDA drugs approved 5940151641
Reposted by David Ryan KoesOlexandr Isayev 🇺🇦 🇺🇸 @olexandr.bsky.social · 18/03/2025Our latest ChemRxiv preprint, "Transferable #MachineLearning Interatomic Potential for Pd-Catalyzed Cross-Coupling Reactions" Collaboration with @nsf-ccas.bsky.social @gabegomes.bsky.social @bobbypaton.bsky.social chemrxiv.org/engage/chemr... #compchem #chemsky 45910
Reposted by David Ryan KoesMatthieu Schapira @mattschap.bsky.social · 10/03/2025The CACHE #2 preprint is now online: bit.ly/3DyCmHN Active learning and fragment growing delivered confirmed hits. A citizen scientist using the Fold-it gaming interface designed the top compound! Kudos to Sasha and Madhushika @thesgc.bsky.social at the bench. @conscience-network.bsky.social 077
Reposted by David Ryan KoesComputational & Systems Biology Dept. at Pitt @csbpitt.bsky.social · 17/02/2025Andrew McNutt, '24 CPCB graduate, is ready for life's next adventure. Before he begins his career in drug discovery, he's taking a well-deserved break to hike the Appalachian Trail from Georgie to Maine. Read more: tinyurl.com/AndrewMcNutt 041
Reposted by David Ryan KoesStand Up for Science! @standupforscience.net · 12/02/2025Welcome to the Bluesky account for Stand Up for Science 2025! Keep an eye on this space for updates, event information, and ways to get involved. We can't wait to see everyone #standupforscience2025 on March 7th, both in DC and locations nationwide! #scienceforall #sciencenotsilence 289114575402
David Ryan Koes @dkoes.compstruct.org · 08/02/2025I’ll have to read the paper, but that’s a bizarre take given the graph. The issue isn’t the amount of data but the ability to generalize from it - which absolutely requires more innovative algorithms. 120
Reposted by David Ryan KoesRazvan Borza @rborza.bsky.social · 05/11/2024AlphaFold can predict protein, DNA, or RNA complexes.. BUT is it easy to determine the reliable interactions?🤔 ➡️ AlphaBridge will identify the most confident interactions, making your analysis easier! 🌐Try it here: alpha-bridge.eu 👀Read more: www.biorxiv.org/content/10.1... 611928
Reposted by David Ryan KoesMarco Trizzino @marcotrizzino.bsky.social · 22/01/2025NIH council meeting (NIDCR)scheduled for today, where our R01 grant (3rd percentile) was supposed to be discussed, was postponed indefinitely as a consequence of Trump's executive order which ordered pausing of all communications from all federal agencies. Not good. 1816080
Reposted by David Ryan KoesDiego del Alamo @delalamo.xyz · 19/01/2025Protein backbone diffusion models consistently undersample catalytically important motifs, and oversample idealized helices, raising questions about the appropriateness of these methods in designing starting points for enzyme design & evolution. From www.biorxiv.org/content/10.1... 28616
Reposted by David Ryan KoesOxford Protein Informatics Group (OPIG) @opig.stats.ox.ac.uk · 15/01/2025OPIG is now on Bluesky! Follow us for updates about the group's latest work, web app updates, and more. opig.stats.ox.ac.ukopig.stats.ox.ac.ukOPIGOxford Protein Informatics Group 0106
Reposted by David Ryan KoesFrank Noe @franknoe.bsky.social · 13/01/2025If you want to learn more about BioEmu, join Sarah Lewis and Michael Gastegger in @hannes-stark.bsky.social ‘s online seminar today. bsky.app/profile/hann... 1195
David Ryan Koes @dkoes.compstruct.org · 03/01/2025Rishal’s colab notebook will suggest pharmacophores given a receptor structure that can be directly imported into Pharmit for screening. Check it out! 072
Reposted by David Ryan KoesGeoff Hutchison @geoffhutchison.net · 30/12/2024I wrote up a 2024 Year in Review for @avogadro.cc 🧪⚗️ #opensource #chemsky In short, the community is amazing. Significant translations into 17 languages including 🇭🇷🇫🇷🇭🇺🇰🇷🇷🇴🇪🇸Tamil, 🇺🇦🇨🇳🇬🇪🇩🇪🇯🇵🇵🇹🇧🇷🇷🇸🇹🇷 .. and of course dozens of features and bug fixes discuss.avogadro.cc/t/2024-year-...discuss.avogadro.cc2024 Year-In-ReviewWhile it’s not strictly the end of 2024, I wanted to draft this early. Obviously a highlight is the release of 1.99 in time for Ubuntu LTS (24.04) … a summer of great coding / rendering, leading to t... 1155
David Ryan Koes @dkoes.compstruct.org · 24/12/2024I get it, and I can't adequately express how grateful I am for the PLINDER resource, but if you label something the test set, then people will `splits=[ "test"]` and use it uncritically. If the MLSB test set is the right one, why not label it "test" and have a larger "test-with-duplicates"? 130
David Ryan Koes @dkoes.compstruct.org · 24/12/2024These ligands make up 33% of the v2 plinder test set (shown with counts): MG 94 NAG 72 NAG-NAG 64 ZN 44 MN 32 BMP 30 HEM 24 EDO 18 SO4 17 PO4 16 ADP 15 GOL 13 ANP 13 CA 13 FMN 11 260
Reposted by David Ryan KoesJanani Durairaj (Jay) @ninjani.bsky.social · 24/12/2024Here's a year-end update from #PLINDER. It's been really great working on this project and all the other projects that it has kickstarted - the gift that keeps on giving. Happy holidays everyone! www.plinder.sh/blog/updatesplinder.shUpdatesUpdates 03813
Reposted by David Ryan KoesGabriele Corso @gcorso.bsky.social · 21/12/2024Boltz v0.4.0 is here! Today, we’re releasing our full data processing pipeline, making it easier than ever to build on top of Boltz. This release also includes our evaluation code and new results. Oh, and also pocket conditioning :) 16015
Reposted by David Ryan KoesLena Steckelberg @lenasteckelberg.bsky.social · 20/12/2024Hi Bluesky, just in time for the holidays I am excited to share the latest pre-print from my group! We solved the 3D structure of a mysterious viral RNA that resists degradation by host nucleases. A short 🧵 &link below – please also check out the full video! #RNA #RNAbiology #RNASky #lovevirology 713739
Reposted by David Ryan KoesCPCB @cmupittcompbio.bsky.social · 19/12/2024Last week several of our students presented their research at NeurIPS 2024 in Vancouver. We are so proud of the excellent work that they've accomplished and shared with the scientific community! 🧪 Check out each of their papers below: 1105
David Ryan Koes @dkoes.compstruct.org · 20/12/2024Explicit to whom? Certainly not those applying for tenure (in my experience). 100
Reposted by David Ryan KoesAlexey Amunts @amunts.bsky.social · 07/12/2024New version of Dockformer preprint landed on arXiv. This virtual screening docking method outperforms all Deep Learning-based approaches, achieving success rates of 90.53% on PDBbind and 82.71% on PoseBusters. Expected to accelerate drug discovery and reduce drug design costs. 1134
David Ryan Koes @dkoes.compstruct.org · 18/12/2024Cumulative percent of all systems. 13% are NAG, 6% are MG, so 19% are NAG or MG, etc 010
Reposted by David Ryan KoesCas @caswognum.nl · 17/12/2024With @polarishub.io we’ve built out infrastructure to make hosting and using large scale, ML ready dataset and benchmarks easy. In addition to the dataloaders, we could also maintain leaderboards. Would be happy to explore ways in which we can support the awesome work you’re doing with Plinder. 163
Reposted by David Ryan KoesAmerican Society of Human Genetics (ASHG) @geneticssociety.bsky.social · 16/12/2024The American Journal of Human Genetics sat with @fritzroth.bsky.social in the latest "Inside AJHG" to discuss his recently published paper, “A missense variant effect map for the human tumor suppressor protein CHK2.”➡️https://www.ashg.org/ajhg/inside-ajhg-with-fritz-roth/ #ASHG #GeneticsDiscoveries 084
David Ryan Koes @dkoes.compstruct.org · 16/12/2024If the test set is good, I am less concerned about the train set - let the developer figure out what works best - but I don’t want the bold numbers on the PLINDER benchmark to go to glycosylation predictors. 030
David Ryan Koes @dkoes.compstruct.org · 16/12/2024Is it a real interaction when the ligand is only there due to a catalyzed covalent bond? If you don’t provide a biochemically meaningful test set by default then all sorts of models will be trained and evaluated inappropriately. 220
David Ryan Koes @dkoes.compstruct.org · 16/12/2024I need to dive into exactly what the quality checks are, but the issue is a lot of the systems are biochemically uninteresting, as @keysandcompounds.bsky.social pointed out. This isn't an issue of the resolution but _what_ is being resolved. 210
David Ryan Koes @dkoes.compstruct.org · 16/12/2024Disagree. This should be the default. Data loader can deal with imbalances. 100
David Ryan Koes @dkoes.compstruct.org · 16/12/2024A way to implement this (in addition to providing full featured data loaders) is for query_index to also take a where argument that defaults to only selecting systems that pass quality checks. 100