🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Scientists CIIRC ČVUT Loschmidt Laboratories, Masaryk University IOCB Prague and ICRC have developed a new method to improve the computational design of biotherapeutics. Their new machine-learning method enables more efficient design of proteins with better interaction properties. bit.ly/3UUdHmO

MassSpecGym: A benchmark for the discovery and identification of molecules • MassSpecGym introduces a comprehensive benchmark and dataset for molecular discovery from mass spectrometry (MS/MS) data, addressing limitations of existing datasets in scope, standardization, and data

Can machine learning help unlock the vast potential of unexplored molecular structures in biological and environmental samples through mass spectrometry data analysis? IOCB Prague "MassSpecGym: A benchmark for the discovery and identification of molecules" • With less than

Training on test proteins improves fitness, structure, and function prediction • This study presents a novel test-time training (TTT) approach for proteins, enabling machine learning models to adapt to individual test proteins dynamically, enhancing prediction accuracy without

New idea: (1) ML approaches try to fit all proteins, limiting accuracy on specific ones. 🔍 (2)Test-time training adapts models to target proteins on the fly ! 🧬 TRAINING ON TEST PROTEINS IMPROVES FITNESS, STRUCTURE, AND FUNCTION PREDICTION arxiv.org/pdf/2411.02109

Can machine learning models adapt to individual proteins in real-time to improve their prediction accuracy across different protein-related tasks? ČVUT v Praze arXiv.org "Training on test proteins improves fitness, structure, and function prediction" • Machine learning models in

Working on predicting molecular structure from mass spec data? Check out MassSpecGym from Roman Bushuiev, Anton Bushuiev, and the team! This might be one of the most well-documented datasets on Polaris right now. MassSpecGym has the largest publicly available collection of 231K

What are the most interesting datasets and benchmark-related work for ML in drug discovery at NeurIPS? We’ll be doing short interviews with researchers at the conference and workshops and handing out some Polaris merch! Here’s who we have on the shortlist. Let us know what

Check out our #NeurIPS2024 spotlight poster on MassSpecGym, a dataset and benchmark for discovering new molecules from nature 🌿. If you work on generative models for graphs/molecules, plug your model into MassSpecGym and see how many molecules you can discover! 🚀 1/6

Met the twins ⁦Anton Bushuiev⁩ ⁦Roman Bushuiev⁩

The MassSpecGym team presenting the poster at #NeurIPS2024! Fei Wang Adamo Young Roman Bushuiev Anton Bushuiev Raman Samusevich

MassSpecGym is the largest publicly available collection of mass spectra data. It’s a standardized collection of 231K high-quality mass spectra representing 29K unique molecular structures, with 33% of the dataset being generated from newly measured, in-house data. 🛡️The dataset

🤝 In April 2024, brothers Roman and Anton Bushuiev from the teams of Tomáš Pluskal IOCB Prague and Josef Šivic CIIRC ČVUT initiated a collaboration among 14 research institutes across the globe to benchmark #AI methods for the discovery of molecules from mass spectrometry data.

Back in July 2023 we organized a small bioML symposium at IOCB Prague, and it turned out to be a very pleasant and successful event. This summer we are following up with a great line-up of speakers. Please register for free, deadline May 30. tinyurl.com/bioMLPrague25

Mass spectrometry is a key method to discover and identify molecules in biological and environmental samples. Yet, >90% of mass spectra remain hard to interpret. We present DreaMS — a foundation model to interpret mass spectra of small molecules. nature.com/articles/s4158…

⚛️ Tomáš Pluskal from IOCB Prague, together with his student Roman Bushuiev and colleagues from #CIIRC CTU, Josef Šivic and Anton Bushuiev, have developed a machine learning model called #DreaMS – which accelerates the analysis of previously unknown molecules.

Today is the registration deadline for our bioML symposium on Aug 21-22. Last chance to secure your spot! More info at tinyurl.com/bioMLPrague25