Machine Learning for Chemistry: Basics and Applications sciencedirect.com/science/articl…

Cordialmente invitados a mi sustentación doctoral modalidad híbrida

Welcome to the new doctor from our group. Adrian did a wonderful job and gave a great dissertation. The jury awarded honorable mention. Congratulations, Dr. Orjuela!

El turno es para AdrianO de la Universidad Nacional de Colombia #IVSBCMC

#SomosCiencia En el mamey rojo del Pacífico habría una esperanza para el tratamiento del Alzheimer 🙌 Así lo demostró computacionalmente Adrián Orjuela, doctor en Química UNAL y quien estudió sus propiedades químicas ➡️ t.ly/u7Sx1 Vía Prensa UNAL - Universidad Nacional de Colombia | #SomosUNAL

Congratulations to Nicolás and Adrián on their graduation. Nicolás earned his master's degree, and Adrián completed his Ph.D. in chemistry, both with honors. It was a true pleasure to be your supervisor. You both did outstanding work. Wishing you great success in your careers!

This is great 👍 Now we only need a proper benchmark to see that none of these models actually work.

Boltz-1: Democratizing Biomolecular Interaction Modeling 1. Boltz-1 introduces the first fully open-source model achieving AlphaFold3-level accuracy in predicting 3D structures of biomolecular complexes, democratizing access to cutting-edge structural biology tools. 2. The

🎉 Our latest article on the role of carotenoids from red mamey in preventing Aβ aggregation is published in Journal of Alzheimer's Disease! 🧠 A great collaboration between @UNAL 🇨🇴 and INDICASAT-AIP 🇵🇦. Special Congratulations to AdrianO for the wonderful work! 👏 journals.sagepub.com/doi/10.1177/13…

XDock: A General Docking Method for Modeling Protein–Ligand and Nucleic Acid–Ligand Interactions • XDock introduces a universal docking framework capable of modeling both protein–ligand and nucleic acid–ligand interactions with high accuracy, bridging a significant gap in

Machine Learning in Drug Discovery Resources page updated for 2025. github.com/PatWalters/res…

I’ll be presenting our #GenerativeAI drug design method DrugHIVE at #ACS tomorrow. Come check it out! JCIM & JCTC Journals talk: Automated drug design and optimization with structure-based generative deep learning paper: pubs.acs.org/doi/10.1021/ac… code: github.com/jssweller/Drug…

PaCS-Q: Python Toolkits for Path Sampling in MD and QM/MM MD Simulation | JCIM pubs.acs.org/doi/10.1021/ac… JCIM & JCTC Journals #comchem #combiol #qmmm

CaTS: machine learning for faster transition state searches for catalysts Catalysis underpins ~90% of chemical production and ~35% of global GDP. Yet discovering new catalysts remains slow and resource-intensive. Most computational screening only relies on adsorption energies,

Excited to announce mBER, our fully open AI tool for de novo design of epitope-specific antibodies. To validate, we ran the largest de novo antibody experiment to date: >1M designs tested against 145 targets, measuring >100M interactions. We found specific binders for nearly half

Impact of Protein Conformational Diversity on Structure-Based Prediction of Druggability pubs.acs.org/doi/10.1021/ac… Ayse A. Bekar Cesaretli Diane Joseph-McCarthy #JCIM Vol65 Issue17 #PharmaceuticalModeling

Machine Learning in Chemistry: A Data Centred, Hands-on Introductory Machine Learning Course for Undergraduate Students 1. This innovative course, Machine Learning in Chemistry (MLChem), is designed specifically for undergraduate students, bridging the gap between traditional

Molecular docking has always been crucial. However, managing poses, profiling their interactions, and doing so with hundreds or thousands of ligands can be challenging. With LiteFold Docking, it's just a matter of minutes. Live now and free. Links in the comments.

🚀 1 BILLION molecules clustered on a single workstation (55 GB RAM, CPU only) in just 2.5 hours. Presenting the most time & memory-efficient method (so far!) for clustering ultra-large molecular libraries. 📄 Preprint: biorxiv.org/content/10.110… 💻 Code: github.com/mqcomplab/bble…