🔥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

Excited to share our preprint “BoltzDesign1: Inverting All-Atom Structure Prediction Model for Generalized Biomolecular Binder Design” — a collaboration with Martin Pacesa, Zhidian Zhang , Bruno E. Correia, and Sergey Ovchinnikov. 🧬 Code will be released in a couple weeks

This is the kind of message that makes it all worth it. When someone takes a moment to say thank you, it reminds me why we keep pushing forward—sharing tools, writing posts, and trying to make science more open and accessible. Grateful for the connection and the kind words!

Wow, is Orb-v3 an edgeless foundation model for materials & molecular dynamics? 30× faster atomistic sims, minimal memory, and near-DFT fidelity—at scale. 🧵1/2

Atom level enzyme active site scaffolding using RFdiffusion2 🚀 New preprint from David Baker!🚀 1. RFdiffusion2 introduces a generative model that designs functional enzymes directly from atomic-level active site descriptions—without needing predefined sequence indices or

A Foundation Model for Accurate Atomistic Simulations in Drug Design 1. This paper introduces FeNNix-Bio1, a foundation machine-learning model for atomistic molecular dynamics simulations, aimed at revolutionizing drug design by providing accurate simulations that include

PepPCBench is a Comprehensive Benchmark for Protein-Peptide Complex Structure Prediction with AlphaFold3 1. PepPCBench introduces the most comprehensive benchmark to date for evaluating protein-peptide complex structure prediction using AlphaFold3 (AF3) and other PFNNs,

developers.google.com/profile/badges…

AF2χ: Predicting protein side-chain rotamer distributions with AlphaFold2

Computational design of conformation-biasing mutations to alter protein functions 1. The authors present Conformational Biasing (CB), a computational workflow that predicts mutations to bias proteins toward specific conformational states, thereby altering or enhancing protein

CreoPep: A Universal Deep Learning Framework for Target-Specific Peptide Design and Optimization 1. CreoPep is a generative deep learning platform that enables target-specific peptide design by combining masked language modeling with progressive masking and energy-based

#SORTEIO🎉 Em gratidão ao apoio de vocês ao meu trabalho, vou sortear um Switch 2 aos membros do ofertasnintendo.com.br - Me segue aí - 💙Curtir +🔄 RT sem comentar - Marque 2 amigos com quem jogaria um Mario Kart e coloque o print de qual grupo você faz parte. Sorteio em 23/06

Deep-learning-based single-domain and multidomain protein structure prediction with D-I-TASSER Nature Biotechnology １．D-I-TASSER is a hybrid deep-learning and physics-based pipeline that outperforms AlphaFold2 and AlphaFold3 in both single-domain and multidomain protein structure

At FutureHouse, we’ve noticed scientific agents are good at applying average intelligence across tasks. They always seem to make the obvious choices, which is good, but discovery sometimes requires more intuition and insight than average. We’ve made the first step today towards

Excited to unveil Boltz-2, our new model capable not only of predicting structures but also binding affinities! Boltz-2 is the first AI model to approach the performance of FEP simulations while being more than 1000x faster! All open-sourced under MIT license! A thread… 🤗🚀

Researchers have discovered previously undetected chemical bonds within archived protein structures, revealing an unexpected complexity in protein chemistry. phys.org/news/2025-05-c…

Our latest work is out: we designed dual GLP1R/GCGR agonists—cyclic peptides that activate both metabolic receptors, entirely from sequence alone. This has never been done before. 🔗 biorxiv.org/content/10.110…

All-Atom Protein Sequence Design using Discrete Diffusion Models １．This paper presents the first application of discrete diffusion models to protein design using an all-atom representation. Instead of relying on the standard 20 amino acids, the authors use SELFIES to model

Structure-guided design of protein attachment points for functional augmentation of complex molecular machines １．A new computational tool, SIMPLIFE, enables structure-guided insertion of peptide tags into proteins to enhance or modify their function without compromising

CovDocker: Benchmarking Covalent Drug Design with Tasks, Datasets, and Solutions １．A major gap in molecular docking is the lack of support for covalent binding, which plays a critical role in drug design due to its strong and enduring interactions. CovDocker addresses this by

A Benchmark for Quantum Chemistry Relaxations via Machine Learning Interatomic Potentials １．PubChemQCR is the largest publicly available dataset of DFT-based molecular relaxation trajectories, with 3.5 million molecules and over 300 million conformations, including 105 million