Breaking: The official release of educational guides for AlphaFold Server from @GoogleDeepMind https://t.co/R00qGf0ZQ0 These tutorials aim to assist new users in gaining a deeper understanding of the latest AlphaFold version’s capabilities and maximizing the potential of

De novo designed bifunctional proteins for targeted protein degradation 1. A new study by Mylemans et al. presents a novel approach to targeted protein degradation (TPD) using de novo designed bifunctional proteins. This method offers an alternative to traditional PROTACs by

Starlink Mini offers fast, reliable internet on the go—great for traveling, camping, exploring, boating, RVing, and more. Stay connected without dead zones or slow speeds. Order online in under 2 minutes.

Greater Than the Sum of Its Parts: Building Substructure into Protein Encoding Models 1. This novel study introduces Magneton, a novel environment for developing protein models that incorporate substructural knowledge. Proteins are not just sequences of amino acids but are

Pushing the Limits of One-Dimensional NMR Spectroscopy for Automated Structure Elucidation Using Artificial Intelligence 1. A novel study leverages deep learning to achieve automated structure elucidation of organic compounds using only 1D NMR spectra. This method can handle

Out-of-Distribution Detection in Molecular Complexes via Diffusion Models for Irregular Graphs 1. A new study introduces a probabilistic framework for detecting out-of-distribution (OOD) inputs in molecular complexes using diffusion models. This approach is particularly

Catch a glimpse of Godzilla Survival, how to unlock Godzilla for FREE, and how to emotionally recover after losing your rings to Shockirus during the Godzilla Meets Sonic Rumble Crossover Event 🩹 Sonic Rumble’s Community Lead, Lukas, is back, and this time he’s explaining how

Missense mutations in cancer: in silico predictions, developing treatments, and overcoming cell resistance 1. This comprehensive review by Mariam Fouad explores the role of missense mutations in cancer, emphasizing their impact on tumor initiation, progression, and therapeutic

ChemATP: A Training-Free Chemical Reasoning Framework for Large Language Models 1. ChemATP introduces a novel framework that decouples chemical knowledge from the reasoning engine, enabling large language models (LLMs) to perform chemically grounded reasoning by retrieving and

Long-range electrostatics for machine learning interatomic potentials is easier than we thought 1. This perspective article by Dongjin Kim and Bingqing Cheng introduces the Latent Ewald Summation (LES) framework, which can capture long-range interactions, charges, and electrical

Taming T-REX: A Canonical Language for Geometry-Aware Generative Design of Transition-Metal Complexes 1. Researchers introduce T-REX, a novel canonical notation for transition-metal complexes (TMCs), addressing the challenge of representing their complex coordination geometries

Go short as easily as you go long. Express your market view nearly 24 hours a day with E-mini S&P 500 options on futures (ES) from CME Group.

Large-scale structure and sequence-based comparative analysis enables functional annotation of animal venom peptides 1. Researchers have conducted a comprehensive analysis of nearly 4,000 venom peptides from marine snails, including teretoxins and conotoxins, using AlphaFold2

CrystalFormer-CSP: Thinking Fast and Slow for Crystal Structure Prediction 1. CrystalFormer-CSP is a novel framework that merges data-driven heuristic and physics-driven optimization approaches to predict stable crystal structures. This hybrid method combines the speed of

SafeBench-Seq: A Homology-Clustered, CPU-Only Baseline for Protein Hazard Screening with Physicochemical/Composition Features and Cluster-Aware Confidence Intervals 1. A novel benchmark named SafeBench-Seq is introduced, focusing on protein hazard screening. It stands out by

Comparative Evaluation of Molecular Generation Methods for Bioactive Compound Design: A Rigorous Statistical Benchmark Across Drug, Agrochemical, and Small Molecule Datasets 1. This study presents a comprehensive benchmark of five molecular generation methods across diverse

Dnamotiftokenizer: Towards Biologically Informed Tokenization of Genomic Sequences 1. A new study introduces DNAMotifTokenizer, a novel approach to tokenizing genomic sequences that incorporates domain knowledge of DNA sequence motifs. This method significantly improves the

Generative Multi-Objective Bayesian Optimization with Scalable Batch Evaluations for Sample-Efficient De Novo Molecular Design 1. A novel “generate-then-optimize” framework is introduced for de novo molecular design, which decouples candidate generation from selection, allowing

Fast, Systematic and Robust Relative Binding Free Energies for Simple and Complex Transformations: Dual-LAO 1. A novel method named dual-LAO has been introduced to revolutionize the calculation of Relative Binding Free Energies (RBFE) in drug discovery. This novel approach

Molecular Quantum Computations on a Protein 1. A novel study presents the first application of quantum-centric supercomputing to simulate the electronic structure of a protein, specifically the Trp-cage miniprotein. This work pushes the boundary of quantum chemistry simulations

Biosecurity-Aware AI: Agentic Risk Auditing of Soft Prompt Attacks on ESM-Based Variant Predictors 1. This novel study introduces SAGE, a novel framework for auditing the adversarial robustness of genomic foundation models (GFMs) like ESM, revealing significant vulnerabilities

ProFam: Open-Source Protein Family Language Modelling for Fitness Prediction and Design 1. ProFam-1 is a 251 M-parameter autoregressive protein-family language model (pfLM) that reaches state-of-the-art zero-shot fitness prediction on ProteinGym: Spearman ρ = 0.47 for

Fold or Flop: Quality Assessment of AlphaFold Predictions on Whole Proteomes 1. The study introduces the “arity map,” a 2-D embedding that simultaneously clusters protein structures and flags unreliable AlphaFold predictions by analyzing local packing density. 2. Using just the

Structure-Aware Antibody Design with Affinity-Optimized Inverse Folding 1. SimBinder-IF turns ESM-IF into a high-affinity antibody generator by freezing the structure encoder and tuning only 18 % of the parameters, slashing GPU memory and wall-clock time while boosting