arXiv | An Interpretable Framework Applying Protein Words to Predict Protein-Small Molecule Complementary Pairing Rules
ABSTRACT: Despite the high accuracy of 'black box' deep learning models, drug discovery still relies on protein-ligand interaction principles and heuristics. To improve interp…
iscience | Predicting Protein-Nucleic Acid Interactions via Protein Language Models with Biophysical and Evolutionary Priors
ABSTRACT: Protein interactions with nucleic acids are fundamental to numerous biological processes. Here, we present PNABPred, a multi-modal framework that integrates biophysi…
Advanced Science | Automatically Defining Protein Words for Diverse Functional Predictions Based on Attention Analysis of a Protein Language Model
ABSTRACT: Understanding the relationship between protein sequence and function remains a longstanding challenge in bioinformatics, and to date the lion's share of related tool…
arXiv | Improving the accuracy and generalizability of molecular property regression models with a substructure-substitution-rule-informed framework
ABSTRACT: Artificial Intelligence (AI)-aided drug discovery is an active research field, yet AI models often exhibit poor accuracy in regression tasks for molecular property p…
Journal of Chemical Information and Modeling | GLMCyp: A Deep Learning-Based Method for CYP450-Mediated Reaction Site Prediction
ABSTRACT: Cytochrome P450 enzymes (CYP450s) play crucial roles in metabolizing many drugs, and thus, local chemical structure can profoundly influence drug efficacy and toxici…
Nature Communications | Barcoded screening identifies nanocarriers for protein delivery to kidney
ABSTRACT: Targeted protein delivery with nanocarriers holds significant potential to enhance therapeutic outcomes by precisely directing proteins to specific organs or tissues…
Neuron | An intermediate open structure reveals the gating transition of the mechanically activated PIEZO1 channel
ABSTRACT: PIEZO1 is a mechanically activated cation channel that undergoes force-induced activation and inactivation. However, its distinct structural states remain undefined.…
Preprint | Enhancing Enzyme Activity with Mutation Combinations Guided by Few-shot Learning and Causal Inference
ABSTRACT: Designing enzyme sequences to enhance product yield represents a fundamental challenge in metabolic engineering. Here, we established a workflow that integrates comp…
Nature Methods | EvoAI enables extreme compression and reconstruction of the protein sequence space
ABSTRACT: Designing proteins with improved functions requires a deep understanding of how sequence and function are related, a vast space that is hard to explore. The ability …
