Jian Peng

This paper introduces PocketXMol, a generative foundation model for molecular interactions with protein pockets, achieving state-of-the-art performance in 11 tasks and demonstrating success in designing inhibitors and peptides.

The paper introduces HIL-DD, a human-in-the-loop drug design framework that uses an Equivariant Rectified Flow Model to enable efficient collaboration between human experts and AI for generating drug-like molecules.

FlowDesign improves antibody CDR design using flow matching and better priors, achieving higher affinity and neutralizing potency against HIV mutants.

The paper identifies a shared genetic risk module involving PSEN2 and actin regulation across alpha-synucleinopathies, linking them to Alzheimer's disease mechanisms.

The paper identifies a molecular-level representation of odors that predicts receptor, neural, and behavioral responses across species and shows metabolic relationships in odor space.

The paper introduces RDE, an unsupervised method that predicts mutation effects on protein-protein binding by estimating conformational flexibility from protein structures, outperforming existing methods.

The paper develops DeepCas13, a deep learning model to predict CRISPR-Cas13d gRNA on-target activity and off-target viability effects, improving accuracy for RNA editing applications.

From a single sequence, OmegaFold reaches mean LDDT 0.82 on 146 CAMEO targets, between MSA-based RoseTTAFold (0.75) and AlphaFold2 (0.86), and runs about ten times faster.

This paper introduces Proximal Exploration (PEX) and MuFacNet to improve protein sequence design by prioritizing low-mutation high-fitness mutants and predicting mutational effects.

This paper introduces a diffusion-based generative model for designing and optimizing antigen-specific antibodies by jointly modeling CDR sequences and structures.

Jumper improves transcript assembly for Nidovirales by addressing discontinuous transcription, outperforming existing methods and identifying non-canonical transcripts.

This study identifies multiple SARS-CoV-2 strains within and across hosts using bulk RNA sequencing and consensus sequences, revealing within-host diversity, recombination, and geographic strain variation.

This paper introduces ECNet, a deep learning model that uses evolutionary context to predict protein variant fitness, outperforming existing methods on multiple datasets.

This paper introduces DeepSyn, a machine learning method for gene functional enrichment that uses a knowledge graph to infer gene functions based on disease and drug context, achieving high accuracy in various applications.

The paper introduces a meta-learning framework to predict phosphorylation sites for kinases with limited experimental data, showing improved transferability and accuracy.

HiCluster improves clustering of low coverage single-cell Hi-C data by imputing using linear convolution and random walk, revealing TAD-like structures consistent with bulk data.

This paper introduces DeepFold, a deep learning model that learns structural motif representations for efficient protein structure search, outperforming existing methods like FragBag.

Opal improves metagenomic binning by using low-density hashing to achieve faster and more accurate identification of sequencing read origins compared to existing methods.

The paper introduces net-SNE, a neural network method for visualizing single-cell RNA sequencing data that scales to millions of cells and generalizes to new cells.

DeepSignal predicts kinase and SH2 domain substrate specificity using deep learning, outperforming existing methods and identifying cancer-related mutations and pathways.

GEM reconstructs 3D chromatin structures from Hi-C data using manifold learning and conformational energy, outperforming existing methods and recovering long-range interactions.

This paper introduces DTINet, a network integration method for predicting drug-target interactions and repositioning drugs, showing improved performance and validated novel COX inhibitor applications.