Xin Gao

BioMINTREL expands biological problem solving through cross-disciplinary representations

BioMINTREL enhances biological analysis by integrating cross-disciplinary methods, improving agreement with experts and uncovering new insights from existing data.

Speciesformer learns conserved cellular states for cross-species generative virtual cell modeling

Speciesformer learns conserved cellular states across species to enable cross-species generative modeling of virtual cell states and their responses to interventions.

CryoForge: A Self-Correcting Agent for Cryo-EM Model Building That Learns When to Act and When to Stop

CryoForge is an evidence-gated agent that improves cryo-EM model building by selectively accepting or rejecting edits based on structural evidence, achieving validated improvements in most test cases.

DQHTFI: Dynamic-Query Hypergraph Transformer for Fine-Grained Drug-Target Interaction and Affinity Prediction

This paper introduces DQHTFI, a framework for drug-target interaction classification and binding affinity regression, achieving competitive results on benchmark datasets.

PG-MLD: Physics-Guided Molecular Representation Learning via Dynamic 3D Trajectory Distillation

PG-MLD transfers dynamic 3D physical knowledge to SMILES-based molecular models, improving property prediction without requiring 3D conformer generation.

ProtSyntax: a protein large language model for decoding post-translational modification syntax and function

ProtSyntax is a protein language model that improves PTM site prediction and functional inference by integrating contextual and structural information.

Evolutionary dynamics of the Timopheevii wheat lineage

The paper presents genomic resources for the Timopheevii wheat lineage, revealing evolutionary dynamics including homoeologous exchange, genome instability, and geographic range expansion.

WattmaMod enables high-resolution and extensible RNA modification profiling for nanopore direct RNA sequencing

WattmaMod detects multiple RNA modifications from nanopore sequencing data using deep learning, achieving high accuracy and extending to low-resource modifications.

ProteinMCP: An Agentic AI Framework for Autonomous Protein Engineering

ProteinMCP accelerates and democratizes protein engineering by automating workflows and integrating 38 tools, achieving a comprehensive fitness modeling task in 11 minutes.

Thermo-Dynamic Flux Balance Analysis, a novel approach to simulate circadian metabolism

The paper introduces tdFBA, a novel method for simulating circadian metabolism across organs, and shows it can recapitulate metabolic oscillations and perturbations in mice and humans.

HINS: HLA-mediated immunogenic neoantigen score for robust prediction of immune checkpoint blockade response

This paper introduces HINS, a deep-learning method that predicts immune checkpoint blockade response using HLA-mediated immunogenic neoantigen scores, achieving high accuracy in identifying responders.

Efficient Identification of Short Tandem Repeats via Context-Aware Motif Discovery and Ultra-Fast Sequence Alignment

FastSTR efficiently identifies and characterizes tandem repeats across 13 species with high accuracy and speed, uncovering new genomic elements and disease-related variations.

Stabilizing mammalian RNA thermometer confers neuroprotection in subarachnoid hemorrhage

This paper identifies RNA G-quadruplexes as temperature and potassium sensors that regulate alternative splicing and neuroprotection in subarachnoid hemorrhage.

THLANet: A Deep Learning Framework for Predicting TCR-pHLA Binding in Immunotherapy Applications

THLANet predicts TCR-pHLA binding using deep learning, outperforming existing methods and providing structural insights into TCR-antigen interactions.

Unify: Learning Cellular Evolution with Universal Multimodal Embeddings

Unify learns universal cell embeddings across species by integrating RNA expression with protein and general language model embeddings, enabling cross-species comparisons and accurate perturbation response prediction.

GeoGAT-site: A Face-Centered Geometric Graph Attention Network for Protein-Protein Interface Prediction

GeoGAT-site predicts protein-protein interaction sites using a geometric graph attention network, achieving high accuracy and efficiency compared to existing methods.

NeuralTE: an accurate approach for Transposable Element superfamily classification with multi-feature fusion

NeuralTE is a deep learning method for classifying transposable elements at the superfamily level, achieving high accuracy and robustness across diverse datasets.

Origin and evolution of the bread wheat D genome

The paper analyzes the genetic composition and history of the bread wheat D genome using a pangenome of its donor species, revealing contributions from discrete subpopulations of Aegilops tauschii.

AI identifies potent inducers of breast cancer stem cell differentiation based on adversarial learning from gene expression data

This study uses AI to identify small molecules that induce breast cancer stem cell differentiation by training a deep neural network on gene expression data and validating results experimentally.

PPML-Omics: a Privacy-Preserving federated Machine Learning method protects patients' privacy in omic data

PPML-Omics is a privacy-preserving federated learning method that balances privacy protection and model utility across three omic data tasks.

Audit to Forget: A Unified Method to Revoke Patients' Private Data in Intelligent Healthcare

The paper introduces AFS, a tool to revoke patients' private data from pre-trained models by auditing usage and purifying knowledge, tested across multiple tasks and datasets.

Influence of autozygosity on common disease risk across the phenotypic spectrum

The paper investigates the association between autozygosity and common diseases in multiple cohorts, finding significant links to twelve diseases and estimating autozygosity's contribution to type 2 diabetes cases.

Deep Learning Enhanced Tandem Repeat Variation Identification via Multi-Modal Conversion of Nanopore Reads Alignment

DeepTRs identifies tandem repeat variations directly from Nanopore reads using multi-modal conversion and deep learning, achieving high sensitivity, accuracy, and completeness.

AB-Gen: Antibody Library Design with Generative Pre-trained Transformer and Deep Reinforcement Learning

AB-Gen uses reinforcement learning and a generative pre-trained Transformer to design antibody sequences with multiple desirable properties, improving success rates over traditional methods.

Online single-cell data integration through projecting heterogeneous datasets into a common cell-embedding space

SCALEX integrates single-cell data into a common embedding space without retraining, outperforming existing methods on diverse datasets and enabling expandable atlases.

Self-supervised contrastive learning for integrative single cell RNA-seq data analysis

CLEAR is a self-supervised contrastive learning framework for scRNA-seq that improves clustering, batch correction, and pseudo-time inference by reducing technical noise and heterogeneity.

Deep learning identifies and quantifies recombination hotspot determinants

This paper introduces RHSNet, a deep learning method that identifies and quantifies recombination hotspot determinants across species, sexes, and populations.

HiC-LDNet: A general and robust deep learning framework for accurate chromatin loop detection in genome-wide contact maps

HiC-LDNet is a deep learning framework for chromatin loop detection in Hi-C data, achieving high accuracy in both bulk and sparse single-cell Hi-C maps.

ReFeaFi: Genome-wide prediction of regulatory elements driving transcription initiation

ReFeaFi predicts regulatory elements genome-wide using a two-model approach, achieving good performance across species and identifying disease-associated variants in human regulatory regions.

ChemPLAN-Net: A deep learning framework to find novel inhibitor fragments for proteins

ChemPLAN-Net uses deep learning to predict novel inhibitor fragments for proteins by analyzing physicochemical features and co-crystal structures.