Min Li

UniPert-G2CP transfers genetic perturbation insights to chemical perturbation modeling, enabling efficient in silico drug screening with reduced data costs.

SpaRank is a transferable spatial deconvolution framework that uses rank-based encodings to robustly infer cell-type compositions across diverse biological contexts and omics modalities.

PROBind predicts, analyzes, and visualizes protein-protein and protein-nucleic acid binding residues using sequence and structure data, integrating multiple predictors and providing interactive tools.

FluNexus provides a web platform for antigenic prediction and visualization of influenza A viruses, offering tools for data preprocessing, prediction, and visualization of antigenic evolution.

ChIANet predicts protein-mediated chromatin architectures across contexts using deep learning, revealing context-dependent reconfiguration and functional biases.

NanoLoop predicts genome-wide chromatin loops using Nanopore sequencing data, identifying methylation patterns that influence loop types and reveal new long-range interactions.

GRAVITY improves RNA velocity modeling by integrating gene regulatory networks, enabling accurate trajectory inference and discovery of terminal cell states in embryonic brain development.

SpatialModal integrates gene expression and histological images in spatial transcriptomics to improve spatial analysis and domain identification.

This paper introduces Tabula, a privacy-preserving foundation model for single-cell transcriptomics using federated learning and tabular modeling, achieving better performance with less data and revealing regulatory logic across biological systems.

ACE provides a contrastive learning framework for mosaic integration of single-cell multi-omics data, improving representation of cellular heterogeneities in datasets with incomplete modalities.

DyNDG identifies leukemia-related genes using a dynamic network model integrating time-series differential genes, showing improved accuracy over existing methods.

FusNet predicts protein-mediated chromatin loops using genome sequence, open chromatin, and ChIP-seq data, showing high consistency with Hi-C and associations with regulatory functions and disease risk variants.

ViPal improves influenza virulence prediction by integrating prior viral knowledge into machine learning models using genomic sequences.

This study constructs a 3D genome atlas of genetic variants and their pathological effects using a scoring algorithm and a web-based database.

This paper introduces HyMM, a hybrid method for disease-gene prediction that integrates multiscale module structures, showing improved performance through cross-validation and independent testing.

DeepLncLoc predicts lncRNA subcellular localization using a subsequence embedding method and text CNN, outperforming k-mer-based models and existing predictors.

SSRE improves cell type identification in scRNA-seq by enhancing similarity measurement through sparse subspace representation and gene selection.

LoopPredictor predicts enhancer-promoter loops in cell types lacking long-range contact maps using ensemble machine learning and multi-omics features.

This paper introduces a method to control leakage in electrophysiological source imaging using structured sparse Bayesian learning and evaluates its performance against existing methods.