Qin Ma

This paper introduces IDAM, a method for inferring disease-associated microbial gene modules from metagenomic and metatranscriptomic data, showing superior performance and reproducibility in inflammatory bowel disease datasets.

LRT integrates scTCR-seq and scRNA-seq data to infer T cell trajectories by combining clonal relationships with transcriptomic profiles.

CEMIG predicts cis-regulatory motifs from ATAC-seq data, outperforming existing methods and identifying cell-type-specific and shared TF motifs in GM12878 and K562 cells.

This paper introduces BSP, a method for identifying spatially variable genes from 2D or 3D spatial transcriptomics data, showing improved accuracy and efficiency in simulations and biological validations.

This study uses spatial transcriptomics to identify gene signatures in the human temporal cortex linked to Alzheimer's pathology.

This paper introduces SpaGFT, a graph Fourier transform model for spatial omics data analysis, enabling accurate identification of tissue modules and their functional relationships in spatial transcriptomics and proteomics data.

The paper shows that SUPT16H, a FACT subunit, interacts with BRD4 to suppress antiviral interferon signaling, and its inhibition enhances IFN responses against multiple viruses.

This paper introduces PHAT, a deep graph learning framework for peptide secondary structure prediction, achieving better accuracy and interpretability for short peptides.

The paper introduces BANYAN, a Bayesian model for analyzing community connectivity in spatial transcriptomics data, revealing cell interactions in tumor microenvironments and adipose tissue.

The paper uses spatial transcriptomics and the MAPLE algorithm to analyze fibrotic lung tissue, identifying spatial biomarkers and fibrotic programs in IPF.

RESEPT uses deep learning to visualize and characterize tissue architecture from spatial transcriptomics data, revealing pathological structures in Alzheimer's and glioblastoma samples.

DeepMAPS infers biological networks from single-cell multi-omics data using a heterogeneous graph transformer, outperforming existing tools in cell clustering and pathway prediction.

This paper introduces scFEA, a graph neural network model to estimate cell-wise metabolic flux from scRNA-seq data, validated with matched metabolomics data and applied to multiple datasets.

The paper introduces a data purification algorithm to improve detection of disease-associated microbes in microbiome data by reducing noise and heterogeneity.

This study evaluates 20 deep learning models for cis-regulatory motif finding using genomic data, finding that model choice depends on data type and size.

This paper introduces scDEAL, a deep transfer learning framework that predicts cancer drug responses from single-cell RNA-seq data by integrating bulk RNA-seq drug response data and interpretable gene signatures.

This paper introduces SPRUCE, a Bayesian spatial multivariate mixture model for spatial transcriptomics data, which identifies cell sub-populations while accounting for skewness and spatial correlation.

scGNN introduces a graph neural network framework for scRNA-Seq analyses, improving gene imputation and cell clustering on benchmark datasets and revealing disease-related neural development in Alzheimer's disease.

IRIS-FGM is an R package for analyzing scRNA-Seq data to identify functional gene modules, cluster cells, and perform enrichment analysis, with support for Seurat objects.

The paper introduces a computational framework, SeqATU, to predict alternative transcription units in bacterial genomes using RNA-Seq data, achieving high precision and recall in E. coli.

scREAD is a database that integrates and provides analysis of scRNA-Seq and snRNA-Seq datasets from Alzheimer's disease human and mouse models.

This paper introduces a PPI prediction method using gradient tree boosting and L1-regularized logistic regression, achieving high accuracy on multiple organisms.

The paper introduces DMLDA-LocLIFT, a method for predicting multi-label protein subcellular localization using dimensionality reduction and a classifier, achieving high accuracy on bacterial and plant datasets.

MiREDiBase is a manually curated database of validated and putative miRNA editing events, including 3,059 sites from 626 pre-miRNAs in humans and three primates.

StackRAM is a cross-species method for identifying m6A sites using machine learning, achieving high accuracy in yeast, human, and Arabidopsis.

This paper introduces GRGNN, a graph neural network for gene regulatory network inference using supervised and semi-supervised learning, achieving state-of-the-art performance on DREAM5 benchmarks.

The paper introduces DESSO, a deep learning framework for predicting regulatory motifs from ChIP-Seq data, showing improved accuracy over existing tools.

The paper introduces LTMG, a model for capturing transcriptional regulatory heterogeneities in scRNA-seq data, showing improved fitting and validation on multiple datasets.

rSeqTU is an R package that predicts bacterial transcription units using machine learning, integrating quality control, feature selection, and visualization tools.