Our methods and models are available as open-source tools at the lab’s GitHub site. We regularly maintain the tools. Please contact for any questions.

deepManReg is an interpretable regularized learning model to predict phenotypes from multi-modal data. First, deepManReg employs deep neural networks to learn cross-modal manifolds and then to align multi-modal features onto a common latent space. Second, deepManReg uses cross-modal manifolds as a feature graph to regularize the classifiers for improving phenotype predictions and also for prioritizing the multi-modal features and cross-modal interactions for the phenotypes. [Publication: Nguyen et al., Nature Computational Science, 2022][Availability: PyTorch, Python,]

scGRNom is a general pipeline for predicting the gene regulatory network via multi-omics data. The pipeline inputs the chromatin interactions of regulatory elements, identifies the transcription factor binding sites on interacting regulatory elements, predicts TF-target gene expression relationships, and finally outputs a gene regulatory network linking TFs, regulatory elements to target genes. [Publication: Jin et al., Genome Medicine, 2021][Availability: R,]

Varmole is an interpretable deep learning model to simultaneously reveal genomic functions and mechanisms while predicting phenotype from genotyping and gene expression data. In particular, it embeds gene regulatory networks and eQTLs into a deep neural network architecture and prioritizes variants, genes and regulatory linkages via biological drop-connect without needing prior feature selections. [Publication: Nguyen, Jin, Wang, Bioinformatics, 2020][Availability: Python, PyTorch,]

ECMarker is an interpretable and scalable machine learning model to predict gene expression biomarkers for disease phenotypes and reveal underlying gene regulatory mechanisms. It is built on the integration of semi- and discriminative- restricted Boltzmann machines, a neural network model for classification allowing lateral connections at the input gene layer. [Publication: Jin, Nguyen, Talos, Wang, Bioinformatics, 2021][Availability: Python, PyTorch, R,]

ManiNetCluster is a manifold learning method that simultaneously aligns and clusters gene networks (e.g., co-expression or protein-protein interaction) to systematically reveal the functional links across networks. Specifically, ManiNetCluster employs manifold learning to uncover and match local and non-linear structures among networks. [Publication: Nguyen, Blaby, Wang, BMC Genomics, 2019][Availability: R, Python,]