Our methods and models are available as open-source tools at the lab’s GitHub site. We regularly maintain the tools. Please contact email@example.com for any questions.
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, https://github.com/daifengwanglab/ManiNetCluster]
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, 2020][Availability: Python, PyTorch, R, https://github.com/daifengwanglab/ECMarker]
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, https://github.com/daifengwanglab/Varmole]