Software
Here is a list of software I developed.
Deep learning methods for analyzing multiome data:
-
- DeepPHiC
- A Python package for implementing a novel multi-task and transfer deep learning model to predicting promoter-centered chromatin interactions using promoter-centered Hi-C data.
-
- MTAE
- A Python package for implementing a novel multi-task deep autoencoder to predict AD progression using longitudinal DNA methylation data in peripheral blood.
-
- TLVar
- A Python package for implementing a deep transfer learning approach to improve the prediction for experimentally validated regulatory variants.
-
- DeepPerVar
- A Python package for implementing a multi-modal deep learning model to predict individual-level noncoding functional variants.
-
- MDeep
- A Python package for implementing a novel deep learning model to predict phenotype using microbiome data by embedding the phylogenetic tree in the deep learning model.
Bayesian methods for analyzing multiome data:
-
- BAMMSC
- An R package for implementing a Bayesian hierarchical model for detecting differential circadian pattern in transcriptomic applications
-
- BAMMSC
- An Rpackage for implementing a novel Bayesian mixture model to cluster droplet-based single cell transcriptomic data from multiple individuals.
-
- scaDA
- An R package for implementing an empirical bayesian methods for differential accessibility analysis using single cell multiome data
Spatial multiome data analysis:
-
- Sami
- A python toolkit for simultaneous spatial analysis of the metabolome, lipidome, and glycome from a single tissue section using mass spectrometry imaging.
-
- MetaVision3D
- A Python toolkit uses advanced algorithms for image registration, normalization and interpolation to enable the integration of serial 2D tissue sections, thereby generating a comprehensive 3D model of unique diverse metabolites across host tissues at submesoscale.
Single-cell multiome data analysis:
-
- BAMMSC
- An Rpackage for implementing a novel Bayesian mixture model to cluster droplet-based single cell transcriptomic data from multiple individuals.
-
- scaDA
- An R package for implementing an empirical bayesian methods for differential accessibility analysis using single cell multiome data
Functional noncoding variants prioritization:
-
- traseR
- An R package for performing GWAS trait-associated SNP enrichment analyses in given genomic intervals.
-
- DIVAN
- An R pipeline for prioritizing disease-specific noncoding risk variants in 45 diseases/traits using genome-wide precomputed functional scores.
-
- WEVar
- A Python package for improving the prediction for noncoding regulatory variants using a weighted ensemble approach by integrating precomputed functional scores from multiple existing methods.
-
- TIVAN
- An R pipeline for predicting noncoding regulatory variants in 44 tissues/cell types.
-
- TIVAN-indel
- A Python package for implementing a novel computational method for predicting noncoding regulatory small insertions and deletions.
-
- TLVar
- A Python package for implementing a deep transfer learning approach to improve the prediction for experimentally validated regulatory variants.
-
- DeepPerVar
- A Python package for implementing a multi-modal deep learning model to predict individual-level noncoding functional variants.
Microbiome data analysis:
-
- GMPR
- An R package for normalizing zero-inflated count data particular microbiome sequencing data.
-
- glmgraph
- An R package for implementing sparse generalized linear models with graph-constrained regularization.
-
- SICS
- An R package for implementing sparse generalized linear models with encouraging local smoothing in a phylogeny-constrained regularization for predictive modeling of microbiome data.
-
- glmmTree
- An R package for implementing a phylogenetic tree-based generalized mixed effects model for predictive modeling of microbiome data.
-
- powmic
- An R package for performing power assessment in microbiome sequencing data.
-
- MDeep
- A Python package for implementing a novel deep learning model to predict phenotype using microbiome data by embedding the phylogenetic tree in the deep learning model.
Epigenetic data analysis:
-
- DeepPHiC
- A Python package for implementing a novel multi-task and transfer deep learning model to predicting promoter-centered chromatin interactions using promoter-centered Hi-C data.
-
- MTAE
- A Python package for implementing a novel multi-task deep autoencoder to predict AD progression using longitudinal DNA methylation data in peripheral blood.
-
- tfLDA
- An R package for applying state-of-the-art topic models to decipher the combinatorial binding events of multiple TFs by integrating multiple ChIP- Seq datasets.
-
- ChIPComp
- An R package for implementing a novel Bayesian hierarchical model for quantitative comparison of multiple ChIP-seq datasets.
-
- hmChIP
- A web server and database for cell type-specific ChIP-seq and ChIP-chip data query.
Noncoding RNA analysis:
-
- circMeta
- An R package for detecting differential expression analysis of circular RNAs for small biological replicates.
-
- circMeta2
- An R package for detecting differential expression analysis of circular RNAs for large-scale population study.