Software

• EPIC-TRACE: predicting TCR binding to unseen epitopes using attention and contextualized embeddings
  
• LNPDE: Learning Space-Time Continuous Neural PDEs from Partially Observed States
  
• GP-prior-VAE-MC: Learning conditional variational autoencoders with missing covariates
  
• ODEmodeling: Importance sampling for inference in Bayesian ordinary differential equation models
  
• TSignal: A transformer model for signal peptide prediction
  
• MSVI: Latent Neural ODEs with Sparse Bayesian Multiple Shooting
  
• TCRconv: Determining recognition between TCRs and epitopes using contextualized motifs
  
• LuxHMM: DNA methylation analysis with genome segmentation via hidden Markov model
  
• HL-VAE: A variational autoencoder for heterogeneous temporal and longitudinal data
  
• GPODE: Variational multiple shooting for Bayesian ODEs with Gaussian processes
  
• ChromDMM: A Dirichlet-multinomial mixture model for clustering heterogeneous epigenetic data
  
• cfMeDIP-seq: cell-free DNA methylation based cancer classification
  
• PairGP: Gaussian process modeling of longitudinal data from paired multi-condition studies
  
• LuxRep: technical replicate-aware method for bisulfite sequencing data analysis
  
• ODERL: Continuous-time model-based reinforcement learning
  
• L-VAE: Longitudinal variational autoencoder
  
• HGPLVM: Latent Gaussian process with composite likelihoods and numerical quadrature
  
• TCRGP:  Determining epitope-specificity of T cell receptors with TCRGP
  
• MPNN-PDE:  Learning continuous-time PDEs from sparse data with graph neural networks
  
• lgpr: An interpretable nonparametric method for inferring covariate effects from longitudinal data
  
• LuxUS: DNA methylation analysis using generalized linear mixed model with spatial correlation
  
• ODE2VAE: Deep generative second order ODEs with Bayesian neural networks
  
• DiffGP: Deep learning with differential Gaussian process flows
  
• SCHiRM: Single cell hierarchical regression model
  
• BaMFA: Bayesian metabolic flux analysis
  
• snpEnrichR: An R package to analyze co-localization of SNPs and their proxies in genomic regions
  
• npODE: Learning unknown ODE (or SDE) models with Gaussian processes
  
• mGPfusion: Gaussian process based method for predicting stability changes upon single and multiple mutations
  
• LonGP: an additive Gaussian process regression model for longitudinal data analysis
  
• Multiscale: A data-driven multiscale modeling framework for spatio-temporal growth dynamics of yeast colonies
  
• LuxGLM: A probabilistic covariate model for quantification of DNA methylation modifications with complex experimental designs
  
• Subpop: A subpopulation model to analyze heterogeneous cell differentiation dynamics
  
• LEM: Data-driven mechanistic analysis method to reveal dynamically evolving regulatory networks
  
• Lux: A probabilistic generative model for quantification of DNA modifications
  
• AdaptiveGP: An implementation of a fully nonstationary, heteroscedastic Gaussian process for Matlab.
  
• MixChIP: A probabilistic method for cell type specific protein-DNA binding analysis
  
• BinDNase: A discriminative approach for transcription factor binding prediction using DNase I hypersensitivity data
  
• DyNB: A probabilistic method to analyze RNA-seq time series data.
  
• Sorad: A nonparametric probabilistic method to infer and analyze dynamic signaling pathways.
  
• LIGAP: A probabilistic method to identify condition/lineage specific time-course profiles.
  
• DSection: A probabilistic model and MCMC sampler for reconstructing cell type specific gene expression profiles from measurements of heterogeneous tissues. A web tool is also available. DSection is also included in an R package called CellMix.
  
• MultiTF-PPI: A probabilistic protein-protein interaction guided method for competitive transcription factor binding prediction.
• ProbTF: Transcription factor binding prediction with multiple data fusion. A Matlab implementation of our transcription factor binding prediction method that can incorporate multiple genome-level data sources: ProbTF software page. We have also developed a web tool that is publicly available at www.probtf.org.
• GPODE: Learning the structure of gene regulatory networks using non-parametric molecular kinetics.
• DBNRJMCMC (*coming soon): Structural learning of dynamic Bayesian networks. A set of Matlab functions that implement our RJMCMC and approximative MCMC DBN structure learning from time series and/or steady state measurements will be added shortly. In the meantime, please contact us directly via email.
• Robust periodicity detection:
  - A set of Matlab functions that implement our robust rank-based periodicity detection method can be downloaded from the supplementary web page and from here.
  - A set of Matlab functions that implement our robust regression-based periodicity detection method can be downloaded from the supplementary web page.
  - GeneCycle R package at CRAN.
  
• Toolbox for Boolean and probabilistic Boolean networks. A comprehensive toolbox to work with Boolean networks and probabilistic Boolean networks can be downloaded from PBN web page maintained by Ilya Shmulevich.