Causal Explorer 1.5
MATLAB library for computational causal discovery and variable selection.
View software →Home / Software
Software tools, research code, and featured resources from mens X machina.
Tools and code releases listed on the group’s September 2024 software page. Links point to their original destinations; version numbers reflect that listing.
MATLAB library for computational causal discovery and variable selection.
View software →A web application for network reconstruction, statistical analysis, and visualization of cytometry (single-cell) data.
View software →Code for “A comparative evaluation of data-merging and meta-analysis methods for reconstructing gene-gene interactions”.
View software →Code for applying the Non-Parametric Combination methodology to integrative analysis of heterogeneous omics data.
View software →MATLAB implementation for “Scoring and Searching over Bayesian Networks with Informative, Causal and Associative Priors”.
Download ZIP →R package for feature selection, statistically equivalent predictive subsets, Bayesian networks, and conditional independence testing.
View software →MATLAB experimental code for “Tools and Algorithms for Causally Interpreting Directed Edges in Maximal Ancestral Graphs”.
Download ZIP →MATLAB experimental code for “Incorporating Causal Prior Knowledge as Path-Constraints in Bayesian Networks and Maximal Ancestral Graphs”.
Download ZIP →MATLAB experimental code for “Towards Integrative Causal Analysis of Heterogeneous Datasets and Studies”.
Download ZIP →MATLAB experimental code accompanying the AISTATS 2010 publication.
Download ZIP →Automated cancer diagnosis and biomarker discovery from microarray gene expression data, developed at Vanderbilt University in collaboration with Ioannis Tsamardinos.
View software →MATLAB and R experimental code accompanying the survival-data variable selection paper.
Download ZIP →Common MATLAB functions used by other toolboxes from the Mens X Machina group.
View software →MATLAB tools for Bayesian networks and probabilistic graphical models, including local and skeleton learning using MMPC.
View software →Creation of a large database of uniformly preprocessed and disease-annotated genomic and epigenomic data. Currently includes 7,345 datasets spanning 847 diseases, enabling large-scale meta-analysis.
View resource →An international discovery study seeking the earliest molecular signals of lung cancer and mesothelioma in blood serum. The consortium brings together five universities in five countries, aiming to develop a blood test for screening smokers and people exposed to asbestos.
View resource →