Drug set enrichment analysis software tools | Drug discovery data analysis
Set enrichment analysis based methods (e.g. gene set enrichment analysis) have provided great helps in mining patterns in biomedical datasets, however, tools for inferring regular patterns in drug-related datasets are still limited.
Detects molecular pathways that are consistently up- or down- regulated by a set of drugs. By diluting drug-specific effects unrelated to the phenotype of interest, DSEA is able to highlight phenotype-specific pathways, thus helping to formulate hypotheses on the mechanism of action (MoA) shared by the drugs in the set. Given a query-set of small-molecules, DSEA checks for each pathway whether small-molecules tend to be significantly ranked at the top (or the bottom) of the list, by applying a Kolmogorov-Smirnov (KS) test. An Enrichment Score for the drug-set and a p-value can thus be computed for each pathway exactly, without the need of random permutations.
Identifies targeted biological pathways for drugs with unclear mechanism of action. iFad is an R package, based on a Bayesian sparse factor analysis model, that merges information from paired gene expression and drug sensitivity from the same set of samples. The application is designed for a natural incorporation of prior knowledge about the connectivity structure of biological pathways.
Performs pathway identification of molecular compounds using the KEGG and Reactome databases.PathwayMap is a deep-learning model based on self-normalizing neural networks and ECFP4 fingerprints. This software was evaluated using different types of splits on both publicly available data extracted from ChEMBL and pharmaceutical data provided by Novartis.
Predicts the Anatomical Therapeutic Chemical (ATC) classes. It has been established by hybridizing of the iATC-mISF method with the powerful iATC-mDO sub-predictor. iATC-mHyb outperforms the best existing ATC predictor in all the five metrics used to examine the prediction quality of a predictor for multi-label systems, particularly in the “absolute true” rate and the “absolute false” rate, the two most difficult to-improve indexes. This multi-label predictor can achieve lower than 3% of absolute false rate.
Performs drug set enrichment analysis for a drug list in drug sets based on hypergeometric test. DrugPattern is a web application able to collect and curate more of 7000 drug sets, which cover a number of big categories, such as drug targets, pathways, chemical classification, diseases, and adverse reaction. For a given list of drugs, DrugPattern then calculated the enrichment of these drugs in each of the drug sets.