Additionally, CSNAP is capable of integrating with biological knowledge-based databases (Uniprot, GO) and high-throughput biology platforms (proteomic, genetic, etc) for system-wise drug target validation.

Determining the targets of compounds identified in cell-based high-throughput chemical screens is a critical step for downstream drug development and understanding of compound mechanism of action.

This indicated that CSNAP could potentially be used for high-throughput target deorphanization and off-target prediction for bioactive compounds from any chemical screen.

Additionally, CSNAP is capable of integrating with chemical and biological knowledge-based databases (Uniprot, GO) and high-throughput biology platforms (proteomic, genetic, etc) for system-wise drug target validation.

Recently, we performed a high-throughput cell-cycle modulator screen with a diverse, unbiased set of 90,000 drug-like compounds, which identified compounds arresting cancer cells in mitosis (212 compounds) (S2, S3 Tables and 81 Text).

Data are increasingly become available for the adoption of such classification techniques since high-throughput methods have been recently applied at low cost.

Our work paves the way towards the use of high-throughput expression datasets to a broad range of applications including detection and characterization of the environmental conditions and bacterial population that are important for clinical, environmental, industrial, and agricultural applications.

Indeed, after aggregating all high-throughput transcriptional data that is currently available for E. coli, the most well-studied model microbe, we are still limited to a few thousands microarray or RNA-Seq experiments that cover more than 30 strains, a dozen different media and a multitude of other genetic (knockout, over-expressions, re-wirings), or environmental (carbon limitation, chemicals, abiotic factors) perturbations.