Integrated epigenomic exposure signature discovery

<b>Aim:</b> The epigenome influences gene regulation and phenotypes in response to exposures. Epigenome assessment can determine exposure history aiding in diagnosis. <b>Materials &amp; methods:</b> Here we developed and implemented a machine learning algorithm, the exposure signature discovery algorithm (ESDA), to identify the most important features present in multiple epigenomic and transcriptomic datasets to produce an integrated exposure signature (ES). <b>Results:</b> Signatures were developed for seven exposures including <i>Staphylococcus aureus</i>, human immunodeficiency virus, SARS-CoV-2, influenza A (H3N2) virus and <i>Bacillus anthracis</i> vaccinations. ESs differed in the assays and features selected and predictive value. <b>Conclusion:</b> Integrated ESs can potentially be utilized for diagnosis or forensic attribution. The ESDA identifies the most distinguishing features enabling diagnostic panel development for future precision health deployment. This article introduces ESDA, a new analytic tool for integrating multiple data types to identify the most distinguishing features following an exposure. Using the ESDA, we were able to identify signatures of infectious diseases. The results of the study indicate that integration of multiple types of large datasets can be used to identify distinguishing features for infectious diseases. Understanding the changes from different exposures will enable development of diagnostic tests for infectious diseases that target responses from the patient. Using the ESDA, we will be able to build a database of human response signatures to different infections and simplify diagnostic testing in the future. The exposure signature discovery algorithm simplifies diagnostic target discovery from integrating epigenomic and transcriptomic data sets enabling rapid diagnostics based on host response to exposure. Integration and parsing of multi-omic data generates precise exposure signatures. The number of features in the ESDA model is not strongly correlated with signature performance, but depends on the underlying biology. The low sample size for some exposure types contributes to instability in some model predictions (BA), and therefore, high variability in accuracy metrics during LOOCV. Ensemble results are robust for most exposure types. The most prominent combination of epigenetic methods deployed in the ESDA models were EPIC array for DNA methylation, RNAseq, H3K4me1 and H3K4me3 histone modification assays. Explosives (PETN) imprint the epigenome and result in a signature that can be detected 6–8 weeks after exposure. ESDA-developed SARS-CoV-2 signatures track with acute SARS-CoV-2 with 89% performance. Individuals with convalescent SARS-CoV-2 have a distinct signature that indicates immune epigenetic remodeling. ESDA-derived <i>S. aureus</i> signature can discriminate robustly between MRSA and MSSA in <i>S. aureus</i> infections. An exposure signature database can enable a universal diagnostic test for exposure health that can distinguish infectious diseases and chemical exposures.