Artificial Intelligence Prediction Across 12,000 Samples Shows Widespread Increased Gene-Gene Chromatin Interactions in Cancers that Constitute Therapeutic Vulnerabilities

Gene-gene chromatin interactions (GGIs) bring distal genes into close spatial proximity to permit strong co-expression, which could potentially contribute to cancer progression. High-throughput methods like Hi-C are impractical for very large cohort analyses, thus we developed AI4Loop, an Artificial Intelligence (AI) Deep Learning -based tool to predict GGIs using RNA-Seq data. Applying AI4Loop to 12,000 patient samples from The Cancer Genome Atlas (TCGA) database across 32 cancer types revealed that GGIs show increased cancer sub-type predictivity compared to RNA-Seq data and demonstrated oncogenic gains of GGIs in almost all cancers examined. To target the therapeutic vulnerability of gain of GGIs in cancers, using low-information RNA expression datasets from the CLUE database, we also constructed a drug-perturbation GGI atlas from 50,000 drug-treated samples to identify and repurposed compounds that disrupt oncogenic GGIs. Notably, we found that the antibiotics eperezolid and radezolid reduced cancer-acquired GGIs, which we confirmed with Hi-C experiment. This work showcases AI-directed research in epigenetics, enhances cancer biology predictivity and can promote wide-range drug repurposing in the future. This GEO submission contains the Hi-C data used to test the accuracy of AI4Loop when applied to compounds leading to loss of gene-gene interactions from the CLUE datasets. Hi-C, performed with the TOPO-Link Hi-C Kit from Dovetail in DMSO, Eperezolid, Radezolid, JQ1 and Trihexyphenidyl treated MCF7 cells for 8h