Machine learning discoveries of ASCL2-X synergy in ETC-1922159 treated colorectal cancer cells

TL;DR

This study uses machine learning to identify potential synergistic gene interactions involving ASCL2 in colorectal cancer cells treated with ETC-1922159, revealing new therapeutic targets.

Contribution

It introduces a novel machine learning search engine to rank and identify promising ASCL2-X gene combinations for colorectal cancer therapy.

Findings

Identified top-ranked ASCL2-X gene pairs with potential synergy.

Confirmed known ASCL2 interactions and suggested new ones.

Provided a ranked list of gene combinations for further experimental validation.

Abstract

Achaete-scute complex homolog 2 (ASCL2) codes a part of the basic helix-loop-helix (BHLH) transcription factor family. WNTs have been found to directly affect the stemness of the tumor cells via regulation of ASCL2. Switching off the ASCL2 literally blocks the stemness process of the tumor cells and vice versa. In colorectal cancer (CRC) cells treated with ETC-1922159, ASCL2 was found to be down regulated along with other genes. A recently developed search engine ranked combinations of ASCL2-X (X, a particular gene/protein) at 2nd order level after drug administration. Some rankings confirm the already tested combinations, while others point to those that are untested/unexplored. These rankings reveal which ASCL2-X combinations might be working synergistically in CRC. In this research work, I cover combinations of ASCL2 with WNT, transforming growth factor beta (TGFB), interleukin (IL), leucine rich repeat containing G protein-coupled receptor (LGR), NOTCH, solute carrier family (SLC), SRY-box transcription factor (SOX), small nucleolar RNA host gene (SNHG), KIAA, F-box protein (FBXO), family with sequence similarity (FAM), B cell CLL/lymphoma (BCL), autophagy related (ATG) and Rho GTPase activating protein (ARHGAP) family.