Which gene combination to test in wet lab? A demonstration of machine learning based search engine using ETC-1922159 static data

Biologists/oncologists often search for a range of combinations of genes/proteins that work synergistically in cells in various processes. This search is often difficult. To address this issue, a design of a machine learning based search engine was published recently. To demonstrate the effectiveness of this search engine on real life data sets, the data set containing recordings of up/down regulated genes generated from colorectal cancer cells which were treated with Porcupine-WNT inhibitor drug ETC-1922159 was taken. The regulation of the genes were recorded individually, but it is still not known which higher (≥ 2) order gene combinations might be playing a greater role after the administration of the drug. The adapted engine revealed the priority of these higher order unknown/untested/unexplored as well as wet lab tested combinations, among the up/down-regulated genes in static data. Based on these rankings, biologists/oncologists would not have to struggle to discover a particular gene/protein combination of interest for further wet lab test, that might be involved in a particular phenomena.