Identification of feasible pathway information for c-di-GMP binding proteins in cellulose production

TL;DR

This study employs machine learning techniques to identify key pathways involved in c-di-GMP signaling proteins, highlighting bacterial chemotaxis as crucial for cellulose production, with implications for genetic pathway regulation.

Contribution

Introduces novel application of Lasso and Random forests to analyze pathways associated with c-di-GMP binding domains in bacteria, emphasizing pathway importance in cellulose synthesis.

Findings

Bacterial chemotaxis is the most essential pathway for c-di-GMP domains.

Lasso fails to associate pathways with MshE domain due to strong regularization.

Results suggest pathways can be targeted to control bacterial cellulose production.

Abstract

In this paper, we utilize a machine learning approach to identify the significant pathways for c-di-GMP signaling proteins. The dataset involves gene counts from 12 pathways and 5 essential c-di-GMP binding domains for 1024 bacterial genomes. Two novel approaches, Least absolute shrinkage and selection operator (Lasso) and Random forests, have been applied for analyzing and modeling the dataset. Both approaches show that bacterial chemotaxis is the most essential pathway for c-di-GMP encoding domains. Though popular for feature selection, the strong regularization of Lasso method fails to associate any pathway to MshE domain. Results from the analysis may help to understand and emphasize the supporting pathways involved in bacterial cellulose production. These findings demonstrate the need for a chassis to restrict the behavior or functionality by deactivating the selective pathways in cellulose production.