Integrating Biological Domain Knowledge with Machine Learning for Identifying Colorectal-Cancer-Associated Microbial Enzymes in Metagenomic Data

Advances in metagenomics have revolutionized our ability to elucidate links between the microbiome and human diseases. Colorectal cancer (CRC), a leading cause of cancer-related mortality worldwide, has been associated with dysbiosis of the gut microbiome. This study aims to develop a method for identifying CRC-associated microbial enzymes by incorporating biological domain knowledge into the feature selection process. Conventional feature selection techniques often evaluate features individually and fail to leverage biological knowledge during metagenomic data analysis. To address this gap, we propose the enzyme commission (EC)-nomenclature-based Grouping-Scoring-Modeling (G-S-M) method, which integrates biological domain knowledge into feature grouping and selection. The proposed method was tested on a CRC-associated metagenomic dataset collected from eight different countries. Community-level relative abundance values of enzymes were considered as features and grouped based on their EC categories to provide biologically informed groupings. Our findings in randomized 10-fold cross-validation experiments imply that glycosidases, CoA-transferases, hydro-lyases, oligo-1,6-glucosidase, crotonobetainyl-CoA hydratase, and citrate CoA-transferase enzymes can be associated with CRC development as part of different molecular pathways. These enzymes are mostly synthesized by Eschericia coli, Salmonella enterica, Klebsiella pneumoniae, Staphylococcus aureus, Streptococcus pneumoniae, and Clostridioides dificile. Comparative evaluation experiments showed that the proposed model consistently outperforms traditional feature selection methods paired with various classifiers.