Understanding the Role of the Microbiome in Cancer Diagnostics and Therapeutics by Creating and Utilizing ML Models

Abstract

Recent studies have highlighted that gut microbiota can alter colorectal cancer susceptibility and progression due to its impact on colorectal carcinogenesis. This work represents a comprehensive technical approach in modeling and interpreting the drug-resistance mechanisms from clinical data for patients diagnosed with colorectal cancer. To accomplish our aim, we developed a methodology based on evaluating high-performance machine learning models where a Python-based random forest classifier provides the best performance metrics, with an overall accuracy of 91.7%. Our approach identified and interpreted the most significant genera in the cases of resistant groups. Thus far, many studies point out the importance of present genera in the microbiome and intend to treat it separately. The symbiotic bacterial analysis generated different sets of joint feature combinations, providing a combined overview of the model’s predictiveness and uncovering additional data correlations where different genera joint impacts support the therapy-resistant effect. This study points out the different perspectives of treatment since our aggregate analysis gives precise results for the genera that are often found together in a resistant group of patients, meaning that resistance is not due to the presence of one pathogenic genus in the patient microbiome, but rather several bacterial genera that live in symbiosis.

Advancing microbiome research with machine learning: key findings from the ML4Microbiome COST action

“…Some could benefit from Short Term Scientific Mission (STMS) grants (16 in total) to work with research teams in different countries on ML4Microbiome-related projects with the view to publish the results of their activities in peer-reviewed journals. 8 In terms of publication output, to date ML4Microbiome members have published work on specific ML applications for particular diseases, such as Cancer Diagnostics and Therapeutics (Cekikj et al, 2022), classification of patients with Celiac Disease (Arcila-Galvis et al, 2022), Coronary Artery Disease Risk Prediction (Vilne et al, 2022), novel paradigms in human gut microbiome metabolism (Bidkhori et al, 2021), Parkinson's disease (Rosario et al, 2021), Type 2 Diabetes (Ruuskanen et al, 2022), oral and related gut diseases (Di Stefano et al, 2023), along with systematic or scoping reviews on ML applications on microbiome data (Tonkovic et al, 2020;Marcos-Zambrano et al, 2021) and its challenges and solutions (Moreno-Indias et al, 2021) of which all are available from the complete list of the Action's publications on the ML4Microbiome website.…”

Interactions between Dietary Micronutrients, Composition of the Microbiome and Efficacy of Immunotherapy in Cancer Patients

“…In addition, we noticed that in the whole group of patients a high abundance of Veillonellaceae was correlated with shorter PFS, which seems to be in line with the results of Song et al [ 70 ]. Moreover, Cekikij et al indicated that patients with CRC non-resistant to ICIs therapy had an increased content of Akkermansia , Clostridium sensu stricto 1 and Oscillospiraceae and decreased content of Streptococcus and Leuconostoc [ 77 ]. Due to the fact that PFS is not the best indicator of the effectiveness of immunotherapy, our 47 advanced NSCLC patients with microbiome genotyping are under surveillance in order to obtain prospective long-term observations in terms of overall survival.…”