Regularized Generalized Linear Models to Disclose Host-Microbiome Associations in Colorectal Cancer

Eliana Ibrahimi, Mina Norouzirad, Melisa Meto, Marta B. Lopes

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Recent studies have shown that gut microbiome is associated with colorectal cancer (CRC) progression and anti-cancer therapy efficacy. This study aims to optimize the ridge, elastic net, and lasso regularized generalized linear models (GLM), widely used for supervised machine learning, for multiclass classification tasks (healthy/adenoma/carcinoma). The models are applied to a benchmark gut microbiome dataset using raw and transformed data. A cross-validation procedure is used to select an optimal value for the shrinkage parameter, λ. The results show a higher accuracy of the ridge and elastic net models compared to the lasso model. We confirm known associations of several microbiome genera with CRC and adenoma. These findings are expected to contribute to the definition of CRC-microbiome signatures to be further validated in microbiome-related therapy studies.
Original languageEnglish
Title of host publicationICoMS '23
Subtitle of host publicationProceedings of the 2023 6th International Conference on Mathematics and Statistics
Place of PublicationNew York
PublisherACM - Association for Computing Machinery
Pages98-102
Number of pages5
ISBN (Print)979-8-4007-0018-7
DOIs
Publication statusPublished - 13 Dec 2023
Event6th International Conference on Mathematics and Statistics, ICoMS 2023 - Hybrid, Leipzig, Germany
Duration: 14 Jul 202316 Jul 2023

Publication series

NameICoMS: International Conference on Mathematics and Statistic
PublisherAssociation for Computing Machinery

Conference

Conference6th International Conference on Mathematics and Statistics, ICoMS 2023
Country/TerritoryGermany
CityHybrid, Leipzig
Period14/07/2316/07/23

Keywords

  • Colorectal Cancer
  • Elastic net
  • Generalized Linear Models
  • Gut Microbiome
  • Lasso
  • Ridge

Fingerprint

Dive into the research topics of 'Regularized Generalized Linear Models to Disclose Host-Microbiome Associations in Colorectal Cancer'. Together they form a unique fingerprint.

Cite this