1. How to submit my research paper? What’s the process of publication of my paper?
The journal receives submitted manuscripts via email only. Please submit your research paper in .doc or.pdf format to the submission email: ijpmbs@ejournal.net.
You’ll be given a paper number if your submission is successful. Your paper then will undergo peer review process, which may take approximately one and a half months under normal circumstances, three tops.
After blind peer review, you will receive the notification letter with the review result of your paper...
2. Can I submit an abstract?
The journal publishes full research papers.[Read More]
 
IJPMBS 2026 Vol.15(4): 196-206
doi: 10.18178/ijpmbs.15.4.196-206

Investigating the Association between Metagenomic Shotgun Data and the Occurrence of IBD Using Machine Learning Models

Ziyu Liu
Mander Portman Woodward, London, The United Kingdom
Email: 15010638483@163.com

Manuscript received September 10, 2026; accepted October 17, 2026; published November 17, 2026.

Abstract—Inflammatory Bowel Disease (IBD) is becoming increasingly common around the world, and changing the gut microbiome has potential to be useful for studying and diagnosing the disease. In this work, we analyzed bacterial abundance data from a previously published shotgun sequencing study [1] with three machine learning classifiers: L2 logistic regression, LASSO logistic regression, and Support Vector Machine (SVM). All the classifiers were trained to distinguish the samples obtained from patients with Ulcerative Colitis (UC) from the healthy population samples. We also studied the 15 bacterial species that contributed the most to each classifier. The three AUROC values were 0.7980 for L2 logistic regression, 0.6970 for LASSO, and 0.8182 for SVM. Salmonella enterica serovar Typhimurium was associated with prediction of IBD, whereas members of the genus Lactobacillus had a beneficial effect on IBD. These observations are in line with results from previously reported IBD studies. However, SVM produced the highest AUROC out of the three models and was therefore the most accurate model on this dataset. Overall, these results illustrate how machine learning can be used to explore microbiome data for disease prediction and possible biomarker detection. They also show how a nonlinear model like SVM might reveal relationships that might not have been uncovered with a linear model.
 
Keywords—inflammatory bowel disease, machine learning, disease biomarkers, bacterial abundance

Cite: Ziyu Liu, "Investigating the Association between Metagenomic Shotgun Data and the Occurrence of IBD Using Machine Learning Models," International Journal of Pharma Medicine and Biological Sciences, Vol. 15, No. 4, pp. 196-206, 2026.

Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).

Copyright © 2012-2026. International Journal of Pharma Medicine and Biological Sciences. Unless otherwise stated.
​E-mail: ijpmbs@ejournal.net
Published by