Machine learning in biological research: key algorithms, applications, and future directions
Machine learning is a robust framework to analyze questions using complex data in a variety of fields. We present definitions and recent applications of four key machine learning methods and discuss their advantages and challenges in biological research. Through a set of systematically selected case studies, we highlight how machine learning models have been used in a range of applications, including phylogenomics, disease prediction, and host taxonomy prediction. We identify additional potential areas of integration of machine learning into questions with biological relevance. This intersection can be further enhanced through collaboration and innovation on parallelization, interpretability, and preprocessing.
Authors
- Md Nafis Ul Alam (ORCID: https://orcid.org/0000-0003-3088-5279)
- Cristian Román‐Palacios (ORCID: https://orcid.org/0000-0003-1696-4886)
- Juan José Salazar (ORCID: https://orcid.org/0000-0003-4211-528X)
- Danielle Van Boxel (ORCID: https://orcid.org/0009-0002-4091-9858)
- H. M. Abdul Fattah (ORCID: https://orcid.org/0000-0001-7581-9852)
- Hector D. Garcia‐Verdugo (ORCID: https://orcid.org/0000-0001-9027-7668)
- Kristen M. Martinet (ORCID: https://orcid.org/0000-0002-3905-9507)
- Kiran Basava
- Shih-Hsuan Lo
- Ani Chitransh
- Tanisha Lohchab
Institutions
- Translational Genomics Research Institute (US)
- University of Arizona (US)
- University of California, Los Angeles (US)
- Washington University in St. Louis (US)
- University of Dhaka (BD)
- WinnMed (US)
- Center for Creative Leadership (US)
- Mayo Clinic in Florida (US)
Publication Details
- Journal
- BMC Biology
- Published
- 2025-10-29
- DOI
- https://doi.org/10.1186/s12915-025-02424-3
- Citations
- 2
- Primary Topic
- Bioinformatics and Genomic Networks
- Type
- article
- Field-Weighted Citation Impact
- 1.61
Funders
- University of Arizona