Feature selection and aggregation for antibiotic resistance GWAS in Mycobacterium tuberculosis: a comparative study
In our analysis, ABESS significantly outperformed the other methods, selecting more relevant sets of mutations. Additionally, we demonstrated that aggregating rare mutations within protein-coding genes into markers indicative of changes in PFAM domains improved prediction quality, and these markers were predominantly selected by ABESS, suggesting their high informativeness. However, ABESS yielded lower prediction accuracy compared to logistic regression methods with regularization.
Authors
- Konstantin V. Kuleshov (ORCID: https://orcid.org/0000-0002-5238-7900)
- Kirill Reshetnikov (ORCID: https://orcid.org/0000-0002-7928-3941)
- Daria Bykova (ORCID: https://orcid.org/0000-0002-2420-971X)
- Alexey D. Neverov (ORCID: https://orcid.org/0000-0002-3594-1682)
- Egor Guguchkin (ORCID: https://orcid.org/0000-0001-7885-9892)
- Gennady G. Fedonin (ORCID: https://orcid.org/0000-0002-9427-8083)
- Konstantin Chukreev (ORCID: https://orcid.org/0000-0002-6568-0874)
Institutions
- National Research University Higher School of Economics (RU)
- Lomonosov Moscow State University (RU)
- Ufa Institute of Chemistry (RU)
- Central Research Institute of Epidemiology (RU)
- All-Russian Scientific Research Institute of Experimental Veterinary Sciences. Ya.R. Kovalenko (RU)
Publication Details
- Journal
- Frontiers in Microbiology
- Published
- 2025-06-18
- DOI
- https://doi.org/10.3389/fmicb.2025.1586476
- Citations
- 3
- Primary Topic
- Tuberculosis Research and Epidemiology
- Type
- article
- Field-Weighted Citation Impact
- 4.19
Funders
- National Research University Higher School of Economics