A Cross-Validated Feature Selection (CVFS) approach for extracting the most parsimonious feature sets and discovering potential antimicrobial resistance (AMR) biomarkers
Understanding genes and their underlying mechanisms is critical in deciphering how antimicrobial-resistant (AMR) bacteria withstand detrimental effects of antibiotic drugs. At the same time the genes related to AMR phenotypes may also serve as biomarkers for predicting whether a microbial strain is...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-01-01
|
| Series: | Computational and Structural Biotechnology Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2001037022006031 |
| _version_ | 1827577645569671168 |
|---|---|
| author | Ming-Ren Yang Yu-Wei Wu |
| author_facet | Ming-Ren Yang Yu-Wei Wu |
| author_sort | Ming-Ren Yang |
| collection | DOAJ |
| description | Understanding genes and their underlying mechanisms is critical in deciphering how antimicrobial-resistant (AMR) bacteria withstand detrimental effects of antibiotic drugs. At the same time the genes related to AMR phenotypes may also serve as biomarkers for predicting whether a microbial strain is resistant to certain antibiotic drugs. We developed a Cross-Validated Feature Selection (CVFS) approach for robustly selecting the most parsimonious gene sets for predicting AMR activities from bacterial pan-genomes. The core idea behind the CVFS approach is interrogating features among non-overlapping sub-parts of the datasets to ensure the representativeness of the features. By randomly splitting the dataset into disjoint sub-parts, conducting feature selection within each sub-part, and intersecting the features shared by all sub-parts, the CVFS approach is able to achieve the goal of extracting the most representative features for yielding satisfactory AMR activity prediction accuracy. By testing this idea on bacterial pan-genome datasets, we showed that this approach was able to extract the most succinct feature sets that predicted AMR activities very well, indicating the potential of these genes as AMR biomarkers. The functional analysis demonstrated that the CVFS approach was able to extract both known AMR genes and novel ones, suggesting the capabilities of the algorithm in selecting relevant features and highlighting the potential of the novel genes in expanding the antimicrobial resistance gene databases. |
| first_indexed | 2024-03-08T21:30:45Z |
| format | Article |
| id | doaj.art-05fa90ec97d74994b207705daaa2056f |
| institution | Directory Open Access Journal |
| issn | 2001-0370 |
| language | English |
| last_indexed | 2024-03-08T21:30:45Z |
| publishDate | 2023-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Computational and Structural Biotechnology Journal |
| spelling | doaj.art-05fa90ec97d74994b207705daaa2056f2023-12-21T07:30:40ZengElsevierComputational and Structural Biotechnology Journal2001-03702023-01-0121769779A Cross-Validated Feature Selection (CVFS) approach for extracting the most parsimonious feature sets and discovering potential antimicrobial resistance (AMR) biomarkersMing-Ren Yang0Yu-Wei Wu1Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, Taipei 110, Taiwan, ROC; Department of Electrical Engineering, National Taiwan University of Science and Technology, Taipei 106, Taiwan, ROCGraduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, Taipei 110, Taiwan, ROC; Clinical Big Data Research Center, Taipei Medical University Hospital, Taipei, Taiwan, ROC; TMU Research Center for Digestive Medicine, Taipei Medical University, Taipei 110, Taiwan, ROC; Correspondence to: Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, 250, Wuxing St., Sinyi Distr., Taipei 110, Taiwan, ROC.Understanding genes and their underlying mechanisms is critical in deciphering how antimicrobial-resistant (AMR) bacteria withstand detrimental effects of antibiotic drugs. At the same time the genes related to AMR phenotypes may also serve as biomarkers for predicting whether a microbial strain is resistant to certain antibiotic drugs. We developed a Cross-Validated Feature Selection (CVFS) approach for robustly selecting the most parsimonious gene sets for predicting AMR activities from bacterial pan-genomes. The core idea behind the CVFS approach is interrogating features among non-overlapping sub-parts of the datasets to ensure the representativeness of the features. By randomly splitting the dataset into disjoint sub-parts, conducting feature selection within each sub-part, and intersecting the features shared by all sub-parts, the CVFS approach is able to achieve the goal of extracting the most representative features for yielding satisfactory AMR activity prediction accuracy. By testing this idea on bacterial pan-genome datasets, we showed that this approach was able to extract the most succinct feature sets that predicted AMR activities very well, indicating the potential of these genes as AMR biomarkers. The functional analysis demonstrated that the CVFS approach was able to extract both known AMR genes and novel ones, suggesting the capabilities of the algorithm in selecting relevant features and highlighting the potential of the novel genes in expanding the antimicrobial resistance gene databases.http://www.sciencedirect.com/science/article/pii/S2001037022006031Cross-Validated Feature SelectionCVFSFeature selectionBiomarkerPan-genomeAntimicrobial resistance |
| spellingShingle | Ming-Ren Yang Yu-Wei Wu A Cross-Validated Feature Selection (CVFS) approach for extracting the most parsimonious feature sets and discovering potential antimicrobial resistance (AMR) biomarkers Computational and Structural Biotechnology Journal Cross-Validated Feature Selection CVFS Feature selection Biomarker Pan-genome Antimicrobial resistance |
| title | A Cross-Validated Feature Selection (CVFS) approach for extracting the most parsimonious feature sets and discovering potential antimicrobial resistance (AMR) biomarkers |
| title_full | A Cross-Validated Feature Selection (CVFS) approach for extracting the most parsimonious feature sets and discovering potential antimicrobial resistance (AMR) biomarkers |
| title_fullStr | A Cross-Validated Feature Selection (CVFS) approach for extracting the most parsimonious feature sets and discovering potential antimicrobial resistance (AMR) biomarkers |
| title_full_unstemmed | A Cross-Validated Feature Selection (CVFS) approach for extracting the most parsimonious feature sets and discovering potential antimicrobial resistance (AMR) biomarkers |
| title_short | A Cross-Validated Feature Selection (CVFS) approach for extracting the most parsimonious feature sets and discovering potential antimicrobial resistance (AMR) biomarkers |
| title_sort | cross validated feature selection cvfs approach for extracting the most parsimonious feature sets and discovering potential antimicrobial resistance amr biomarkers |
| topic | Cross-Validated Feature Selection CVFS Feature selection Biomarker Pan-genome Antimicrobial resistance |
| url | http://www.sciencedirect.com/science/article/pii/S2001037022006031 |
| work_keys_str_mv | AT mingrenyang acrossvalidatedfeatureselectioncvfsapproachforextractingthemostparsimoniousfeaturesetsanddiscoveringpotentialantimicrobialresistanceamrbiomarkers AT yuweiwu acrossvalidatedfeatureselectioncvfsapproachforextractingthemostparsimoniousfeaturesetsanddiscoveringpotentialantimicrobialresistanceamrbiomarkers AT mingrenyang crossvalidatedfeatureselectioncvfsapproachforextractingthemostparsimoniousfeaturesetsanddiscoveringpotentialantimicrobialresistanceamrbiomarkers AT yuweiwu crossvalidatedfeatureselectioncvfsapproachforextractingthemostparsimoniousfeaturesetsanddiscoveringpotentialantimicrobialresistanceamrbiomarkers |