Applicability Domain of Active Learning in Chemical Probe Identification: Convergence in Learning from Non-Specific Compounds and Decision Rule Clarification
Efficient identification of chemical probes for the manipulation and understanding of biological systems demands specificity for target proteins. Computational means to optimize candidate compound selection for experimental selectivity evaluation are being sought. The active learning virtual screeni...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-07-01
|
| Series: | Molecules |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1420-3049/24/15/2716 |
| _version_ | 1811280725423423488 |
|---|---|
| author | Ahsan Habib Polash Takumi Nakano Shunichi Takeda J.B. Brown |
| author_facet | Ahsan Habib Polash Takumi Nakano Shunichi Takeda J.B. Brown |
| author_sort | Ahsan Habib Polash |
| collection | DOAJ |
| description | Efficient identification of chemical probes for the manipulation and understanding of biological systems demands specificity for target proteins. Computational means to optimize candidate compound selection for experimental selectivity evaluation are being sought. The active learning virtual screening method has demonstrated the ability to efficiently converge on predictive models with reduced datasets, though its applicability domain to probe identification has yet to be determined. In this article, we challenge active learning’s ability to predict inhibitory bioactivity profiles of selective compounds when learning from chemogenomic features found in non-selective ligand-target pairs. Comparison of controls versus multiple molecule representations de-convolutes factors contributing to predictive capability. Experiments using the matrix metalloproteinase family demonstrate maximum probe bioactivity prediction achieved from only approximately 20% of non-probe bioactivity; this data volume is consistent with prior chemogenomic active learning studies despite the increased difficulty from chemical biology experimental settings used here. Feature weight analyses are combined with a custom visualization to unambiguously detail how active learning arrives at classification decisions, yielding clarified expectations for chemogenomic modeling. The results influence tactical decisions for computational probe design and discovery. |
| first_indexed | 2024-04-13T01:19:57Z |
| format | Article |
| id | doaj.art-68884c14268b4e05b4062f57f8cc05c9 |
| institution | Directory Open Access Journal |
| issn | 1420-3049 |
| language | English |
| last_indexed | 2024-04-13T01:19:57Z |
| publishDate | 2019-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Molecules |
| spelling | doaj.art-68884c14268b4e05b4062f57f8cc05c92022-12-22T03:08:47ZengMDPI AGMolecules1420-30492019-07-012415271610.3390/molecules24152716molecules24152716Applicability Domain of Active Learning in Chemical Probe Identification: Convergence in Learning from Non-Specific Compounds and Decision Rule ClarificationAhsan Habib Polash0Takumi Nakano1Shunichi Takeda2J.B. Brown3Kyoto University Graduate School of Medicine, Department of Molecular Biosciences, Life Science Informatics Research Unit, Kyoto, Sakyo, Yoshida, Konoemachi, Kyoto 606-8501, JapanKyoto University Graduate School of Medicine, Department of Molecular Biosciences, Life Science Informatics Research Unit, Kyoto, Sakyo, Yoshida, Konoemachi, Kyoto 606-8501, JapanKyoto University Graduate School of Medicine, Department of Radiation Genetics; Kyoto, Sakyo, Yoshida, Konoemachi, Kyoto 606-8501, JapanKyoto University Graduate School of Medicine, Department of Molecular Biosciences, Life Science Informatics Research Unit, Kyoto, Sakyo, Yoshida, Konoemachi, Kyoto 606-8501, JapanEfficient identification of chemical probes for the manipulation and understanding of biological systems demands specificity for target proteins. Computational means to optimize candidate compound selection for experimental selectivity evaluation are being sought. The active learning virtual screening method has demonstrated the ability to efficiently converge on predictive models with reduced datasets, though its applicability domain to probe identification has yet to be determined. In this article, we challenge active learning’s ability to predict inhibitory bioactivity profiles of selective compounds when learning from chemogenomic features found in non-selective ligand-target pairs. Comparison of controls versus multiple molecule representations de-convolutes factors contributing to predictive capability. Experiments using the matrix metalloproteinase family demonstrate maximum probe bioactivity prediction achieved from only approximately 20% of non-probe bioactivity; this data volume is consistent with prior chemogenomic active learning studies despite the increased difficulty from chemical biology experimental settings used here. Feature weight analyses are combined with a custom visualization to unambiguously detail how active learning arrives at classification decisions, yielding clarified expectations for chemogenomic modeling. The results influence tactical decisions for computational probe design and discovery.https://www.mdpi.com/1420-3049/24/15/2716chemical probescompound specificityligand-target interactionschemogenomicsactive learningactive projectiondecision treemolecular representation |
| spellingShingle | Ahsan Habib Polash Takumi Nakano Shunichi Takeda J.B. Brown Applicability Domain of Active Learning in Chemical Probe Identification: Convergence in Learning from Non-Specific Compounds and Decision Rule Clarification Molecules chemical probes compound specificity ligand-target interactions chemogenomics active learning active projection decision tree molecular representation |
| title | Applicability Domain of Active Learning in Chemical Probe Identification: Convergence in Learning from Non-Specific Compounds and Decision Rule Clarification |
| title_full | Applicability Domain of Active Learning in Chemical Probe Identification: Convergence in Learning from Non-Specific Compounds and Decision Rule Clarification |
| title_fullStr | Applicability Domain of Active Learning in Chemical Probe Identification: Convergence in Learning from Non-Specific Compounds and Decision Rule Clarification |
| title_full_unstemmed | Applicability Domain of Active Learning in Chemical Probe Identification: Convergence in Learning from Non-Specific Compounds and Decision Rule Clarification |
| title_short | Applicability Domain of Active Learning in Chemical Probe Identification: Convergence in Learning from Non-Specific Compounds and Decision Rule Clarification |
| title_sort | applicability domain of active learning in chemical probe identification convergence in learning from non specific compounds and decision rule clarification |
| topic | chemical probes compound specificity ligand-target interactions chemogenomics active learning active projection decision tree molecular representation |
| url | https://www.mdpi.com/1420-3049/24/15/2716 |
| work_keys_str_mv | AT ahsanhabibpolash applicabilitydomainofactivelearninginchemicalprobeidentificationconvergenceinlearningfromnonspecificcompoundsanddecisionruleclarification AT takuminakano applicabilitydomainofactivelearninginchemicalprobeidentificationconvergenceinlearningfromnonspecificcompoundsanddecisionruleclarification AT shunichitakeda applicabilitydomainofactivelearninginchemicalprobeidentificationconvergenceinlearningfromnonspecificcompoundsanddecisionruleclarification AT jbbrown applicabilitydomainofactivelearninginchemicalprobeidentificationconvergenceinlearningfromnonspecificcompoundsanddecisionruleclarification |