Cargando…

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...

Descripción completa

Detalles Bibliográficos
Autores principales: Polash, Ahsan Habib, Nakano, Takumi, Takeda, Shunichi, Brown, J.B.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6696588/
https://www.ncbi.nlm.nih.gov/pubmed/31357419
http://dx.doi.org/10.3390/molecules24152716
_version_ 1783444288349143040
author Polash, Ahsan Habib
Nakano, Takumi
Takeda, Shunichi
Brown, J.B.
author_facet Polash, Ahsan Habib
Nakano, Takumi
Takeda, Shunichi
Brown, J.B.
author_sort Polash, Ahsan Habib
collection PubMed
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.
format Online
Article
Text
id pubmed-6696588
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-66965882019-09-05 Applicability Domain of Active Learning in Chemical Probe Identification: Convergence in Learning from Non-Specific Compounds and Decision Rule Clarification Polash, Ahsan Habib Nakano, Takumi Takeda, Shunichi Brown, J.B. Molecules Article 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. MDPI 2019-07-26 /pmc/articles/PMC6696588/ /pubmed/31357419 http://dx.doi.org/10.3390/molecules24152716 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Polash, Ahsan Habib
Nakano, Takumi
Takeda, Shunichi
Brown, J.B.
Applicability Domain of Active Learning in Chemical Probe Identification: Convergence in Learning from Non-Specific Compounds and Decision Rule Clarification
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 Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6696588/
https://www.ncbi.nlm.nih.gov/pubmed/31357419
http://dx.doi.org/10.3390/molecules24152716
work_keys_str_mv AT polashahsanhabib applicabilitydomainofactivelearninginchemicalprobeidentificationconvergenceinlearningfromnonspecificcompoundsanddecisionruleclarification
AT nakanotakumi applicabilitydomainofactivelearninginchemicalprobeidentificationconvergenceinlearningfromnonspecificcompoundsanddecisionruleclarification
AT takedashunichi applicabilitydomainofactivelearninginchemicalprobeidentificationconvergenceinlearningfromnonspecificcompoundsanddecisionruleclarification
AT brownjb applicabilitydomainofactivelearninginchemicalprobeidentificationconvergenceinlearningfromnonspecificcompoundsanddecisionruleclarification