Fundamental Bioinformatic and Chemoinformatic Data Processing

Brown, J.

doi:10.1007/978-1-4939-8639-2_3

Cited by 2 publications

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, a dummy identity vector unique to each target was generated for use in control experiments; hence the collection of dummy vectors forms an identity matrix. Second, protein primary sequence subsequence frequencies (“k-mers”) were tabulated for lengths one, two, and three [33]. For multimer frequency calculation, the overlapped sliding window approach was used (e.g., for sequence MKSLP in MMP3, computation of a 2-mer is a vector of length 4 and a 3-mer is of length 3 comprised of subsequences MKS, KSL, SLP each occurring once).…”

Section: Methodsmentioning

confidence: 99%

Applicability Domain of Active Learning in Chemical Probe Identification: Convergence in Learning from Non-Specific Compounds and Decision Rule Clarification

et al. 2019

View full text Add to dashboard Cite

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.

show abstract

Section: Methodsmentioning

confidence: 99%