Selection of Informative Examples in Chemogenomic Datasets

Reker, Daniel; Brown, J.B.

doi:10.1007/978-1-4939-8639-2_13

Cited by 12 publications

(16 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chemogenomic active learning using random forest as the underlying estimator algorithm was employed similar to previous studies [15,16,34]. Based on previous studies [16,28], the number of trees to comprise a forest was set to 100.…”

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%

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

show abstract

“…Many of the current, successful applications of AI such as image classification have required large training datasets, often in combination with data augmentation and model pre-training with weakly labeled data to capture the diversity of the input and obtain a model that generalizes well 46,47 . The number and nature of molecules required to build a predictive model for drug design is still undetermined 48,49 .…”

Section: Challenge 1: Generating and Obtaining Appropriate Datasetsmentioning

confidence: 99%

Rethinking drug design in the artificial intelligence era

Schneider

Walters

Plowright

et al. 2019

Nat Rev Drug Discov

566

349

View full text Add to dashboard Cite

Perspective │2 Artificial intelligence (AI) tools are increasingly being applied in drug discovery. Whilst some protagonists point to vast opportunities potentially offered by such tools, others remain skeptical, waiting for a clear impact to be shown in drug discovery projects. The truth is probably somewhere between these extremes, but it is clear that AI is providing new challenges not only for the scientists involved but also for the biopharma industry and its established processes for discovering and developing new medicines. This article presents the views of a diverse group of international experts on the 'grand challenges' for small-molecule drug discovery with AI and approaches to address them.

show abstract

“…Indeed, not all data are equally valuable, and similar training entries may be considered redundant or uninformative from a machine-learning vantage point. As a consequence, more data does not necessarily translate into better predictive models; the performance of learning algorithms may actually improve if only informative, high-quality data are kept for training 102,103 . Therefore, active learning is primed to compress search spaces to the bare minimum, absorb relevant knowledge through fast feedback loops and design experiments 'on the fly' by leveraging lean models, i.e.…”

Section: Optimization Of Reaction Conditionsmentioning

confidence: 99%

Synthetic organic chemistry driven by artificial intelligence

2019

View full text Add to dashboard Cite

Synthetic organic chemistry underpins several areas of chemistry, including drug discovery, chemical biology, materials science and engineering. However, the execution of complex chemical syntheses in itself requires expert knowledge, usually acquired over many years of study and hands-on laboratory practice. The development of technologies with potential to streamline and automate chemical synthesis is a half-century-old endeavour yet to be fulfilled. Renewed interest in artificial intelligence (AI), driven by improved computing power, data availability and algorithms, is overturning the limited success previously obtained. In this Review, we discuss the recent impact of AI on different tasks of synthetic chemistry and dissect selected examples from the literature. By examining the underlying concepts, we aim to demystify AI for bench chemists in order that they may embrace it as a tool rather than fear it as a competitor, spur future research by pinpointing the gaps in knowledge and delineate how chemical AI will run in the era of digital chemistry.

show abstract

Selection of Informative Examples in Chemogenomic Datasets

Cited by 12 publications

References 74 publications

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

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

Rethinking drug design in the artificial intelligence era

Synthetic organic chemistry driven by artificial intelligence

Contact Info

Product

Resources

About