Active machine learning-driven experimentation to determine compound effects on protein patterns

Naik, Armaghan W.; Kangas, Joshua; Sullivan, Devin P.; Murphy, Robert F.

doi:10.7554/elife.10047

Cited by 45 publications

(48 citation statements)

References 36 publications

(41 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A reduced need for experimentation has been identified as a major breakthrough achieved through active learning, with estimates of the required training data ranging from as low as 10% [56] to 30% [51] of the c omplete training set.…”

Section: Model Size and Parametersmentioning

confidence: 99%

“…As a number of recent studies have indeed validated that the computational chemogenomic concept can lead to prospective discovery of interactions [36][37][87][88], we anticipate that actively learned models will be capable of similar novel discovery [48,49,51] . Given the increasing applicability of chemogenomics to uncover untested ligand-target pairs, many different exciting applications come to mind.…”

Section: Implications and Future Directionsmentioning

confidence: 99%

“…The machine learning model is re-trained after every data addition in order to adapt experimental design 'on-the-fly' for improved experimental efficiency. Prospective studies have recognized the ability of active learning to dynamically steer model development and rapidly identify structurally novel compounds for individual targets [46][47][48][49][50][51]. In such prospective chemistry applications, novel compounds would be predicted and assayed, after which those experimental results become the additional examples to learn from, and another round of modeling, prediction and validation begins.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Active Learning for Computational Chemogenomics

et al. 2017

View full text Add to dashboard Cite

Aim: Computational chemogenomics models the compound–protein interaction space, typically for drug discovery, where existing methods predominantly either incorporate increasing numbers of bioactivity samples or focus on specific subfamilies of proteins and ligands. As an alternative to modeling entire large datasets at once, active learning adaptively incorporates a minimum of informative examples for modeling, yielding compact but high quality models. Results/methodology: We assessed active learning for protein/target family-wide chemogenomic modeling by replicate experiment. Results demonstrate that small yet highly predictive models can be extracted from only 10–25% of large bioactivity datasets, irrespective of molecule descriptors used. Conclusion: Chemogenomic active learning identifies small subsets of ligand–target interactions in a large screening database that lead to knowledge discovery and highly predictive models.

show abstract

Section: Model Size and Parametersmentioning

confidence: 99%

Section: Implications and Future Directionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Active Learning for Computational Chemogenomics

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Furthermore, actively trained models not only reached significantly higher hit rates compared to experimental standards which frequently remain below 1 % in cases of unbiased chemical libraries [34,39,40,[47][48][49], but such models also contributed to successful identification of novel bioactive compounds [33,36,42] and cancer rescue mutants of p53 [31]. Overall, AL approaches bear the potential to improve drug discovery processes by increasing hit rates, reducing the amount of time-and cost-intensive experimentation, and accelerate hit-to-lead processes through integration into a feedback-driven experimentation workflow [33,36,42,43,50].…”

Section: Introductionmentioning

confidence: 99%

“…To date, several pro-and retrospective studies report successful applications of AL strategies throughout different fields of research [27][28][29][30][31][32][33][34][35][36][37][38][39][40][41][42][43][44][45][46]. In the area of drug discovery, active learning has been shown to efficiently derive high-performance prediction models based on small subsets of input data [32,34,39,46].…”

Section: Introductionmentioning

confidence: 99%

Small Random Forest Models for Effective Chemogenomic Active Learning

Rakers

Reker

Brown

2017

J. Comput. Aided Chem.

View full text Add to dashboard Cite

The identification of new compound-protein interactions has long been the fundamental quest in the field of medicinal chemistry. With increasing amounts of biochemical data, advanced machine learning techniques such as active learning have been proven to be beneficial for building high-performance prediction models upon subsets of such complex data. In a recently published paper, chemogenomic active learning had been applied to the interaction spaces of kinases and G protein-coupled receptors featuring over 150,000 compound-protein interactions. Prediction models were actively trained based on random forest classification using 500 decision trees per experiment. In a new direction for chemogenomic active learning, we address the question of how forest size influences model evolution and performance. In addition to the original chemogenomic active learning findings that highly predictive models could be constructed from a small fraction of the available data, we find here that that model complexity as viewed by forest size can be reduced to one-fourth or one-fifth of the previously investigated forest size while still maintaining reliable prediction performance. Thus, chemogenomic active learning can yield predictive models with reduced complexity based on only a fraction of the data available for model construction.

show abstract

Large‐scale image‐based screening and profiling of cellular phenotypes

et al. 2016

View full text Add to dashboard Cite

Cellular phenotypes are observable characteristics of cells resulting from the interactions of intrinsic and extrinsic chemical or biochemical factors. Image-based phenotypic screens under large numbers of basal or perturbed conditions can be used to study the influences of these factors on cellular phenotypes. Hundreds to thousands of phenotypic descriptors can also be quantified from the images of cells under each of these experimental conditions. Therefore, huge amounts of data can be generated, and the analysis of these data has become a major bottleneck in large-scale phenotypic screens. Here, we review current experimental and computational methods for large-scale image-based phenotypic screens. Our focus is on phenotypic profiling, a computational procedure for constructing quantitative and compact representations of cellular phenotypes based on the images collected in these screens.

show abstract

Active machine learning-driven experimentation to determine compound effects on protein patterns

Cited by 45 publications

References 36 publications

Active Learning for Computational Chemogenomics

Active Learning for Computational Chemogenomics

Small Random Forest Models for Effective Chemogenomic Active Learning

Large‐scale image‐based screening and profiling of cellular phenotypes

Contact Info

Product

Resources

About