Unknown

Dataset Information

0

An Analysis of Proteochemometric and Conformal Prediction Machine Learning Protein-Ligand Binding Affinity Models.

ABSTRACT: Protein-ligand binding affinity is a key pharmacodynamic endpoint in drug discovery. Sole reliance on experimental design, make, and test cycles is costly and time consuming, providing an opportunity for computational methods to assist. Herein, we present results comparing random forest and feed-forward neural network proteochemometric models for their ability to predict pIC50 measurements for held out generic Bemis-Murcko scaffolds. In addition, we assess the ability of conformal prediction to provide calibrated prediction intervals in both a retrospective and semi-prospective test using the recently released Grand Challenge 4 data set as an external test set. In total, random forest and deep neural network proteochemometric models show quality retrospective performance but suffer in the semi-prospective setting. However, the conformal predictor prediction intervals prove to be well-calibrated both retrospectively and semi-prospectively showing that they can be used to guide hit discovery and lead optimization campaigns.

SUBMITTER: Parks C 

PROVIDER: S-EPMC7328444 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

Json Xml
altmetric image

Publications

An Analysis of Proteochemometric and Conformal Prediction Machine Learning Protein-Ligand Binding Affinity Models.

Parks Conor C   Gaieb Zied Z   Amaro Rommie E RE  

Frontiers in molecular biosciences 20200624

Protein-ligand binding affinity is a key pharmacodynamic endpoint in drug discovery. Sole reliance on experimental design, make, and test cycles is costly and time consuming, providing an opportunity for computational methods to assist. Herein, we present results comparing random forest and feed-forward neural network proteochemometric models for their ability to predict pIC50 measurements for held out generic Bemis-Murcko scaffolds. In addition, we assess the ability of conformal prediction to  ...[more]

Similar Datasets

Unknown Dowker complex based machine learning (DCML) models for protein-ligand binding affinity prediction.
| S-EPMC8985993 | biostudies-literature
Unknown Structure-based, deep-learning models for protein-ligand binding affinity prediction.
| S-EPMC10765576 | biostudies-literature
Unknown Prediction of protein-ligand binding affinity from sequencing data with interpretable machine learning.
| S-EPMC9546773 | biostudies-literature
Unknown Machine learning on ligand-residue interaction profiles to significantly improve binding affinity prediction.
| S-EPMC8425425 | biostudies-literature
Unknown A machine learning approach towards the prediction of protein-ligand binding affinity based on fundamental molecular properties.
| S-EPMC9079328 | biostudies-literature
Unknown Exploring protein-ligand binding affinity prediction with electron density-based geometric deep learning.
| S-EPMC10835705 | biostudies-literature
Unknown Benchmarking Active Learning Protocols for Ligand-Binding Affinity Prediction.
| S-EPMC10966646 | biostudies-literature
Unknown Development and evaluation of a deep learning model for protein-ligand binding affinity prediction.
| S-EPMC6198856 | biostudies-literature
Unknown A machine learning approach to predicting protein-ligand binding affinity with applications to molecular docking.
| S-EPMC3524828 | biostudies-literature
Unknown Prediction of GPCR-Ligand Binding Using Machine Learning Algorithms.
| S-EPMC5831789 | biostudies-literature