Machine Learned Classification of Ligand Intrinsic Activities at Human μ-Opioid Receptor
Oh, M.; Shen, M.; Liu, R.; Stavitskaya, L.; Shen, J.
Show abstract
Opioids are small-molecule agonists of {micro}-opioid receptor ({micro}OR), while reversal agents such as naloxone are antagonists of {micro}OR. Here we developed machine learning (ML) models to classify the intrinsic activities of ligands at the human {micro}OR based on the SMILE strings and two-dimensional molecular descriptors. We first manually curated a database of 983 small molecules with measured Emax values at the human {micro}OR. Analysis of the chemical space allowed identification of dominant scaffolds and structurally similar agonists and antagonists. Decision tree models and directed message passing neural networks (MPNNs) were then trained to classify agonistic and antagonistic ligands. The hold-out test AUCs (areas under the receiver operator curves) of the extra-tree (ET) and MPNN models are 91.5 {+/-} 3.9% and 91.8 {+/-} 4.4%, respectively. To overcome the challenge of small dataset, a student-teacher learning method called tri-training with disagreement was tested using an unlabeled dataset comprised of 15,816 ligands of human, mouse, or rat {micro}OR,{kappa} OR, or{delta} OR. We found that the tri-training scheme was able to increase the hold-out AUC of MPNN to as high as 95.7%. Our work demonstrates the feasibility of developing ML models to accurately predict the intrinsic activities of {micro}OR ligands, even with limited data. We envisage potential applications of these models in evaluating uncharacterized substances for public safety risks and discovering new therapeutic agents to counteract opioid overdoses. TOC Graphic O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=105 SRC="FIGDIR/small/588485v2_ufig1.gif" ALT="Figure 1"> View larger version (16K): org.highwire.dtl.DTLVardef@1bf13f7org.highwire.dtl.DTLVardef@1b7f04aorg.highwire.dtl.DTLVardef@1009569org.highwire.dtl.DTLVardef@1515139_HPS_FORMAT_FIGEXP M_FIG C_FIG
Matching journals
The top 1 journal accounts for 50% of the predicted probability mass.
Similar papers in this journal
- Deep Learning-based Ligand Design using Shared Latent Implicit Fingerprints from Collaborative Filtering 97%
- MolAI: A Deep Learning Framework for Data-driven Molecular Descriptor Generation and Advanced Drug Discovery Applications 97%
- Benchmarking of Small Molecule Feature Representations for hERG, Nav1.5, and Cav1.2 Cardiotoxicity Prediction 96%
Similar papers in this journal
- Thinking like a structural biologist: A pocket-based 3D molecule generative model fueled by electron density 95%
- Discovery of Z1362873773: A Novel Fascin Inhibitor from a Large Chemical Library for Colorectal Cancer 95%
- Bacopa monnieri phytochemicals as promising BACE1 inhibitors for Alzheimers Disease Therapy 94%
Similar papers in this journal
- Merging Bioactivity Predictions from Cell Morphology and Chemical Fingerprint Models Using Similarity to Training Data 96%
- BitterMatch: Recommendation systems for matching molecules with bitter taste receptors 95%
- Comprehensive machine learning boosts structure-based virtual screening for PARP1 inhibitors 95%
Similar papers in this journal
- Machine learning approaches identify chemical features for stage-specific antimalarial compounds 96%
- How far are we in the rapid prediction of drug resistance caused by kinase mutations? 95%
- Discovery of a Novel Non-Narcotic Analgesic Derived from the CL-20 Explosive: Synthesis, Pharmacology and Target Identification of Thio-wurtzine, a Potent Inhibitor of the Opioid Receptors and the Voltage-Dependent Calcium Channels 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.