Construction of a Virtual Opioid Bioprofile: A Data-Driven QSAR Modeling Study to Identify New Analgesic Opioids

Abstract

Compared to traditional experimental approaches, computational modeling is a promising strategy to efficiently prioritize new candidates with low cost. In this study, we developed a novel data mining and computational modeling workflow proven to be applicable by screening new analgesic opioids. To this end, a large opioid data set was used as the probe to automatically obtain bioassay data from the PubChem portal. There were 114 PubChem bioassays selected to build quantitative structure−activity relationship (QSAR) models based on the testing results across the probe compounds. The compounds tested in each bioassay were used to develop 12 models using the combination of three machine learning approaches and four types of chemical descriptors. The model performance was evaluated by the coefficient of determination (R 2 ) obtained from 5-fold cross-validation. In total, 49 models developed for 14 bioassays were selected based on the criteria and were identified to be mainly associated with binding affinities to different opioid receptors. The models for these 14 bioassays were further used to fill data gaps in the probe opioids data set and to predict general drug compounds in the DrugBank data set. This study provides a universal modeling strategy that can take advantage of large public data sets for computer-aided drug design (CADD).

The Psychonauts’ Benzodiazepines; Quantitative Structure-Activity Relationship (QSAR) Analysis and Docking Prediction of Their Biological Activity

“…Indeed, computational models are well established, and successfully/extensively used tools, and especially so for drug development [ 44 ]. They have already been applied to classical and designer benzodiazepines [ 45 , 46 ] and other NPS classes (e.g., synthetic cannabinoids [ 47 , 48 , 49 ], opioids [ 50 , 51 ], hallucinogenic phenylalkylamines [ 52 ], and tryptamines [ 53 ] and phenethylamines [ 54 , 55 ].…”

Rapid Screening of Human Transthyretin Disruptors through a Tiered in Silico Approach

“…While eight and two compounds were moderate and strong hTTR binders, respectively. This analysis result indicated that the compounds with no hTTR binding potency or weak binding potency were more easily misclassified than those of moderate and strong hTTR binders, which may be caused by the factor of activity cliffs (i.e., the chemicals with similar structures elicit significantly different activities). , …”

“…This analysis result indicated that the compounds with no hTTR binding potency or weak binding potency were more easily misclassified than those of moderate and strong hTTR binders, which may be caused by the factor of activity cliffs (i.e., the chemicals with similar structures elicit significantly different activities). 96,97 Construction of QSAR Models. The optimum kNN-QSAR (Radio) model was developed based on four predictive variables (m), i.e., E HOMO-adj (the chemical form adjusted energies of highest occupied molecular orbital), nArOH, H-052 (H attached to C0(sp3) with 1X attached to next C), and ω adj .…”

Sustainable Management of Synthetic Chemicals

“…Computational modeling driven by the latest progress of informatics and data science is a promising direction for this goal. In this VSI, Jia et al reported a data-driven modeling study to select safe analgesic drugs . An automatic data-mining tool was used in this study to obtain relevant data from public big data resources to generate predictive models for virtual screening purposes.…”

“…In this VSI, Jia et al reported a datadriven modeling study to select safe analgesic drugs. 1 An automatic data-mining tool was used in this study to obtain relevant data from public big data resources to generate predictive models for virtual screening purposes. Another study by Minerali et al is to develop a quantitative structure−activity relationship (QSAR) toolbox, named Assay Central, for predicting rat oral acute toxicity of chemicals.…”