Quantitative structure activity relationship model for predicting the depletion percentage of skin allergic chemical substances of glutathione

QSAR and molecular docking studies on designing potent inhibitors of SARS-CoVs main protease

Background: Severe acute respiratory syndrome coronavirus (SARS-CoVs) have emerged as a global health threat, which had caused a high rate of mortality. There is an urgent need to find effective drugs against these viruses. Objective: This study aims to predict the activity of unsymmetrical aromatic disulfides by constructing a QSAR model, and to design new compounds according to the structural and physicochemical attributes responsible for higher activity towards SARS-CoVs main protease. Methods: All molecules were constructed in ChemOffice software and molecular descriptors were calculated by CODESSA software. A regression-based linear heuristic method was established by changing descriptors datasets and calculating predicted IC50 values of compounds. Then, some new compounds were designed according to molecular descriptors from the heuristic method model. The compounds with predicted values smaller than a set point were constantly screened out. Finally, the properties analysis and molecular docking were conducted to further understand the structure-activity relationships of these finalized compounds. Results: The heuristic method explored the various descriptors responsible for bioactivity and gained the best linear model with R2 0.87. The success of the model fully passed the testing set validation, proving that the model has both high statistical significance and excellent predictive ability. A total of 5 compounds with ideal predicted IC50 were found from the 96 newly designed derivatives and their properties analyze was carried out. Molecular docking experiments were conducted for the optimal compound 31a, which has the best compound activity with good target protein binding capability. Conclusion: The heuristic method was quite reliable for predicting IC50 values of unsymmetrical aromatic disulfides. The present research provides meaningful guidance for further exploration of the highly active inhibitors for SARS-CoVs.

A Deep Learning-Based Chemical System for QSAR Prediction

Research on quantitative structure-activity relationships (QSAR) provides an effective approach to determine new hits and promising lead compounds during drug discovery. In the past decades, various works have gained good performance for QSAR with the development of machine learning. The rise of deep learning, along with massive accessible chemical databases, made improvement on the QSAR performance. This article proposes a novel deep-learning-based method to implement QSAR prediction by the concatenation of end-to-end encoder-decoder model and convolutional neural network (CNN) architecture. The encoder-decoder model is mainly used to generate fixed-size latent features to represent chemical molecules; while these features are then input into CNN framework to train a robust and stable model and finally to predict active chemicals. Two models with different schemes are investigated to evaluate the validity of our proposed model on the same data sets. Experimental results showed that our proposed method outperforms other state-of-the-art methods in successful identification of chemical molecule whether it is active.

DG-GL: Differential geometry-based geometric learning of molecular datasets

MOTIVATION

Despite its great success in various physical modeling, differential geometry (DG) has rarely been devised as a versatile tool for analyzing large, diverse, and complex molecular and biomolecular datasets because of the limited understanding of its potential power in dimensionality reduction and its ability to encode essential chemical and biological information in differentiable manifolds.

RESULTS

We put forward a differential geometry-based geometric learning (DG-GL) hypothesis that the intrinsic physics of three-dimensional (3D) molecular structures lies on a family of low-dimensional manifolds embedded in a high-dimensional data space. We encode crucial chemical, physical, and biological information into 2D element interactive manifolds, extracted from a high-dimensional structural data space via a multiscale discrete-to-continuum mapping using differentiable density estimators. Differential geometry apparatuses are utilized to construct element interactive curvatures in analytical forms for certain analytically differentiable density estimators. These low-dimensional differential geometry representations are paired with a robust machine learning algorithm to showcase their descriptive and predictive powers for large, diverse, and complex molecular and biomolecular datasets. Extensive numerical experiments are carried out to demonstrate that the proposed DG-GL strategy outperforms other advanced methods in the predictions of drug discovery-related protein-ligand binding affinity, drug toxicity, and molecular solvation free energy.

AVAILABILITY AND IMPLEMENTATION

http://weilab.math.msu.edu/DG-GL/ Contact: wei@math.msu.edu.

Prediction of PKCθ inhibitory activity using the Random Forest Algorithm

This work is devoted to the prediction of a series of 208 structurally diverse PKCθ inhibitors using the Random Forest (RF) based on the Mold(2) molecular descriptors. The RF model was established and identified as a robust predictor of the experimental pIC(50) values, producing good external R(2) (pred) of 0.72, a standard error of prediction (SEP) of 0.45, for an external prediction set of 51 inhibitors which were not used in the development of QSAR models. By using the RF built-in measure of the relative importance of the descriptors, an important predictor-the number of group donor atoms for H-bonds (with N and O)-has been identified to play a crucial role in PKCθ inhibitory activity. We hope that the developed RF model will be helpful in the screening and prediction of novel unknown PKCθ inhibitory activity.

Current mathematical methods used in QSAR/QSPR studies

This paper gives an overview of the mathematical methods currently used in quantitative structure-activity/property relationship (QASR/QSPR) studies. Recently, the mathematical methods applied to the regression of QASR/QSPR models are developing very fast, and new methods, such as Gene Expression Programming (GEP), Project Pursuit Regression (PPR) and Local Lazy Regression (LLR) have appeared on the QASR/QSPR stage. At the same time, the earlier methods, including Multiple Linear Regression (MLR), Partial Least Squares (PLS), Neural Networks (NN), Support Vector Machine (SVM) and so on, are being upgraded to improve their performance in QASR/QSPR studies. These new and upgraded methods and algorithms are described in detail, and their advantages and disadvantages are evaluated and discussed, to show their application potential in QASR/QSPR studies in the future.