Interpretation of QSAR Models: Mining Structural Patterns Taking into Account Molecular Context

Matveieva, Mariia; Cronin, Mark T.D.; Polishchuk, Pavel

doi:10.1002/minf.201800084

Cited by 10 publications

(5 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specific functional groups, such as cyano, isothiocyanate, and halogens ,− enhance the toxicities of molecules . However, the extent of the increase appears to be dependent upon the molecular structure and position of the group in the molecule.…”

Section: Resultsmentioning

confidence: 99%

Prior Knowledge for Predictive Modeling: The Case of Acute Aquatic Toxicity

Shavalieva

Papadokonstantakis

Peters

2022

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Early assessment of the potential impact of chemicals on health and the environment requires toxicological properties of the molecules. Predictive modeling is often used to estimate the property values in silico from pre-existing experimental data, which is often scarce and uncertain. One of the ways to advance the predictive modeling procedure might be the use of knowledge existing in the field. Scientific publications contain a vast amount of knowledge. However, the amount of manual work required to process the enormous volumes of information gathered in scientific articles might hinder its utilization. This work explores the opportunity of semiautomated knowledge extraction from scientific papers and investigates a few potential ways of its use for predictive modeling. The knowledge extraction and predictive modeling are applied to the field of acute aquatic toxicity. Acute aquatic toxicity is an important parameter of the safety assessment of chemicals. The extensive amount of diverse information existing in the field makes acute aquatic toxicity an attractive area for investigation of knowledge use for predictive modeling. The work demonstrates that the knowledge collection and classification procedure could be useful in hybrid modeling studies concerning the model and predictor selection, addressing data gaps, and evaluation of models’ performance.

show abstract

Section: Resultsmentioning

confidence: 99%

Prior Knowledge for Predictive Modeling: The Case of Acute Aquatic Toxicity

Shavalieva

Papadokonstantakis

Peters

2022

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…Designing task-specific ILs with desired MPs is challenging because a wide range of factors, including hydrogen bonding, van der Waals interaction, and charge distribution, can affect the MPs . Because trillion types of ILs can be synthesized in a lab, finding the appropriate ILs via experimental screening is costly and time-consuming. , Quantitative structure–property relationship (QSPR) studies − have been used to accurately forecast the MPs of ILs. The goal of QSPR techniques is to create mathematical representations of numerical properties based on the structural details of chemical substances .…”

Section: Introductionmentioning

confidence: 99%

Prediction and Interpretability of Melting Points of Ionic Liquids Using Graph Neural Networks

Feng,

Qin,

Zhang

et al. 2024

ACS Omega

View full text Add to dashboard Cite

Ionic liquids (ILs) have wide and promising applications in fields such as chemical engineering, energy, and the environment. However, the melting points (MPs) of ILs are one of the most crucial properties affecting their applications. The MPs of ILs are affected by various factors, and tuning these in a laboratory is time-consuming and costly. Therefore, an accurate and efficient method is required to predict the desired MPs in the design of novel targeted ILs. In this study, three descriptor-based machine learning (DBML) models and eight graph neural network (GNN) models were proposed to predict the MPs of ILs. Fingerprints and molecular graphs were used to represent molecules for the DBML and GNNs, respectively. The GNN models demonstrated performance superior to that of the DBML models. Among all of the examined models, the graph convolutional model exhibited the best performance with high accuracy (root-mean-squared error = 37.06, mean absolute error = 28.79, and correlation coefficient = 0.76). Benefiting from molecular graph representation, we built a GNN-based interpretable model to reveal the atomistic contribution to the MPs of ILs using a data-driven procedure. According to our interpretable model, amino groups, S + , N + , and P + would increase the MPs of ILs, while the negatively charged halogen atoms, S − , and N − would decrease the MPs of ILs. The results of this study provide new insight into the rapid screening and synthesis of targeted ILs with appropriate MPs.

show abstract

“…There are also other interpretation methods for molecules by introducing special designs. Matveieva et al 42 utilize a clustering strategy to mine the structural patterns of molecular fragments that are associated with desired properties. Tang et al 43 adopt a self-attention module to identify important features for lipophilicity and solubility prediction.…”

Section: Introductionmentioning

confidence: 99%

MolSHAP: Interpreting Quantitative Structure–Activity Relationships Using Shapley Values of R-Groups

Tian

Fang

et al. 2023

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Optimizing the activities and properties of lead compounds is an essential step in the drug discovery process. Despite recent advances in machine learning-aided drug discovery, most of the existing methods focus on making predictions for the desired objectives directly while ignoring the explanations for predictions. Although several techniques can provide interpretations for machine learning-based methods such as feature attribution, there are still gaps between these interpretations and the principles commonly adopted by medicinal chemists when designing and optimizing molecules. Here, we propose an interpretation framework, named MolSHAP, for quantitative structure−activity relationship analysis by estimating the contributions of R-groups. Instead of attributing the activities to individual input features, MolSHAP regards the R-group fragments as the basic units of interpretation, which is in accordance with the fragment-based modifications in molecule optimization. MolSHAP is a model-agnostic method that can interpret activity regression models with arbitrary input formats and model architectures. Based on the evaluations of numerous representative activity regression models on a specially designed R-group ranking task, MolSHAP achieved significantly better interpretation power compared with other methods. In addition, we developed a compound optimization algorithm based on MolSHAP and illustrated the reliability of the optimized compounds using an independent case study. These results demonstrated that MolSHAP can provide a useful tool for accurately interpreting the quantitative structure−activity relationships and rationally optimizing the compound activities in drug discovery.

show abstract

Interpretation of QSAR Models: Mining Structural Patterns Taking into Account Molecular Context

Cited by 10 publications

References 34 publications

Prior Knowledge for Predictive Modeling: The Case of Acute Aquatic Toxicity

Prior Knowledge for Predictive Modeling: The Case of Acute Aquatic Toxicity

Prediction and Interpretability of Melting Points of Ionic Liquids Using Graph Neural Networks

MolSHAP: Interpreting Quantitative Structure–Activity Relationships Using Shapley Values of R-Groups

Contact Info

Product

Resources

About