Protocol to explain graph neural network predictions using an edge-centric Shapley value-based approach

Mastropietro, Andrea; Pasculli, Giuseppe; Bajorath, Jürgen

doi:10.1016/j.xpro.2022.101887

Cited by 3 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…45 The BBB penetration ability of organic structures has also been investigated with good accuracy using artificial neural networks (ANN) 46 and graph neural networks. 47 It is also known that random forest models have better predictive capacity to describe the BBB penetration. 48 One of the recent discoveries of XAI in minimizing the black box effects is that these methods have the applicability to interpret the binding of chemical structures with two protein targets of pharmacological relevance using a locally interpretable model.…”

Section: ■ Introductionmentioning

confidence: 99%

“…Additionally, methods with graph convolutional networks are used to improve the understanding of the penetration mechanism, which occurs mainly by passive diffusion . The BBB penetration ability of organic structures has also been investigated with good accuracy using artificial neural networks (ANN) and graph neural networks . It is also known that random forest models have better predictive capacity to describe the BBB penetration .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Identifying Substructures That Facilitate Compounds to Penetrate the Blood–Brain Barrier via Passive Transport Using Machine Learning Explainer Models

Rosa,

Argolo,

Nascimento

et al. 2024

ACS Chem. Neurosci.

View full text Add to dashboard Cite

The local interpretable model-agnostic explanation (LIME) method was used to interpret two machine learning models of compounds penetrating the blood–brain barrier. The classification models, Random Forest, ExtraTrees, and Deep Residual Network, were trained and validated using the blood–brain barrier penetration dataset, which shows the penetrability of compounds in the blood–brain barrier. LIME was able to create explanations for such penetrability, highlighting the most important substructures of molecules that affect drug penetration in the barrier. The simple and intuitive outputs prove the applicability of this explainable model to interpreting the permeability of compounds across the blood–brain barrier in terms of molecular features. LIME explanations were filtered with a weight equal to or greater than 0.1 to obtain only the most relevant explanations. The results showed several structures that are important for blood–brain barrier penetration. In general, it was found that some compounds with nitrogenous substructures are more likely to permeate the blood–brain barrier. The application of these structural explanations may help the pharmaceutical industry and potential drug synthesis research groups to synthesize active molecules more rationally.

show abstract

Section: ■ Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Identifying Substructures That Facilitate Compounds to Penetrate the Blood–Brain Barrier via Passive Transport Using Machine Learning Explainer Models

Rosa,

Argolo,

Nascimento

et al. 2024

ACS Chem. Neurosci.

View full text Add to dashboard Cite

show abstract

Calculation of exact Shapley values for explaining support vector machine models using the radial basis function kernel

Mastropietro,

Feldmann,

Bajorath

2023

Sci Rep

View full text Add to dashboard Cite

Machine learning (ML) algorithms are extensively used in pharmaceutical research. Most ML models have black-box character, thus preventing the interpretation of predictions. However, rationalizing model decisions is of critical importance if predictions should aid in experimental design. Accordingly, in interdisciplinary research, there is growing interest in explaining ML models. Methods devised for this purpose are a part of the explainable artificial intelligence (XAI) spectrum of approaches. In XAI, the Shapley value concept originating from cooperative game theory has become popular for identifying features determining predictions. The Shapley value concept has been adapted as a model-agnostic approach for explaining predictions. Since the computational time required for Shapley value calculations scales exponentially with the number of features used, local approximations such as Shapley additive explanations (SHAP) are usually required in ML. The support vector machine (SVM) algorithm is one of the most popular ML methods in pharmaceutical research and beyond. SVM models are often explained using SHAP. However, there is only limited correlation between SHAP and exact Shapley values, as previously demonstrated for SVM calculations using the Tanimoto kernel, which limits SVM model explanation. Since the Tanimoto kernel is a special kernel function mostly applied for assessing chemical similarity, we have developed the Shapley value-expressed radial basis function (SVERAD), a computationally efficient approach for the calculation of exact Shapley values for SVM models based upon radial basis function kernels that are widely applied in different areas. SVERAD is shown to produce meaningful explanations of SVM predictions.

show abstract

Learning characteristics of graph neural networks predicting protein–ligand affinities

Mastropietro,

Pasculli,

Bajorath

2023

Nat Mach Intell

View full text Add to dashboard Cite

Protocol to explain graph neural network predictions using an edge-centric Shapley value-based approach

Cited by 3 publications

References 5 publications

Identifying Substructures That Facilitate Compounds to Penetrate the Blood–Brain Barrier via Passive Transport Using Machine Learning Explainer Models

Identifying Substructures That Facilitate Compounds to Penetrate the Blood–Brain Barrier via Passive Transport Using Machine Learning Explainer Models

Calculation of exact Shapley values for explaining support vector machine models using the radial basis function kernel

Learning characteristics of graph neural networks predicting protein–ligand affinities

Contact Info

Product

Resources

About