Enpowering Diet Management Happy and Sustainable via Positive Design Method

Liu, Zhiqi; Xu, Juanfang; Liu, Zheng

doi:10.3233/faia220718

Cited by 1 publication

(1 citation statement)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As such, there has been an effort to understand their predictions better. 69,70 In particular, the field of computer vision has seen several developments to better understand neural network predictions, with one of the more prominent techniques being gradient activation mapping. Pope et al, have shown that GradCAM can be adapted to the graph neural networks; 71 first, we can calculate the class-specific weights for class c at layer l and for feature k using the following expression:…”

Section: Gradient Activation Mapping (Gradcam)mentioning

confidence: 99%

Graph Neural Networks for Identifying Protein-Reactive Compounds

Cano Gil,

Rowley

2024

Preprint

View full text Add to dashboard Cite

The identification of protein-reactive electrophilic compounds is critical to the design of new covalent modifier drugs, screening for toxic compounds, and the exclusion of reactive compounds from high throughput screening. In this work, we employ traditional and graph machine learning (ML) algorithms to classify molecules being reactive towards proteins or nonreactive. For training data, we built a new dataset, ProteinReactiveDB, composed primarily of covalent and noncovalent inhibitors from the DrugBank, BindingDB, and CovalentInDB databases. To assess the transferability of the trained models, we created a custom set of covalent and noncovalent inhibitors, which was constructed from the recent literature. Baseline models were developed using Morgan fingerprints as training inputs, but they performed poorly when applied to compounds outside the training set. We then trained various Graph Neural Networks (GNNs), with the best GNN model achieving an Area Under the Receiver Operator Characteristic (AUROC) curve of 0.80, precision of 0.89, and recall of 0.72. We also explore the interpretability of these GNNs using Gradient Activation Mapping (GradCAM), which shows regions of the molecules GNNs deem most relevant when making a prediction. These maps indicated that our trained models can identify electrophilic functional groups in a molecule and classify molecules as protein-reactive based on their presence. We demonstrate the use of these models by comparing their performance against common chemical filters, identifying covalent modifiers in the ChEMBL database and generating a putative covalent inhibitor based on an established noncovalent inhibitor.

show abstract

Section: Gradient Activation Mapping (Gradcam)mentioning

confidence: 99%