deepGraphh: AI-driven web service for graph-based quantitative structure–activity relationship analysis

Abstract

Artificial intelligence (AI)-based computational techniques allow rapid exploration of the chemical space. However, representation of the compounds into computational-compatible and detailed features is one of the crucial steps for quantitative structure–activity relationship (QSAR) analysis. Recently, graph-based methods are emerging as a powerful alternative to chemistry-restricted fingerprints or descriptors for modeling. Although graph-based modeling offers multiple advantages, its implementation demands in-depth domain knowledge and programming skills. Here we introduce deepGraphh, an end-to-end web service featuring a conglomerate of established graph-based methods for model generation for classification or regression tasks. The graphical user interface of deepGraphh supports highly configurable parameter support for model parameter tuning, model generation, cross-validation and testing of the user-supplied query molecules. deepGraphh supports four widely adopted methods for QSAR analysis, namely, graph convolution network, graph attention network, directed acyclic graph and Attentive FP. Comparative analysis revealed that deepGraphh supported methods are comparable to the descriptors-based machine learning techniques. Finally, we used deepGraphh models to predict the blood–brain barrier permeability of human and microbiome-generated metabolites. In summary, deepGraphh offers a one-stop web service for graph-based methods for chemoinformatics.

Unlocking The Mysteries of DNA Adducts with Artificial Intelligence

“…Some widely used graph-based algorithms facilitating Graph-based modeling of chemical compounds include Graph Deep Learning frameworks (Figure 1). [40,41] Briefly, Graph Convolutional Neural Networks (GCNNs) or related graph-based Deep Learning algorithms can be used to learn the representation of DNA adducts by performing convolution operations on the graph's adjacency matrix and node feature matrix. Once optimally trained, GCNN coupled with similarity algorithms can compute structural feature-based similarities between the DNA adducts and the target compounds.…”

“…Notably, the DeepChem library provides off-the-shelf solutions for the Graph-based modeling of chemical compounds. [40,41] Some of the widely used graph-based algorithms include Graph Convolution Network (GCN), [42] Graph Attention Network (GAT), [43] Directed Acyclic Graph (DAG), and AttentiveFP. [44] Graph-based modeling algorithms, besides being proven effective in such applications, also possess several limitations, such as scalability when dealing with a large number of DNA adducts and target compounds, limited training data, interpretability of results, and requirement of computational resources, etc.…”

“…Once optimally trained, GCNN coupled with similarity algorithms can compute structural feature‐based similarities between the DNA adducts and the target compounds. Notably, the DeepChem library provides off‐the‐shelf solutions for the Graph‐based modeling of chemical compounds [40,41] . Some of the widely used graph‐based algorithms include Graph Convolution Network (GCN), [42] Graph Attention Network (GAT), [43] Directed Acyclic Graph (DAG), and AttentiveFP [44] .…”