Dataset Information

Layer-wise relevance propagation of InteractionNet explains protein-ligand interactions at the atom level.

ABSTRACT: Development of deep-learning models for intermolecular noncovalent (NC) interactions between proteins and ligands has great potential in the chemical and pharmaceutical tasks, including structure-activity relationship and drug design. It still remains an open question how to convert the three-dimensional, structural information of a protein-ligand complex into a graph representation in the graph neural networks (GNNs). It is also difficult to know whether a trained GNN model learns the NC interactions properly. Herein, we propose a GNN architecture that learns two distinct graphs-one for the intramolecular covalent bonds in a protein and a ligand, and the other for the intermolecular NC interactions between the protein and the ligand-separately by the corresponding covalent and NC convolutional layers. The graph separation has some advantages, such as independent evaluation on the contribution of each convolutional step to the prediction of dissociation constants, and facile analysis of graph-building strategies for the NC interactions. In addition to its prediction performance that is comparable to that of a state-of-the art model, the analysis with an explainability strategy of layer-wise relevance propagation shows that our model successfully predicts the important characteristics of the NC interactions, especially in the aspect of hydrogen bonding, in the chemical interpretation of protein-ligand binding.

SUBMITTER: Cho H

PROVIDER: S-EPMC7713352 | biostudies-literature | 2020 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Layer-wise relevance propagation of InteractionNet explains protein-ligand interactions at the atom level.

Cho Hyeoncheol H Lee Eok Kyun EK Choi Insung S IS

Scientific reports 20201203 1

Development of deep-learning models for intermolecular noncovalent (NC) interactions between proteins and ligands has great potential in the chemical and pharmaceutical tasks, including structure-activity relationship and drug design. It still remains an open question how to convert the three-dimensional, structural information of a protein-ligand complex into a graph representation in the graph neural networks (GNNs). It is also difficult to know whether a trained GNN model learns the NC intera ...[more]

PMID: 33273642

Similar Datasets

Project description:Machine learning-based imaging diagnostics has recently reached or even surpassed the level of clinical experts in several clinical domains. However, classification decisions of a trained machine learning system are typically non-transparent, a major hindrance for clinical integration, error tracking or knowledge discovery. In this study, we present a transparent deep learning framework relying on 3D convolutional neural networks (CNNs) and layer-wise relevance propagation (LRP) for diagnosing multiple sclerosis (MS), the most widespread autoimmune neuroinflammatory disease. MS is commonly diagnosed utilizing a combination of clinical presentation and conventional magnetic resonance imaging (MRI), specifically the occurrence and presentation of white matter lesions in T2-weighted images. We hypothesized that using LRP in a naive predictive model would enable us to uncover relevant image features that a trained CNN uses for decision-making. Since imaging markers in MS are well-established this would enable us to validate the respective CNN model. First, we pre-trained a CNN on MRI data from the Alzheimer's Disease Neuroimaging Initiative (n = 921), afterwards specializing the CNN to discriminate between MS patients (n = 76) and healthy controls (n = 71). Using LRP, we then produced a heatmap for each subject in the holdout set depicting the voxel-wise relevance for a particular classification decision. The resulting CNN model resulted in a balanced accuracy of 87.04% and an area under the curve of 96.08% in a receiver operating characteristic curve. The subsequent LRP visualization revealed that the CNN model focuses indeed on individual lesions, but also incorporates additional information such as lesion location, non-lesional white matter or gray matter areas such as the thalamus, which are established conventional and advanced MRI markers in MS. We conclude that LRP and the proposed framework have the capability to make diagnostic decisions of CNN models transparent, which could serve to justify classification decisions for clinical review, verify diagnosis-relevant features and potentially gather new disease knowledge.

Project description:BackgroundAlthough deep neural networks (DNNs) are showing state of the art performance in clinical gait analysis, they are considered to be black-box algorithms. In other words, there is a lack of direct understanding of a DNN's ability to identify relevant features, hindering clinical acceptance. Interpretability methods have been developed to ameliorate this concern by providing a way to explain DNN predictions.MethodsThis paper proposes the use of an interpretability method to explain DNN decisions for classifying the movement that precedes freezing of gait (FOG), one of the most debilitating symptoms of Parkinson's disease (PD). The proposed two-stage pipeline consists of (1) a convolutional neural network (CNN) to model the reduction of movement present before a FOG episode, and (2) layer-wise relevance propagation (LRP) to visualize the underlying features that the CNN perceives as important to model the pathology. The CNN was trained with the sagittal plane kinematics from a motion capture dataset of fourteen PD patients with FOG. The robustness of the model predictions and learned features was further assessed on fourteen PD patients without FOG and fourteen age-matched healthy controls.ResultsThe CNN proved highly accurate in modelling the movement that precedes FOG, with 86.8% of the strides being correctly identified. However, the CNN model was unable to model the movement for one of the seven patients that froze during the protocol. The LRP interpretability case study shows that (1) the kinematic features perceived as most relevant by the CNN are the reduced peak knee flexion and the fixed ankle dorsiflexion during the swing phase, (2) very little relevance for FOG is observed in the PD patients without FOG and the healthy control subjects, and (3) the poor predictive performance of one subject is attributed to the patient's unique and severely flexed gait signature.ConclusionsThe proposed pipeline can aid clinicians in explaining DNN decisions in clinical gait analysis and aid machine learning practitioners in assessing the generalization of their models by ensuring that the predictions are based on meaningful kinematic features.

Project description:BACKGROUND: Shape complementarity and non-covalent interactions are believed to drive protein-ligand interaction. To date protein-protein, protein-DNA, and protein-RNA interactions were systematically investigated, which is in contrast to interactions with small ligands. We investigate the role of covalent and non-covalent bonds in protein-small ligand interactions using a comprehensive dataset of 2,320 complexes. METHODOLOGY AND PRINCIPAL FINDINGS: We show that protein-ligand interactions are governed by different forces for different ligand types, i.e., protein-organic compound interactions are governed by hydrogen bonds, van der Waals contacts, and covalent bonds; protein-metal ion interactions are dominated by electrostatic force and coordination bonds; protein-anion interactions are established with electrostatic force, hydrogen bonds, and van der Waals contacts; and protein-inorganic cluster interactions are driven by coordination bonds. We extracted several frequently occurring atomic-level patterns concerning these interactions. For instance, 73% of investigated covalent bonds were summarized with just three patterns in which bonds are formed between thiol of Cys and carbon or sulfur atoms of ligands, and nitrogen of Lys and carbon of ligands. Similar patterns were found for the coordination bonds. Hydrogen bonds occur in 67% of protein-organic compound complexes and 66% of them are formed between NH- group of protein residues and oxygen atom of ligands. We quantify relative abundance of specific interaction types and discuss their characteristic features. The extracted protein-organic compound patterns are shown to complement and improve a geometric approach for prediction of binding sites. CONCLUSIONS AND SIGNIFICANCE: We show that for a given type (group) of ligands and type of the interaction force, majority of protein-ligand interactions are repetitive and could be summarized with several simple atomic-level patterns. We summarize and analyze 10 frequently occurring interaction patterns that cover 56% of all considered complexes and we show a practical application for the patterns that concerns interactions with organic compounds.

Project description:Motivation:Sequence-order independent structural comparison, also called structural alignment, of small ligand molecules is often needed for computer-aided virtual drug screening. Although many ligand structure alignment programs are proposed, most of them build the alignments based on rigid-body shape comparison which cannot provide atom-specific alignment information nor allow structural variation; both abilities are critical to efficient high-throughput virtual screening. Results:We propose a novel ligand comparison algorithm, LS-align, to generate fast and accurate atom-level structural alignments of ligand molecules, through an iterative heuristic search of the target function that combines inter-atom distance with mass and chemical bond comparisons. LS-align contains two modules of Rigid-LS-align and Flexi-LS-align, designed for rigid-body and flexible alignments, respectively, where a ligand-size independent, statistics-based scoring function is developed to evaluate the similarity of ligand molecules relative to random ligand pairs. Large-scale benchmark tests are performed on prioritizing chemical ligands of 102 protein targets involving 1 415 871 candidate compounds from the DUD-E (Database of Useful Decoys: Enhanced) database, where LS-align achieves an average enrichment factor (EF) of 22.0 at the 1% cutoff and the AUC score of 0.75, which are significantly higher than other state-of-the-art methods. Detailed data analyses show that the advanced performance is mainly attributed to the design of the target function that combines structural and chemical information to enhance the sensitivity of recognizing subtle difference of ligand molecules and the introduces of structural flexibility that help capture the conformational changes induced by the ligand-receptor binding interactions. These data demonstrate a new avenue to improve the virtual screening efficiency through the development of sensitive ligand structural alignments. Availability and implementation:http://zhanglab.ccmb.med.umich.edu/LS-align/. Supplementary information:Supplementary data are available at Bioinformatics online.

Dataset Information

Layer-wise relevance propagation of InteractionNet explains protein-ligand interactions at the atom level.

Publications

Layer-wise relevance propagation of InteractionNet explains protein-ligand interactions at the atom level.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure