Structure-based protein function prediction using graph convolutional networks.
Ontology highlight
ABSTRACT:
SUBMITTER: Gligorijevic V
PROVIDER: S-EPMC8155034 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:High-throughput sequencing technologies have generated massive protein sequences, but the annotations of protein sequences highly rely on the low-throughput and expensive biological experiments. Therefore, accurate and fast computational alternatives are needed to infer functional knowledge from protein sequences. The gene ontology (GO) directed acyclic graph (DAG) contains the hierarchical relationships between GO terms but is hard to be integrated into machine learning algorithms for functional predictions. We developed a deep learning system named PANDA2 to predict protein functions, which used the cutting-edge graph neural network to model the topology of the GO DAG and integrated the features generated by transformer protein language models. Compared with the top 10 methods in CAFA3, PANDA2 ranked first in cellular component ontology (CCO), tied first in biological process ontology (BPO) but had a higher coverage rate, and second in molecular function ontology (MFO). Compared with other recently-developed cutting-edge predictors DeepGOPlus, GOLabeler, and DeepText2GO, and benchmarked on another independent dataset, PANDA2 ranked first in CCO, first in BPO, and second in MFO. PANDA2 can be freely accessed from http://dna.cs.miami.edu/PANDA2/.
| S-EPMC8808544 | biostudies-literature
Project description:Epilepsy is a chronic brain disease that causes persistent and severe damage to the physical and mental health of patients. Daily effective prediction of epileptic seizures is crucial for epilepsy patients especially those with refractory epilepsy. At present, a large number of deep learning algorithms such as Convolutional Neural Networks and Recurrent Neural Networks have been used to predict epileptic seizures and have obtained better performance than traditional machine learning methods. However, these methods usually transform the Electroencephalogram (EEG) signal into a Euclidean grid structure. The conversion suffers from loss of adjacent spatial information, which results in deep learning models requiring more storage and computational consumption in the process of information fusion after information extraction. This study proposes a general Graph Convolutional Networks (GCN) model architecture for predicting seizures to solve the problem of oversized seizure prediction models based on exploring the graph structure of EEG signals. As a graph classification task, the network architecture includes graph convolution layers that extract node features with one-hop neighbors, pooling layers that summarize abstract node features; and fully connected layers that implement classification, resulting in superior prediction performance and smaller network size. The experiment shows that the model has an average sensitivity of 96.51%, an average AUC of 0.92, and a model size of 15.5 k on 18 patients in the CHB-MIT scalp EEG dataset. Compared with traditional deep learning methods, which require a large number of parameters and computational effort and are demanding in terms of storage space and energy consumption, this method is more suitable for implementation on compact, low-power wearable devices as a standard process for building a generic low-consumption graph network model on similar biomedical signals. Furthermore, the edge features of graphs can be used to make a preliminary determination of locations and types of discharge, making it more clinically interpretable.
| S-EPMC9376592 | biostudies-literature
Project description:MotivationProteins are ubiquitous molecules whose function in biological processes is determined by their 3D structure. Experimental identification of a protein's structure can be time-consuming, prohibitively expensive and not always possible. Alternatively, protein folding can be modeled using computational methods, which however are not guaranteed to always produce optimal results. GraphQA is a graph-based method to estimate the quality of protein models, that possesses favorable properties such as representation learning, explicit modeling of both sequential and 3D structure, geometric invariance and computational efficiency.ResultsGraphQA performs similarly to state-of-the-art methods despite using a relatively low number of input features. In addition, the graph network structure provides an improvement over the architecture used in ProQ4 operating on the same input features. Finally, the individual contributions of GraphQA components are carefully evaluated.Availability and implementationPyTorch implementation, datasets, experiments and link to an evaluation server are available through this GitHub repository: github.com/baldassarreFe/graphqa.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC8058777 | biostudies-literature
Project description:MotivationConvolutional neural networks have enabled unprecedented breakthroughs in a variety of computer vision tasks. They have also drawn much attention from other domains, including drug discovery and drug development. In this study, we develop a computational method based on convolutional neural networks to tackle a fundamental question in drug discovery and development, i.e. the prediction of compound-protein interactions based on compound structure and protein sequence. We propose a hierarchical graph convolutional network (HGCN) to encode small molecules. The HGCN aggregates a molecule embedding from substructure embeddings, which are synthesized from atom embeddings. As small molecules usually share substructures, computing a molecule embedding from those common substructures allows us to learn better generic models. We then combined the HGCN with a one-dimensional convolutional network to construct a complete model for predicting compound-protein interactions. Furthermore we apply an explanation technique, Grad-CAM, to visualize the contribution of each amino acid into the prediction.ResultsExperiments using different datasets show the improvement of our model compared to other GCN-based methods and a sequence based method, DeepDTA, in predicting compound-protein interactions. Each prediction made by the model is also explainable and can be used to identify critical residues mediating the interaction.
| S-EPMC9302762 | biostudies-literature
Project description:An important stage in the process of discovering new drugs is when candidate molecules are tested of their efficacy. It is reported that testing drug efficacy empirically costs billions of dollars in the drug discovery pipeline. As a mechanism of expediting this process, researchers have resorted to using computational methods to predict the action of molecules in silico. Here, we present a way of predicting the therapeutic-use class of drugs from chemical structures only using graph convolutional networks. In comparison with existing methods which use fingerprints or images as training samples, our approach has yielded better results in all metrics under consideration. In particular, validation accuracy increased from 83-88% to 86-90% for single label tasks. Similarly, the model achieved an accuracy of over 88% on new test data. Finally, our multi-label classification model made new predictions which indicated that some of the drugs could have other therapeutic uses other than those indicated in the dataset. We performed a literature-based evaluation of these predictions and found evidence that validates them. This renders the model a potential tool to be used in search of drugs that are candidates for repurposing.
| S-EPMC8622176 | biostudies-literature
Project description:Experimental protein function annotation does not scale with the fast-growing sequence databases. Only a tiny fraction (<0.1%) of protein sequences has experimentally determined functional annotations. Computational methods may predict protein function very quickly, but their accuracy is not very satisfactory. Based upon recent breakthroughs in protein structure prediction and protein language models, we develop GAT-GO, a graph attention network (GAT) method that may substantially improve protein function prediction by leveraging predicted structure information and protein sequence embedding. Our experimental results show that GAT-GO greatly outperforms the latest sequence- and structure-based deep learning methods. On the PDB-mmseqs testset where the train and test proteins share <15% sequence identity, our GAT-GO yields Fmax (maximum F-score) 0.508, 0.416, 0.501, and area under the precision-recall curve (AUPRC) 0.427, 0.253, 0.411 for the MFO, BPO, CCO ontology domains, respectively, much better than the homology-based method BLAST (Fmax 0.117, 0.121, 0.207 and AUPRC 0.120, 0.120, 0.163) that does not use any structure information. On the PDB-cdhit testset where the training and test proteins are more similar, although using predicted structure information, our GAT-GO obtains Fmax 0.637, 0.501, 0.542 for the MFO, BPO, CCO ontology domains, respectively, and AUPRC 0.662, 0.384, 0.481, significantly exceeding the just-published method DeepFRI that uses experimental structures, which has Fmax 0.542, 0.425, 0.424 and AUPRC only 0.313, 0.159, 0.193.
| S-EPMC8898000 | biostudies-literature
Project description:Cancer is a complex and evolutionary disease mainly driven by the accumulation of genetic variations in genes. Identifying cancer driver genes is important. However, most related studies have focused on the population level. Cancer is a disease with high heterogeneity. Thus, the discovery of driver genes at the individual level is becoming more valuable but is a great challenge. Although there have been some computational methods proposed to tackle this challenge, few can cover all patient samples well, and there is still room for performance improvement. In this study, to identify individual-level driver genes more efficiently, we propose the PDGCN method. PDGCN integrates multiple types of data features, including mutation, expression, methylation, copy number data, and system-level gene features, along with network structural features extracted using Node2vec in order to construct a sample-gene interaction network. Prediction is performed using a graphical convolutional neural network model with a conditional random field layer, which is able to better combine the network structural features with biological attribute features. Experiments on the ACC (Adrenocortical Cancer) and KICH (Kidney Chromophobe) datasets from TCGA (The Cancer Genome Atlas) demonstrated that the method performs better compared to other similar methods. It can identify not only frequently mutated driver genes, but also rare candidate driver genes and novel biomarker genes. The results of the survival and enrichment analyses of these detected genes demonstrate that the method can identify important driver genes at the individual level.
| S-EPMC10968662 | biostudies-literature
Project description:Structural information about protein-protein interactions, often missing at the interactome scale, is important for mechanistic understanding of cells and rational discovery of therapeutics. Protein docking provides a computational alternative for such information. However, ranking near-native docked models high among a large number of candidates, often known as the scoring problem, remains a critical challenge. Moreover, estimating model quality, also known as the quality assessment problem, is rarely addressed in protein docking. In this study, the two challenging problems in protein docking are regarded as relative and absolute scoring, respectively, and addressed in one physics-inspired deep learning framework. We represent protein and complex structures as intra- and inter-molecular residue contact graphs with atom-resolution node and edge features. And we propose a novel graph convolutional kernel that aggregates interacting nodes' features through edges so that generalized interaction energies can be learned directly from 3D data. The resulting energy-based graph convolutional networks (EGCN) with multihead attention are trained to predict intra- and inter-molecular energies, binding affinities, and quality measures (interface RMSD) for encounter complexes. Compared to a state-of-the-art scoring function for model ranking, EGCN significantly improves ranking for a critical assessment of predicted interactions (CAPRI) test set involving homology docking; and is comparable or slightly better for Score_set, a CAPRI benchmark set generated by diverse community-wide docking protocols not known to training data. For Score_set quality assessment, EGCN shows about 27% improvement to our previous efforts. Directly learning from 3D structure data in graph representation, EGCN represents the first successful development of graph convolutional networks for protein docking.
| S-EPMC7374013 | biostudies-literature
Project description:Computational prediction of ligand-target interactions is a crucial part of modern drug discovery as it helps to bypass high costs and labor demands of in vitro and in vivo screening. As the wealth of bioactivity data accumulates, it provides opportunities for the development of deep learning (DL) models with increasing predictive powers. Conventionally, such models were either limited to the use of very simplified representations of proteins or ineffective voxelization of their 3D structures. Herein, we present the development of the PSG-BAR (Protein Structure Graph-Binding Affinity Regression) approach that utilizes 3D structural information of the proteins along with 2D graph representations of ligands. The method also introduces attention scores to selectively weight protein regions that are most important for ligand binding. Results: The developed approach demonstrates the state-of-the-art performance on several binding affinity benchmarking datasets. The attention-based pooling of protein graphs enables identification of surface residues as critical residues for protein-ligand binding. Finally, we validate our model predictions against an experimental assay on a viral main protease (Mpro)-the hallmark target of SARS-CoV-2 coronavirus.
| S-EPMC9416537 | biostudies-literature
Project description:Protein-protein interactions (PPIs) are essential for most biological processes. However, current PPI networks present high levels of noise, sparseness and incompleteness, which limits our ability to understand the cell at the system level from the PPI network. Predicting novel (missing) links in noisy PPI networks is an essential computational method for automatically expanding the human interactome and for identifying biologically legitimate but undetected interactions for experimental determination of PPIs, which is both expensive and time-consuming. Recently, graph convolutional networks (GCN) have shown their effectiveness in modeling graph-structured data, which employ a 1-hop neighborhood aggregation procedure and have emerged as a powerful architecture for node or graph representations. In this paper, we propose a novel node (protein) embedding method by combining GCN and PageRank as the latter can significantly improve the GCN's aggregation scheme, which has difficulty in extending and exploring topological information of networks across higher-order neighborhoods of each node. Building on this novel node embedding model, we develop a higher-order GCN variational auto-encoder (HO-VGAE) architecture, which can learn a joint node representation of higher-order local and global PPI network topology for novel protein interaction prediction. It is worth noting that our method is based exclusively on network topology, with no protein attributes or extra biological features used. Extensive computational validations on PPI prediction task demonstrate our method without leveraging any additional biological information shows competitive performance-outperforms all existing graph embedding-based link prediction methods in both accuracy and robustness.
| S-EPMC7514053 | biostudies-literature