Protein Interface Prediction using Graph Convolutional Networks

By Alex Fout, Jonathon Byrd, Basir Shariat, Asa Ben-Hur. 2017

869 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Hierarchical Graph Representation Learning with Differentiable Pooling (2018, methodology): “GNNs have been applied to a wide variety of tasks, including node classification [16, 21], link prediction [31], graph classification [7, 11, 39], and chemoinformatics [14, 19, 27, 28, 32].”
Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks (2018, methodology): “…on several graph classiﬁcation benchmarks in recent years, see, e.g., (Ying et al. 2018b)—as well as applications such as protein-protein interaction prediction (Fout et al. 2017), recommender systems (Ying et al. 2018a), and the analysis of quantum interactions in molecules (Sch¨utt et al. 2017).”
Multi-Scale Representation Learning on Proteins (2022, methodology): “A protein typically has four structural levels: (i.) primary structure (sequence), (ii.) secondary structure ( α -helices and β -sheets), (iii.) tertiary structure (3D structure) and (iv.) quaternary structure (complexes) [Fout et al., 2017].”
Permutation Invariant Graph Generation via Score-Based Generative Modeling (2020, methodology): “, 2017; Kipf and Welling, 2016), protein interaction networks (Fout et al., 2017), and physical systems (Batagelj and Zaversnik,”
Simple and Deep Graph Convolutional Networks (2020, methodology): “…of applications, including social analysis (Qiu et al., 2018; Li & Goldwasser, 2019), trafﬁc prediction (Guo et al., 2019; Li et al., 2019), biology (Fout et al., 2017; Shang et al., 2019), recommender systems (Ying et al., 2018), and com-1 School of Information, Renmin University of China 2…”
DropEdge: Towards Deep Graph Convolutional Networks on Node Classification (2019, methodology): “Self Feature Modeling We also implement a variant of graph convolution layer with self feature modeling (Fout et al., 2017): H(l+1) = σ ( ÂH(l)W(l) +H(l)W (l) self ) , (10) where W(l)self ∈ RCl×Cl−1 .”
Explainability Techniques for Graph Convolutional Networks (2019, background): “…thanks to their consistency to the native data representation, with examples from biochemistry (Duvenaud et al., 2015; Kearnes et al., 2016; Fout et al., 2017; Zitnik et al., 2018), physics (Battaglia et al., 2016; Chang et al., 2017; Gilmer et al., 2017; Watters et al., 2017;…”
GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs (2018, background): “Some models only integrate the node features of neighborhoods (Du-venaud et al., 2015; Kipf and Welling, 2017; Hamilton et al., 2017a), while others integrated edge features as well (Atwood and Towsley, 2016; Fout et al., 2017; Sch ¨ utt et al., 2017).”
HyGCN: A GCN Accelerator with Hybrid Architecture (2020, background): “solve problems including node classification [12], link prediction [9, 13], graph clustering [10], and recommendation [14].”
Edge Attention-based Multi-Relational Graph Convolutional Networks (2018, methodology): “In chemistry field, neural networks and GCNs have been applied to studies such as protein interface prediction[11], molecular representation and prediction [7, 10, 12, 19, 26].”
Optimized Graph Convolution Recurrent Neural Network for Traffic Prediction (2021, methodology): “Then, some research ﬁelds have successfully utilized GCN to achieve improvements, such as protein interface [42], action recognition [43] and semi-supervised classiﬁcation [44], etc.”
MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding (2020, background): “urally represented in a graph data structure, where objects and the relationships among them are embodied by nodes and edges, respectively. Examples include social networks [14, 29], physical systems [2, 10], traffic networks [18, 34], citation networks [1, 14, 16], recommender systems [26, 35], kno”
Graph Neural Networks with Heterophily (2020, methodology): “To propagate the belief vectors through linear formulations, following Gatterbauer et al. (2015), we ﬁrst center B p with We parameterize the compatibility matrix as ¯ H to replace the weight matrix W in traditional GNN models as the end-to-end trainable parameter.”
Utilizing graph machine learning within drug discovery and development (2021, methodology): “[19] used Siamese architectures [201] based on GNNs to predict at which amino acid residues are involved in the interface of a protein–protein”
Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting (2020, background): “In particular, Graph Neural Networks (GNNs), a family of neural architectures designed for irregularly structured data, have been successfully applied to problems ranging from social networks and recommender systems [1] to bioinformatics [2], [3], chemistry [4], [5], [6] and physics [7], [8], to nam”
Enhanced Deep‐Learning Prediction of Molecular Properties via Augmentation of Bond Topology (2018, background): “The attempts to predict molecular properties of solubility, 13,16,17 ab initio calculations, 18,19 and biological activities, 20,21 with relatively small molecules, have provided the basis for the GCN-based generative models such as variational autoencoder, 8,22 adversarial autoencoder, 23 and…”
Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking (2021, background): “We represent a protein as a graph G = ( , E ) , similar to Fout et al. (2017); Townshend et al. (2019); Liu et al. (2020). i represents V Each node ∈ V one residue and has 3D coordinates x i ∈ R 3 corresponding to the α -carbon atom’s location. k-NN Edges are given by a k-nearest-neighbor (k-NN…”