DeepSite: protein‐binding site predictor using 3D‐convolutional neural networks

By J. Jiménez, Stefan Doerr, Gerard Martínez-Rosell, Alexander S. Rose, G. de Fabritiis. 2017

650 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Molecular Biology

How researchers see this paper

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

In Computational Theory and Mathematics

In Molecular Biology

Citations in the corpus

Machine-learning-guided directed evolution for protein engineering (2018, methodology): “They have been applied to protein–nucleic acid binding 46–48 , protein–major histocompatibility complex binding 49 , binding-site prediction 50 , protein–ligand binding 51,52 , solubility 53 , thermostability 54,55 , subcellular localization 56 , secondary structure 57 , functional class 58–60 ,…”
Recent developments in deep learning applied to protein structure prediction (2019, methodology): “Also of use recently have been 3D CNNs, where the input is generally a representation of the protein tertiary structure and the output is a measure such as an estimation of model accuracy(50) or a binding site prediction.(51) In this case the filters learn favorable residue orientation patterns, ana”
PrankWeb: a web server for ligand binding site prediction and visualization (2019, methodology): “0 (6) 2011 Consensus –– Jmol PyMOL –– FTSite (7) 2012 Energetic –– Jmol, static PyMOL –– COFACTOR(12,13) 2012, 2017 Template Yes JSmol –– –– COACH (14) 2013 Template Yes JSmol –– –– eFindSite (27)a 2014 Template Yes –– PyMOL, VMD, Chimera Yes GalaxySite (24) 2014 Template/docking –– PV, static –– ––”
A geometric deep learning approach to predict binding conformations of bioactive molecules (2021, background): “input vectors (vh−1 i and e h−1 i,j ) to create a skip connection and later modified by an activation function (equations (10) and (11)): edown i,j = MLP (”
PointSite: a point cloud segmentation tool for identification of protein ligand binding atoms (2019, background): “g, DeepSite [21] based on 3D-CNN) or rank (e.”
AlphaFold2-aware protein-DNA binding site prediction using graph transformer (2022, positive): “For example, DeepSite [25] maps protein atoms into 3D voxels and employs 3D convolutional neural networks (3DCNN) to extract features from neighborhood of the target residue.”
Development and evaluation of a deep learning model for protein–ligand binding affinity prediction (2017, methodology): “Deep learning has been relatively widely used by the bioinformatics (Leung et al. , 2014; Alipanahi et al. , 2015; Park and Kellis, 2015; Jurtz et al. , 2017; Jim´enez et al. , 2017) and computational biology community (Angermueller et al. , 2016).”
End-to-End Learning on 3D Protein Structure for Interface Prediction (2018, methodology): “3D convolutional networks have been used for protein-ligand binding afﬁnity [14], [15], [16], as well as for protein fold quality assessment [17], protein structure classication [18], ﬁngerprint prediction [19], and ﬁlling in missing amino acids [20].”