EurekaMag
+ Translate
+ Most Popular
Gaucher's disease;thirty-two years experience at Siriraj Hospital
A study of Macrobathra Meyrick from China (Lepidoptera, Cosmopterigidae)
First occurrence in ores of tetragonal chalcocite
Effects of trace element nutrition on sleep patterns in adult women
N.Z. range management guidelines. 2. Design of grazing management systems for tussock country
A case of lipoma of the esophagus
A revision of world Acanthosomatidae (Heteroptera: Pentatomidae): keys to and descriptions of subfamilies, tribes and genera, with designation of types
Life history of the coronate scyphozoan Linuche unguiculata (Swartz, 1788)
Perceptual restoration of obliterated sounds
Mutagenicity studies on two chromium(III) coordination compounds
The formation of the skeleton. I. Growth of a long bone. 1st appearance of a center of calcification
Leucopenia and abnormal liver function in travellers on malaria chemoprophylaxis
The joint commission: four key root causes loom large in sentinel event data
Treatment of vitiligo with topical 15% lactic acid solution in combination with ultra violet-A
Behaviour of dairy cows within three hours after feed supply: I. Influence of housing type and time elapsing after feed supply
Observations of the propagation velocity and formation mechanism of burst fractures caused by gunshot
Management and control of patients with type 2 diabetes mellitus in Lebanon: results from the International Diabetes Management Practices Study (IDMPS)
The diet composition and nutritional knowledge of patients with anorexia nervosa
Physoporella croatica Herak, 1958 of the Slovak karst Anisian (Slovakia, the West Carpathians Mts.)
Bright lights, big noise. How effective are vehicle warning systems?
Ein Plesiosaurier-Rest mit Magensteinen aus mittlerem Lias von Quedlinburg
Incidence of Chlamydia trachomatis in patients with sterility
Monster soup: the microscope and Victorian fantasy
Preliminary tests with residual sprays against poultry lice
Duration of the life of plants in phylogeny

DeepBindPoc: a deep learning method to rank ligand binding pockets using molecular vector representation


DeepBindPoc: a deep learning method to rank ligand binding pockets using molecular vector representation



Peerj 8: E8864



ISSN/ISBN: 2167-8359

PMID: 32292649

Accurate identification of ligand-binding pockets in a protein is important for structure-based drug design. In recent years, several deep learning models were developed to learn important physical-chemical and spatial information to predict ligand-binding pockets in a protein. However, ranking the native ligand binding pockets from a pool of predicted pockets is still a hard task for computational molecular biologists using a single web-based tool. Hence, we believe, by using closer to real application data set as training and by providing ligand information, an enhanced model to identify accurate pockets can be obtained. In this article, we propose a new deep learning method called DeepBindPoc for identifying and ranking ligand-binding pockets in proteins. The model is built by using information about the binding pocket and associated ligand. We take advantage of the mol2vec tool to represent both the given ligand and pocket as vectors to construct a densely fully connected layer model. During the training, important features for pocket-ligand binding are automatically extracted and high-level information is preserved appropriately. DeepBindPoc demonstrated a strong complementary advantage for the detection of native-like pockets when combined with traditional popular methods, such as fpocket and P2Rank. The proposed method is extensively tested and validated with standard procedures on multiple datasets, including a dataset with G-protein Coupled receptors. The systematic testing and validation of our method suggest that DeepBindPoc is a valuable tool to rank near-native pockets for theoretically modeled protein with unknown experimental active site but have known ligand. The DeepBindPoc model described in this article is available at GitHub (https://github.com/haiping1010/DeepBindPoc) and the webserver is available at (http://cbblab.siat.ac.cn/DeepBindPoc/index.php).

Please choose payment method:






(PDF emailed within 1 workday: $29.90)

Accession: 070021831

Download citation: RISBibTeXText

Related references

Effects of the difference in similarity measures on the comparison of ligand-binding pockets using a reduced vector representation of pockets. Biophysics and Physicobiology 13: 139-147, 2016

Combining Docking Pose Rank and Structure with Deep Learning Improves Protein-Ligand Binding Mode Prediction over a Baseline Docking Approach. Journal of Chemical Information and Modeling 60(9): 4170-4179, 2020

Identification of ligand binding pockets on nuclear receptors by machine learning methods. Protein and Peptide Letters 21(8): 808-814, 2014

A molecular description of ligand binding to the two overlapping binding pockets of the nuclear vitamin D receptor (VDR): structure-function implications. Journal of Steroid Biochemistry and Molecular Biology 121(1-2): 98-105, 2010

DeepDrug3D: Classification of ligand-binding pockets in proteins with a convolutional neural network. Plos Computational Biology 15(2): E1006718, 2019

Use of the Multilayer Fragment Molecular Orbital Method to Predict the Rank Order of Protein-Ligand Binding Affinities: A Case Study Using Tankyrase 2 Inhibitors. Acs Omega 3(4): 4475-4485, 2018

Protein ligand-binding site comparison by a reduced vector representation derived from multidimensional scaling of generalized description of binding sites. Methods 93: 35-40, 2016

A simple method for finding a protein's ligand-binding pockets. Bmc Structural Biology 14: 18, 2014

A method for localizing ligand binding pockets in protein structures. Proteins 62(2): 479-488, 2005

Molecular similarities in the ligand binding pockets of an odorant receptor and the metabotropic glutamate receptors. Journal of Biological Chemistry 278(43): 42551-42559, 2003

In-silico screening using flexible ligand binding pockets: a molecular dynamics-based approach. Journal of Computer-Aided Molecular Design 19(4): 213-228, 2005

Identification of Glucose-Binding Pockets in Human Serum Albumin Using Support Vector Machine and Molecular Dynamics Simulations. Ieee/Acm Transactions on Computational Biology and Bioinformatics 13(1): 148-157, 2016

Exploring Multi-Subsite Binding Pockets in Proteins: DEEP-STD NMR Fingerprinting and Molecular Dynamics Unveil a Cryptic Subsite at the GM1 Binding Pocket of Cholera Toxin B. Chemistry 26(44): 10024-10034, 2020

Similarity preserving low-rank representation for enhanced data representation and effective subspace learning. Neural Networks: the Official Journal of the International Neural Network Society 53: 81-94, 2014

DeepBindRG: a deep learning based method for estimating effective protein-ligand affinity. Peerj 7: E7362, 2019