scholarly journals Graph Convolutional Neural Networks for Predicting Drug-Target Interactions

2018 ◽  
Author(s):  
Wen Torng ◽  
Russ B. Altman
Keyword(s):  
Drug Target ◽  
Accurate Determination ◽  
Supplementary Information ◽  
Fixed Size ◽  
Protein Ligand Interactions ◽  
Ligand Interactions ◽  
Comparable Performance ◽  
Benchmark Datasets ◽  
Protein Pockets

AbstractAccurate determination of target-ligand interactions is crucial in the drug discovery process. In this paper, we propose a two-staged graph-convolutional (Graph-CNN) framework for predicting protein-ligand interactions. We first describe an unsupervised graph-autoencoder to learn fixed-size representations of protein pockets. Two Graph-CNNs are then trained to automatically extract features from pocket graphs and 2D molecular graphs, respectively. We demonstrate that graph-autoencoders can learn meaningful fixed-size representation for protein pockets of varying sizes and the Graph-CNN framework can effectively capture protein-ligand binding interactions without relying on target-ligand co-complexes. Across several metrics, Graph-CNNs achieved better or comparable performance to 3DCNN ligand-scoring, AutoDock Vina, RF-Score, and NNScore on common virtual screening benchmark datasets. Visualization of key pocket residues and ligand atoms contributing to the classification decisions confirms that our networks recognize meaningful interactions between pockets and ligands.Availability and ImplementationContact: [email protected] information:

scholarly journals ASFP (Artificial Intelligence based Scoring Function Platform): a web server for the development of customized scoring functions

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Xujun Zhang ◽  
Chao Shen ◽  
Xueying Guo ◽  
Zhe Wang ◽  
Gaoqi Weng ◽  
...  
Keyword(s):  
High Efficiency ◽  
Low Cost ◽  
Pearson Correlation ◽  
Scoring Function ◽  
Web Server ◽  
Scoring Functions ◽  
Protein Ligand Interactions ◽  
Prediction Module ◽  
Ligand Interactions ◽  
Benchmark Datasets

AbstractVirtual screening (VS) based on molecular docking has emerged as one of the mainstream technologies of drug discovery due to its low cost and high efficiency. However, the scoring functions (SFs) implemented in most docking programs are not always accurate enough and how to improve their prediction accuracy is still a big challenge. Here, we propose an integrated platform called ASFP, a web server for the development of customized SFs for structure-based VS. There are three main modules in ASFP: (1) the descriptor generation module that can generate up to 3437 descriptors for the modelling of protein–ligand interactions; (2) the AI-based SF construction module that can establish target-specific SFs based on the pre-generated descriptors through three machine learning (ML) techniques; (3) the online prediction module that provides some well-constructed target-specific SFs for VS and an additional generic SF for binding affinity prediction. Our methodology has been validated on several benchmark datasets. The target-specific SFs can achieve an average ROC AUC of 0.973 towards 32 targets and the generic SF can achieve the Pearson correlation coefficient of 0.81 on the PDBbind version 2016 core set. To sum up, the ASFP server is a powerful tool for structure-based VS.

scholarly journals DeepPurpose: a deep learning library for drug–target interaction prediction

2020 ◽  
Author(s):  
Kexin Huang ◽  
Tianfan Fu ◽  
Lucas M Glass ◽  
Marinka Zitnik ◽  
Cao Xiao ◽  
...  
Keyword(s):  
Deep Learning ◽  
Drug Target ◽  
Prediction Models ◽  
State Of The Art ◽  
Supplementary Information ◽  
Target Interaction ◽  
Interaction Prediction ◽  
Computer Scientists ◽  
Benchmark Datasets ◽  
Biomedical Field

Abstract Summary Accurate prediction of drug–target interactions (DTI) is crucial for drug discovery. Recently, deep learning (DL) models for show promising performance for DTI prediction. However, these models can be difficult to use for both computer scientists entering the biomedical field and bioinformaticians with limited DL experience. We present DeepPurpose, a comprehensive and easy-to-use DL library for DTI prediction. DeepPurpose supports training of customized DTI prediction models by implementing 15 compound and protein encoders and over 50 neural architectures, along with providing many other useful features. We demonstrate state-of-the-art performance of DeepPurpose on several benchmark datasets. Availability and implementation https://github.com/kexinhuang12345/DeepPurpose. Contact [email protected] Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals AutoDock Bias: improving binding mode prediction and virtual screening using known protein–ligand interactions

2019 ◽  
Vol 35 (19) ◽  
pp. 3836-3838 ◽  
Author(s):  
Juan Pablo Arcon ◽  
Carlos P Modenutti ◽  
Demian Avendaño ◽  
Elias D Lopez ◽  
Lucas A Defelipe ◽  
...  
Keyword(s):  
Binding Mode ◽  
Fine Tuning ◽  
Supplementary Information ◽  
Tuning Parameters ◽  
Interaction Sites ◽  
Binding Mode Prediction ◽  
Protein Ligand Interactions ◽  
Different Types ◽  
Ligand Interactions ◽  
Docking Calculations

Abstract Summary The performance of docking calculations can be improved by tuning parameters for the system of interest, e.g. biasing the results towards the formation of relevant protein–ligand interactions, such as known ligand pharmacophore or interaction sites derived from cosolvent molecular dynamics. AutoDock Bias is a straightforward and easy to use script-based method that allows the introduction of different types of user-defined biases for fine-tuning AutoDock4 docking calculations. Availability and implementation AutoDock Bias is distributed with MGLTools (since version 1.5.7), and freely available on the web at http://ccsb.scripps.edu/mgltools/ or http://autodockbias.wordpress.com. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Structure Based Design and Molecular Docking Studies for Phosphorylated Tau Inhibitors in Alzheimer’s Disease

Cells ◽  
2019 ◽  
Vol 8 (3) ◽  
pp. 260 ◽  
Author(s):  
Jangampalli Pradeepkiran ◽  
P. Reddy
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Molecular Docking ◽  
Drug Target ◽  
Docking Studies ◽  
Toxicity Tests ◽  
Phosphorylated Tau ◽  
Protein Ligand Interactions ◽  
Ligand Interactions ◽  
Alternative Drug

The purpose of our study is to identify phosphorylated tau (p-tau) inhibitors. P-tau has recently received great interest as a potential drug target in Alzheimer’s disease (AD). The continuous failure of Aβ-targeted therapeutics recommends an alternative drug target to treat AD. There is increasing evidence and growing awareness of tau, which plays a central role in AD pathophysiology, including tangles formation, abnormal activation of phosphatases/kinases, leading p-tau aggregation in AD neurons. In the present study, we performed computational pharmacophore models, molecular docking, and simulation studies for p-tau in order to identify hyperphosphorylated sites. We found multiple serine sites that altered the R1/R2 repeats flanking sequences in the tau protein, affecting the microtubule binding ability of tau. The ligand molecules exhibited the p-O ester scaffolds with inhibitory and/or blocking actions against serine residues of p-tau. Our molecular docking results revealed five ligands that showed high docking scores and optimal protein-ligand interactions of p-tau. These five ligands showed the best pharmacokinetic and physicochemical properties, including good absorption, distribution, metabolism, and excretion (ADME) and admetSAR toxicity tests. The p-tau pharmacophore based drug discovery models provide the comprehensive and rapid drug interventions in AD, and tauopathies are expected to be the prospective future therapeutic approach in AD.

scholarly journals The analysis of NQO1 isoforms as an Off-target to anti-cancer drug RH1 using molecular modeling and structure-based drug discovery approaches

2020 ◽  
Vol 11 (3) ◽  
pp. 3780-3792
Author(s):  
Pramodkumar P Gupta ◽  
Shanker L Kothari ◽  
Mindaugas Valius ◽  
Jonas Cicenas ◽  
Virupaksha A Bastikar
Keyword(s):  
Drug Target ◽  
Conformational Stability ◽  
3D Structure ◽  
Protein Isoforms ◽  
Cancer Drug ◽  
Normal Tissues ◽  
Protein Ligand Interactions ◽  
Ligand Interactions ◽  
Docking Approach ◽  
High Level

NQO1 is already evaluated for its high-level expression in numerous human cancers as compared with normal tissues. RH1 acts as an indigenous prodrug to NQO1. In our preceding work Off-targeting of (RH1) drug to protein kinases is well reported. Numerous protein isoforms have reported a potential drug target and biomarkers in cancer and related diseases. In the present study, the 3D structure of all the three NQO1 isoforms is modelled using the homologybased concept, evaluated for their conformational stability and energy forms by MD simulation. MSA and related method used for binding site prediction. Protein-ligand interactions were studied using molecular docking approach. The 3D modelled structure of NQO1 isoform 2 and 3 exhibited a conformational change in the protein FAD and RH1 binding region due to the absence of a few key amino acids. Docking results revealed a good degree of binding energy and interaction between the selected NQO1 isoforms, FAD and RH1. As FAD acts as a floor surface to RH1, a similar trend observed in the NQO1 isoform 2 and 3. Hence the NQO1 isoforms 2 and 3 could be a drug target to anticancer prodrug RH1 and can be further investigated in the lab.

Sign in / Sign up

Export Citation Format

Share Document