A NMR-spectra-based scoring function for protein docking

2001 ◽  
Author(s):  
O. Kohlbacher ◽  
A. Burchardt ◽  
A. Moll ◽  
A. Hildebrandt ◽  
P. Bayer ◽  
...  
Keyword(s):  
Nmr Spectra ◽  
Scoring Function ◽  
Protein Docking

scholarly journals GNINA 1.0: molecular docking with deep learning

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Andrew T. McNutt ◽  
Paul Francoeur ◽  
Rishal Aggarwal ◽  
Tomohide Masuda ◽  
Rocco Meli ◽  
...  
Keyword(s):  
Molecular Docking ◽  
Root Mean Square ◽  
Root Mean Square Deviation ◽  
Computational Cost ◽  
Scoring Function ◽  
Binding Pocket ◽  
Protein Docking ◽  
Mean Square ◽  
Mean Square Deviation ◽  
Autodock Vina

AbstractMolecular docking computationally predicts the conformation of a small molecule when binding to a receptor. Scoring functions are a vital piece of any molecular docking pipeline as they determine the fitness of sampled poses. Here we describe and evaluate the 1.0 release of the Gnina docking software, which utilizes an ensemble of convolutional neural networks (CNNs) as a scoring function. We also explore an array of parameter values for Gnina 1.0 to optimize docking performance and computational cost. Docking performance, as evaluated by the percentage of targets where the top pose is better than 2Å root mean square deviation (Top1), is compared to AutoDock Vina scoring when utilizing explicitly defined binding pockets or whole protein docking. Gnina, utilizing a CNN scoring function to rescore the output poses, outperforms AutoDock Vina scoring on redocking and cross-docking tasks when the binding pocket is defined (Top1 increases from 58% to 73% and from 27% to 37%, respectively) and when the whole protein defines the binding pocket (Top1 increases from 31% to 38% and from 12% to 16%, respectively). The derived ensemble of CNNs generalizes to unseen proteins and ligands and produces scores that correlate well with the root mean square deviation to the known binding pose. We provide the 1.0 version of Gnina under an open source license for use as a molecular docking tool at https://github.com/gnina/gnina.

Accurate refinement of docked protein complexes using evolutionary information and deep learning

2016 ◽  
Vol 14 (03) ◽  
pp. 1642002 ◽  
Author(s):  
Bahar Akbal-Delibas ◽  
Roshanak Farhoodi ◽  
Marc Pomplun ◽  
Nurit Haspel
Keyword(s):  
Deep Learning ◽  
Protein Complexes ◽  
Scoring Function ◽  
Protein Docking ◽  
Training Data ◽  
Evolutionary Information ◽  
Native Structure ◽  
Learning Network ◽  
Small Set ◽  
Deep Learning Network

One of the major challenges for protein docking methods is to accurately discriminate native-like structures from false positives. Docking methods are often inaccurate and the results have to be refined and re-ranked to obtain native-like complexes and remove outliers. In a previous work, we introduced AccuRefiner, a machine learning based tool for refining protein–protein complexes. Given a docked complex, the refinement tool produces a small set of refined versions of the input complex, with lower root-mean-square-deviation (RMSD) of atomic positions with respect to the native structure. The method employs a unique ranking tool that accurately predicts the RMSD of docked complexes with respect to the native structure. In this work, we use a deep learning network with a similar set of features and five layers. We show that a properly trained deep learning network can accurately predict the RMSD of a docked complex with 1.40 Å error margin on average, by approximating the complex relationship between a wide set of scoring function terms and the RMSD of a docked structure. The network was trained on 35000 unbound docking complexes generated by RosettaDock. We tested our method on 25 different putative docked complexes produced also by RosettaDock for five proteins that were not included in the training data. The results demonstrate that the high accuracy of the ranking tool enables AccuRefiner to consistently choose the refinement candidates with lower RMSD values compared to the coarsely docked input structures.

scholarly journals Pushing the accuracy limit of shape complementarity for protein-protein docking

2019 ◽  
Vol 20 (S25) ◽  
Author(s):  
Yumeng Yan ◽  
Sheng-You Huang
Keyword(s):  
Success Rate ◽  
Protein Interactions ◽  
Shape Representation ◽  
Scoring Function ◽  
Protein Docking ◽  
Protein Protein Interactions ◽  
Second Best ◽  
Shape Complementarity ◽  
Docking Program ◽  
Docking Approach

Abstract Background Protein-protein docking is a valuable computational approach for investigating protein-protein interactions. Shape complementarity is the most basic component of a scoring function and plays an important role in protein-protein docking. Despite significant progresses, shape representation remains an open question in the development of protein-protein docking algorithms, especially for grid-based docking approaches. Results We have proposed a new pairwise shape-based scoring function (LSC) for protein-protein docking which adopts an exponential form to take into account long-range interactions between protein atoms. The LSC scoring function was incorporated into our FFT-based docking program and evaluated for both bound and unbound docking on the protein docking benchmark 4.0. It was shown that our LSC achieved a significantly better performance than four other similar docking methods, ZDOCK 2.1, MolFit/G, GRAMM, and FTDock/G, in both success rate and number of hits. When considering the top 10 predictions, LSC obtained a success rate of 51.71% and 6.82% for bound and unbound docking, respectively, compared to 42.61% and 4.55% for the second-best program ZDOCK 2.1. LSC also yielded an average of 8.38 and 3.94 hits per complex in the top 1000 predictions for bound and unbound docking, respectively, followed by 6.38 and 2.96 hits for the second-best ZDOCK 2.1. Conclusions The present LSC method will not only provide an initial-stage docking approach for post-docking processes but also have a general implementation for accurate representation of other energy terms on grids in protein-protein docking. The software has been implemented in our HDOCK web server at http://hdock.phys.hust.edu.cn/.

scholarly journals HawkRank: a new scoring function for protein–protein docking based on weighted energy terms

2017 ◽  
Vol 9 (1) ◽  
Author(s):  
Ting Feng ◽  
Fu Chen ◽  
Yu Kang ◽  
Huiyong Sun ◽  
Hui Liu ◽  
...  
Keyword(s):  
Scoring Function ◽  
Protein Docking ◽  
Weighted Energy ◽  
New Scoring

scholarly journals GNINA 1.0: Molecular Docking with Deep Learning

2021 ◽  
Author(s):  
Andrew McNutt ◽  
Paul Francoeur ◽  
Rishal Aggarwal ◽  
Tomohide Masuda ◽  
Rocco Meli ◽  
...  
Keyword(s):  
Molecular Docking ◽  
Root Mean Square ◽  
Root Mean Square Deviation ◽  
Computational Cost ◽  
Scoring Function ◽  
Binding Pocket ◽  
Protein Docking ◽  
Mean Square ◽  
Mean Square Deviation ◽  
Autodock Vina

Molecular docking computationally predicts the conformation of a small molecule when binding to a receptor. Scoring functions are a vital piece of any molecular docking pipeline as they determine the fitness of sampled poses. Here we describe and evaluate the 1.0 release of the Gnina docking software, which utilizes an ensemble of convolutional neural networks (CNNs) as a scoring function. We also explore an array of parameter values for Gnina 1.0 to optimize docking performance and computational cost. Docking performance, as evaluated by the percentage of targets where the top pose is better than 2A root mean square deviation (Top1), is compared to AutoDock Vina scoring when utilizing explicitly defined binding pockets or whole protein docking. Gnina, utilizing a CNN scoring function to rescore the output poses, outperforms AutoDock Vina scoring on redocking and cross-docking tasks when the binding pocket is defined (Top1 increases from 58% to 73% and from 27% to 37%, respectively) and when the whole protein defines the binding pocket (Top1 increases from 31% to 38% and from 12% to 16%, respectively). The derived ensemble of CNNs generalizes to unseen proteins and ligands and produces scores that correlate well with the root mean square deviation to the known binding pose. We provide the 1.0 version of Gnina under and open source license for use as a molecular docking tool at https://github.com/gnina/gnina.

scholarly journals GNINA 1.0: Molecular Docking with Deep Learning

2021 ◽  
Author(s):  
Andrew McNutt ◽  
Paul Francoeur ◽  
Rishal Aggarwal ◽  
Tomohide Masuda ◽  
Rocco Meli ◽  
...  
Keyword(s):  
Molecular Docking ◽  
Root Mean Square ◽  
Root Mean Square Deviation ◽  
Computational Cost ◽  
Scoring Function ◽  
Binding Pocket ◽  
Protein Docking ◽  
Mean Square ◽  
Mean Square Deviation ◽  
Autodock Vina

Molecular docking computationally predicts the conformation of a small molecule when binding to a receptor. Scoring functions are a vital piece of any molecular docking pipeline as they determine the fitness of sampled poses. Here we describe and evaluate the 1.0 release of the Gnina docking software, which utilizes an ensemble of convolutional neural networks (CNNs) as a scoring function. We also explore an array of parameter values for Gnina 1.0 to optimize docking performance and computational cost. Docking performance, as evaluated by the percentage of targets where the top pose is better than 2A root mean square deviation (Top1), is compared to AutoDock Vina scoring when utilizing explicitly defined binding pockets or whole protein docking. Gnina, utilizing a CNN scoring function to rescore the output poses, outperforms AutoDock Vina scoring on redocking and cross-docking tasks when the binding pocket is defined (Top1 increases from 58% to 73% and from 27% to 37%, respectively) and when the whole protein defines the binding pocket (Top1 increases from 31% to 38% and from 12% to 16%, respectively). The derived ensemble of CNNs generalizes to unseen proteins and ligands and produces scores that correlate well with the root mean square deviation to the known binding pose. We provide the 1.0 version of Gnina under and open source license for use as a molecular docking tool at https://github.com/gnina/gnina.

Sign in / Sign up

Export Citation Format

Share Document