scholarly journals Improved protein docking by predicted interface residues.

2021 ◽  
Author(s):  
Gabriele Pozzati ◽  
Petras Kundrotas ◽  
Arne Elofsson
Keyword(s):  
State Of The Art ◽  
Protein Docking ◽  
Prediction Methods ◽  
Scoring Functions ◽  
Protein Interface ◽  
High Importance ◽  
Docking Algorithm ◽  
Docking Protocol ◽  
Template Free ◽  
Interface Prediction

Scoring docking solutions is a difficult task, and many methods have been developed for this purpose. In docking, only a handful of the hundreds of thousands of models generated by docking algorithms are acceptable, causing difficulties when developing scoring functions. Today’s best scoring functions can significantly increase the number of top-ranked models but still fails for most targets. Here, we examine the possibility of utilising predicted residues on a protein-protein interface to score docking models generated during the scan stage of a docking algorithm. Many methods have been developed to infer the portions of a protein surface that interact with another protein, but most have not been benchmarked using docking algorithms. Different interface prediction methods are systematically tested for scoring >300.000 low-resolution rigid-body template free docking decoys. Overall we find that BIPSPI is the best method to identify interface amino acids and score docking solutions. Further, using BIPSPI provides better docking results than state of the art scoring functions, with >12% of first ranked docking models being acceptable. Additional experiments indicated precision as a high-importance metric when estimating interface prediction quality, focusing on docking constraints production. We also discussed several limitations for the adoption of interface predictions as constraints in a docking protocol.

scholarly journals Improved protein docking by predicted interface residues

2021 ◽  
Author(s):  
Gabriele Pozzati ◽  
Petras Kundrotas ◽  
Arne Elofsson
Keyword(s):  
State Of The Art ◽  
Protein Docking ◽  
Prediction Methods ◽  
Scoring Functions ◽  
Protein Interface ◽  
High Importance ◽  
Docking Algorithm ◽  
Docking Protocol ◽  
Template Free ◽  
Interface Prediction

ABSTRACTScoring docking solutions is a difficult task, and many methods have been developed for this purpose. In docking, only a handful of the hundreds of thousands of models generated by docking algorithms are acceptable, causing difficulties when developing scoring functions. Today’s best scoring functions can significantly increase the number of top-ranked models but still fails for most targets. Here, we examine the possibility of utilising predicted residues on a protein-protein interface to score docking models generated during the scan stage of a docking algorithm. Many methods have been developed to infer the portions of a protein surface that interact with another protein, but most have not been benchmarked using docking algorithms. Different interface prediction methods are systematically tested for scoring >300.000 low-resolution rigid-body template free docking decoys. Overall we find that BIPSPI is the best method to identify interface amino acids and score docking solutions. Further, using BIPSPI provides better docking results than state of the art scoring functions, with >12% of first ranked docking models being acceptable. Additional experiments indicated precision as a high-importance metric when estimating interface prediction quality, focusing on docking constraints production. We also discussed several limitations for the adoption of interface predictions as constraints in a docking protocol.

scholarly journals RetroXpert: Decompose Retrosynthesis Prediction Like A Chemist

2020 ◽  
Author(s):  
Chaochao Yan ◽  
Qianggang Ding ◽  
Peilin Zhao ◽  
Shuangjia Zheng ◽  
Jinyu Yang ◽  
...  
Keyword(s):  
Neural Network ◽  
Reaction Center ◽  
Organic Synthesis ◽  
State Of The Art ◽  
Building Blocks ◽  
Prediction Methods ◽  
Generation Model ◽  
Synthesis Planning ◽  
Target Molecules ◽  
Template Free

<div>Retrosynthesis is the process of recursively decomposing target molecules into available building blocks. It plays an important role in solving problems in organic synthesis planning. To automate the retrosynthesis analysis, many retrosynthesis prediction methods have been proposed.</div><div>However, most of them are cumbersome and lack interpretability about their predictions.</div><div>In this paper, we devise a novel template-free algorithm, RetroXpert, for automatic retrosynthetic expansion by automating the procedure that chemists used to do.</div><div>Our method disassembles retrosynthesis into two steps: i) we identify the potential reaction center within the target molecule through a graph neural network and generate intermediate synthons; and ii) we predict the associated reactants based on the obtained synthons via a reactant generation model. </div><div>While outperforming the state-of-the-art baselines by a significant margin, our model also provides chemically reasonable interpretation.</div>

scholarly journals RetroXpert: Decompose Retrosynthesis Prediction Like A Chemist

2020 ◽  
Author(s):  
Chaochao Yan ◽  
Qianggang Ding ◽  
Peilin Zhao ◽  
Shuangjia Zheng ◽  
Jinyu Yang ◽  
...  
Keyword(s):  
Neural Network ◽  
Reaction Center ◽  
Organic Synthesis ◽  
State Of The Art ◽  
Building Blocks ◽  
Prediction Methods ◽  
Generation Model ◽  
Synthesis Planning ◽  
Target Molecules ◽  
Template Free

<div>Retrosynthesis is the process of recursively decomposing target molecules into available building blocks. It plays an important role in solving problems in organic synthesis planning. To automate the retrosynthesis analysis, many retrosynthesis prediction methods have been proposed.</div><div>However, most of them are cumbersome and lack interpretability about their predictions.</div><div>In this paper, we devise a novel template-free algorithm, RetroXpert, for automatic retrosynthetic expansion by automating the procedure that chemists used to do.</div><div>Our method disassembles retrosynthesis into two steps: i) we identify the potential reaction center within the target molecule through a graph neural network and generate intermediate synthons; and ii) we predict the associated reactants based on the obtained synthons via a reactant generation model. </div><div>While outperforming the state-of-the-art baselines by a significant margin, our model also provides chemically reasonable interpretation.</div>

scholarly journals High-resolution global peptide-protein docking using fragments-based PIPER-FlexPepDock

2017 ◽  
Author(s):  
Nawsad Alam ◽  
Oriel Goldstein ◽  
Bing Xia ◽  
Kathryn A. Porter ◽  
Dima Kozakov ◽  
...  
Keyword(s):  
High Resolution ◽  
Protein Interactions ◽  
Protein Docking ◽  
Academic Community ◽  
Conformational Space ◽  
Complex Structures ◽  
Docking Algorithm ◽  
Docking Protocol ◽  
Protein Interactome ◽  
Rigid Body Docking

AbstractPeptide-protein interactions contribute a significant fraction of the protein-protein interactome. Accurate modeling of these interactions is challenging due to the vast conformational space associated with interactions of highly flexible peptides with large receptor surfaces. To address this challenge we developed a fragment based high-resolution peptide-protein docking protocol. By streamlining the Rosetta fragment picker for accurate peptide fragment ensemble generation, the PIPER docking algorithm for exhaustive fragment-receptor rigid-body docking and Rosetta FlexPepDock for flexible full-atom refinement of PIPER docked models, we successfully addressed the challenge of accurate and efficient global peptide-protein docking at high-resolution with remarkable accuracy. Validation on a representative set of solved peptide-protein complex structures demonstrates the accuracy and robustness of our approach, and opens up the way to high-resolution modeling of many more peptide-protein interactions and to the detailed study of peptide-protein association in general. PIPER-FlexPepDock is freely available to the academic community as a server at http://piperfpd.furmanlab.cs.huji.ac.il.

scholarly journals RetroXpert: Decompose Retrosynthesis Prediction Like A Chemist

2020 ◽  
Author(s):  
Chaochao Yan ◽  
Qianggang Ding ◽  
Peilin Zhao ◽  
Shuangjia Zheng ◽  
Jinyu Yang ◽  
...  
Keyword(s):  
Neural Network ◽  
Reaction Center ◽  
Organic Synthesis ◽  
State Of The Art ◽  
Building Blocks ◽  
Prediction Methods ◽  
Generation Model ◽  
Synthesis Planning ◽  
Target Molecules ◽  
Template Free

<div>Retrosynthesis is the process of recursively decomposing target molecules into available building blocks. It plays an important role in solving problems in organic synthesis planning. To automate the retrosynthesis analysis, many retrosynthesis prediction methods have been proposed.</div><div>However, most of them are cumbersome and lack interpretability about their predictions.</div><div>In this paper, we devise a novel template-free algorithm, RetroXpert, for automatic retrosynthetic expansion by automating the procedure that chemists used to do.</div><div>Our method disassembles retrosynthesis into two steps: i) we identify the potential reaction center within the target molecule through a graph neural network and generate intermediate synthons; and ii) we predict the associated reactants based on the obtained synthons via a reactant generation model. </div><div>While outperforming the state-of-the-art baselines by a significant margin, our model also provides chemically reasonable interpretation.</div>

scholarly journals RetroXpert: Decompose Retrosynthesis Prediction like A Chemist

2020 ◽  
Author(s):  
Chaochao Yan ◽  
Qianggang Ding ◽  
Peilin Zhao ◽  
Shuangjia Zheng ◽  
Jinyu Yang ◽  
...  
Keyword(s):  
Neural Network ◽  
Reaction Center ◽  
Organic Synthesis ◽  
State Of The Art ◽  
Building Blocks ◽  
Prediction Methods ◽  
Generation Model ◽  
Synthesis Planning ◽  
Target Molecules ◽  
Template Free

<div>Retrosynthesis is the process of recursively decomposing target molecules into available building blocks. It plays an important role in solving problems in organic synthesis planning. To automate the retrosynthesis analysis, many retrosynthesis prediction methods have been proposed.</div><div>However, most of them are cumbersome and lack interpretability about their predictions.</div><div>In this paper, we devise a novel template-free algorithm, RetroXpert, for automatic retrosynthetic expansion by automating the procedure that chemists used to do.</div><div>Our method disassembles retrosynthesis into two steps: i) we identify the potential reaction center within the target molecule through a graph neural network and generate intermediate synthons; and ii) we predict the associated reactants based on the obtained synthons via a reactant generation model. </div><div>While outperforming the state-of-the-art baselines by a significant margin, our model also provides chemically reasonable interpretation.</div>

scholarly journals Suitable Docking Protocol for the Design of Novel Coumarin Derivatives with Selective MAO-B Effects

2021 ◽  
Vol 1 (1) ◽  
pp. 40-47
Author(s):  
Emilio Viktorov Mateev ◽  
Iva Valkova ◽  
Maya Georgieva ◽  
Alexander Zlatkov
Keyword(s):  
Correlation Coefficient ◽  
Scoring Functions ◽  
Pearson’S Correlation ◽  
Chain Flexibility ◽  
Pearson’S Correlation Coefficient ◽  
Pairwise Correlation ◽  
Mao B ◽  
Docking Protocol ◽  
Pearson's Correlation ◽  
Pearson's Correlation Coefficient

Recently, the application of molecular docking is drastically increasing due to the rapid growth of resolved crystallographic receptors with co-crystallized ligands. However, the inability of docking softwares to correctly score the occurred interactions between ligands and receptors is still a relevant issue. This study examined the Pearson’s correlation coefficient between the experimental monoamine oxidase-B (MAO-B) inhibitory activity of 44 novel coumarins and the obtained GOLD 5.3 docking scores. Subsequently, optimization of the docking protocol was carried out to achieve the best possible pairwise correlation. Numerous modifications in the docking settings such as alteration in the scoring functions, size of the grid space, presence of active waters, and side-chain flexibility were conducted. Furthermore, ensemble docking simulations into two superimposed complexes were performed. The model was validated with a test set. A significant Pearson’s correlation coefficient of 0.8217 was obtained for the latter. In the final stage of our work, we observed the major interactions between the top-scored ligands and the active site of 1S3B.

Sign in / Sign up

Export Citation Format

Share Document