PocketPipe: A computational pipeline for integrated Pocketome prediction and comparison

Ansar, Samdani; Sadhasivam, Anupriya; Vetrivel, Umashankar

doi:10.6026/97320630015295

Cited by 4 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For special needs, the tool PocketPipe can be used to analyze the pocketome of a single organism (30). Recently, comparative analyses of binding sites have gained momentum due to their capacity to reveal ligandbinding similarities among proteins, regardless of their evolution (31,32).…”

Section: Introductionmentioning

confidence: 99%

PickPocket : Pocket binding prediction for specific ligands family using neural networks.

Viart

Lorenzi

Moriel‐Carretero³

et al. 2020

Preprint

View full text Add to dashboard Cite

Most of the protein biological functions occur through contacts with other proteins or ligands. The residues that constitute the contact surface of a ligand-binding pocket are usually located far away within its sequence.Therefore, the identification of such motifs is more challenging than the linear protein domains. To discover new binding sites, we developed a tool called PickPocket that focuses on a small set of user-defined ligands and PickPocket: Pocket binding prediction for specific ligand families using neural networks.uses neural networks to train a ligand-binding prediction model. We tested PickPocket on fatty acid-like ligands due to their structural similarities and their under-representation in the ligand-pocket binding literature.Our results show that for fatty acid-like molecules, pocket descriptors and secondary structures are enough to obtain predictions with accuracy >90% using a dataset of 1740 manually curated ligand-binding pockets. The trained model could also successfully predict the ligandbinding pockets using unseen structural data of two recently reported fatty acid-binding proteins. We think that the PickPocket tool can help to discover new protein functions by investigating the binding sites of specific ligand families. The source code and all datasets contained in this work are freely available at https://github.com/benjaminviart/PickPocket . Author Summary :Most of the protein biological functions are defined by its interactions with other proteins or ligands. The cavity of the protein structure that receives a ligand, also called a pocket, is made of residues that are usually located far away within its sequence. Therefore understanding the PickPocket: Pocket binding prediction for specific ligand families using neural networks.complementarity of pocket and ligand is a real challenge. To discover new binding sites, we developed a tool called PickPocket that focuses on a small set of user-defined ligands to train a prediction model. Our resultsshow that for fatty acid-like molecules, pocket descriptors ( such as volume, shape, hydrophobicity… ) and secondary structures are enough to obtain predictions with accuracy >90% using a dataset of 1740 manually curated ligand-binding pockets. The trained model could also successfully predict the ligand-binding pockets using unseen structural data of two recently reported fatty acid-binding proteins. We think that the PickPocket tool can help to discover new protein functions by investigating the binding sites of specific ligand families.

show abstract

Section: Introductionmentioning

confidence: 99%

PickPocket : Pocket binding prediction for specific ligands family using neural networks.

Viart

Lorenzi

Moriel‐Carretero³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Computer‐aided drug design has substantially reduced the time and cost of experiments involved in the drug development process (Ansar, Sadhasivam, & Vetrivel, 2019; Ansar & Vetrivel, 2019; Bajorath, 2015; Vetrivel, Arunkumar, & Dorairaj, 2007; Vetrivel & Subramanian, 2015; Vetrivel Umashankar, 2011a, 2011b). Target screening has been an integral part of the computational drug designing process.…”

Section: Introductionmentioning

confidence: 99%

KinomeRun: An interactive utility for kinome target screening and interaction fingerprint analysis towards holistic visualization on kinome tree

Ansar

Vetrivel

2020

Chem Biol Drug Des

Self Cite

View full text Add to dashboard Cite

Kinases are key targets for many of the pathological conditions. Inverse screening of ligands serves as an essential mode to identify potential kinase targets in modern drug discovery research. Hence, we intend to develop KinomeRun, a robust pipeline for inverse screening and kinome tree visualization through the seamless integration of kinome structures, docking and kinome–drug interaction fingerprint analysis. In this pipeline, the hurdle of residue numbering in kinome is also resolved by creating a common index file with the conserved kinase pocket residues for comparative interaction analysis. KinomeRun can be used to screen the ligands of interest docked against multiple kinase structures in parallel around the kinase binding site and also to filter out the targets with unique interaction patterns. This automation is essential for prioritization of kinase targets that show specificity for a given drug and will also serve as a crucial tool kit for holistic approaches in kinase drug discovery. KinomeRun is developed using python and bash programming language and is distributed freely under the GNU GPL licence‐3.0 and can be downloaded at https://github.com/inpacdb/KinomeRun. The tutorial videos for installation, target screening and customized filtration are available at https://www.youtube.com/playlist?list=PLuIaEFtMVgQ7v__WigQH9ilGVxrfI1LKs and also be downloaded for offline viewing from the github link.

show abstract

“…In this in silico era, computer-aided drug design has made a paradigm shift in drug discovery through automated pipelines (Samdani, Anupriya, & Umashankar, 2019;Umashankar & Gurunathan, 2009a, 2009bVetrivel, Arunkumar, & Dorairaj, 2007). Especially in case of peptide therapeutics geared by robust algorithms that could efficiently model the protein-peptide interactions.…”

Section: Introductionmentioning

confidence: 99%

PepVis: An integrated peptide virtual screening pipeline for ensemble and flexible docking protocols

Ansar

Vetrivel

2019

Chem Biol Drug Des

Self Cite

View full text Add to dashboard Cite

Peptide therapeutics is proven to be highly potential in the treatment of various diseases due to its specificity, biological safety, and cost‐effectiveness. Many of the FDA‐approved peptides are currently available for therapeutic applications. In the current postgenomic era, high‐throughput computational screening of drugs and peptides are highly exploited in peptide therapeutics for cost‐effective and robustness. However, there is a paucity of efficient pipelines that automate virtual screening process of peptides through integration of open‐source tools that are optimal to perform ensemble and flexible docking protocols. Hence, in this study, we developed a GUI‐based pipeline named PepVis for automated script generation for large‐scale peptide modeling and virtual screening. PepVis integrates Modpep and Gromacs for peptide structure modeling and optimization; AutoDock Vina, ZDOCK, and AutoDock CrankPep for virtual screening of peptides; ZRANK2 for rescoring of protein–peptide complexes, and FlexPepDock for flexible refinement of protein–peptide complexes. Benchmarking of ensemble docking through PepVis infers that ModPep + Vina to outperform ModPep + ZDock in terms of detecting near‐natives from LEADS‐PEP dataset. PepVis is built modular to incorporate many other docking algorithms in the future. This pipeline is distributed freely under the GNU GPL license and can be downloaded at https://github.com/inpacdb/PepVis.

show abstract

PocketPipe: A computational pipeline for integrated Pocketome prediction and comparison

Cited by 4 publications

References 9 publications

PickPocket : Pocket binding prediction for specific ligands family using neural networks.

PickPocket : Pocket binding prediction for specific ligands family using neural networks.

KinomeRun: An interactive utility for kinome target screening and interaction fingerprint analysis towards holistic visualization on kinome tree

PepVis: An integrated peptide virtual screening pipeline for ensemble and flexible docking protocols

Contact Info

Product

Resources

About