Druggability Assessment in TRAPP Using Machine Learning Approaches

Yuan, Jui-Hung; Han, Sungho; Richter, Stefan; Wade, Rebecca C.; Kokh, Daria B.

doi:10.1021/acs.jcim.9b01185

Cited by 40 publications

(73 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The open-source availability of CAVIAR on GitHub and Anaconda combined with its comprehensive Python language defines it as a powerful toolkit to build upon. CAVIAR is mmCIF-ready, which is important as the PDB format may be retired around 2021 (https://www.ebi.ac.uk/pdbe/about/news/mandatory-mmcif-format-crystallographicdepositions-pdb-0) as well as one of the few (Yuan et al, 2020) pocket detection tools to incorporate a molecular dynamics trajectory parser, and the only open-source tool for subpocket characterization solely based on the protein. A dedicated website is available with step-by-step usage notes and an extended manual to help the community adjust CAVIAR to their needs (see the Availability paragraph for the website, GitHub and Anaconda links).…”

Section: Discussionmentioning

confidence: 99%

Automatic Cavity Identification and Decomposition into Subpockets with CAVIAR

Marchand

Pirard²,

Ertl³

et al. 2020

Preprint

View full text Add to dashboard Cite

Motivation. The detection of small molecules binding sites in proteins is central to structure-based drug design and chemical biology. Many tools were developed in the last 40 years, but few of them are still available in 2020, open-source, and suitable for the analysis of large databases or for the integration in automatic workflows. No software can characterize subpockets solely with the information of the protein structure, a pivotal concept in fragment-based drug design. Results. CAVIAR is a new open source tool for protein cavity identification and rationalization, supporting PDB and mmCIF files as well as DCD trajectories from molecular dynamics simulations. The protein structure serves as input for automatic cavity detection and computation of properties, including ligandability. A subcavity segmentation algorithm decomposes binding sites into subpockets without requiring the presence of a ligand. The defined subpockets mimick the empirical definitions of subpockets in medicinal chemistry projects. A tool like CAVIAR may be valuable to support chemical biology, medicinal chemistry and ligand identification efforts. Our analysis of the PDB shows that liganded cavities tend to be bigger, more hydrophobic and more complex than apo cavities. Moreover, in line with the paradigm of fragment-based drug design, the binding affinity scales relatively well with the number of subcavities filled by the ligand. Compounds binding to more than three subcavities are mostly in the nanomolar or better range of affinities to their target. Availability and implementation. Installation notes, user manual and support for CAVIAR are available at <a href="https://jr-marchand.github.io/caviar/">https://jr-marchand.github.io/caviar/</a>. The CAVIAR GUI and CAVIAR command line tool are available on GitHub at <a href="https://github.com/jr-marchand/caviar">https://github.com/jr-marchand/caviar</a> and a conda package is hosted on Anaconda cloud at <a href="https://anaconda.org/jr-marchand/caviar">https://anaconda.org/jr-marchand/caviar</a>. The software suite is free and all of the source code is available under a permissive MIT license. The lists of PDB files used for validation, as well as the results of subpocket decomposition with CAVIAR and DoGSite are hosted on GitHub at <a href="https://github.com/jr-marchand/caviar/tree/master/validation_sets">https://github.com/jr-marchand/caviar/tree/master/validation_sets</a>. Contact: <a href="mailto:jean-remy.marchand@novartis.com">jean-remy.marchand@novartis.com</a>; <a href="mailto:finton.sirockin@novartis.com">finton.sirockin@novartis.com</a>

show abstract

Section: Discussionmentioning

confidence: 99%

Automatic Cavity Identification and Decomposition into Subpockets with CAVIAR

Marchand

Pirard²,

Ertl³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Interpreting predictions from ML models can be challenging but is an important step to build trust in them and to increase our understanding of the underlying biological phenomena; also observed and discussed in (Yuan et al, 2020). To make our prediction model easily interpretable and intuitive, we used a decision path analysis approach.…”

Section: Decision Tree Path Analysismentioning

confidence: 99%

Predicting Cell-Penetrating Peptides: Building and Interpreting Random Forest based prediction Models

Yadahalli

Verma

2020

Preprint

View full text Add to dashboard Cite

Targeting intracellular pathways with peptide drugs is becoming increasingly desirable but often limited in application due to their poor cell permeability. Understanding cellular permeability of peptides remains a major challenge with very little structure-activity relationship known. Fortunately, there exist a class of peptides called Cell-Penetrating Peptides (CPPs), which have the ability to cross cell membranes and are also capable of delivering biologically active cargo into cells. Discovering patterns that make peptides cell-permeable have a variety of applications in drug delivery. In the current study, we build prediction models for CPPs exploring features covering a range of properties based on amino acid sequences, using Random forest classifiers which are often more interpretable than other ensemble machine learning algorithms. While obtaining prediction accuracies of ~96%, we also interpret our prediction models using TreeInterpreter, LIME and SHAP to decipher the contributions of important features and optimal feature space for CPP class. We propose that our work might offer an intuitive guide for incorporating features that impart cell-penetrability into the design of novel CPPs.

show abstract

“…Additionally, the volume of the protein pocket (PVol) was computed using tools from the TRAPP software suite. 35,36 Thus, in total, 6 ligand and 14 protein descriptors were computed per ligand-protein complex.…”

Section: Generation Of Molecular Descriptorsmentioning

confidence: 99%

RASPD+: Fast Protein-Ligand Binding Free Energy Prediction Using Simplified Physicochemical Features

Holderbach

Adam

Jayaram

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

The virtual screening of large numbers of compounds against target protein binding sites has become an integral component of drug discovery workflows. This screening is often done by computationally docking ligands into a protein binding site of interest, but this has the drawback that a large number of poses must be evaluated to obtain accurate estimates of protein-ligand binding affinity. We here introduce a fast prefiltering method for ligand prioritization that is based on a set of machine learning models and uses simple pose-invariant physicochemical descriptors of the ligands and the protein binding pocket. Our method, Rapid Screening with Physicochemical Descriptors + machine learning (RASPD+), is trained on PDBbind data and achieves a regression performance better than for the original RASPD method and comparable to traditional scoring functions on a range of different test sets without the need for generating ligand poses. Additionally, we use RASPD+ to identify molecular features important for binding affinity and assess the ability of RASPD+ to enrich active molecules from decoys.

show abstract

Druggability Assessment in TRAPP Using Machine Learning Approaches

Cited by 40 publications

References 48 publications

Automatic Cavity Identification and Decomposition into Subpockets with CAVIAR

Automatic Cavity Identification and Decomposition into Subpockets with CAVIAR

Predicting Cell-Penetrating Peptides: Building and Interpreting Random Forest based prediction Models

RASPD+: Fast Protein-Ligand Binding Free Energy Prediction Using Simplified Physicochemical Features

Contact Info

Product

Resources

About