Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/bjorntropf/plbaffinity-reproduction

https://github.com/bjorntropf/plbaffinity-reproduction

Science Score: 36.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ○
    .zenodo.json file
  • ✓
    DOI references
    Found 2 DOI reference(s) in README
  • ✓
    Academic publication links
    Links to: ncbi.nlm.nih.gov
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (11.0%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: bjorntropf
  • License: gpl-3.0
  • Language: Jupyter Notebook
  • Default Branch: main
  • Size: 51.8 KB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 2 years ago · Last pushed about 2 years ago
Metadata Files
Readme License

README.md

PLBAffinity: Reproduction

Abstract

This is a reproduction of Protein-ligand binding affinity prediction exploiting sequence constituent homology.

Results

Plot 1 See Table 1 for the underlying data.

Overview

This repository contains three Jupyter notebooks:

  • prepare_input.ipynb for data preparation. This notebook reproduces the procedures described in the Materials and Methods section of the paper.
  • generate_output.ipynb for prediction and estimation. The original R code has been rewritten in Python, based on the existing code in the PLBAffinity repository.
  • generate_figures.ipynb for creating tables and figures. This notebook compares the figures from the paper with the results of this reproduction.

Deviations

This reproduction method has some deviations from the original paper:

  • Python and Jupyter notebooks are used instead of R.
  • Corrected values for NumRotatableBonds, confirmed with PUG REST.
  • Train/Test split performed using a random seed (42) (split method not mentioned in the paper).
  • Inclusion of the latest refined 2020 dataset from PDBbind.

Reproduction

To reproduce the results, please follow these steps:

  • Clone the PLBAffinity repository and place it in the same parent directory as this repository.
  • Register a PDBbind account if you haven't already.
  • Set the PDBBIND_USER and PDBBIND_PASS global variables based on your PDBbind account.
  • Adjust the DATASET_YEAR and USE_ORIG_INPUT variables in prepare_input.py and generate_output.py.

Please note: The notebooks need to be run for all possible configurations (2007-2020, with and without USE_ORIG_INPUT) in order to use generate_figures.py.

Libraries

A few Python scripts are included to keep the code in the Jupyter notebooks concise:

Owner

  • Name: Björn Tropf
  • Login: bjorntropf
  • Kind: user

GitHub Events

Total
Last Year