From f4c1e634087238f907bbab3a2391e4eec5faf0d4 Mon Sep 17 00:00:00 2001 From: rdk Date: Wed, 1 Apr 2020 20:48:03 +0200 Subject: [PATCH] updated readme, version changed to 2.1 --- README.md | 21 ++++++++++++--------- build.gradle | 2 +- 2 files changed, 13 insertions(+), 10 deletions(-) diff --git a/README.md b/README.md index a846ed11..5551318c 100644 --- a/README.md +++ b/README.md @@ -7,7 +7,7 @@ Ligand-binding site prediction based on machine learning.

-[![version 2.1-beta.1](https://img.shields.io/badge/version-2.1.beta.1-green.svg)](/build.gradle) +[![version 2.1](https://img.shields.io/badge/version-2.1-green.svg)](/build.gradle) [![Build Status](https://travis-ci.org/rdk/p2rank.svg?branch=master)](https://travis-ci.org/rdk/p2rank) [![License: MIT](http://img.shields.io/badge/license-MIT-blue.svg?style=flat)](/LICENSE.txt) @@ -17,8 +17,8 @@ P2Rank is a stand-alone command line program that predicts ligand-binding pocket ### Requirements -* JRE 8 (Java 1.8) or JRE 11 (Java 11) -* PyMOL 1.7.x for viewing visualizations (optional) +* Java 8 or newer +* PyMOL 1.7 (or newer) for viewing visualizations (optional) ### Setup @@ -44,7 +44,7 @@ This project uses [Gradle](https://gradle.org/) build system. Build with `./make P2Rank makes predictions by scoring and clustering points on the protein's solvent accessible surface. Ligandability score of individual points is determined by a machine learning based model trained on the dataset of known protein-ligand complexes. For more details see slides and publications. -Slides: http://bit.ly/p2rank_slides +Slides introducing original version of the algotithm: http://bit.ly/p2rank_slides ### Publications @@ -96,17 +96,20 @@ prank eval-predict test.ds ### Prediction output - For each file in the dataset program produces a CSV file in the output directory named - `_predictions.csv`, which contains an ordered list of predicted pockets, their scores, coordinates - of their centroids and list of PDBSerials of adjacent amino acids and solvent exposed atoms. + For each file in the dataset P2Rank produces produces several output files: + * `_predictions.csv`: contains an ordered list of predicted pockets, their scores, coordinates + of their centers together with a list of adjacent residues and a list of adjacent protein surface atoms + * `_residues.csv`: contains list of all residues from the input protein with their scores, + mapping to predicted pockets and calibrated probability of being a ligand-binding residue + * PyMol visualization (`.pml` script with data files) - If coordinates of SAS points that belong to predicted pockets are needed they can be found + If coordinates of SAS points that belong to predicted pockets are needed, they can be found in `visualizations/data/_points.pdb`. There "Residue sequence number" (23-26) of HETATM record corresponds to the rank of corresponding pocket (points with value 0 do not belong to any pocket). ### Configuration -You can override default params with custom config file: +You can override the default params with a custom config file: ~~~ prank predict -c config/example.groovy test.ds diff --git a/build.gradle b/build.gradle index 05a2ccda..1f3a22b5 100644 --- a/build.gradle +++ b/build.gradle @@ -4,7 +4,7 @@ apply plugin: 'idea' group = 'cz.siret' -version = '2.1-ions.4' +version = '2.1' description = 'Ligand binding site prediction based on machine learning.'