Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2015 May 13;6:105. doi: 10.3389/fphar.2015.00105

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

Copyright © 2015 O'Hagan and Kell.

This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

PMC Copyright notice

DES and MACCS encodings predict receptor binding in ChEMBL datasets. PLS Prediction of (A) the ChEMBL 4333 and (B) the ChEMBL 245 dataset pIC50 values using DES Fingerprints (for various fractions, N, of scaffolds used) and MACCS Fingerprints. Scaffolds were sorted according to maximum of their (frequency of occurrence in Drugs, frequency of occurrence in Recon2 metabolites). Datasets were split 60:40 into training and test sets, and training data were pre-processed using a low variance filter, and a correlation filter prior to PLS (5 latent variables). The test data were used for plotting the scatter plot and the REC curve. PLS was carried out using the R plsdepot package using the Knime R Integration and Scripting Nodes. The REC curve plot also shows the curve for using the mean value as predictor; this is taken as a reference worst-case method.