An Algorithm to Identify Target-Selective Ligands - A Case Study of 5-HT7/5-HT1A Receptor Selectivity.
A computational procedure to search for selective ligands for structurally related protein targets was developed and verified for serotonergic 5-HT7/5-HT1A receptor ligands. Starting from a set of compounds with annotated activity at both targets (grouped into four classes according to their activit...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2016-01-01
|
Series: | PLoS ONE |
Online Access: | http://europepmc.org/articles/PMC4896471?pdf=render |
id |
doaj-73faac2748bc404d817474d3cdec7011 |
---|---|
record_format |
Article |
spelling |
doaj-73faac2748bc404d817474d3cdec70112020-11-25T01:33:18ZengPublic Library of Science (PLoS)PLoS ONE1932-62032016-01-01116e015698610.1371/journal.pone.0156986An Algorithm to Identify Target-Selective Ligands - A Case Study of 5-HT7/5-HT1A Receptor Selectivity.Rafał KurczabVittorio CanalePaweł ZajdelAndrzej J BojarskiA computational procedure to search for selective ligands for structurally related protein targets was developed and verified for serotonergic 5-HT7/5-HT1A receptor ligands. Starting from a set of compounds with annotated activity at both targets (grouped into four classes according to their activity: selective toward each target, not-selective and not-selective but active) and with an additional set of decoys (prepared using DUD methodology), the SVM (Support Vector Machines) models were constructed using a selective subset as positive examples and four remaining classes as negative training examples. Based on these four component models, the consensus classifier was then constructed using a data fusion approach. The combination of two approaches of data representation (molecular fingerprints vs. structural interaction fingerprints), different training set sizes and selection of the best SVM component models for consensus model generation, were evaluated to determine the optimal settings for the developed algorithm. The results showed that consensus models with molecular fingerprints, a larger training set and the selection of component models based on MCC maximization provided the best predictive performance.http://europepmc.org/articles/PMC4896471?pdf=render |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Rafał Kurczab Vittorio Canale Paweł Zajdel Andrzej J Bojarski |
spellingShingle |
Rafał Kurczab Vittorio Canale Paweł Zajdel Andrzej J Bojarski An Algorithm to Identify Target-Selective Ligands - A Case Study of 5-HT7/5-HT1A Receptor Selectivity. PLoS ONE |
author_facet |
Rafał Kurczab Vittorio Canale Paweł Zajdel Andrzej J Bojarski |
author_sort |
Rafał Kurczab |
title |
An Algorithm to Identify Target-Selective Ligands - A Case Study of 5-HT7/5-HT1A Receptor Selectivity. |
title_short |
An Algorithm to Identify Target-Selective Ligands - A Case Study of 5-HT7/5-HT1A Receptor Selectivity. |
title_full |
An Algorithm to Identify Target-Selective Ligands - A Case Study of 5-HT7/5-HT1A Receptor Selectivity. |
title_fullStr |
An Algorithm to Identify Target-Selective Ligands - A Case Study of 5-HT7/5-HT1A Receptor Selectivity. |
title_full_unstemmed |
An Algorithm to Identify Target-Selective Ligands - A Case Study of 5-HT7/5-HT1A Receptor Selectivity. |
title_sort |
algorithm to identify target-selective ligands - a case study of 5-ht7/5-ht1a receptor selectivity. |
publisher |
Public Library of Science (PLoS) |
series |
PLoS ONE |
issn |
1932-6203 |
publishDate |
2016-01-01 |
description |
A computational procedure to search for selective ligands for structurally related protein targets was developed and verified for serotonergic 5-HT7/5-HT1A receptor ligands. Starting from a set of compounds with annotated activity at both targets (grouped into four classes according to their activity: selective toward each target, not-selective and not-selective but active) and with an additional set of decoys (prepared using DUD methodology), the SVM (Support Vector Machines) models were constructed using a selective subset as positive examples and four remaining classes as negative training examples. Based on these four component models, the consensus classifier was then constructed using a data fusion approach. The combination of two approaches of data representation (molecular fingerprints vs. structural interaction fingerprints), different training set sizes and selection of the best SVM component models for consensus model generation, were evaluated to determine the optimal settings for the developed algorithm. The results showed that consensus models with molecular fingerprints, a larger training set and the selection of component models based on MCC maximization provided the best predictive performance. |
url |
http://europepmc.org/articles/PMC4896471?pdf=render |
work_keys_str_mv |
AT rafałkurczab analgorithmtoidentifytargetselectiveligandsacasestudyof5ht75ht1areceptorselectivity AT vittoriocanale analgorithmtoidentifytargetselectiveligandsacasestudyof5ht75ht1areceptorselectivity AT pawełzajdel analgorithmtoidentifytargetselectiveligandsacasestudyof5ht75ht1areceptorselectivity AT andrzejjbojarski analgorithmtoidentifytargetselectiveligandsacasestudyof5ht75ht1areceptorselectivity AT rafałkurczab algorithmtoidentifytargetselectiveligandsacasestudyof5ht75ht1areceptorselectivity AT vittoriocanale algorithmtoidentifytargetselectiveligandsacasestudyof5ht75ht1areceptorselectivity AT pawełzajdel algorithmtoidentifytargetselectiveligandsacasestudyof5ht75ht1areceptorselectivity AT andrzejjbojarski algorithmtoidentifytargetselectiveligandsacasestudyof5ht75ht1areceptorselectivity |
_version_ |
1725078152519090176 |