Dataset Information

Conditional probabilistic analysis for prediction of the activity landscape and relative compound activities.

ABSTRACT: Structure-property relationships and structure-activity relationships play an important role in many research areas, such as medicinal chemistry and drug discovery. Such methods, however, have focused on providing post-hoc descriptions of such relationships based on known data. The ability for these descriptions to remain relevant when considering compounds of unknown activity, and thus the prediction of activity and property landscapes using existing data, remains little explored. In this study, we present a novel method of evaluating the ability of a compound comparison methodology to provide accurate information about a set of unknown compounds and also explore the ability of these predicted activity landscapes to prioritize active compounds over inactive. These methods are applied to three distinct and diverse sets of compounds, each with activity data for multiple targets, for a total of eight target-compound set pairs. Six methodologically distinct compound comparison methods were evaluated. We show that overall, all compound comparison methods provided an improvement in structure-activity relationship prediction over random and were able to prioritize compounds in a superior manner to random sampling, but the degree of success and therefore applicability varied markedly.

SUBMITTER: Santos RG

PROVIDER: S-EPMC3850180 | biostudies-literature | 2013 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Conditional probabilistic analysis for prediction of the activity landscape and relative compound activities.

Santos Radleigh G RG Giulianotti Marc A MA Houghten Richard A RA Medina-Franco José L JL

Journal of chemical information and modeling 20130917 10

Structure-property relationships and structure-activity relationships play an important role in many research areas, such as medicinal chemistry and drug discovery. Such methods, however, have focused on providing post-hoc descriptions of such relationships based on known data. The ability for these descriptions to remain relevant when considering compounds of unknown activity, and thus the prediction of activity and property landscapes using existing data, remains little explored. In this study ...[more]

PMID: 23971977

Similar Datasets

Project description:In predicting hierarchical protein function annotations, such as terms in the Gene Ontology (GO), the simplest approach makes predictions for each term independently. However, this approach has the unfortunate consequence that the predictor may assign to a single protein a set of terms that are inconsistent with one another; for example, the predictor may assign a specific GO term to a given protein ('purine nucleotide binding') but not assign the parent term ('nucleotide binding'). Such predictions are difficult to interpret. In this work, we focus on methods for calibrating and combining independent predictions to obtain a set of probabilistic predictions that are consistent with the topology of the ontology. We call this procedure 'reconciliation'. We begin with a baseline method for predicting GO terms from a collection of data types using an ensemble of discriminative classifiers. We apply the method to a previously described benchmark data set, and we demonstrate that the resulting predictions are frequently inconsistent with the topology of the GO. We then consider 11 distinct reconciliation methods: three heuristic methods; four variants of a Bayesian network; an extension of logistic regression to the structured case; and three novel projection methods - isotonic regression and two variants of a Kullback-Leibler projection method. We evaluate each method in three different modes - per term, per protein and joint - corresponding to three types of prediction tasks. Although the principal goal of reconciliation is interpretability, it is important to assess whether interpretability comes at a cost in terms of precision and recall. Indeed, we find that many apparently reasonable reconciliation methods yield reconciled probabilities with significantly lower precision than the original, unreconciled estimates. On the other hand, we find that isotonic regression usually performs better than the underlying, unreconciled method, and almost never performs worse; isotonic regression appears to be able to use the constraints from the GO network to its advantage. An exception to this rule is the high precision regime for joint evaluation, where Kullback-Leibler projection yields the best performance.

Dataset Information

Conditional probabilistic analysis for prediction of the activity landscape and relative compound activities.

Publications

Conditional probabilistic analysis for prediction of the activity landscape and relative compound activities.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure