Using random forests for assistance in the curation of G-protein coupled receptor databases

Abstract

BackgroundBiology is experiencing a gradual but fast transformation from a laboratory-centred science towards a data-centred one. As such, it requires robust data engineering and the use of quantitative data analysis methods as part of database curation. This paper focuses on G protein-coupled receptors, a large and heterogeneous super-family of cell membrane proteins of interest to biology in general. One of its families, Class C, is of particular interest to pharmacology and drug design. This family is quite heterogeneous on its own, and the discrimination of its several sub-families is a challenging problem. In the absence of known crystal structure, such discrimination must rely on their primary amino acid sequences.MethodsWe are interested not as much in achieving maximum sub-family discrimination accuracy using quantitative methods, but in exploring sequence misclassification behavior. Specifically, we are interested in isolating those sequences showing consistent misclassification, that is, sequences that are very often misclassified and almost always to the same wrong sub-family. Random forests are used for this analysis due to their ensemble nature, which makes them naturally suited to gauge the consistency of misclassification. This consistency is here defined through the voting scheme of their base tree classifiers.ResultsDetailed consistency results for the random forest ensemble classification were obtained for all receptors and for all data transformations of their unaligned primary sequences. Shortlists of the most consistently misclassified receptors for each subfamily and transformation, as well as an overall shortlist including those cases that were consistently misclassified across transformations, were obtained. The latter should be referred to experts for further investigation as a data curation task.ConclusionThe automatic discrimination of the Class C sub-families of G protein-coupled receptors from their unaligned primary sequences shows clear limits. This study has investigated in some detail the consistency of their misclassification using random forest ensemble classifiers. Different sub-families have been shown to display very different discrimination consistency behaviors. The individual identification of consistently misclassified sequences should provide a tool for quality control to GPCR database curators.Electronic supplementary materialThe online version of this article (doi:10.1186/s12938-017-0357-4) contains supplementary material, which is available to authorized users.

Development and validation of predictive models for Crohn’s disease patients with prothrombotic state: a 6-year clinical analysis

“…Multivariate models were developed with candidate variables that were significant in the univariate analysis using logistic regression and random forest analysis, and their predictive capabilities for PTS were compared. The logistic regression model is binary whereas the random forest creates multiple training sets for decision trees, wherein each tree is built based on a bootstrap sample drawn randomly from the original dataset using the CART method and the Decrease Gini Impurity as the splitting criterion (12). Furthermore, at each branching, only a given number of randomly selected features were considered as candidates.…”

Using machine learning tools for protein database biocuration assistance

“…Work on the 2011 version of the database provided evidence of clearly defined limits to the separability of the different class C subtypes. This evidence was produced using both supervised 25 , 26 and semi-supervised 22 machine learning approaches and from different data transformation strategies. Interestingly, the subtypes shown to be most responsible for such lack of complete subtype separability were precisely those which were removed in the 2016 versions of the databases (namely vomeronasal, odorant and pheromone receptors).…”

“…Subsequent work reported in 26 , which again employed alignment-free data transformations, used a Random Forest (RF) classifier 36 to further investigate the consistency of misclassification in this problem. Note that RF is an ensemble learning technique 37 with an internal classification voting system that is naturally suited to classification consistency analyses.…”

“…Class C, investigated in the current study, in turn comprises several subtypes. From GPCRdb, a class C dataset from March 2011 was object of extensive analysis using machine learning methods in our previous research 22 – 26 . These analyses revealed a possible receptor label noise problem 27 .…”

A statistical approach to identify, monitor, and manage incomplete curated data sets

“…Although assessing how complete or correct a large data set may be remains a challenge, examples have been reported. Examples include computational methods for identifying data updates and artifacts that may be of interest to downstream data consumers [ 1 ], machine learning methods to identify incorrectly classified G-protein coupled receptors [ 2 ], and to improve the quality of large data sets prior to quantitative structure-activity relationship modeling [ 3 ]. The completeness and quality of curated nanomaterial data has also been explored [ 4 ].…”