Computational algorithms to predict Gene Ontology annotations

Abstract

BackgroundGene function annotations, which are associations between a gene and a term of a controlled vocabulary describing gene functional features, are of paramount importance in modern biology. Datasets of these annotations, such as the ones provided by the Gene Ontology Consortium, are used to design novel biological experiments and interpret their results. Despite their importance, these sources of information have some known issues. They are incomplete, since biological knowledge is far from being definitive and it rapidly evolves, and some erroneous annotations may be present. Since the curation process of novel annotations is a costly procedure, both in economical and time terms, computational tools that can reliably predict likely annotations, and thus quicken the discovery of new gene annotations, are very useful.MethodsWe used a set of computational algorithms and weighting schemes to infer novel gene annotations from a set of known ones. We used the latent semantic analysis approach, implementing two popular algorithms (Latent Semantic Indexing and Probabilistic Latent Semantic Analysis) and propose a novel method, the Semantic IMproved Latent Semantic Analysis, which adds a clustering step on the set of considered genes. Furthermore, we propose the improvement of these algorithms by weighting the annotations in the input set.ResultsWe tested our methods and their weighted variants on the Gene Ontology annotation sets of three model organism genes (Bos taurus, Danio rerio and Drosophila melanogaster ). The methods showed their ability in predicting novel gene annotations and the weighting procedures demonstrated to lead to a valuable improvement, although the obtained results vary according to the dimension of the input annotation set and the considered algorithm.ConclusionsOut of the three considered methods, the Semantic IMproved Latent Semantic Analysis is the one that provides better results. In particular, when coupled with a proper weighting policy, it is able to predict a significant number of novel annotations, demonstrating to actually be a helpful tool in supporting scientists in the curation process of gene functional annotations.

Supervised deep learning embeddings for the prediction of cervical cancer diagnosis

“…We also plan to try alternative prediction models, like probabilistic latent semantic analysis (Pinoli, Chicco & Masseroli, 2015). Finally, we plan to extend our computational system by adding a feature selection step, able to state the most relevant features among the dataset.…”

“…We validated the performance of traditional machine learning models such as support vector machines (SVM) with radial basis function kernel (Scholkopf et al, 1997), k-nearest neighbors (Peterson, 2009), and decision trees (Quinlan, 1986). In general, the proposed models surpassed the performance of the classical methodologies in terms of area under the PR curve.…”

Novelty Indicator for Enhanced Prioritization of Predicted Gene Ontology Annotations

“…We used the annotation prediction and prioritization pipeline described in [20], which includes the prediction methods truncated singular value decomposition (tSVD), semantically improved tSVD with gene clustering (SIM1), and Semantically IMproved tSVD with gene clustering and feature term similarity weights (SIM2), all described in [12] [13]. Figure 1 shows the used computational pipeline and its extension with the novelty indicator proposed in this paper.…”

“…We tested the use of the GOscore BM measure as a novelty indicator on all the GO annotations predicted for the Homo sapiens genes, based on the gene GO annotations available in the GPDW dataset of July 2009 and using the (tSVD), Semantically IMproved tSVD with gene clustering (SIM1), Semantically IMproved tSVD with gene clustering and feature term similarity weights (SIM2) tSVD, SIM1 and SIM2 methods described in [12]. The GOscore BM measure resulted in concordance with the visual evaluation of the gene annotations performed by an expert.…”

Inferring weighted gene annotations from expression data

“…Genome annotation is a central task in modern biology, and a great deal of effort has been dedicated to the construction of controlled vocabularies to describe cellular organization and function, and to the association of terms in these controlled vocabularies to specific genes. Because annotating genes empirically is costly and time consuming, computational methods have been developed to infer gene annotations from existing annotations and additional data, such as gene sequences, interaction network connectivity, and gene-expression profiles [1][2][3][4][5] . To date, the aim of such methods has been to decide whether a gene should or should not be annotated with a particular term.…”