Combining heterogeneous data sources for accurate functional annotation of proteins

Abstract

Combining heterogeneous sources of data is essential for accurate prediction of protein function. The task is complicated by the fact that while sequence-based features can be readily compared across species, most other data are species-specific. In this paper, we present a multi-view extension to GOstruct, a structured-output framework for function annotation of proteins. The extended framework can learn from disparate data sources, with each data source provided to the framework in the form of a kernel. Our empirical results demonstrate that the multi-view framework is able to utilize all available information, yielding better performance than sequence-based models trained across species and models trained from collections of data within a given species. This version of GOstruct participated in the recent Critical Assessment of Functional Annotations (CAFA) challenge; since then we have significantly improved the natural language processing component of the method, which now provides performance that is on par with that provided by sequence information. The GOstruct framework is available for download at http://strut.sourceforge.net.

Multitask Protein Function Prediction through Task Dissimilarity

“…Several approaches to the predicton of protein functions were proposed in the literature, including sequencebased [10], [11], [12] and network-based methods [13], [14], [15], structured output algorithms based on kernels [3], [16], [17] and hierarchical ensemble methods [18], [19], [20]. In particular, the availability of large-scale networks, in which nodes are genes/proteins and edges their functional pairwise relationships, has promoted the development of several machine learning methods where novel annotations are inferred by exploiting the topology of the resulting biomolecular network.…”

The Ortholog Conjecture Revisited: the Value of Orthologs and Paralogs in Function Prediction

“…The prediction of gene function generally proceeds by the transfer of function from genes with experimental evidence to unannotated, or less-annotated, genes that are similar by some measure [42]. While several methods use multiple data types to carry out predictions [31,47,11], many solely rely on evolutionary relationships [16,24,6,10] and are the focus of the current study.…”

Text as data: Using text-based features for proteins representation and for computational prediction of their characteristics

“…For instance, Pérez et al [40] introduced a dictionary-based system that extracts keywords from the literature or from databases and associates them with GO categories; Other systems used pattern matching and sentence structure to retrieve sentences containing a protein along with Gene Ontology (GO) terms denoting function [8,26]. A recent function prediction system [56] identifies pairs of GO terms and proteins within abstracts, and uses them as part of an integrative similarity measure (kernel) employed in classifying proteins by function. Additional information extraction systems have been used in a variety of knowledge discovery tasks within the biomedical domain (see surveys, e.g., [11,25,52]).…”