Functional Knowledge Transfer for High-accuracy Prediction of Under-studied Biological Processes

Abstract

A key challenge in genetics is identifying the functional roles of genes in pathways. Numerous functional genomics techniques (e.g. machine learning) that predict protein function have been developed to address this question. These methods generally build from existing annotations of genes to pathways and thus are often unable to identify additional genes participating in processes that are not already well studied. Many of these processes are well studied in some organism, but not necessarily in an investigator's organism of interest. Sequence-based search methods (e.g. BLAST) have been used to transfer such annotation information between organisms. We demonstrate that functional genomics can complement traditional sequence similarity to improve the transfer of gene annotations between organisms. Our method transfers annotations only when functionally appropriate as determined by genomic data and can be used with any prediction algorithm to combine transferred gene function knowledge with organism-specific high-throughput data to enable accurate function prediction.We show that diverse state-of-art machine learning algorithms leveraging functional knowledge transfer (FKT) dramatically improve their accuracy in predicting gene-pathway membership, particularly for processes with little experimental knowledge in an organism. We also show that our method compares favorably to annotation transfer by sequence similarity. Next, we deploy FKT with state-of-the-art SVM classifier to predict novel genes to 11,000 biological processes across six diverse organisms and expand the coverage of accurate function predictions to processes that are often ignored because of a dearth of annotated genes in an organism. Finally, we perform in vivo experimental investigation in Danio rerio and confirm the regulatory role of our top predicted novel gene, wnt5b, in leftward cell migration during heart development. FKT is immediately applicable to many bioinformatics techniques and will help biologists systematically integrate prior knowledge from diverse systems to direct targeted experiments in their organism of study.

Fruit Flies in Biomedical Research

“…One approach to fill the gap used in cancer studies is to integrate information from the transcriptome, proteome, and interactome to identify a group of genes and proteins that functions together (Brennan et al 2013). Another is to work toward improved bioinformatics platforms using clustering algorithms or machine learning to find similarities between known and unknown variables for genes (Park et al 2013). However, for human geneticists and clinicians, the idea that each patient is unique suggests that in reality our understanding of each and every gene will have to be individually improved, ideally with in vivo functional studies.…”

Applying Genomic and Genetic Tools to Understand and Mitigate Damage from Exposure to Toxins

“…Using ORIOGEN to study the dose-response using this grouping identified 24 transcripts with a decreasing profile and 16 transcripts that were upregulated with increasing degrees of inhibition of AChE. The DAVID Functional Analysis Tool is generally not appropriate for gene lists this small; however, the Integrative Multi-species Prediction (IMP) tool (27,28) was developed specifically for gene sets of this size and was used to search for enrichments of biological processes predicted to be involved with these genes. The upregulated genes were enriched for antigen processing and tcell mediated cytotoxicity, whereas the downregulated genes were enriched for neuron synaptic transmission, positive regulation of G protein coupled receptor protein signaling pathway, circadian sleep wake cycle, regulation of renal sodium excretion, and elevation of cytosolic calcium ion concentration.…”

Determining Microbial Products and Identifying Molecular Targets in the Human Microbiome

“…comparative metagenomics, phylogenetic profiling, and network context-based approaches (Bornigen et al, 2012; Goncalves et al, 2012; Hwang et al, 2011; Park et al, 2010; Park et al, 2013; Radivojac et al, 2013; Wang et al, 2012; Zuberi et al, 2013), integrate additional information to generate hypotheses regarding gene function, while manual curation of automated sequence-based function predictions can provide additional insight (Fig. 2).…”