Annotation of the Giardia proteome through structure-based homology and machine learning
Journal Title
Publication Type
Journal Article in press
Background: Large-scale computational prediction of protein structures represents a cost-effective alternative to empirical structure determination with particular promise for non-model organisms and neglected pathogens. Conventional sequence-based tools are insufficient to annotate the genomes of such divergent biological systems. Conversely, protein structure tolerates substantial variation in primary amino acid sequence, and is thus a robust indicator of biochemical function. Structural proteomics is poised to become a standard part of pathogen genomics research, however informatic methods are now required to assign confidence in large volumes of predicted structures. Aims: To predict the proteome of a neglected human pathogen, Giardia duodenalis, and stratify predicted structures into high- and lower-confidence categories using a variety of metrics in isolation and combination. Methods: We used the I-TASSER suite to predict structural models for approximately 5000 proteins encoded in Giardia duodenalis and identify their closest empirically determined structural homologues in the Protein Data Bank. Models were assigned to high or lower-confidence categories depending on the presence of matching PFAM domains in query and reference peptides. Metrics output from the suite and derived metrics were assessed for their ability to predict the high confidence category individually, and in combination through development of a random forest classifier. Results: We identified 1095 high confidence models including 212 hypothetical proteins. Amino acid identity between query and reference peptides was the greatest individual predictor of high confidence status, however the random forest classifier out-performed any metric in isolation (AUC = 0.977), and identified a subset of 305 high confidence-like models, corresponding to false positive predictions. High confidence models exhibited higher transcriptional abundance, and the classifier generalized across species, indicating the broad utility of this approach for automatically stratifying predicted structures. Additional structure-based clustering was used to cross-check confidence predictions in an expanded family of Nek kinases. Several high confidence-like proteins yielded substantial new insight into mechanisms of redox balance in Giardia duodenalis-a system central to the efficacy of limited anti-giardial drugs. Conclusion: Structural proteomics combined with machine learning can aid genome annotation for genetically divergent organisms including human pathogens, and stratify predicted structures to promote efficient allocation of limited resources for experimental investigatio.
Oxford Academic
WEHI Research Division(s)
Population Health And Immunity
PubMed ID
Open Access at Publisher's Site
ARC Grants
Rights Notice
Refer to copyright notice on published article.

Creation Date: 2018-12-18 02:54:27
Last Modified: 2019-06-14 11:49:46
An error has occurred. This application may no longer respond until reloaded. Reload 🗙