Hyunjung Shin1, Andreas Martin Lisewski, Olivier Lichtarge. 1. Department of Industrial & Information Systems Engineering, Ajou University, San 5, Wonchun-dong, Yeoungtong-gu, 443-749, Suwon, Korea. shin@ajou.ac.kr
Abstract
MOTIVATION: Predicting protein function is a central problem in bioinformatics, and many approaches use partially or fully automated methods based on various combination of sequence, structure and other information on proteins or genes. Such information establishes relationships between proteins that can be modelled most naturally as edges in graphs. A priori, however, it is often unclear which edges from which graph may contribute most to accurate predictions. For that reason, one established strategy is to integrate all available sources, or graphs as in graph integration, in the hope that the positive signals will add to each other. However, in the problem of functional prediction, noise, i.e. the presence of inaccurate or false edges, can still be large enough that integration alone has little effect on prediction accuracy. In order to reduce noise levels and to improve integration efficiency, we present here a recent method in graph-based learning, graph sharpening, which provides a theoretically firm yet intuitive and practical approach for disconnecting undesirable edges from protein similarity graphs. This approach has several attractive features: it is quick, scalable in the number of proteins, robust with respect to errors and tolerant of very diverse types of protein similarity measures. RESULTS: We tested the classification accuracy in a test set of 599 proteins with remote sequence homology spread over 20 Gene Ontology (GO) functional classes. When compared to integration alone, graph sharpening plus integration of four vastly different molecular similarity measures improved the overall classification by nearly 30% [0.17 average increase in the area under the ROC curve (AUC)]. Moreover, and partially through the increased sparsity of the graphs induced by sharpening, this gain in accuracy came at negligible computational cost: sharpening and integration took on average 4.66 (+/-4.44) CPU seconds. AVAILABILITY: Software and Supplementary data will be available on http://mammoth.bcm.tmc.edu/
MOTIVATION: Predicting protein function is a central problem in bioinformatics, and many approaches use partially or fully automated methods based on various combination of sequence, structure and other information on proteins or genes. Such information establishes relationships between proteins that can be modelled most naturally as edges in graphs. A priori, however, it is often unclear which edges from which graph may contribute most to accurate predictions. For that reason, one established strategy is to integrate all available sources, or graphs as in graph integration, in the hope that the positive signals will add to each other. However, in the problem of functional prediction, noise, i.e. the presence of inaccurate or false edges, can still be large enough that integration alone has little effect on prediction accuracy. In order to reduce noise levels and to improve integration efficiency, we present here a recent method in graph-based learning, graph sharpening, which provides a theoretically firm yet intuitive and practical approach for disconnecting undesirable edges from protein similarity graphs. This approach has several attractive features: it is quick, scalable in the number of proteins, robust with respect to errors and tolerant of very diverse types of protein similarity measures. RESULTS: We tested the classification accuracy in a test set of 599 proteins with remote sequence homology spread over 20 Gene Ontology (GO) functional classes. When compared to integration alone, graph sharpening plus integration of four vastly different molecular similarity measures improved the overall classification by nearly 30% [0.17 average increase in the area under the ROC curve (AUC)]. Moreover, and partially through the increased sparsity of the graphs induced by sharpening, this gain in accuracy came at negligible computational cost: sharpening and integration took on average 4.66 (+/-4.44) CPU seconds. AVAILABILITY: Software and Supplementary data will be available on http://mammoth.bcm.tmc.edu/
Authors: Marylyn D Ritchie; Emily R Holzinger; Ruowang Li; Sarah A Pendergrass; Dokyoon Kim Journal: Nat Rev Genet Date: 2015-01-13 Impact factor: 53.242
Authors: Dokyoon Kim; Sungeun Kim; Shannon L Risacher; Li Shen; Marylyn D Ritchie; Michael W Weiner; Andrew J Saykin; Kwangsik Nho Journal: Multimodal Brain Image Anal (2013) Date: 2013
Authors: Eric Venner; Andreas Martin Lisewski; Serkan Erdin; R Matthew Ward; Shivas R Amin; Olivier Lichtarge Journal: PLoS One Date: 2010-12-13 Impact factor: 3.240
Authors: Teng-Kuei Hsu; Jennifer Asmussen; Amanda Koire; Byung-Kwon Choi; Mayur A Gadhikar; Eunna Huh; Chih-Hsu Lin; Daniel M Konecki; Young Won Kim; Curtis R Pickering; Marek Kimmel; Lawrence A Donehower; Mitchell J Frederick; Jeffrey N Myers; Panagiotis Katsonis; Olivier Lichtarge Journal: Genome Res Date: 2022-03-17 Impact factor: 9.438