Protein networks—built by association

Mayer, Melanie L.; Hieter, Philip

doi:10.1038/82342

Cited by 36 publications

(22 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(Continued) and because it suggests the function of uncharacterized proteins (Mayer and Hieter 2000). Thus, global analysis has been performed in yeast PPIs, which showed that most of the interactions were involved in a complicated large network; the results were used to reasonably predict the function of 29 previously uncharacterized proteins (Schwikowski et al 2000).…”

Section: Discussionmentioning

confidence: 99%

Protein–Protein Interaction Panel Using Mouse Full-Length cDNAs

Suzuki¹,

Fukunishi²,

Kagawa³

et al. 2001

Genome Res.

103

View full text Add to dashboard Cite

We have developed a novel assay system for systematic analysis of protein-protein interactions (PPIs) that is characteristic of a PCR-mediated rapid sample preparation and a high-throughput assay system based on the mammalian two-hybrid method. Using gene-specific primers, we successfully constructed the assay samples by two rounds of PCR with up to 3.6 kb from the first-round PCR fragments. In the assay system, we designed all the steps to be performed by adding only samples, reagents, and cells into 384-well assay plates using two types of semiautomatic multiple dispensers. The system enabled us examine more than 20,000 assay wells per day. We detected 145 interactions in our pilot study using 3500 samples derived from mouse full-length enriched cDNAs. Analysis of the interaction data showed both several significant interaction clusters and predicted functions of a few uncharacterized proteins. In combination with our comprehensive mouse full-length cDNA clone bank covering a large part of the whole genes, our high-throughput assay system will discover many interactions to facilitate understanding of the function of uncharacterized proteins and the molecular mechanism of crucial biological processes, and also enable completion of a rough draft of the entire PPI panel in certain cell types or tissues of mouse within a short time.

show abstract

Section: Discussionmentioning

confidence: 99%

Protein–Protein Interaction Panel Using Mouse Full-Length cDNAs

Suzuki¹,

Fukunishi²,

Kagawa³

et al. 2001

Genome Res.

103

View full text Add to dashboard Cite

show abstract

“…We compared our method with several state-of-the-art competitors: GBA, an algorithm based on the guilt-by-association principle [39]; GeneMANIA [44], the top method in the MouseFunc challenge [52]; MS-kNN [32], one of the top ranking algorithm in the recent CAFA challenge [53]; LP, a semisupervised label propagation algorithm based on Gaussian random fields, and its class mass normalized version LP-CMN [70]; RW, the classical random walk algorithm without restart with at most 1000 random walk steps [36]; COSNet, a recently proposed algorithm for label prediction in graph, which is explicitly designed to cope with the imbalance in the instance labeling [21]. Furthermore, to assess the improvements introduced by partitioning proteins into categories, we also apply a different version of HoMCat, in which all the proteins are considered belonging to the same category (named HoMCat-1c).…”

Section: Comparison With State-of-the-art Methodsmentioning

confidence: 99%

Learning node labels with multi-category Hopfield networks

Frasca

Bassis

Valentini

2015

Neural Comput & Applic

View full text Add to dashboard Cite

In several real-world node-label prediction problems on graphs, in fields ranging from computational biology to World-Wide-Web analysis, nodes can be partitioned into categories different from the classes to be predicted, on the basis of their characteristics or their common properties. Such partitions may provide further information about node classification that classical machine learning algorithms do not take into account. We introduce a novel family of parametric Hopfield networks (m-Category Hopfield Networks) and a novel algorithm (Hopfield Multi-Category -HoMCat), designed to appropriately exploit the presence of propertybased partitions of nodes into multiple categories. Moreover, the proposed model adopts a cost-sensitive learning strategy to prevent the remarkable decay in performance usually observed when instance labels are unbalanced, that is when one class of labels is highly under-represented than the other one. We validate the proposed model on both synthetic and real-world data, in the context of multi-species function prediction, where the classes to be predicted are the Gene Ontology terms and the categories the different species in the multi-species protein network. We carried out an intensive experimental validation, which on the one hand compares HoMCat with several state-of-the-art graph-based algorithms, and on the other hand reveals that exploiting meaningful prior partitions of input data can substantially improve classification performances.

show abstract

“…In particular, we considered GeneMANIA [26], an algorithm based on ridge regression integration and Gaussian Random Fields, that ranked among the best methods in the MouseFunc competition for mouse AFP [54], and, as a baseline, the classical guilt-by-association algorithm (GBA) [55]. We also evaluated a classical inductive method, the Support Vector Machine (SVM ), largely applied in computational biology and in AFP; more precisely, we tested the probabilistic version of SVM [56], which provides a probabilistic score to genes with respect to the functional class being predicted.…”

Section: Resultsmentioning

confidence: 99%

Automated gene function prediction through gene multifunctionality in biological networks

Frasca

2015

Neurocomputing

View full text Add to dashboard Cite

As the number of sequenced genomes rapidly grows, automated prediction of gene function (AFP) is now a challenging problem. Despite significant progresses in the last several years, the accuracy of gene function prediction still needs to be improved in order to be used effectively in practice. Two of the main issues of AFP problem are the imbalance of gene functional annotations and the 'multifunctional properties' of genes. While the former is a well studied problem in machine learning, the latter has recently emerged in bioinformatics and few studies have been carried out about it. Here we propose a method for AFP which appropriately handles the label imbalance characterizing biological taxonomies, and embeds in the model the property of some genes of being 'multifunctional'. We tested the method in predicting the functions of the Gene Ontology functional hierarchy for genes of yeast and fly model organisms, in a genome-wide approach. The achieved results show that cost-sensitive strategies and 'gene multifunctionality' can be combined to achieve significantly better results than the compared state-of-the-art algorithms for AFP.

show abstract

Protein networks—built by association

Cited by 36 publications

References 11 publications

Protein–Protein Interaction Panel Using Mouse Full-Length cDNAs

Protein–Protein Interaction Panel Using Mouse Full-Length cDNAs

Learning node labels with multi-category Hopfield networks

Automated gene function prediction through gene multifunctionality in biological networks

Contact Info

Product

Resources

About