dorsal/arxiv
View SchemaProbabilistic methods for predicting protein functions in protein-protein interaction networks
| Authors | Christoph Best, Ralf Zimmer, Joannis Apostolakis |
|---|---|
| Categories | |
| ArXiv ID | q-bio/0503018 |
| URL | https://arxiv.org/abs/q-bio/0503018 |
| Journal | in: R. Giegerich, J. Stoye (eds.), German Conference on Bioinformatics 2004, Lecture Notes in Informatics, Ges. f. Informatik, Bonn, Germany, 2004 |
Abstract
We discuss probabilistic methods for predicting protein functions from protein-protein interaction networks. Previous work based on Markov Randon Fields is extended and compared to a general machine-learning theoretic approach. Using actual protein interaction networks for yeast from the MIPS database and GO-SLIM function assignments, we compare the predictions of the different probabilistic methods and of a standard support vector machine. It turns out that, with the currently available networks, the simple methods based on counting frequencies perform as well as the more sophisticated approaches.
{
"annotation_id": "ca2d247c-6a36-4131-b4b0-aa727f1b79a9",
"date_created": "2026-03-02T18:01:31.161000Z",
"date_modified": "2026-03-02T18:01:31.161000Z",
"file_hash": "64bfedae85f67f45f6bc34477b95eb6e4ac230c13cc6acd8685e302f0a069a13",
"private": false,
"record": {
"abstract": "We discuss probabilistic methods for predicting protein functions from\nprotein-protein interaction networks. Previous work based on Markov Randon\nFields is extended and compared to a general machine-learning theoretic\napproach. Using actual protein interaction networks for yeast from the MIPS\ndatabase and GO-SLIM function assignments, we compare the predictions of the\ndifferent probabilistic methods and of a standard support vector machine. It\nturns out that, with the currently available networks, the simple methods based\non counting frequencies perform as well as the more sophisticated approaches.",
"arxiv_id": "q-bio/0503018",
"authors": [
"Christoph Best",
"Ralf Zimmer",
"Joannis Apostolakis"
],
"categories": [
"q-bio.MN"
],
"journal_ref": "in: R. Giegerich, J. Stoye (eds.), German Conference on\n Bioinformatics 2004, Lecture Notes in Informatics, Ges. f. Informatik, Bonn,\n Germany, 2004",
"title": "Probabilistic methods for predicting protein functions in protein-protein interaction networks",
"url": "https://arxiv.org/abs/q-bio/0503018"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "4cc13e41-1e13-42d4-9c6d-11075356bc69",
"id": "arXiv Dataset IDs",
"type": "Model",
"variant": "snapshot-2026-03-01",
"version": "0.1.0"
},
"user_id": 1000002
}