dorsal/arxiv
View SchemaCRNPRED: Highly Accurate Prediction of One-dimensional Protein Structures by Large-scale Critical Random Networks
| Authors | Akira R. Kinjo, Ken Nishikawa |
|---|---|
| Categories | |
| ArXiv ID | q-bio/0604013 |
| URL | https://arxiv.org/abs/q-bio/0604013 |
| DOI | 10.1186/1471-2105-7-401 |
| Journal | BMC Bioinformatics, 7:401 (2006) |
Abstract
Background: One-dimensional protein structures such as secondary structures or contact numbers are useful for three-dimensional structure prediction and helpful for intuitive understanding of the sequence-structure relationship. Accurate prediction methods will serve as a basis for these and other purposes. Results: We implemented a program CRNPRED which predicts secondary structures, contact numbers and residue-wise contact orders. This program is based on a novel machine learning scheme called critical random networks. Unlike most conventional one-dimensional structure prediction methods which are based on local windows of an amino acid sequence, CRNPRED takes into account the whole sequence. CRNPRED achieves, on average per chain, Q3 = 81% for secondary structure prediction, and correlation coefficients of 0.75 and 0.61 for contact number and residue-wise contact order predictions, respectively. Conclusion: CRNPRED will be a useful tool for computational as well as experimental biologists who need accurate one-dimensional protein structure predictions.
{
"annotation_id": "6bb38576-52d6-4ee5-b087-e80d8ad7b3d0",
"date_created": "2026-03-02T18:01:35.300000Z",
"date_modified": "2026-03-02T18:01:35.300000Z",
"file_hash": "6105e0531b40fdf260270b9c51258e1151eae25acb6e11217dbbd6f4d90a332e",
"private": false,
"record": {
"abstract": "Background: One-dimensional protein structures such as secondary structures\nor contact numbers are useful for three-dimensional structure prediction and\nhelpful for intuitive understanding of the sequence-structure relationship.\nAccurate prediction methods will serve as a basis for these and other purposes.\nResults: We implemented a program CRNPRED which predicts secondary structures,\ncontact numbers and residue-wise contact orders. This program is based on a\nnovel machine learning scheme called critical random networks. Unlike most\nconventional one-dimensional structure prediction methods which are based on\nlocal windows of an amino acid sequence, CRNPRED takes into account the whole\nsequence. CRNPRED achieves, on average per chain, Q3 = 81% for secondary\nstructure prediction, and correlation coefficients of 0.75 and 0.61 for contact\nnumber and residue-wise contact order predictions, respectively. Conclusion:\nCRNPRED will be a useful tool for computational as well as experimental\nbiologists who need accurate one-dimensional protein structure predictions.",
"arxiv_id": "q-bio/0604013",
"authors": [
"Akira R. Kinjo",
"Ken Nishikawa"
],
"categories": [
"q-bio.BM"
],
"doi": "10.1186/1471-2105-7-401",
"journal_ref": "BMC Bioinformatics, 7:401 (2006)",
"title": "CRNPRED: Highly Accurate Prediction of One-dimensional Protein Structures by Large-scale Critical Random Networks",
"url": "https://arxiv.org/abs/q-bio/0604013"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "9eb7ee72-4403-4926-9623-fc78f37c60b2",
"id": "arXiv Dataset IDs",
"type": "Model",
"variant": "snapshot-2026-03-01",
"version": "0.1.0"
},
"user_id": 1000002
}