dorsal/arxiv
View SchemaA Machine Learning Strategy to Identity Exonic Splice Enhancers in Human Protein-coding Sequence
| Authors | Thomas A. Down, Bernard Leong, Tim J. P. Hubbard |
|---|---|
| Categories | |
| ArXiv ID | q-bio/0403024 |
| URL | https://arxiv.org/abs/q-bio/0403024 |
Abstract
Background: Exonic splice enhancers are sequences embedded within exons which promote and regulate the splicing of the transcript in which they are located. A class of exonic splice enhancers are the SR proteins, which are thought to mediate interactions between splicing factors bound to the 5' and 3' splice sites. Method and results: We present a novel strategy for analysing protein-coding sequence by first randomizing the codons used at each position within the coding sequence, then applying a motif-based machine learning algorithm to compare the true and randomized sequences. This strategy identified a collection of motifs which can successfully discriminate between real and randomized coding sequence, including -- but not restricted to -- several previously reported splice enhancer elements. As well as successfully distinguishing coding exons from randomized sequences, we show that our model is able to recognize non-coding exons. Conclusions: Our strategy succeeded in detecting signals in coding exons which seem to be orthogonal to the sequences' primary function of coding for proteins. We believe that many of the motifs detected here may represent binding sites for previously unrecognized proteins which influence RNA splicing. We hope that this development will lead to improved knowledge of exonic splice enhancers, and new developments in the field of computational gene prediction.
{
"annotation_id": "27343e5e-387f-4f77-81ed-f0d1cdb4e8be",
"date_created": "2026-03-02T18:01:31.667000Z",
"date_modified": "2026-03-02T18:01:31.667000Z",
"file_hash": "0eb0c3fe143675faf4c104ef545c472750696e96119ce24c8c9c739ba5761235",
"private": false,
"record": {
"abstract": "Background: Exonic splice enhancers are sequences embedded within exons which\npromote and regulate the splicing of the transcript in which they are located.\nA class of exonic splice enhancers are the SR proteins, which are thought to\nmediate interactions between splicing factors bound to the 5\u0027 and 3\u0027 splice\nsites. Method and results: We present a novel strategy for analysing\nprotein-coding sequence by first randomizing the codons used at each position\nwithin the coding sequence, then applying a motif-based machine learning\nalgorithm to compare the true and randomized sequences. This strategy\nidentified a collection of motifs which can successfully discriminate between\nreal and randomized coding sequence, including -- but not restricted to --\nseveral previously reported splice enhancer elements. As well as successfully\ndistinguishing coding exons from randomized sequences, we show that our model\nis able to recognize non-coding exons. Conclusions: Our strategy succeeded in\ndetecting signals in coding exons which seem to be orthogonal to the sequences\u0027\nprimary function of coding for proteins. We believe that many of the motifs\ndetected here may represent binding sites for previously unrecognized proteins\nwhich influence RNA splicing. We hope that this development will lead to\nimproved knowledge of exonic splice enhancers, and new developments in the\nfield of computational gene prediction.",
"arxiv_id": "q-bio/0403024",
"authors": [
"Thomas A. Down",
"Bernard Leong",
"Tim J. P. Hubbard"
],
"categories": [
"q-bio.GN"
],
"title": "A Machine Learning Strategy to Identity Exonic Splice Enhancers in Human Protein-coding Sequence",
"url": "https://arxiv.org/abs/q-bio/0403024"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "0521923a-7616-435c-82db-40bf913a158a",
"id": "arXiv Dataset IDs",
"type": "Model",
"variant": "snapshot-2026-03-01",
"version": "0.1.0"
},
"user_id": 1000002
}