CI-SpliceAI—Improving machine learning predictions of disease causing splicing variants using curated alternative splice sites
<h4>Background</h4> It is estimated that up to 50% of all disease causing variants disrupt splicing. Due to its complexity, our ability to predict which variants disrupt splicing is limited, meaning missed diagnoses for patients. The emergence of machine learning for targeted medicine ho...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2022-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9165884/?tool=EBI |
| _version_ | 1818549283774791680 |
|---|---|
| author | Yaron Strauch Jenny Lord Mahesan Niranjan Diana Baralle |
| author_facet | Yaron Strauch Jenny Lord Mahesan Niranjan Diana Baralle |
| author_sort | Yaron Strauch |
| collection | DOAJ |
| description | <h4>Background</h4> It is estimated that up to 50% of all disease causing variants disrupt splicing. Due to its complexity, our ability to predict which variants disrupt splicing is limited, meaning missed diagnoses for patients. The emergence of machine learning for targeted medicine holds great potential to improve prediction of splice disrupting variants. The recently published SpliceAI algorithm utilises deep neural networks and has been reported to have a greater accuracy than other commonly used methods. <h4>Methods and findings</h4> The original SpliceAI was trained on splice sites included in primary isoforms combined with novel junctions observed in GTEx data, which might introduce noise and de-correlate the machine learning input with its output. Limiting the data to only validated and manual annotated primary and alternatively spliced GENCODE sites in training may improve predictive abilities. All of these gene isoforms were collapsed (aggregated into one pseudo-isoform) and the SpliceAI architecture was retrained (CI-SpliceAI). Predictive performance on a newly curated dataset of 1,316 functionally validated variants from the literature was compared with the original SpliceAI, alongside MMSplice, MaxEntScan, and SQUIRLS. Both SpliceAI algorithms outperformed the other methods, with the original SpliceAI achieving an accuracy of ∼91%, and CI-SpliceAI showing an improvement at ∼92% overall. Predictive accuracy increased in the majority of curated variants. <h4>Conclusions</h4> We show that including only manually annotated alternatively spliced sites in training data improves prediction of clinically relevant variants, and highlight avenues for further performance improvements. |
| first_indexed | 2024-12-12T08:31:20Z |
| format | Article |
| id | doaj.art-3fa027916905467994647ecd5fc0b678 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-12T08:31:20Z |
| publishDate | 2022-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-3fa027916905467994647ecd5fc0b6782022-12-22T00:31:05ZengPublic Library of Science (PLoS)PLoS ONE1932-62032022-01-01176CI-SpliceAI—Improving machine learning predictions of disease causing splicing variants using curated alternative splice sitesYaron StrauchJenny LordMahesan NiranjanDiana Baralle<h4>Background</h4> It is estimated that up to 50% of all disease causing variants disrupt splicing. Due to its complexity, our ability to predict which variants disrupt splicing is limited, meaning missed diagnoses for patients. The emergence of machine learning for targeted medicine holds great potential to improve prediction of splice disrupting variants. The recently published SpliceAI algorithm utilises deep neural networks and has been reported to have a greater accuracy than other commonly used methods. <h4>Methods and findings</h4> The original SpliceAI was trained on splice sites included in primary isoforms combined with novel junctions observed in GTEx data, which might introduce noise and de-correlate the machine learning input with its output. Limiting the data to only validated and manual annotated primary and alternatively spliced GENCODE sites in training may improve predictive abilities. All of these gene isoforms were collapsed (aggregated into one pseudo-isoform) and the SpliceAI architecture was retrained (CI-SpliceAI). Predictive performance on a newly curated dataset of 1,316 functionally validated variants from the literature was compared with the original SpliceAI, alongside MMSplice, MaxEntScan, and SQUIRLS. Both SpliceAI algorithms outperformed the other methods, with the original SpliceAI achieving an accuracy of ∼91%, and CI-SpliceAI showing an improvement at ∼92% overall. Predictive accuracy increased in the majority of curated variants. <h4>Conclusions</h4> We show that including only manually annotated alternatively spliced sites in training data improves prediction of clinically relevant variants, and highlight avenues for further performance improvements.https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9165884/?tool=EBI |
| spellingShingle | Yaron Strauch Jenny Lord Mahesan Niranjan Diana Baralle CI-SpliceAI—Improving machine learning predictions of disease causing splicing variants using curated alternative splice sites PLoS ONE |
| title | CI-SpliceAI—Improving machine learning predictions of disease causing splicing variants using curated alternative splice sites |
| title_full | CI-SpliceAI—Improving machine learning predictions of disease causing splicing variants using curated alternative splice sites |
| title_fullStr | CI-SpliceAI—Improving machine learning predictions of disease causing splicing variants using curated alternative splice sites |
| title_full_unstemmed | CI-SpliceAI—Improving machine learning predictions of disease causing splicing variants using curated alternative splice sites |
| title_short | CI-SpliceAI—Improving machine learning predictions of disease causing splicing variants using curated alternative splice sites |
| title_sort | ci spliceai improving machine learning predictions of disease causing splicing variants using curated alternative splice sites |
| url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9165884/?tool=EBI |
| work_keys_str_mv | AT yaronstrauch cispliceaiimprovingmachinelearningpredictionsofdiseasecausingsplicingvariantsusingcuratedalternativesplicesites AT jennylord cispliceaiimprovingmachinelearningpredictionsofdiseasecausingsplicingvariantsusingcuratedalternativesplicesites AT mahesanniranjan cispliceaiimprovingmachinelearningpredictionsofdiseasecausingsplicingvariantsusingcuratedalternativesplicesites AT dianabaralle cispliceaiimprovingmachinelearningpredictionsofdiseasecausingsplicingvariantsusingcuratedalternativesplicesites |