SemanticCAP: Chromatin Accessibility Prediction Enhanced by Features Learning from a Language Model
A large number of inorganic and organic compounds are able to bind DNA and form complexes, among which drug-related molecules are important. Chromatin accessibility changes not only directly affect drug–DNA interactions, but they can promote or inhibit the expression of the critical genes associated...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-03-01
|
| Series: | Genes |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4425/13/4/568 |
| _version_ | 1797434632574074880 |
|---|---|
| author | Yikang Zhang Xiaomin Chu Yelu Jiang Hongjie Wu Lijun Quan |
| author_facet | Yikang Zhang Xiaomin Chu Yelu Jiang Hongjie Wu Lijun Quan |
| author_sort | Yikang Zhang |
| collection | DOAJ |
| description | A large number of inorganic and organic compounds are able to bind DNA and form complexes, among which drug-related molecules are important. Chromatin accessibility changes not only directly affect drug–DNA interactions, but they can promote or inhibit the expression of the critical genes associated with drug resistance by affecting the DNA binding capacity of TFs and transcriptional regulators. However, the biological experimental techniques for measuring it are expensive and time-consuming. In recent years, several kinds of computational methods have been proposed to identify accessible regions of the genome. Existing computational models mostly ignore the contextual information provided by the bases in gene sequences. To address these issues, we proposed a new solution called SemanticCAP. It introduces a gene language model that models the context of gene sequences and is thus able to provide an effective representation of a certain site in a gene sequence. Basically, we merged the features provided by the gene language model into our chromatin accessibility model. During the process, we designed methods called SFA and SFC to make feature fusion smoother. Compared to DeepSEA, gkm-SVM, and k-mer using public benchmarks, our model proved to have better performance, showing a 1.25% maximum improvement in auROC and a 2.41% maximum improvement in auPRC. |
| first_indexed | 2024-03-09T10:35:55Z |
| format | Article |
| id | doaj.art-27761d86800044b6bdc79dc686f67841 |
| institution | Directory Open Access Journal |
| issn | 2073-4425 |
| language | English |
| last_indexed | 2024-03-09T10:35:55Z |
| publishDate | 2022-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Genes |
| spelling | doaj.art-27761d86800044b6bdc79dc686f678412023-12-01T20:56:19ZengMDPI AGGenes2073-44252022-03-0113456810.3390/genes13040568SemanticCAP: Chromatin Accessibility Prediction Enhanced by Features Learning from a Language ModelYikang Zhang0Xiaomin Chu1Yelu Jiang2Hongjie Wu3Lijun Quan4School of Computer Science and Technology, Soochow University, Suzhou 215006, ChinaSchool of Computer Science and Technology, Soochow University, Suzhou 215006, ChinaSchool of Computer Science and Technology, Soochow University, Suzhou 215006, ChinaSchool of Electronic and Information Engineering, Suzhou University of Science and Technology, Suzhou 215009, ChinaSchool of Computer Science and Technology, Soochow University, Suzhou 215006, ChinaA large number of inorganic and organic compounds are able to bind DNA and form complexes, among which drug-related molecules are important. Chromatin accessibility changes not only directly affect drug–DNA interactions, but they can promote or inhibit the expression of the critical genes associated with drug resistance by affecting the DNA binding capacity of TFs and transcriptional regulators. However, the biological experimental techniques for measuring it are expensive and time-consuming. In recent years, several kinds of computational methods have been proposed to identify accessible regions of the genome. Existing computational models mostly ignore the contextual information provided by the bases in gene sequences. To address these issues, we proposed a new solution called SemanticCAP. It introduces a gene language model that models the context of gene sequences and is thus able to provide an effective representation of a certain site in a gene sequence. Basically, we merged the features provided by the gene language model into our chromatin accessibility model. During the process, we designed methods called SFA and SFC to make feature fusion smoother. Compared to DeepSEA, gkm-SVM, and k-mer using public benchmarks, our model proved to have better performance, showing a 1.25% maximum improvement in auROC and a 2.41% maximum improvement in auPRC.https://www.mdpi.com/2073-4425/13/4/568chromatin accessibilitydrug designlanguage modeltransformerfeature fusion |
| spellingShingle | Yikang Zhang Xiaomin Chu Yelu Jiang Hongjie Wu Lijun Quan SemanticCAP: Chromatin Accessibility Prediction Enhanced by Features Learning from a Language Model Genes chromatin accessibility drug design language model transformer feature fusion |
| title | SemanticCAP: Chromatin Accessibility Prediction Enhanced by Features Learning from a Language Model |
| title_full | SemanticCAP: Chromatin Accessibility Prediction Enhanced by Features Learning from a Language Model |
| title_fullStr | SemanticCAP: Chromatin Accessibility Prediction Enhanced by Features Learning from a Language Model |
| title_full_unstemmed | SemanticCAP: Chromatin Accessibility Prediction Enhanced by Features Learning from a Language Model |
| title_short | SemanticCAP: Chromatin Accessibility Prediction Enhanced by Features Learning from a Language Model |
| title_sort | semanticcap chromatin accessibility prediction enhanced by features learning from a language model |
| topic | chromatin accessibility drug design language model transformer feature fusion |
| url | https://www.mdpi.com/2073-4425/13/4/568 |
| work_keys_str_mv | AT yikangzhang semanticcapchromatinaccessibilitypredictionenhancedbyfeatureslearningfromalanguagemodel AT xiaominchu semanticcapchromatinaccessibilitypredictionenhancedbyfeatureslearningfromalanguagemodel AT yelujiang semanticcapchromatinaccessibilitypredictionenhancedbyfeatureslearningfromalanguagemodel AT hongjiewu semanticcapchromatinaccessibilitypredictionenhancedbyfeatureslearningfromalanguagemodel AT lijunquan semanticcapchromatinaccessibilitypredictionenhancedbyfeatureslearningfromalanguagemodel |