Parameterized hypercomplex convolutional network for accurate protein backbone torsion angle prediction
Abstract Predicting the backbone torsion angles corresponding to each residue of a protein from its amino acid sequence alone is a challenging problem in computational biology. Existing torsion angle predictors mainly use profile features, which are generated by performing time-consuming multiple se...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-11-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-77412-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846171984443998208 |
|---|---|
| author | Wei Yang Shujia Wei Lei Zhang |
| author_facet | Wei Yang Shujia Wei Lei Zhang |
| author_sort | Wei Yang |
| collection | DOAJ |
| description | Abstract Predicting the backbone torsion angles corresponding to each residue of a protein from its amino acid sequence alone is a challenging problem in computational biology. Existing torsion angle predictors mainly use profile features, which are generated by performing time-consuming multiple sequence alignments, for torsion angle prediction. Compared with traditional profile features, embedding features from pretrained protein language models have significant advantages in prediction performance and computational speed. However, embedding features usually have higher dimensions and different embedding features have significantly different dimensions. To this end, we design a novel parameter-efficient deep torsion angle predictor, PHAngle, specifically for embedding features. PHAngle is a parameterized hypercomplex convolutional network consisting of parameterized hypercomplex linear and convolutional layers whose weight parameters can be characterized as the sum of Kronecker products. Experimental results on six benchmark test sets including TEST2016, TEST2018, TEST2020_HQ, CASP12, CASP13 and CASP-FM demonstrate that PHAngle achieves the state-of-the-art torsion angle performance with the fewest parameters compared to the nine existing methods. The source code and datasets are available at https://github.com/fengtuan/PHAngle . |
| format | Article |
| id | doaj-art-cb252e49f8924a7aa0f3ba75b1d20147 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-cb252e49f8924a7aa0f3ba75b1d201472024-11-10T12:25:42ZengNature PortfolioScientific Reports2045-23222024-11-0114111310.1038/s41598-024-77412-8Parameterized hypercomplex convolutional network for accurate protein backbone torsion angle predictionWei Yang0Shujia Wei1Lei Zhang2Henan Key Laboratory of Big Data Analysis and Processing, Henan Engineering Laboratory of Spatial Information Processing, School of Computer and Information Engineering, Henan UniversityHenan Key Laboratory of Big Data Analysis and Processing, Henan Engineering Laboratory of Spatial Information Processing, School of Computer and Information Engineering, Henan UniversityHenan Key Laboratory of Big Data Analysis and Processing, Henan Engineering Laboratory of Spatial Information Processing, School of Computer and Information Engineering, Henan UniversityAbstract Predicting the backbone torsion angles corresponding to each residue of a protein from its amino acid sequence alone is a challenging problem in computational biology. Existing torsion angle predictors mainly use profile features, which are generated by performing time-consuming multiple sequence alignments, for torsion angle prediction. Compared with traditional profile features, embedding features from pretrained protein language models have significant advantages in prediction performance and computational speed. However, embedding features usually have higher dimensions and different embedding features have significantly different dimensions. To this end, we design a novel parameter-efficient deep torsion angle predictor, PHAngle, specifically for embedding features. PHAngle is a parameterized hypercomplex convolutional network consisting of parameterized hypercomplex linear and convolutional layers whose weight parameters can be characterized as the sum of Kronecker products. Experimental results on six benchmark test sets including TEST2016, TEST2018, TEST2020_HQ, CASP12, CASP13 and CASP-FM demonstrate that PHAngle achieves the state-of-the-art torsion angle performance with the fewest parameters compared to the nine existing methods. The source code and datasets are available at https://github.com/fengtuan/PHAngle .https://doi.org/10.1038/s41598-024-77412-8Torsion angle predictionParameterized hypercomplex convolutional networkPretrained protein language modelEmbedding feature |
| spellingShingle | Wei Yang Shujia Wei Lei Zhang Parameterized hypercomplex convolutional network for accurate protein backbone torsion angle prediction Scientific Reports Torsion angle prediction Parameterized hypercomplex convolutional network Pretrained protein language model Embedding feature |
| title | Parameterized hypercomplex convolutional network for accurate protein backbone torsion angle prediction |
| title_full | Parameterized hypercomplex convolutional network for accurate protein backbone torsion angle prediction |
| title_fullStr | Parameterized hypercomplex convolutional network for accurate protein backbone torsion angle prediction |
| title_full_unstemmed | Parameterized hypercomplex convolutional network for accurate protein backbone torsion angle prediction |
| title_short | Parameterized hypercomplex convolutional network for accurate protein backbone torsion angle prediction |
| title_sort | parameterized hypercomplex convolutional network for accurate protein backbone torsion angle prediction |
| topic | Torsion angle prediction Parameterized hypercomplex convolutional network Pretrained protein language model Embedding feature |
| url | https://doi.org/10.1038/s41598-024-77412-8 |
| work_keys_str_mv | AT weiyang parameterizedhypercomplexconvolutionalnetworkforaccurateproteinbackbonetorsionangleprediction AT shujiawei parameterizedhypercomplexconvolutionalnetworkforaccurateproteinbackbonetorsionangleprediction AT leizhang parameterizedhypercomplexconvolutionalnetworkforaccurateproteinbackbonetorsionangleprediction |