ISSEC: inferring contacts among protein secondary structure elements using deep object detection
Abstract Background The formation of contacts among protein secondary structure elements (SSEs) is an important step in protein folding as it determines topology of protein tertiary structure; hence, inferring inter-SSE contacts is crucial to protein structure prediction. One of the existing strateg...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2020-11-01
|
| Series: | BMC Bioinformatics |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12859-020-03793-y |
| _version_ | 1819212916764704768 |
|---|---|
| author | Qi Zhang Jianwei Zhu Fusong Ju Lupeng Kong Shiwei Sun Wei-Mou Zheng Dongbo Bu |
| author_facet | Qi Zhang Jianwei Zhu Fusong Ju Lupeng Kong Shiwei Sun Wei-Mou Zheng Dongbo Bu |
| author_sort | Qi Zhang |
| collection | DOAJ |
| description | Abstract Background The formation of contacts among protein secondary structure elements (SSEs) is an important step in protein folding as it determines topology of protein tertiary structure; hence, inferring inter-SSE contacts is crucial to protein structure prediction. One of the existing strategies infers inter-SSE contacts directly from the predicted possibilities of inter-residue contacts without any preprocessing, and thus suffers from the excessive noises existing in the predicted inter-residue contacts. Another strategy defines SSEs based on protein secondary structure prediction first, and then judges whether each candidate SSE pair could form contact or not. However, it is difficult to accurately determine boundary of SSEs due to the errors in secondary structure prediction. The incorrectly-deduced SSEs definitely hinder subsequent prediction of the contacts among them. Results We here report an accurate approach to infer the inter-SSE contacts (thus called as ISSEC) using the deep object detection technique. The design of ISSEC is based on the observation that, in the inter-residue contact map, the contacting SSEs usually form rectangle regions with characteristic patterns. Therefore, ISSEC infers inter-SSE contacts through detecting such rectangle regions. Unlike the existing approach directly using the predicted probabilities of inter-residue contact, ISSEC applies the deep convolution technique to extract high-level features from the inter-residue contacts. More importantly, ISSEC does not rely on the pre-defined SSEs. Instead, ISSEC enumerates multiple candidate rectangle regions in the predicted inter-residue contact map, and for each region, ISSEC calculates a confidence score to measure whether it has characteristic patterns or not. ISSEC employs greedy strategy to select non-overlapping regions with high confidence score, and finally infers inter-SSE contacts according to these regions. Conclusions Comprehensive experimental results suggested that ISSEC outperformed the state-of-the-art approaches in predicting inter-SSE contacts. We further demonstrated the successful applications of ISSEC to improve prediction of both inter-residue contacts and tertiary structure as well. |
| first_indexed | 2024-12-23T06:50:34Z |
| format | Article |
| id | doaj.art-b4a31ab8b1724892b4756a4f3d6941dd |
| institution | Directory Open Access Journal |
| issn | 1471-2105 |
| language | English |
| last_indexed | 2024-12-23T06:50:34Z |
| publishDate | 2020-11-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Bioinformatics |
| spelling | doaj.art-b4a31ab8b1724892b4756a4f3d6941dd2022-12-21T17:56:27ZengBMCBMC Bioinformatics1471-21052020-11-0121111310.1186/s12859-020-03793-yISSEC: inferring contacts among protein secondary structure elements using deep object detectionQi Zhang0Jianwei Zhu1Fusong Ju2Lupeng Kong3Shiwei Sun4Wei-Mou Zheng5Dongbo Bu6Key Lab of Intelligent Information Processing, Big Data Academy, Institute of Computing Technology, Chinese Academy of SciencesKey Lab of Intelligent Information Processing, Big Data Academy, Institute of Computing Technology, Chinese Academy of SciencesKey Lab of Intelligent Information Processing, Big Data Academy, Institute of Computing Technology, Chinese Academy of SciencesKey Lab of Intelligent Information Processing, Big Data Academy, Institute of Computing Technology, Chinese Academy of SciencesKey Lab of Intelligent Information Processing, Big Data Academy, Institute of Computing Technology, Chinese Academy of SciencesInstitute of Theoretical Physics, Chinese Academy of SciencesKey Lab of Intelligent Information Processing, Big Data Academy, Institute of Computing Technology, Chinese Academy of SciencesAbstract Background The formation of contacts among protein secondary structure elements (SSEs) is an important step in protein folding as it determines topology of protein tertiary structure; hence, inferring inter-SSE contacts is crucial to protein structure prediction. One of the existing strategies infers inter-SSE contacts directly from the predicted possibilities of inter-residue contacts without any preprocessing, and thus suffers from the excessive noises existing in the predicted inter-residue contacts. Another strategy defines SSEs based on protein secondary structure prediction first, and then judges whether each candidate SSE pair could form contact or not. However, it is difficult to accurately determine boundary of SSEs due to the errors in secondary structure prediction. The incorrectly-deduced SSEs definitely hinder subsequent prediction of the contacts among them. Results We here report an accurate approach to infer the inter-SSE contacts (thus called as ISSEC) using the deep object detection technique. The design of ISSEC is based on the observation that, in the inter-residue contact map, the contacting SSEs usually form rectangle regions with characteristic patterns. Therefore, ISSEC infers inter-SSE contacts through detecting such rectangle regions. Unlike the existing approach directly using the predicted probabilities of inter-residue contact, ISSEC applies the deep convolution technique to extract high-level features from the inter-residue contacts. More importantly, ISSEC does not rely on the pre-defined SSEs. Instead, ISSEC enumerates multiple candidate rectangle regions in the predicted inter-residue contact map, and for each region, ISSEC calculates a confidence score to measure whether it has characteristic patterns or not. ISSEC employs greedy strategy to select non-overlapping regions with high confidence score, and finally infers inter-SSE contacts according to these regions. Conclusions Comprehensive experimental results suggested that ISSEC outperformed the state-of-the-art approaches in predicting inter-SSE contacts. We further demonstrated the successful applications of ISSEC to improve prediction of both inter-residue contacts and tertiary structure as well.http://link.springer.com/article/10.1186/s12859-020-03793-yProtein structureSecondary structure elementsInter-SSE contacts |
| spellingShingle | Qi Zhang Jianwei Zhu Fusong Ju Lupeng Kong Shiwei Sun Wei-Mou Zheng Dongbo Bu ISSEC: inferring contacts among protein secondary structure elements using deep object detection BMC Bioinformatics Protein structure Secondary structure elements Inter-SSE contacts |
| title | ISSEC: inferring contacts among protein secondary structure elements using deep object detection |
| title_full | ISSEC: inferring contacts among protein secondary structure elements using deep object detection |
| title_fullStr | ISSEC: inferring contacts among protein secondary structure elements using deep object detection |
| title_full_unstemmed | ISSEC: inferring contacts among protein secondary structure elements using deep object detection |
| title_short | ISSEC: inferring contacts among protein secondary structure elements using deep object detection |
| title_sort | issec inferring contacts among protein secondary structure elements using deep object detection |
| topic | Protein structure Secondary structure elements Inter-SSE contacts |
| url | http://link.springer.com/article/10.1186/s12859-020-03793-y |
| work_keys_str_mv | AT qizhang issecinferringcontactsamongproteinsecondarystructureelementsusingdeepobjectdetection AT jianweizhu issecinferringcontactsamongproteinsecondarystructureelementsusingdeepobjectdetection AT fusongju issecinferringcontactsamongproteinsecondarystructureelementsusingdeepobjectdetection AT lupengkong issecinferringcontactsamongproteinsecondarystructureelementsusingdeepobjectdetection AT shiweisun issecinferringcontactsamongproteinsecondarystructureelementsusingdeepobjectdetection AT weimouzheng issecinferringcontactsamongproteinsecondarystructureelementsusingdeepobjectdetection AT dongbobu issecinferringcontactsamongproteinsecondarystructureelementsusingdeepobjectdetection |