DenSec: Secreted Protein Prediction in Cerebrospinal Fluid Based on DenseNet and Transformer
Cerebrospinal fluid (CSF) exists in the surrounding spaces of mammalian central nervous systems (CNS); therefore, there are numerous potential protein biomarkers associated with CNS disease in CSF. Currently, approximately 4300 proteins have been identified in CSF by protein profiling. However, due...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/10/14/2490 |
| _version_ | 1797417157565349888 |
|---|---|
| author | Lan Huang Yanli Qu Kai He Yan Wang Dan Shao |
| author_facet | Lan Huang Yanli Qu Kai He Yan Wang Dan Shao |
| author_sort | Lan Huang |
| collection | DOAJ |
| description | Cerebrospinal fluid (CSF) exists in the surrounding spaces of mammalian central nervous systems (CNS); therefore, there are numerous potential protein biomarkers associated with CNS disease in CSF. Currently, approximately 4300 proteins have been identified in CSF by protein profiling. However, due to the diverse modifications, as well as the existing technical limits, large-scale protein identification in CSF is still considered a challenge. Inspired by computational methods, this paper proposes a deep learning framework, named DenSec, for secreted protein prediction in CSF. In the first phase of DenSec, all input proteins are encoded as a matrix with a fixed size of 1000 × 20 by calculating a position-specific score matrix (PSSM) of protein sequences. In the second phase, a dense convolutional network (DenseNet) is adopted to extract the feature from these PSSMs automatically. After that, Transformer with a fully connected dense layer acts as classifier to perform a binary classification in terms of secretion into CSF or not. According to the experiment results, DenSec achieves a mean accuracy of 86.00% in the test dataset and outperforms the state-of-the-art methods. |
| first_indexed | 2024-03-09T06:15:43Z |
| format | Article |
| id | doaj.art-7d5f0b39206c4dbf90e5857b0fba1972 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-09T06:15:43Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-7d5f0b39206c4dbf90e5857b0fba19722023-12-03T11:53:57ZengMDPI AGMathematics2227-73902022-07-011014249010.3390/math10142490DenSec: Secreted Protein Prediction in Cerebrospinal Fluid Based on DenseNet and TransformerLan Huang0Yanli Qu1Kai He2Yan Wang3Dan Shao4Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education, College of Computer Science and Technology, Jilin University, Changchun 130012, ChinaKey Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education, College of Computer Science and Technology, Jilin University, Changchun 130012, ChinaKey Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education, College of Computer Science and Technology, Jilin University, Changchun 130012, ChinaKey Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education, College of Computer Science and Technology, Jilin University, Changchun 130012, ChinaCollege of Computer Science and Technology, Changchun University, Changchun 130022, ChinaCerebrospinal fluid (CSF) exists in the surrounding spaces of mammalian central nervous systems (CNS); therefore, there are numerous potential protein biomarkers associated with CNS disease in CSF. Currently, approximately 4300 proteins have been identified in CSF by protein profiling. However, due to the diverse modifications, as well as the existing technical limits, large-scale protein identification in CSF is still considered a challenge. Inspired by computational methods, this paper proposes a deep learning framework, named DenSec, for secreted protein prediction in CSF. In the first phase of DenSec, all input proteins are encoded as a matrix with a fixed size of 1000 × 20 by calculating a position-specific score matrix (PSSM) of protein sequences. In the second phase, a dense convolutional network (DenseNet) is adopted to extract the feature from these PSSMs automatically. After that, Transformer with a fully connected dense layer acts as classifier to perform a binary classification in terms of secretion into CSF or not. According to the experiment results, DenSec achieves a mean accuracy of 86.00% in the test dataset and outperforms the state-of-the-art methods.https://www.mdpi.com/2227-7390/10/14/2490cerebrospinal fluidsecreted protein predictionDenseNettransformer |
| spellingShingle | Lan Huang Yanli Qu Kai He Yan Wang Dan Shao DenSec: Secreted Protein Prediction in Cerebrospinal Fluid Based on DenseNet and Transformer Mathematics cerebrospinal fluid secreted protein prediction DenseNet transformer |
| title | DenSec: Secreted Protein Prediction in Cerebrospinal Fluid Based on DenseNet and Transformer |
| title_full | DenSec: Secreted Protein Prediction in Cerebrospinal Fluid Based on DenseNet and Transformer |
| title_fullStr | DenSec: Secreted Protein Prediction in Cerebrospinal Fluid Based on DenseNet and Transformer |
| title_full_unstemmed | DenSec: Secreted Protein Prediction in Cerebrospinal Fluid Based on DenseNet and Transformer |
| title_short | DenSec: Secreted Protein Prediction in Cerebrospinal Fluid Based on DenseNet and Transformer |
| title_sort | densec secreted protein prediction in cerebrospinal fluid based on densenet and transformer |
| topic | cerebrospinal fluid secreted protein prediction DenseNet transformer |
| url | https://www.mdpi.com/2227-7390/10/14/2490 |
| work_keys_str_mv | AT lanhuang densecsecretedproteinpredictionincerebrospinalfluidbasedondensenetandtransformer AT yanliqu densecsecretedproteinpredictionincerebrospinalfluidbasedondensenetandtransformer AT kaihe densecsecretedproteinpredictionincerebrospinalfluidbasedondensenetandtransformer AT yanwang densecsecretedproteinpredictionincerebrospinalfluidbasedondensenetandtransformer AT danshao densecsecretedproteinpredictionincerebrospinalfluidbasedondensenetandtransformer |