دورية أكاديمية
DeepPLM_mCNN: An approach for enhancing ion channel and ion transporter recognition by multi-window CNN based on features from pre-trained language models.
العنوان: | DeepPLM_mCNN: An approach for enhancing ion channel and ion transporter recognition by multi-window CNN based on features from pre-trained language models. |
---|---|
المؤلفون: | Le VT; Department of Computer Science and Engineering, Yuan Ze University, Chung-Li, 32003, Taiwan., Malik MS; Department of Computer Science and Engineering, Yuan Ze University, Chung-Li, 32003, Taiwan; Department of Computer Science and Engineering, Karakoram International University, Pakistan., Tseng YH; Department of Computer Science and Engineering, Yuan Ze University, Chung-Li, 32003, Taiwan., Lee YC; Department of Computer Science and Engineering, Yuan Ze University, Chung-Li, 32003, Taiwan., Huang CI; Department of Computer Science and Engineering, Yuan Ze University, Chung-Li, 32003, Taiwan., Ou YY; Department of Computer Science and Engineering, Yuan Ze University, Chung-Li, 32003, Taiwan; Graduate Program in Biomedical Informatics, Yuan Ze University, Chung-Li, 32003, Taiwan. Electronic address: yien@saturn.yzu.edu.tw. |
المصدر: | Computational biology and chemistry [Comput Biol Chem] 2024 Jun; Vol. 110, pp. 108055. Date of Electronic Publication: 2024 Mar 20. |
نوع المنشور: | Journal Article |
اللغة: | English |
بيانات الدورية: | Publisher: Elsevier Country of Publication: England NLM ID: 101157394 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1476-928X (Electronic) Linking ISSN: 14769271 NLM ISO Abbreviation: Comput Biol Chem Subsets: MEDLINE |
أسماء مطبوعة: | Publication: Oxford : Elsevier Original Publication: Oxford : Pergamon, c2003- |
مواضيع طبية MeSH: | Ion Channels*/metabolism , Ion Channels*/chemistry , Neural Networks, Computer*, Deep Learning ; Ion Transport |
مستخلص: | Accurate classification of membrane proteins like ion channels and transporters is critical for elucidating cellular processes and drug development. We present DeepPLM_mCNN, a novel framework combining Pretrained Language Models (PLMs) and multi-window convolutional neural networks (mCNNs) for effective classification of membrane proteins into ion channels and ion transporters. Our approach extracts informative features from protein sequences by utilizing various PLMs, including TAPE, ProtT5_XL_U50, ESM-1b, ESM-2_480, and ESM-2_1280. These PLM-derived features are then input into a mCNN architecture to learn conserved motifs important for classification. When evaluated on ion transporters, our best performing model utilizing ProtT5 achieved 90% sensitivity, 95.8% specificity, and 95.4% overall accuracy. For ion channels, we obtained 88.3% sensitivity, 95.7% specificity, and 95.2% overall accuracy using ESM-1b features. Our proposed DeepPLM_mCNN framework demonstrates significant improvements over previous methods on unseen test data. This study illustrates the potential of combining PLMs and deep learning for accurate computational identification of membrane proteins from sequence data alone. Our findings have important implications for membrane protein research and drug development targeting ion channels and transporters. The data and source codes in this study are publicly available at the following link: https://github.com/s1129108/DeepPLM_mCNN. Competing Interests: Declaration of Competing Interest I, Van The Le, hereby declare that I have no financial interests or relationships with any organizations that could potentially influence the subject matter of this work. I also confirm that I do not hold any professional or personal affiliations that may be perceived as affecting the impartiality and objectivity of my research. I have received no funding, grants, or honoraria related to the research presented in this work. Additionally, I have no personal relationships or collaborations that might pose a conflict of interest. This work is conducted with complete transparency, and I am committed to upholding the highest standards of integrity in my scholarly contributions. (Copyright © 2024 Elsevier Ltd. All rights reserved.) |
فهرسة مساهمة: | Keywords: Convolutional neural networks; Deep learning; Membrane proteins; Multiple windows scanning; Pre-trained language model |
المشرفين على المادة: | 0 (Ion Channels) |
تواريخ الأحداث: | Date Created: 20240331 Date Completed: 20240525 Latest Revision: 20240525 |
رمز التحديث: | 20240526 |
DOI: | 10.1016/j.compbiolchem.2024.108055 |
PMID: | 38555810 |
قاعدة البيانات: | MEDLINE |
كن أول من يترك تعليقا!