Literature DB >> 35157015

EMBER: Multi-label prediction of kinase-substrate phosphorylation events through deep learning.

Kathryn E Kirchoff1, Shawn M Gomez2,3.   

Abstract

MOTIVATION: Kinase-catalyzed phosphorylation of proteins forms the backbone of signal transduction within the cell, enabling the coordination of numerous processes such as the cell cycle, apoptosis, and differentiation. While on the order of 105 phosphorylation events have been described, we know the specific kinase performing these functions for less than 5% of cases. The ability to predict which kinases initiate specific individual phosphorylation events has the potential to greatly enhance the design of downstream experimental studies, while simultaneously creating a preliminary map of the broader phosphorylation network that controls cellular signaling.
RESULTS: We describe EMBER, a deep learning method that integrates kinase-phylogeny information and motif-dissimilarity information into a multi-label classification model for the prediction of kinase-motif phosphorylation events. Unlike previous deep learning methods that perform single-label classification, we restate the task of kinase-motif phosphorylation prediction as a multi-label problem, allowing us to train a single unified model rather than a separate model for each of the 134 kinase families. We utilize a Siamese network to generate novel vector representations, or an embedding, of motif sequences, and we compare our novel embedding to a previously proposed peptide embedding. Our motif vector representations are used, along with one-hot encoded motif sequences, as input to a classification network while also leveraging kinase phylogenetic relationships into our model via a kinase phylogeny-weighted loss function. Results suggest that this approach holds significant promise for improving our map of phosphorylation relations that underlie kinome signaling. AVAILABILITY: https://github.com/gomezlab/EMBER. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
© The Author(s) 2022. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

Entities:  

Year:  2022        PMID: 35157015      PMCID: PMC9004653          DOI: 10.1093/bioinformatics/btac083

Source DB:  PubMed          Journal:  Bioinformatics        ISSN: 1367-4803            Impact factor:   6.937


  22 in total

Review 1.  The protein kinase complement of the human genome.

Authors:  G Manning; D B Whyte; R Martinez; T Hunter; S Sudarsanam
Journal:  Science       Date:  2002-12-06       Impact factor: 47.728

2.  PhosphoNetworks: a database for human phosphorylation networks.

Authors:  Jianfei Hu; Hee-Sool Rho; Robert H Newman; Jin Zhang; Heng Zhu; Jiang Qian
Journal:  Bioinformatics       Date:  2013-11-13       Impact factor: 6.937

3.  Using support vector machines to identify protein phosphorylation sites in viruses.

Authors:  Shu-Yun Huang; Shao-Ping Shi; Jian-Ding Qiu; Ming-Chu Liu
Journal:  J Mol Graph Model       Date:  2014-12-24       Impact factor: 2.518

Review 4.  Illuminating the dark phosphoproteome.

Authors:  Elise J Needham; Benjamin L Parker; Timur Burykin; David E James; Sean J Humphrey
Journal:  Sci Signal       Date:  2019-01-22       Impact factor: 8.192

5.  Prediction of protein kinase-specific phosphorylation sites in hierarchical structure using functional information and random forest.

Authors:  Wenwen Fan; Xiaoyi Xu; Yi Shen; Huanqing Feng; Ao Li; Minghui Wang
Journal:  Amino Acids       Date:  2014-01-23       Impact factor: 3.520

6.  Phospho.ELM: a database of phosphorylation sites--update 2011.

Authors:  Holger Dinkel; Claudia Chica; Allegra Via; Cathryn M Gould; Lars J Jensen; Toby J Gibson; Francesca Diella
Journal:  Nucleic Acids Res       Date:  2010-11-09       Impact factor: 16.971

Review 7.  Pathogenic and Therapeutic Relevance of JAK/STAT Signaling in Systemic Lupus Erythematosus: Integration of Distinct Inflammatory Pathways and the Prospect of Their Inhibition with an Oral Agent.

Authors:  Alessia Alunno; Ivan Padjen; Antonis Fanouriakis; Dimitrios T Boumpas
Journal:  Cells       Date:  2019-08-15       Impact factor: 6.600

8.  Integrative biology approach identifies cytokine targeting strategies for psoriasis.

Authors:  Gayathri K Perera; Chrysanthi Ainali; Ekaterina Semenova; Christian Hundhausen; Guillermo Barinaga; Deepika Kassen; Andrew E Williams; Muddassar M Mirza; Mercedesz Balazs; Xiaoting Wang; Robert Sanchez Rodriguez; Andrej Alendar; Jonathan Barker; Sophia Tsoka; Wenjun Ouyang; Frank O Nestle
Journal:  Sci Transl Med       Date:  2014-02-12       Impact factor: 17.956

9.  Continuous Distributed Representation of Biological Sequences for Deep Proteomics and Genomics.

Authors:  Ehsaneddin Asgari; Mohammad R K Mofrad
Journal:  PLoS One       Date:  2015-11-10       Impact factor: 3.240

10.  Proteomic analysis defines kinase taxonomies specific for subtypes of breast cancer.

Authors:  Kyla A L Collins; Timothy J Stuhlmiller; Jon S Zawistowski; Michael P East; Trang T Pham; Claire R Hall; Daniel R Goulet; Samantha M Bevill; Steven P Angus; Sara H Velarde; Noah Sciaky; Tudor I Oprea; Lee M Graves; Gary L Johnson; Shawn M Gomez
Journal:  Oncotarget       Date:  2018-01-29
View more
  1 in total

Review 1.  Mini-review: Recent advances in post-translational modification site prediction based on deep learning.

Authors:  Lingkuan Meng; Wai-Sum Chan; Lei Huang; Linjing Liu; Xingjian Chen; Weitong Zhang; Fuzhou Wang; Ke Cheng; Hongyan Sun; Ka-Chun Wong
Journal:  Comput Struct Biotechnol J       Date:  2022-06-30       Impact factor: 6.155

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.