1
|
Zhang Y, Yao L, Chung CR, Huang Y, Li S, Zhang W, Pang Y, Lee TY. KinPred-RNA-kinase activity inference and cancer type classification using machine learning on RNA-seq data. iScience 2024; 27:109333. [PMID: 38523792 PMCID: PMC10959666 DOI: 10.1016/j.isci.2024.109333] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/26/2023] [Revised: 12/07/2023] [Accepted: 02/21/2024] [Indexed: 03/26/2024] Open
Abstract
Kinases as important enzymes can transfer phosphate groups from high-energy and phosphate-donating molecules to specific substrates and play essential roles in various cellular processes. Existing algorithms for kinase activity from phosphorylated proteomics data are often costly, requiring valuable samples. Moreover, methods to extract kinase activities from bulk RNA sequencing data remain undeveloped. In this study, we propose a computational framework KinPred-RNA to derive kinase activities from bulk RNA-sequencing data in cancer samples. KinPred-RNA framework, using the extreme gradient boosting (XGBoost) regression model, outperforms random forest regression, multiple linear regression, and support vector machine regression models in predicting kinase activities from cancer-related RNA sequencing data. Efficient gene signatures from the LINCS-L1000 dataset were used as inputs for KinPred-RNA. The results highlight its potential to be related to biological function. In conclusion, KinPred RNA constitutes a significant advance in cancer research by potentially facilitating the identification of cancer.
Collapse
Affiliation(s)
- Yuntian Zhang
- Warshel Institute for Computational Biology, The Chinese University of Hong Kong, Shenzhen 518172, China
- School of Medicine, The Chinese University of Hong Kong, Shenzhen 518172, China
| | - Lantian Yao
- School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen 518172, China
- Kobilka Institute of Innovative Drug Discovery, School of Medicine, The Chinese University of Hong Kong, Shenzhen 518172, China
| | - Chia-Ru Chung
- Department of Computer Science and Information Engineering, National Central University, Taoyuan 320953, Taiwan
| | - Yixian Huang
- Warshel Institute for Computational Biology, The Chinese University of Hong Kong, Shenzhen 518172, China
- School of Medicine, The Chinese University of Hong Kong, Shenzhen 518172, China
| | - Shangfu Li
- Warshel Institute for Computational Biology, The Chinese University of Hong Kong, Shenzhen 518172, China
| | - Wenyang Zhang
- School of Medicine, The Chinese University of Hong Kong, Shenzhen 518172, China
| | - Yuxuan Pang
- Division of Health Medical Intelligence, Human Genome Center, The Institute of Medical Science, The University of Tokyo, Minato-ku, Tokyo, Japan
| | - Tzong-Yi Lee
- Institute of Bioinformatics and Systems Biology, National Yang Ming Chiao Tung University, Hsinchu 300093, Taiwan
- Center for Intelligent Drug Systems and Smart Bio-devices (IDSB), National Yang Ming Chiao Tung University, Hsinchu 300093, Taiwan
| |
Collapse
|
2
|
Gomez SM, Axtman AD, Willson TM, Major MB, Townsend RR, Sorger PK, Johnson GL. Illuminating function of the understudied druggable kinome. Drug Discov Today 2024; 29:103881. [PMID: 38218213 DOI: 10.1016/j.drudis.2024.103881] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/01/2023] [Revised: 12/21/2023] [Accepted: 01/09/2024] [Indexed: 01/15/2024]
Abstract
The human kinome, with more than 500 proteins, is crucial for cell signaling and disease. Yet, about one-third of kinases lack in-depth study. The Data and Resource Generating Center for Understudied Kinases has developed multiple resources to address this challenge including creation of a heavy amino acid peptide library for parallel reaction monitoring and quantitation of protein kinase expression, use of understudied kinases tagged with a miniTurbo-biotin ligase to determine interaction networks by proximity-dependent protein biotinylation, NanoBRET probe development for screening chemical tool target specificity in live cells, characterization of small molecule chemical tools inhibiting understudied kinases, and computational tools for defining kinome architecture. These resources are available through the Dark Kinase Knowledgebase, supporting further research into these understudied protein kinases.
Collapse
Affiliation(s)
- Shawn M Gomez
- University of North Carolina School of Medicine, Chapel Hill, NC, USA.
| | - Alison D Axtman
- University of North Carolina School of Medicine, Chapel Hill, NC, USA
| | - Timothy M Willson
- University of North Carolina School of Medicine, Chapel Hill, NC, USA
| | - Michael B Major
- Washington University School of Medicine in St. Louis, MO, USA
| | - Reid R Townsend
- Washington University School of Medicine in St. Louis, MO, USA
| | | | - Gary L Johnson
- University of North Carolina School of Medicine, Chapel Hill, NC, USA.
| |
Collapse
|
3
|
Taujale R, Gravel N, Zhou Z, Yeung W, Kochut K, Kannan N. Informatic challenges and advances in illuminating the druggable proteome. Drug Discov Today 2024; 29:103894. [PMID: 38266979 DOI: 10.1016/j.drudis.2024.103894] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/15/2023] [Revised: 01/08/2024] [Accepted: 01/17/2024] [Indexed: 01/26/2024]
Abstract
The understudied members of the druggable proteomes offer promising prospects for drug discovery efforts. While large-scale initiatives have generated valuable functional information on understudied members of the druggable gene families, translating this information into actionable knowledge for drug discovery requires specialized informatics tools and resources. Here, we review the unique informatics challenges and advances in annotating understudied members of the druggable proteome. We demonstrate the application of statistical evolutionary inference tools, knowledge graph mining approaches, and protein language models in illuminating understudied protein kinases, pseudokinases, and ion channels.
Collapse
Affiliation(s)
- Rahil Taujale
- Department of Biochemistry and Molecular Biology, University of Georgia, Athens, GA, USA
| | - Nathan Gravel
- Institute of Bioinformatics, University of Georgia, Athens, GA, USA
| | | | - Wayland Yeung
- Institute of Bioinformatics, University of Georgia, Athens, GA, USA
| | - Krystof Kochut
- School of Computing, University of Georgia, Athens, GA, USA
| | - Natarajan Kannan
- Department of Biochemistry and Molecular Biology, University of Georgia, Athens, GA, USA; Institute of Bioinformatics, University of Georgia, Athens, GA, USA.
| |
Collapse
|
4
|
Zhou Z, Yeung W, Soleymani S, Gravel N, Salcedo M, Li S, Kannan N. Using explainable machine learning to uncover the kinase-substrate interaction landscape. Bioinformatics 2024; 40:btae033. [PMID: 38244571 PMCID: PMC10868336 DOI: 10.1093/bioinformatics/btae033] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/27/2023] [Revised: 12/09/2023] [Accepted: 01/17/2024] [Indexed: 01/22/2024] Open
Abstract
MOTIVATION Phosphorylation, a post-translational modification regulated by protein kinase enzymes, plays an essential role in almost all cellular processes. Understanding how each of the nearly 500 human protein kinases selectively phosphorylates their substrates is a foundational challenge in bioinformatics and cell signaling. Although deep learning models have been a popular means to predict kinase-substrate relationships, existing models often lack interpretability and are trained on datasets skewed toward a subset of well-studied kinases. RESULTS Here we leverage recent peptide library datasets generated to determine substrate specificity profiles of 300 serine/threonine kinases to develop an explainable Transformer model for kinase-peptide interaction prediction. The model, trained solely on primary sequences, achieved state-of-the-art performance. Its unique multitask learning paradigm built within the model enables predictions on virtually any kinase-peptide pair, including predictions on 139 kinases not used in peptide library screens. Furthermore, we employed explainable machine learning methods to elucidate the model's inner workings. Through analysis of learned embeddings at different training stages, we demonstrate that the model employs a unique strategy of substrate prediction considering both substrate motif patterns and kinase evolutionary features. SHapley Additive exPlanation (SHAP) analysis reveals key specificity determining residues in the peptide sequence. Finally, we provide a web interface for predicting kinase-substrate associations for user-defined sequences and a resource for visualizing the learned kinase-substrate associations. AVAILABILITY AND IMPLEMENTATION All code and data are available at https://github.com/esbgkannan/Phosformer-ST. Web server is available at https://phosformer.netlify.app.
Collapse
Affiliation(s)
- Zhongliang Zhou
- School of Computing, University of Georgia, Athens, GA 30602, United States
| | - Wayland Yeung
- Institute of Bioinformatics, University of Georgia, Athens, GA 30602, United States
| | - Saber Soleymani
- School of Computing, University of Georgia, Athens, GA 30602, United States
| | - Nathan Gravel
- Institute of Bioinformatics, University of Georgia, Athens, GA 30602, United States
| | - Mariah Salcedo
- Department of Biochemistry and Molecular Biology, University of Georgia, Athens, GA 30602, United States
| | - Sheng Li
- School of Data Science, University of Virginia, Charlottesville, VA 22903, United States
| | - Natarajan Kannan
- Institute of Bioinformatics, University of Georgia, Athens, GA 30602, United States
- Department of Biochemistry and Molecular Biology, University of Georgia, Athens, GA 30602, United States
| |
Collapse
|
5
|
Varshney N, Mishra AK. Deep Learning in Phosphoproteomics: Methods and Application in Cancer Drug Discovery. Proteomes 2023; 11:proteomes11020016. [PMID: 37218921 DOI: 10.3390/proteomes11020016] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/13/2023] [Revised: 04/24/2023] [Accepted: 04/25/2023] [Indexed: 05/24/2023] Open
Abstract
Protein phosphorylation is a key post-translational modification (PTM) that is a central regulatory mechanism of many cellular signaling pathways. Several protein kinases and phosphatases precisely control this biochemical process. Defects in the functions of these proteins have been implicated in many diseases, including cancer. Mass spectrometry (MS)-based analysis of biological samples provides in-depth coverage of phosphoproteome. A large amount of MS data available in public repositories has unveiled big data in the field of phosphoproteomics. To address the challenges associated with handling large data and expanding confidence in phosphorylation site prediction, the development of many computational algorithms and machine learning-based approaches have gained momentum in recent years. Together, the emergence of experimental methods with high resolution and sensitivity and data mining algorithms has provided robust analytical platforms for quantitative proteomics. In this review, we compile a comprehensive collection of bioinformatic resources used for the prediction of phosphorylation sites, and their potential therapeutic applications in the context of cancer.
Collapse
Affiliation(s)
- Neha Varshney
- Division of Biological Sciences, Department of Cellular and Molecular Medicine, University of California, San Diego, CA 93093, USA
- Ludwig Institute for Cancer Research, La Jolla, CA 92093, USA
| | - Abhinava K Mishra
- Molecular, Cellular and Developmental Biology Department, University of California, Santa Barbara, CA 93106, USA
| |
Collapse
|
6
|
Zhou Z, Yeung W, Gravel N, Salcedo M, Soleymani S, Li S, Kannan N. Phosformer: an explainable transformer model for protein kinase-specific phosphorylation predictions. Bioinformatics 2023; 39:7000331. [PMID: 36692152 PMCID: PMC9900213 DOI: 10.1093/bioinformatics/btad046] [Citation(s) in RCA: 6] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/12/2022] [Revised: 01/16/2023] [Accepted: 01/23/2023] [Indexed: 01/25/2023] Open
Abstract
MOTIVATION The human genome encodes over 500 distinct protein kinases which regulate nearly all cellular processes by the specific phosphorylation of protein substrates. While advances in mass spectrometry and proteomics studies have identified thousands of phosphorylation sites across species, information on the specific kinases that phosphorylate these sites is currently lacking for the vast majority of phosphosites. Recently, there has been a major focus on the development of computational models for predicting kinase-substrate associations. However, most current models only allow predictions on a subset of well-studied kinases. Furthermore, the utilization of hand-curated features and imbalances in training and testing datasets pose unique challenges in the development of accurate predictive models for kinase-specific phosphorylation prediction. Motivated by the recent development of universal protein language models which automatically generate context-aware features from primary sequence information, we sought to develop a unified framework for kinase-specific phosphosite prediction, allowing for greater investigative utility and enabling substrate predictions at the whole kinome level. RESULTS We present a deep learning model for kinase-specific phosphosite prediction, termed Phosformer, which predicts the probability of phosphorylation given an arbitrary pair of unaligned kinase and substrate peptide sequences. We demonstrate that Phosformer implicitly learns evolutionary and functional features during training, removing the need for feature curation and engineering. Further analyses reveal that Phosformer also learns substrate specificity motifs and is able to distinguish between functionally distinct kinase families. Benchmarks indicate that Phosformer exhibits significant improvements compared to the state-of-the-art models, while also presenting a more generalized, unified, and interpretable predictive framework. AVAILABILITY AND IMPLEMENTATION Code and data are available at https://github.com/esbgkannan/phosformer. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
| | | | - Nathan Gravel
- Institute of Bioinformatics, University of Georgia, GA 30602, USA
| | - Mariah Salcedo
- Department of Biochemistry and Molecular Biology, University of Georgia, GA 30602, USA
| | | | - Sheng Li
- To whom correspondence should be addressed. or
| | | |
Collapse
|
7
|
Mini-review: Recent advances in post-translational modification site prediction based on deep learning. Comput Struct Biotechnol J 2022; 20:3522-3532. [PMID: 35860402 PMCID: PMC9284371 DOI: 10.1016/j.csbj.2022.06.045] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/11/2022] [Revised: 06/21/2022] [Accepted: 06/21/2022] [Indexed: 11/23/2022] Open
Abstract
Post-translational modifications (PTMs) are closely linked to numerous diseases, playing a significant role in regulating protein structures, activities, and functions. Therefore, the identification of PTMs is crucial for understanding the mechanisms of cell biology and diseases therapy. Compared to traditional machine learning methods, the deep learning approaches for PTM prediction provide accurate and rapid screening, guiding the downstream wet experiments to leverage the screened information for focused studies. In this paper, we reviewed the recent works in deep learning to identify phosphorylation, acetylation, ubiquitination, and other PTM types. In addition, we summarized PTM databases and discussed future directions with critical insights.
Collapse
Key Words
- AAindex, Amino acid index
- ATP, Adenosine triphosphate
- AUC, Area under curve
- Ac, Acetylation
- BE, Binary encoding
- BLOSUM, Blocks substitution matrix
- Bi-LSTM, Bidirectional LSTM
- CKSAAP, Composition of k-spaced amino acid Pairs
- CNN, Convolutional neural network
- CNNOH, CNN with the one-hot encoding
- CNNWE, CNN with the word-embedding encoding
- CNNrgb, CNN red green blue
- CV, Cross-validation
- DC-CNN, Densely connected convolutional neural network
- DL, Deep learning
- DNNs, Deep neural networks
- Deep learning
- E. coli, Escherichia coli
- EBGW, Encoding based on grouped weight
- EGAAC, Enhanced grouped amino acids content
- IG, Information gain
- K, Lysine
- KNN, k nearest neighbor
- LASSO, Least absolute shrinkage and selection operator
- LSTM, Long short-term memory
- LSTMWE, LSTM with the word-embedding encoding
- M.musculus, Mus musculus
- MDC, Modular densely connected convolutional networks
- MDCAN, Multilane dense convolutional attention network
- ML, Machine learning
- MLP, Multilayer perceptron
- MMI, Multivariate mutual information
- Machine learning
- Mass spectrometry
- NMBroto, Normalized Moreau-Broto autocorrelation
- P, Proline
- PSP, PhosphoSitePlus
- PSSM, Position-specific scoring matrix
- PTM, Post-translational modifications
- Ph, Phosphorylation
- Post-translational modification
- Prediction
- PseAAC, Pseudo-amino acid composition
- R, Arginine
- RF, Random forest
- RNN, Recurrent neural network
- ROC, Receiver operating characteristic
- S, Serine
- S. typhimurium, Salmonella typhimurium
- S.cerevisiae, Saccharomyces cerevisiae
- SE, Squeeze and excitation
- SEV, Split to Equal Validation
- ST, Source and target
- SUMO, Small ubiquitin-like modifier
- SVM, Support vector machines
- T, Threonine
- Ub, Ubiquitination
- Y, Tyrosine
- ZSL, Zero-shot learning
Collapse
|