Machine learning methods for prediction of CDK-inhibitors
Jayashree Ramana1, Dinesh Gupta
1Structural and Computational Biology Group, International Centre for Genetic Engineering and Biotechnology, New Delhi, India.
Abstract:
Progression through the cell cycle involves the coordinated activities of a suite of cyclin/cyclin-dependent kinase (CDK) complexes. The activities of the complexes are regulated by CDK inhibitors (CDKIs). Apart from its role as cell cycle regulators, CDKIs are involved in apoptosis, transcriptional regulation, cell fate determination, cell migration and cytoskeletal dynamics. As the complexes perform crucial and diverse functions, these are important drug targets for tumour and stem cell therapeutic interventions. However, CDKIs are represented by proteins with considerable sequence heterogeneity and may fail to be identified by simple similarity search methods. In this work we have evaluated and developed machine learning methods for identification of CDKIs. We used different compositional features and evolutionary information in the form of PSSMs, from CDKIs and non-CDKIs for generating SVM and ANN classifiers. In the first stage, both the ANN and SVM models were evaluated using Leave-One-Out Cross-Validation and in the second stage these were tested on independent data sets. The PSSM-based SVM model emerged as the best classifier in both the stages and is publicly available through a user-friendly web interface at http://bioinfo.icgeb.res.in/cdkipred.
Insights
Cyclin-dependent kinase inhibitors (CDKIs) regulate cell cycles and have diverse functions. A new PSSM-based SVM machine learning model accurately identifies CDKIs, offering a valuable tool for cancer and stem cell research.
Area of Science:
- Molecular Biology
- Biochemistry
- Computational Biology
Background:
- Cell cycle progression relies on cyclin/cyclin-dependent kinase (CDK) complexes, regulated by CDK inhibitors (CDKIs).
- CDKIs play critical roles beyond cell cycle regulation, including apoptosis, transcriptional regulation, cell fate, migration, and cytoskeletal dynamics.
- These diverse functions make CDKIs significant therapeutic targets for cancer and stem cell interventions.
Purpose of the Study:
- To develop and evaluate machine learning methods for accurate identification of CDKIs.
- To address the challenge of sequence heterogeneity in CDKIs that hinders traditional identification methods.
Main Methods:
- Utilized Support Vector Machine (SVM) and Artificial Neural Network (ANN) classifiers.
- Incorporated compositional features and Position-Specific Scoring Matrices (PSSMs) derived from CDKIs and non-CDKIs.
- Evaluated models using Leave-One-Out Cross-Validation and independent datasets.
Main Results:
- The PSSM-based SVM model demonstrated superior performance as a classifier in both evaluation stages.
- The developed model effectively identifies CDKIs despite their sequence heterogeneity.
Conclusions:
- Machine learning, particularly PSSM-based SVM, offers a robust approach for identifying CDKIs.
- A user-friendly web interface (http://bioinfo.icgeb.res.in/cdkipred) is available for public use, facilitating CDKIs identification in research.
Related Concept Videos
02:34Inhibition of Cdk Activity
02:34Inhibition of CDK Activity
02:15M-Cdk Drives Transition Into Mitosis
Cyclin-dependent kinases, or Cdks, work in concert with cyclins to control cell cycle transitions. M-Cdk, a complex of Cdk1 bound to M cyclin, is a well-known example of this coordinated control that drives the transition from the G2 to the M phase.
M cyclin...
02:39Positive Regulator Molecules