Related Experiment Video
Updated: Aug 5, 2025
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
Computational method for aromatase-related proteins using machine learning approach
Muthu Krishnan Selvaraj1, Jasmeet Kaur2
1Data Center/Bioinformatics, MTCC, CSIR-Institute of Microbial Technology, Chandigarh, India.
Abstract:
Human aromatase enzyme is a microsomal cytochrome P450 and catalyzes aromatization of androgens into estrogens during steroidogenesis. For breast cancer therapy, third-generation aromatase inhibitors (AIs) have proven to be effective; however patients acquire resistance to current AIs. Thus there is a need to predict aromatase-related proteins to develop efficacious AIs. A machine learning method was established to identify aromatase-related proteins using a five-fold cross validation technique. In this study, different SVM approach-based models were built using the following approaches like amino acid, dipeptide composition, hybrid and evolutionary profiles in the form of position-specific scoring matrix (PSSM); with maximum accuracy of 87.42%, 84.05%, 85.12%, and 92.02% respectively. Based on the primary sequence, the developed method is highly accurate to predict the aromatase-related proteins. Prediction scores graphs were developed using the known dataset to check the performance of the method. Based on the approach described above, a webserver for predicting aromatase-related proteins from primary sequence data was developed and implemented at https://bioinfo.imtech.res.in/servers/muthu/aromatase/home.html. We hope that the developed method will be useful for aromatase protein related research.
Insights
Researchers developed a machine learning model to accurately predict aromatase-related proteins, aiding in the development of new aromatase inhibitors (AIs) for breast cancer therapy and overcoming drug resistance.
Area of Science:
- Biochemistry
- Computational Biology
- Drug Discovery
Background:
- Human aromatase, a cytochrome P450 enzyme, is crucial in steroidogenesis, converting androgens to estrogens.
- Third-generation aromatase inhibitors (AIs) are effective breast cancer treatments, but drug resistance is a significant clinical challenge.
- Predicting aromatase-related proteins is essential for developing novel and more efficacious AIs to combat resistance.
Purpose of the Study:
- To develop a computational method for accurately identifying aromatase-related proteins.
- To create a webserver tool for predicting aromatase-related proteins based on primary sequence data.
- To facilitate research into aromatase protein function and the development of new therapeutic strategies.
Main Methods:
- Machine learning models, specifically Support Vector Machine (SVM) approaches, were employed.
- Models utilized various feature extraction techniques: amino acid composition, dipeptide composition, hybrid profiles, and evolutionary profiles (Position-Specific Scoring Matrix - PSSM).
- A five-fold cross-validation technique was used to assess model performance and accuracy.
Main Results:
- SVM models achieved maximum accuracies of 87.42% (amino acid), 84.05% (dipeptide), 85.12% (hybrid), and 92.02% (PSSM).
- The developed method demonstrated high accuracy in predicting aromatase-related proteins directly from primary sequence data.
- Prediction score graphs were generated using a known dataset to validate the method's performance.
Conclusions:
- The machine learning approach provides a highly accurate and efficient method for predicting aromatase-related proteins.
- A webserver implementing this prediction method is available at https://bioinfo.imtech.res.in/servers/muthu/aromatase/home.html.
- This tool is expected to significantly benefit research focused on aromatase proteins and the development of next-generation aromatase inhibitors.
