PESM
The software tool 'PESM' introduces a method for predicting the essentiality of microRNAs (miRNAs) in complex diseases. Leveraging gradient boosting machines and miRNA sequences, PESM extracts both sequence and structural features of miRNAs to enhance prediction accuracy. Through a 5-fold cross-validation, the method demonstrates superior performance, evaluated by metrics such as the area under the receiver operating characteristic curve (AUC), F-measure, and accuracy (ACC). Comparative analysis with three other methods, including miES, Gaussian Naive Bayes, and Support Vector Machine, confirms PESM's effectiveness, with notable achievements in AUC (0.9117), F-measure (0.8572), and ACC (0.8516).
Topic
Functional, regulatory and non-coding RNA;Gene transcripts;Machine learning;Zoology;Model organisms
Detail
Operation: miRNA target prediction;miRNA expression analysis;Protein feature detection
Software interface: Command-line user interface
Language: Python
License: -
Cost: Free
Version name: -
Credit: National Natural Science Foundation of China, Hunan Provinvial Science and Technology Program.
Input: -
Output: -
Contact: Guihua Duan duangh@csu.edu.cn
Collection: -
Maturity: -
Publications
- PESM: predicting the essentiality of miRNAs based on gradient boosting machines and sequences.
- Yan C, et al. PESM: predicting the essentiality of miRNAs based on gradient boosting machines and sequences. PESM: predicting the essentiality of miRNAs based on gradient boosting machines and sequences. 2020; 21:111. doi: 10.1186/s12859-020-3426-9
- https://doi.org/10.1186/S12859-020-3426-9
- PMID: 32183740
- PMC: PMC7079416
Download and documentation
Home page: https://github.com/bioinfomaticsCSU/PESM
Data: https://github.com/bioinfomaticsCSU/PESM/blob/master/dataset.npz
< Back to DB search