Pse-Analysis: a python package for DNA/RNA and protein/peptide sequence analysis based on pseudo components and kernel methods

• DOI: 10.18632/oncotarget.14524
• Publication Date: 2017-01-08T15:05:47Z
• Authors: Bin Liu; Hao Wu; Deyuan Zhang; Xiaolong Wang; Kuo-Chen Chou
• Keywords: Python; Benchmark (surveying); R package; Speedup

To expedite the pace in conducting genome/proteome analysis, we have developed a Python package called Pse-Analysis. The powerful can automatically complete following five procedures: (1) sample feature extraction, (2) optimal parameter selection, (3) model training, (4) cross validation, and (5) evaluating prediction quality. All work user needs to do is input benchmark dataset along with query biological sequences concerned. Based on dataset, Pse-Analysis will construct an ideal predictor, followed by yielding predicted results for submitted samples. aforementioned tedious jobs be done computer. Moreover, multiprocessing technique was adopted enhance computational speed about 6 folds. freely accessible public at http://bioinformatics.hitsz.edu.cn/Pse-Analysis/, directly run Windows, Linux, Unix.