ProteinPipe: A pipeline with an ensemble learning classifier for processing protein sequence data
|
|
|
ProteinPipe
    ProteinPipe is a friendly Java pipeline tool for processing protein sequence data. This pipeline provides users with four functions, which are feature extraction, data imbalance processing, feature selection and classification. Each function can be used alone or in combination, which is more flexible and convenient. You can use this tool in any OS with JVM.Usage
    Java -jar PPL.jar
Feature Extraction
- Input:  The input files must be in fasta format, and different types of data need to be stored separately
- Result:  The result file must be in arff format.
Imbalanced data Process
- Input:  The input files must be in arff format.
Follow the guide to configure the parameters of the unbalanced algorithm.
Feature Selection
- Required parameters:  -i input.arff -o output.txt
- Optional parameters:  -df numberDF -a arffName -m model
-i means inputFile, -o means outputFile
-df means the distance function(1 = Euclidean Distance, 2 = Cosine Distance, 3 = Tanimoto coefficient, 4 = mean), -a is the arff file obtained after feature selection(opt.arff), -m is the opt model type(rf, svm, bagging)
Classifier
- Cross-validation:  -c fold-num trainFile
- Train model:  -t trainFile
- Prediction:  -p train.model testFile resultFile
-c means crossvalidation, fold-num is the crossValiditon folds, trainFile is the file path for the training data
-t means train model and the model would be saved in the same filePath(a new file "train.model" will be created) ,trainFile is the file path for the training data,resultFile is the file path save prediction result
-p means prediction and train.model is the filePath you trained before ,trainFile is the file path for the training data, resultFile is the file path save prediction result
Download
    You should download PPL.jar and classifiers.xml.You should also put them together(in the same file path).We have got our project on Github:(https://github.com/smilida/ProteinPipe)All Rights Reserved Copyright @ 2021|Prof. Quan Zou
Last Modified in 2021/8/8