We can directly download by clicking the link.

Note: The package will download in zip format (.zip) named PyFeat-master.zip.

or,

Cloning a repository syncs it to our local machine (Example for Linux-based OS). After clone, we can add and edit files and then push and pull updates.

• Clone over HTTPS: user@machine:~$ git clone https://github.com/mrzResearchArena/PyFeat.git
• Clone over SSH: user@machine:~$ git clone [email protected]:mrzResearchArena/PyFeat.git

Note #1: If the clone was successful, a new sub-directory appears on our local drive. This directory has the same name (PyFeat) as the GitHub repository that we cloned.

Note #2: We can run any Linux-based command from any valid location or path, but by default, a command generally runs from /home/user/.

Note #2.1: user is the name of our computer but your computer name can be different (Example: /home/bioinformatics/).

Major (Generate Features):

• Install: python (version >= 3.5)
• Install: numpy (version >= 1.13.0)

Minor (Performance Measures):

• Install: sklearn (version >= 0.19.0)
• Install: pandas (version >= 0.21.0)
• Install: matplotlib (version >= 2.1.0)

Using PIP: pip install <package name>

user@machine:~$ pip install scikit-learn

or,

Using anaconda environment: conda install <package name>

user@machine:~$ conda install scikit-learn

Run command on your console or terminal.

user@machine:~$ python main.py --sequenceType=DNA --fullDataset=1 --optimumDataset=1 --fasta=/home/user/PyFeat/Datasets/DNA/FASTA.txt --label=/home/user/PyFeat/Datasets/DNA/Labels.txt --kTuple=3 --kGap=5 --pseudoKNC=1 --zCurve=1 --gcContent=1 --cumulativeSkew=1 --atgcRatio=1 --monoMono=1 --monoDi=1 --monoTri=1 --diMono=1 --diDi=1 --diTri=1 --triMono=1 --triDi=1

or,

user@machine:~$ python main.py -seq=DNA -full=1 -optimum=1 -fa=/home/user/PyFeat/Datasets/DNA/FASTA.txt -la=/home/user/PyFeat/Datasets/DNA/Label.txt -ktuple=3 -kgap=5 -pseudo=1 -zcurve=1 -gc=1 -skew=1 -atgc=1 -f11=1 -f12=1 -f13=1 -f21=1 -f22=1 -f23=1 -f31=1 -f32=1

user@machine:~$ python main.py --sequenceType=Protein --testDataset=1 --fasta=/home/user/PyFeat/Datasets/Protein/independentFASTA.txt --label=/home/user/PyFeat/Datasets/Protein/independentLabel.txt --kTuple=3 --kGap=5 --pseudoKNC=1 --zCurve=1 --gcContent=1 --cumulativeSkew=1 --atgcRatio=1 --monoMono=1 --monoDi=1 --monoTri=1 --diMono=1 --diDi=1 --diTri=1 --triMono=1 --triDi=1

or,

user@machine:~$ python main.py -seq=Protein -test=1 -fa=/home/user/PyFeat/Datasets/Protein/independentFASTA.txt -la=/home/user/PyFeat/Datasets/Protein/independentLabel.txt -ktuple=3 -kgap=5 -pseudo=1 -zcurve=1 -gc=1 -skew=1 -atgc=1 -f11=1 -f12=1 -f13=1 -f21=1 -f22=1 -f23=1 -f31=1 -f32=1

[ Comment: The = sign is optional. ]

Note #1: It will generate a full dataset named fullDataset.csv (if -full=1 or, --fullDataset==1)
Note #2: It will generate a selected features dataset named optimumDataset.csv (if -optimum=1 or, --optimumDataset==1), and It will also track the selected features index.
Note #3: It will generate a full dataset named testDataset.csv (if -test=1 or, --testDataset==1) [ Especially for the independent (testing) dataset purpose. ] [ 3.1.2. ]
Note #4: The process will run smoothly for valid FASTA sequences and row-wise class label.

Note: When sequence becomes DNA, RNA, and Protein then X = {A,C,G,T}, X = {A,C,G,U}, and X = {A,C,D,E,F,G,H,I,K,L,M,N,P,Q,R,S,T,V,W,Y} respectively.

Arguments Details for the Features Generation and Feature Description are provided in Tables 1 and Table 2, respectively.

user@machine:~$ python runClassifiers.py --nFCV=10 --dataset=optimumDataset.csv --auROC=1 --boxPlot=1

Note #1: It will provide classification results (evaluationResults.txt) from the user provides binary class dataset (.csv format).
Note #2: Generate a ROC Curve (auROC.png).
Note #3: Generate an accuracy comparison via boxPlot (AccuracyBoxPlot.png).

user@machine:~$ python trainModel.py --dataset=optimumDataset.csv --model=LR

Note #1: It will provide a dumpModel.pkl from the user provides binary class dataset (.csv format).

Note: LR, SVM, KNN, DT, NB, Bagging, RF, AB, GB, and LDA represents Logistics Regression, Support Vector Machine, k-Nearest Neighbor, Decision Tree, Naive Bayes, Bagging, Random Forest, AdaBoost, Gradient Boosting, Linear Discriminant Analysis classifier respectively.

user@machine:~$ python evaluateModel.py --optimumDatasetPath=optimumDataset.csv --testDatasetPath=testDataset.csv

Note #1: Here, optimumDataset.csv, and testDataset.csv using as a traing dataset and test dataset respectively.

[1] Bin Liu, Fule Liu, Longyun Fang, Xiaolong Wang, and Kuo-Chen Chou. repdna: a python package to generate various modes of feature vectors for dna sequences by in- corporating user-defined physicochemical properties and sequence-order effects. Bioin- formatics, 31(8):1307–1309, 2014.

[2] Dong-Sheng Cao, Qing-Song Xu, and Yi-Zeng Liang. propy: a tool to generate various modes of chous pseaac. Bioinformatics, 29(7):960–962, 2013.

[3] Zhen Chen, Pei Zhao, Fuyi Li, André Leier, Tatiana T Marquez-Lago, Yanan Wang, Geoffrey I Webb, A Ian Smith, Roger J Daly, Kuo-Chen Chou, et al. ifeature: a python package and web server for features extraction and selection from protein and peptide sequences. Bioinformatics, 1:4, 2018.

[4] Md Rafsan Jani, Md Toha Khan Mozlish, Sajid Ahmed, Dewan Md Farid, and Swakkhar Shatabda. irecspot-ef: Effective sequence based features for recombination hotspot prediction. Computers in biology and medicine, 2018.

[5] Bin Liu, Fule Liu, Longyun Fang, Xiaolong Wang, and Kuo-Chen Chou. reprna: a web server for generating various feature vectors of rna sequences. Molecular Genetics and Genomics, 291(1):473–481, 2016.

[6] Nan Xiao, Dong-Sheng Cao, Min-Feng Zhu, and Qing-Song Xu. protr/protrweb: R package and web server for generating various numerical representation schemes of pro- tein sequences. Bioinformatics, 31(11):1857–1859, 2015.

[7] Bin Liu. Bioseq-analysis: a platform for dna, rna and protein sequence analysis based on machine learning approaches. Briefings in bioinformatics, 2017.

[8] Bin Liu, Hao Wu, Deyuan Zhang, Xiaolong Wang, and Kuo-Chen Chou. Pse-analysis: a python package for dna/rna and protein/peptide sequence analysis based on pseudo components and kernel methods. Oncotarget, 8(8):13338, 2017.

[9] Bin Liu, Fule Liu, Xiaolong Wang, Junjie Chen, Longyun Fang, and Kuo-Chen Chou. Pse-in-one: a web server for generating various modes of pseudo components of dna, rna, and protein sequences. Nucleic acids research, 43(W1):W65–W71, 2015.

[10] Fabian Pedregosa, Gaël Varoquaux, Alexandre Gramfort, Vincent Michel, Bertrand Thirion, Olivier Grisel, Mathieu Blondel, Peter Prettenhofer, Ron Weiss, Vincent Dubourg, et al. Scikit-learn: Machine learning in python. Journal of machine learning research, 12(Oct):2825–2830, 2011.

[11] Eamonn Keogh and Abdullah Mueen. Curse of dimensionality. In Encyclopedia of Machine Learning and Data Mining, pages 314–315. Springer, 2017.

[12] Ruihu Wang. Adaboost for feature selection, classification and its relation with svm, a review. Physics Procedia, 25:800–807, 2012.

[13] Hao Lin, En-Ze Deng, Hui Ding, Wei Chen, and Kuo-Chen Chou. ipro54-pseknc: a sequence-based predictor for identifying sigma-54 promoters in prokaryote with pseudo k-tuple nucleotide composition. Nucleic acids research, 42(21):12961–12972, 2014.

[14] Wei Chen, Pengmian Feng, Hui Ding, and Hao Lin. Pai: Predicting adenosine to inosine editing sites by using pseudo nucleotide compositions. Scientific reports, 6:35123, 2016.

[15] Hao Lin, Zhi-Yong Liang, Hua Tang, and Wei Chen. Identifying sigma70 promoters with novel pseudo nucleotide composition. IEEE/ACM transactions on computational biology and bioinformatics, 2017.

[16] Mahmoud Ghandi, Dongwon Lee, Morteza Mohammad-Noori, and Michael A Beer. Enhanced regulatory sequence prediction using gapped k-mer features. PLoS computa- tional biology, 10(7):e1003711, 2014.

[17] Shahana Yasmin Chowdhury, Swakkhar Shatabda, and Abdollah Dehzangi. Idnaprot- es: Identification of dna-binding proteins using evolutionary and structural features. Scientific Reports, 7(1):14938, 2017.