1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15

git clone https://github.com/TatianneNegri/RNAplonc.git
cd RNAplonc/RNAplonc
chmod +x FilterResults.py
chmod +x *.pl
chmod +x txCdsPredict
sed -i 's/#!\/usr\/bin\/perl/#!\/usr\/bin\/env perl/g' *.pl #修改下调用的perl，方便调用我们conda安装的模块。
# FilterResults.py 中作者用的`#!/usr/bin/env python3`

# 当前文件夹文件。留意RNAplonc.model文件！！！
# 200nt.pl  feature_extraction.pl  FilterResults.py  random_selection.pl  README.txt  RNAplonc.model  seq_test  txCdsPredict  weka.jar
pwd
# /home/data/vip13t28/biosoft/RNAplonc/RNAplonc
# 添加环境变量
conda install -c bioconda cd-hit
conda install -c bioconda perl-bioperl #feature_extraction.pl的依赖

1
2
3

$ perl /home/data/vip13t28/biosoft/RNAplonc/RNAplonc/200nt.pl test.fa
$ ls
test.fa  test_.fasta #这个结果文件名称……

1
2
3

$ cd-hit-est -c 0.8 -T 5 -i test_.fasta  -o cd-hit-est0.8.fasta 
$ ls
cd-hit-est0.8.fasta  cd-hit-est0.8.fasta.clstr  test.fa  test_.fasta

1
2
3

$ /home/data/vip13t28/biosoft/RNAplonc/RNAplonc/txCdsPredict cd-hit-est0.8.fasta cd-hit-est0.8.cds
$ ls
cd-hit-est0.8.cds  cd-hit-est0.8.fasta  cd-hit-est0.8.fasta.clstr  test.fa  test_.fasta

1
2
3
4

lcl|Csinensis_orange1.1g033490m 109     466     txCdsPredict    .       507.5   1       1       1       109,    357,
lcl|Csinensis_orange1.1g033508m 109     466     txCdsPredict    .       507.5   1       1       1       109,    357,
lcl|Csinensis_orange1.1g033990m 39      360     txCdsPredict    .       521     1       1       1       39,     321,
lcl|Csinensis_orange1.1g033802m 682     1018    txCdsPredict    .       297.5   1       1       1       682,    336,

1
2
3
4

$ /home/data/vip13t28/biosoft/RNAplonc/RNAplonc/feature_extraction.pl cd-hit-est0.8.fasta cd-hit-est0.8.cds > cd-hit-est0.8.arff
$ ls
cd-hit-est0.8.ar   cd-hit-est0.8.fasta        cd-hit-est0.8.fasta.index  test_.fasta
cd-hit-est0.8.cds  cd-hit-est0.8.fasta.clstr  test.fa

1

java -cp /home/data/vip13t28/biosoft/RNAplonc/RNAplonc/weka.jar weka.classifiers.trees.REPTree 

1

java -cp /home/data/vip13t28/biosoft/RNAplonc/RNAplonc/weka.jar weka.classifiers.trees.REPTree -l /home/data/vip13t28/biosoft/RNAplonc/RNAplonc/RNAplonc.model -T cd-hit-est0.8.arff  -p 0 >cd-hit-est0.8_end.txt

1

/home/data/vip13t28/biosoft/RNAplonc/RNAplonc/FilterResults.py -c cd-hit-est0.8.cds -r cd-hit-est0.8_end.txt -o cd-hit-est0.8_result.txt -t 1 -p 0.5 

  1
  2
  3
  4
  5
  6
  7
  8
  9
 10
 11
 12
 13
 14
 15
 16
 17
 18
 19
 20
 21
 22
 23
 24
 25
 26
 27
 28
 29
 30
 31
 32
 33
 34
 35
 36
 37
 38
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116

$ java -cp /home/data/vip13t28/biosoft/RNAplonc/RNAplonc/weka.jar weka.classifiers.trees.REPTree 

Weka exception: No training file and no object input file given.

General options:

-h or -help
	Output help information.
-synopsis or -info
	Output synopsis for classifier (use in conjunction  with -h)
-t <name of training file>
	Sets training file.
-T <name of test file>
	Sets test file. If missing, a cross-validation will be performed
	on the training data.
-c <class index>
	Sets index of class attribute (default: last).
-x <number of folds>
	Sets number of folds for cross-validation (default: 10).
-no-cv
	Do not perform any cross validation.
-force-batch-training
	Always train classifier in batch mode, never incrementally.
-split-percentage <percentage>
	Sets the percentage for the train/test set split, e.g., 66.
-preserve-order
	Preserves the order in the percentage split.
-s <random number seed>
	Sets random number seed for cross-validation or percentage split
	(default: 1).
-m <name of file with cost matrix>
	Sets file with cost matrix.
-toggle <comma-separated list of evaluation metric names>
	Comma separated list of metric names to toggle in the output.
	All metrics are output by default with the exception of 'Coverage' and 'Region size'.
	Available metrics:
	Correct,Incorrect,Kappa,Total cost,Average cost,KB relative,KB information,
	Correlation,Complexity 0,Complexity scheme,Complexity improvement,
	MAE,RMSE,RAE,RRSE,Coverage,Region size,TP rate,FP rate,Precision,Recall,
	F-measure,MCC,ROC area,PRC area
-l <name of input file>
	Sets model input file. In case the filename ends with '.xml',
	a PMML file is loaded or, if that fails, options are loaded
	from the XML file.
-d <name of output file>
	Sets model output file. In case the filename ends with '.xml',
	only the options are saved to the XML file, not the model.
-v
	Outputs no statistics for training data.
-o
	Outputs statistics only, not the classifier.
-do-not-output-per-class-statistics
	Do not output statistics for each class.
-k
	Outputs information-theoretic statistics.
-classifications "weka.classifiers.evaluation.output.prediction.AbstractOutput + options"
	Uses the specified class for generating the classification output.
	E.g.: weka.classifiers.evaluation.output.prediction.PlainText
-p range
	Outputs predictions for test instances (or the train instances if
	no test instances provided and -no-cv is used), along with the 
	attributes in the specified range (and nothing else). 
	Use '-p 0' if no attributes are desired.
	Deprecated: use "-classifications ..." instead.
-distribution
	Outputs the distribution instead of only the prediction
	in conjunction with the '-p' option (only nominal classes).
	Deprecated: use "-classifications ..." instead.
-r
	Only outputs cumulative margin distribution.
-z <class name>
	Only outputs the source representation of the classifier,
	giving it the supplied name.
-g
	Only outputs the graph representation of the classifier.
-xml filename | xml-string
	Retrieves the options from the XML-data instead of the command line.
-threshold-file <file>
	The file to save the threshold data to.
	The format is determined by the extensions, e.g., '.arff' for ARFF 
	format or '.csv' for CSV.
-threshold-label <label>
	The class label to determine the threshold data for
	(default is the first label)
-no-predictions
	Turns off the collection of predictions in order to conserve memory.

Options specific to weka.classifiers.trees.REPTree:

-M <minimum number of instances>
	Set minimum number of instances per leaf (default 2).
-V <minimum variance for split>
	Set minimum numeric class variance proportion
	of train variance for split (default 1e-3).
-N <number of folds>
	Number of folds for reduced error pruning (default 3).
-S <seed>
	Seed for random data shuffling (default 1).
-P
	No pruning.
-L
	Maximum tree depth (default -1, no maximum)
-I
	Initial class value count (default 0)
-R
	Spread initial count over all class values (i.e. don't use 1 per value)
-output-debug-info
	If set, classifier is run in debug mode and
	may output additional info to the console
-do-not-check-capabilities
	If set, classifier capabilities are not checked before classifier is built
	(use with caution).
-num-decimal-places
	The number of decimal places for the output of numbers in the model (default 2).
-batch-size
	The desired batch size for batch prediction  (default 100).

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14

$ FilterResults.py -h
usage: FilterResults.py [-h] -c CDSFILE -r RESULTFILE -o OUTPUTFILE [-t TYPE] [-p PERCENT]

optional arguments:
  -h, --help            show this help message and exit
  -c CDSFILE, --cdsFile CDSFILE
                        Path of the cds file, or the txCdsPredict output
  -r RESULTFILE, --resultFile RESULTFILE
                        Path of the result file, or the RNAplonc.model output
  -o OUTPUTFILE, --outputFile OUTPUTFILE
                        Path of the output file
  -t TYPE, --type TYPE  Filter the output type in the terminal, 1- lncRNA , 2-mRNA
  -p PERCENT, --percent PERCENT
                        Filter the output percentage in the terminal, float valeu between 0 and 1