Sleipnir
Txt2Bin

Txt2Bin converts between SVM Light compatible text feature files, Sleipnir binary feature files containing the same information (Sleipnir::CSVM::Learn and Sleipnir::CSVM::Evaluate), and DAT/DAB files containing data. This is primarily useful for condensing multiple DAT/DAB files into a binary SVM example file for learning/evaluation or for displaying the contents of such a file as human-readable text.

Usage

Basic Usage

 Txt2Bin -f dat -t bin -w <answers.dab> -o <examples.bin> <data.dab>*

Generates the binary SVM examples/features file examples.bin using the labels for gene pairs in answers.dab and the data (features) for those gene pairs in the one or more data.dab files.

 Txt2Bin -f txt -t bin -i <examples.txt> -o <examples.bin>

Convert the SVM Light text-based examples file examples.txt into a Sleipnir binary SVM examples file examples.bin.

 Txt2Bin -f bin -t txt -i <examples.bin> -o <examples.txt>

Convert the Sleipnir binary SVM examples file examples.bin into an SVM Light text-based examples file examples.txt.

Detailed Usage

package "Txt2Bin"
version "1.0"
purpose "SVM binary input manipulator"

section "Main"
option  "input"     i   "Input text/binary file"
                        string  typestr="filename"
option  "answers"   w   "Answer file"
                        string  typestr="filename"
option  "output"    o   "Output binary file"
                        string  typestr="filename"

section "Miscellaneous"
option  "from"      f   "Source format"
                        values="txt","dat","bin"    default="txt"
option  "to"        t   "Target format"
                        values="txt","bin"  default="bin"
option  "matrix"    m   "Read/write simple matrix format"
                        flag    off

section "Learning/Evaluation"
option  "genes"     g   "Gene inclusion file"
                        string  typestr="filename"
option  "genex"     G   "Gene exclusion file"
                        string  typestr="filename"

section "Optional"
option  "verbosity" v   "Message verbosity"
                        int default="5"
Flag Default Type Description
None None DAT/DAB files When converting from DAT/DAB files to SVM features, the data files to be read. Each gene pair becomes one example in the output and each DAT/DAB one feature.
-i None Text or binary feature file When converting from text or binary feature files, the feature file to be opened. Can be in SVM Light text format or Sleipnir binary format.
-w None stdin When converting from DAT/DAB data files, the gold standard answer file used to label the resulting training examples.
-f txt txt, dat, or bin Format of input file to be converted from.
-t bin txt or bin Format of output file to be converted to.
-g None Text gene list If given, use only gene pairs for which both genes are in the list. For details, see Sleipnir::CDat::FilterGenes.
-G None Text gene list If given, use only gene pairs for which neither gene is in the list. For details, see Sleipnir::CDat::FilterGenes.