1. libsleipnir
  2. sleipnir

Source

sleipnir / tools / SeekPrep / SeekPrep.ggo

package	"SeekPrep"
version	"1.0"
purpose	"Preprocess datasets for Seek"

section "Mode"
option	"dab"				d	"DAB mode, suitable for dataset wide gene average and stdev calculation"
								flag	off
option	"pclbin"			e	"PCL BIN mode, suitable for dataset gene variance calculation"
								flag	off
option	"db"				f	"DB mode, suitable for platform wide gene average and stdev calculation"
								flag	off
option	"dabset"			g	"DAB set mode, sums a set of sparse rank-normalized (or subtract-z-normalized) DAB files, with weights or no weights"
								flag 	off
option	"combined_dab"		h	"Combined DAB mode, divides a summed DAB file by total pair counts or dataset weights, generates a new normalized DAB file"
								flag 	off

section "Combined DAB mode"
option	"dab_dir2"			H	"Directory containing the summed DAB file"
								string typestr="directory" default="NA"
option	"dab_basename"		J	"Summed DAB basename (ie without extension)"
								string typestr="filename" default="NA"

section "DAB set mode (also see Misc options)"
option	"dab_dir"			G	"Directory containing the DAB files"
								string typestr="directory" default="NA"
option	"dablist"			L	"List of DAB files"
								string typestr="filename" default="NA"
option	"out_dab"			O	"Output DAB file basename (ie without extension)"
								string typestr="filename" default="NA"
option	"dataset_w"			W	"Dataset weights (optional)"
								string typestr="filename" default="NA"

section "DAB mode"
option	"gavg"				a	"Generates gene average file"
								flag	off
option	"gpres"				p	"Generates gene presence file"
								flag	off
option	"dabinput"			B	"DAB dataset file"
								string typestr="filename"
option	"top_avg_percent"	C	"For gene average, top X percent of the values to take average (0 - 1.0)"
								float	default="1.0"
option	"norm"				F	"Normalize matrix then sparsify it (needs --norm_mode)"
								flag	off
option	"view"				X	"View distribution of values in the matrix"
								flag	off

section "PCL mode"
option	"pclinput"			V	"PCL BIN file"
								string typestr="filename"
option	"gexpvarmean"		v	"Generates gene expression variance and mean files (.gexpvar, .gexpmean)"
								flag	off
option	"sinfo"				s	"Generates sinfo file (dataset z score mean and stdev)"
								flag	off

section "DB mode"
option	"gplat"				P	"Generates platform wide gene average and stdev file"
								flag	off
option	"dblist"			b	"The DB file list (incl. file path)"
								string typestr="filename"
option	"dir_prep_in"		I	"The prep directory containing the .gavg and .gpres files"
								string typestr="directory"
option	"dset"				A	"The dataset platform mapping file"
								string typestr="filename"
option	"useNibble"			N	"If the DB is nibble type"
								flag	off
option	"quant"				Q	"Quant file"
								string typestr="filename"

section "Misc"
option	"default_type"		T	"Default gene index type (choose unsigned short for genes, or unsigned int (32-bit) for transcripts) (required for DAB set mode and if --norm is enabled in DAB mode) (0 - unsigned int, 1 - unsigned short)"
								int default="-1"
option	"norm_mode"			n	"Normalization method: rank - rank-normalize matrix, subtract_z - subtract-z-normalize matrix (required for DAB set mode and if --norm is enabled, topological_overlap - TO measure from Ravasz et al)"
								values="rank","subtract_z","topological_overlap","NA" default="NA"
option	"logit"				l	"For --gavg and --gplat, whether to take logit of the value first (useful if edge value is probability)"
								flag	off
option	"max_rank"			M	"Maximum rank value (for --norm_mode=rank)"
								int default="-1"
option	"rbp_p"				R	"RBP p parameter (for --norm_mode=rank)"
								float default="-1"
option	"cutoff_value"		U	"The cutoff value (for --norm_mode=subtract_z)"
								float	default="-1.0"
option	"exp"				E	"Raise the z-score to the power of this value (for --norm_mode=subtract_z)"
								float	default="-1.0"

section "Input"
option	"input"				i	"Gene mapping file"
								string typestr="filename"	yes

section "Output"
option	"dir_out"			D	"Output directory"
								string typestr="directory"	yes