| Previous changeset 83:3e214a2fcec9 (2017-11-15) Next changeset 85:8f5c05be4efe (2017-11-22) |
|
Commit message:
Deleted selected files |
|
removed:
ideas.xml |
| b |
| diff -r 3e214a2fcec9 -r 1863d847749b ideas.xml --- a/ideas.xml Wed Nov 15 07:36:12 2017 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
| [ |
| b'@@ -1,330 +0,0 @@\n-<tool id="ideas" name="IDEAS" version="1.2.0">\n- <description>accounts for position dependent epigenetic events and detects local cell type relationships</description>\n- <requirements>\n- <requirement type="package" version="2.26.0">bedtools</requirement>\n- <requirement type="package" version="332">ucsc-bedgraphtobigwig</requirement>\n- <requirement type="package" version="332">ucsc-bedsort</requirement>\n- <requirement type="package" version="332">ucsc-bigwigaverageoverbed</requirement>\n- <requirement type="package" version="1.20">ideas</requirement>\n- <requirement type="package" version="1.4.4">r-optparse</requirement>\n- </requirements>\n- <command detect_errors="exit_code"><![CDATA[\n-#set output_dir = "output_dir"\n-#set tmp_dir = "tmp"\n-#set prep_input_config = "prep_input_config.txt"\n-#set prep_output_config = \'$project_name\'\n-##############################################\n-## Create the config file and prepare the data\n-##############################################\n-#set specify_genomic_window = $specify_genomic_window_cond.specify_genomic_window\n-mkdir \'$output_dir\' &&\n-cp \'$gen_prep_input_config\' $prep_input_config &&\n-prepMat\n-$prep_input_config\n-#if str($specify_genomic_window) == "yes":\n- -bed \'$specify_genomic_window_cond.bed_input\'\n-#else:\n- -gsz \'$chromInfo\'\n- -wsz $specify_genomic_window_cond.window_size\n- #set restrict_chromosomes = $specify_genomic_window_cond.restrict_chromosomes_cond.restrict_chromosomes\n- #if str($restrict_chromosomes) == "yes":\n- #set chroms = []\n- #set chrom_repeat = $specify_genomic_window_cond.restrict_chromosomes_cond.chrom_repeat\n- #for $i in $chrom_repeat.chrom\n- $chroms.append($i)\n- #end for\n- -chr ",".join(chroms)\n- #end if\n-#end if\n-$bychr\n--c $reads_per_bp\n-#if str($blacklist_input) not in ["None", ""]:\n- -exclude \'$blacklist_input\'\n-#end if\n-$norm\n-##############################################\n-## Coerce the prepMat config output to the\n-## format expected by IDEAS.\n-##############################################\n-&& cut -d\' \' $prep_input_config -f1,2 > file1.txt\n-&& ls tmp/*.bed.gz > file2.txt\n-&& paste <(cat file1.txt) <(cat file2.txt) -d\' \' > $prep_output_config\n-##############################################\n-## Run IDEAS\n-##############################################\n-&& ideas\n-\'$prep_output_config\'\n-#set specify_genomic_window = $specify_genomic_window_cond.specify_genomic_window\n-#if str($specify_genomic_window) == "yes":\n- \'$specify_genomic_window_cond.bed_input\'\n-#else:\n- $tmp_dir/*.bed\n-#end if\n-$hp\n-#if str($log2) != "0.0":\n- -log2 $log2\n-#end if\n-#if str($max_states) != "0.0":\n- -G $max_states\n-#end if\n-#if str($initial_states) != "0":\n- -C $initial_states\n-#end if\n-#if str($max_position_classes) != "0":\n- -P $max_position_classes\n-#end if\n-#if str($max_cell_type_clusters) != "0":\n- -K $max_cell_type_clusters\n-#end if\n-#if str($prior_concentration) != "0.0":\n- -A $prior_concentration\n-#end if\n--sample $burnin_num $mcmc_num\n-#if str($minerr) != "0.0":\n- -minerr $minerr\n-#end if\n-#if str($maxerr) != "0.0":\n- -maxerr $maxerr\n-#end if\n--rseed $rseed\n--thread \\${GALAXY_SLOTS:-4}\n-#if str($save_ideas_log) == "yes":\n- > $output_log\n-#else:\n- > /dev/null\n-#end if\n-&& mv ./*.cluster \'$output_dir\'\n-&& mv ./*.para \'$output_dir\'\n-&& mv ./*.profile \'$output_dir\'\n-&& mv ./*.state \'$output_dir\'\n-&& Rscript \'$__tool_directory__/create_heatmap.R\'\n--i \'$output_dir/prep_output_config.txt.para\'\n--o \'$output_heatmap\'\n- ]]></command>\n- <configfiles>\n- <configfile name="gen_prep_input_config"><![CDATA[#if str($cell_type_epigenetic_factor_cond.cell_type_epigenetic_factor) == "extract":\n- #set input_name_positions = $cell_type_epigenetic_factor_cond.input_name_positions\n- #for $i in $cell_type_epigenetic_factor_cond.input:\n- #set file_name_with_ext = $i.name\n- #assert str($file_name_with'..b'n different chromosomes separately.\n-* **Calculate the signal in each genomic window using** - use the bigWigAverageOverBed utility from the UCSC genome browser to calculate the signal (i.e., the number of reads per bp) in each genomic window.\n-* **Select file(s) containing regions to exclude** - select one or more bed files that contains regions you\'d like excluded from your datasets.\n-* **Standardize all datasets** - select "Yes" to standardize all datasets (e.g., reads / total_reads * 20 million) so that the signals from different cell types become comparable - your datasets can be read counts, logp-values or fold change.\n-\n-* **Discourage state transition across chromosomes** - select "Yes" to produce similar states in adjacent windows, making the annotation smoother, but at risk of reducing precision.\n-* **Use log2(x+number) transformation** - perform Log2-transformation of the input data by log2(x+number) (recommended for read count data to reduce skewness). You can enter a number that is representative of the noise level in your data (e.g., a number less than 1). If this number is at a similar scale or larger than the signal in your data, it will lose power. For example, if your input data is mean read count per window, using 0.1 may produce better results.\n-* **Maximum number of states to be inferred** - restrict the maximum number of states to be generated by IDEAS; the final number of inferred states may be smaller than the number you specified\n-* **Initial number of states** - while IDEAS may infer 30 states or more by starting from just 20 states, it may not do so if it is trapped in a local mode. We recommend setting the initial number of states slightly larger than the number of states you expect.\n-* **Maximum number of position classes to be inferred** - Set this value only if:\n-\n- * you do not want position classes (e.g., for testing purposes), in this case set the value to 1\n- * IDEAS runs slow because there are too many position classes, generally less than 100 position classes will run fine\n-\n-* **Maximum number of cell type clusters allowed** - If you set the value to 1, then all cell types will be clustered in one group, which may be desirable if all cell types are homogeneous and you want IDEAS to use information in all cell types equally.\n-* **Prior concentration** - specify the prior concentration parameter; default is A=sqrt(number of cell types). A smaller concentration parameter (e.g., 1 or less) will emphasize more on position specificity and a larger concentration parameter (e.g., 10 * number of cell types) will emphasize more on global homogeneity.\n-* **Number of burnin steps** - specify the number of burnin steps; default is 20. Increasing the burnin and maximization steps will increase computing and only slightly increase accuracy, while decreasing them will reduce computing resources but may also reduce accuracy. We recommend to run IDEAS with at least 20 burnins and 20 maximizations. IDEAS will not stop even if it reaches a maximum mode.\n-* **Number of maximization steps** - specify the number of maximization steps; default is 20.\n-* **Minimum standard deviation for the emission Gaussian distribution** - This number multiplied by the overall standard deviation of your data will be used as a lower bound for the standard deviation for each factor in each epigenetic state (the default is 0.5). This number is useful for removing very subtle clusters in the data. Setting this value near 0 will allow IDEAS to discover many subtle states, while setting it greater than 1 will result in IDEAS losing the ability to detect meaningful states.\n-* **Maximim standard deviation for the emission Gaussian distribution** - if you want to find fine-grained states you may use this option (if not used, IDEAS uses infinity), but it is rearely used unless you need more states to be inferred. \n-\n- </help>\n- <citations>\n- <citation type="doi">10.1093/nar/gkw278</citation>\n- </citations>\n-</tool>\n' |