| 1 | <tool id="phastOdds_for_intervals" name="Compute phastOdds score" version="1.0.0"> |
|---|
| 2 | <description>for each interval</description> |
|---|
| 3 | <command interpreter="python">get_scores_galaxy.py $per_col ${score_file}.h5 ${score_file}.mapping.bed $input $output ${input.metadata.chromCol} ${input.metadata.startCol} ${input.metadata.endCol}</command> |
|---|
| 4 | <inputs> |
|---|
| 5 | <param format="interval" name="input" type="data" label="Interval file"> |
|---|
| 6 | <validator type="unspecified_build" message="Unspecified build, this tool works with data from genome builds hg17. Click the pencil icon in your history item to set the genome build."/> |
|---|
| 7 | <validator type="dataset_metadata_in_file" filename="phastOdds.loc" metadata_name="dbkey" metadata_column="0" message="Sequences are currently unavailable for the specified build." /> |
|---|
| 8 | </param> |
|---|
| 9 | <param name="score_file" type="select" label="Available datasets"> |
|---|
| 10 | <options from_file="phastOdds.loc"> |
|---|
| 11 | <column name="name" index="1"/> |
|---|
| 12 | <column name="value" index="2"/> |
|---|
| 13 | <column name="dbkey" index="0"/> |
|---|
| 14 | <filter type="data_meta" ref="input" key="dbkey" column="0" /> |
|---|
| 15 | </options> |
|---|
| 16 | </param> |
|---|
| 17 | <param name="per_col" type="boolean" label="Standardize" help="Standardizes the score to be per alignment column" checked="yes" truevalue="-p" falsevalue=""/> |
|---|
| 18 | </inputs> |
|---|
| 19 | <outputs> |
|---|
| 20 | <data format="interval" name="output" metadata_source="input"/> |
|---|
| 21 | </outputs> |
|---|
| 22 | <requirements> |
|---|
| 23 | <requirement type="python-module">numpy</requirement> |
|---|
| 24 | <requirement type="python-module">tables</requirement> |
|---|
| 25 | </requirements> |
|---|
| 26 | <tests> |
|---|
| 27 | <test> |
|---|
| 28 | <param name="input" value="4.bed" dbkey="hg17" ftype="bed"/> |
|---|
| 29 | <param name="score_file" value="/galaxy/data/phastOdds_precomputed/encode_SEP-2005_tba.v2_phastOdds" /> |
|---|
| 30 | <param name="per_col" value="true" /> |
|---|
| 31 | <output name="output" file="phastOdds_tool_out.interval" /> |
|---|
| 32 | </test> |
|---|
| 33 | </tests> |
|---|
| 34 | <help> |
|---|
| 35 | |
|---|
| 36 | .. class:: warningmark |
|---|
| 37 | |
|---|
| 38 | This tool currently only works with interval data from genome build hg17. |
|---|
| 39 | |
|---|
| 40 | .. class:: warningmark |
|---|
| 41 | |
|---|
| 42 | This tool assumes that the input dataset is in interval format and contains at least a chrom column, a start column and an end column. These 3 columns can be dispersed throughout any number of other data columns. |
|---|
| 43 | |
|---|
| 44 | ----- |
|---|
| 45 | |
|---|
| 46 | **Syntax** |
|---|
| 47 | |
|---|
| 48 | Append a column to each line of an interval file containing the phastOdds score for that interval. |
|---|
| 49 | |
|---|
| 50 | ----- |
|---|
| 51 | |
|---|
| 52 | **Example** |
|---|
| 53 | |
|---|
| 54 | If your original data has the following format: |
|---|
| 55 | |
|---|
| 56 | +-----+-----+---+ |
|---|
| 57 | |chrom|start|end| |
|---|
| 58 | +-----+-----+---+ |
|---|
| 59 | |
|---|
| 60 | and you choose to compute phastOdds scores, your output will look like this: |
|---|
| 61 | |
|---|
| 62 | +-----+-----+---+-----+ |
|---|
| 63 | |chrom|start|end|score| |
|---|
| 64 | +-----+-----+---+-----+ |
|---|
| 65 | |
|---|
| 66 | </help> |
|---|
| 67 | </tool> |
|---|