Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

add preferedName #12

Merged
merged 4 commits into from
Nov 3, 2023
Merged

add preferedName #12

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
41391e2
add preferedName
lldelisle Nov 2, 2023
cb87884
remove useGene option
lldelisle Nov 3, 2023
6e3d237
update wrapper + tests
lldelisle Nov 3, 2023
3756bab
fix linting
lldelisle Nov 3, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 9 additions & 7 deletions tools/fromgtfTobed12/fromgtfTobed12.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,13 +23,16 @@
"database creation")


def convert_gtf_to_bed(fn, fo, useGene, mergeTranscripts,
def convert_gtf_to_bed(fn, fo, preferedName, mergeTranscripts,
mergeTranscriptsAndOverlappingExons, ucsc):
db = gffutils.create_db(fn, ':memory:')
# For each transcript:
prefered_name = "transcript_name"
if useGene or mergeTranscripts or mergeTranscriptsAndOverlappingExons:
if preferedName is not None:
prefered_name = preferedName
elif mergeTranscripts or mergeTranscriptsAndOverlappingExons:
prefered_name = "gene_name"
else:
prefered_name = "transcript_name"
if mergeTranscripts or mergeTranscriptsAndOverlappingExons:
all_items = db.features_of_type("gene", order_by='start')
else:
Expand Down Expand Up @@ -127,12 +130,11 @@ def convert_gtf_to_bed(fn, fo, useGene, mergeTranscripts,
argp.add_argument('--output', default=sys.stdout,
type=argparse.FileType('w'),
help="Output bed12 file.")
argp.add_argument('--useGene', action="store_true",
help="Use the gene name instead of the "
"transcript name.")
argp.add_argument('--ucscformat', action="store_true",
help="If you want that all chromosome names "
"begin with 'chr'.")
argp.add_argument('--preferedName', default=None,
help="Name to use for bed output.")
group = argp.add_mutually_exclusive_group()
group.add_argument('--mergeTranscripts', action="store_true",
help="Merge all transcripts into a single "
Expand All @@ -144,7 +146,7 @@ def convert_gtf_to_bed(fn, fo, useGene, mergeTranscripts,
" overlapping exons.")

args = argp.parse_args()
convert_gtf_to_bed(args.input, args.output, args.useGene,
convert_gtf_to_bed(args.input, args.output, args.preferedName,
args.mergeTranscripts,
args.mergeTranscriptsAndOverlappingExons,
args.ucscformat)
18 changes: 12 additions & 6 deletions tools/fromgtfTobed12/fromgtfTobed12.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
<tool id="fromgtfTobed12" name="fromgtftobed12" version="0.11.1+galaxy0">
<tool id="fromgtfTobed12" name="fromgtftobed12" version="0.11.1+galaxy1">
<description> Convert a gtf to a bed12.</description>
<requirements>
<requirement type="package" version="0.11.1">gffutils</requirement>
Expand All @@ -14,7 +14,9 @@
<command>
<![CDATA[
python3 $__tool_directory__/fromgtfTobed12.py
$useGene
#if str($preferedName) != "":
--preferedName $preferedName
#end if
$mergeTranscripts
$ucscformat
--output $output
Expand All @@ -23,12 +25,12 @@
</command>
<inputs>
<param name="input" multiple="false" type="data" format="gtf" label="Select the gtf to convert."/>
<param argument="--useGene" type="boolean" checked="False" truevalue="--useGene" falsevalue="" label="Uses the gene name instead of the transcript name."/>
<param name="mergeTranscripts" type="select" label="Do you want to merge all transcripts of a gene in a single line?">
<option value="" selected="true">No</option>
<option value="--mergeTranscripts">Yes</option>
<option value="--mergeTranscriptsAndOverlappingExons">Yes and merge overlapping exons</option>
</param>
<param argument="--preferedName" type="text" value="" label="Use a specific name for the 4th column" help="By default the 4th column will be transcript_name or gene_name if you merge transcripts. If you prefer 'gene_id', for example, then set this option." />
<param argument="--ucscformat" type="boolean" checked="True" truevalue="--ucscformat" falsevalue="" label="If you want that all chromosome names begin with 'chr'."/>
</inputs>

Expand All @@ -45,20 +47,24 @@
<test>
<param name="input" value="Homo_sapiens.GRCh38.95_491firstLines.gtf.gz"/>
<param name="ucscformat" value="--ucscformat"/>
<param name="useGene" value="--useGene"/>
<param name="preferedName" value="gene_name"/>
<output name="output" file="testWithGenes.bed"/>
</test>
<test>
<param name="input" value="Homo_sapiens.GRCh38.95_491firstLines.gtf.gz"/>
<param name="ucscformat" value="--ucscformat"/>
<param name="preferedName" value="gene_id"/>
<output name="output" file="testWithGeneIds.bed"/>
</test>
<test>
<param name="input" value="Homo_sapiens.GRCh38.95_491firstLines.gtf.gz"/>
<param name="mergeTranscripts" value="--mergeTranscripts"/>
<param name="useGene" value="--useGene"/>
<param name="ucscformat" value=""/>
<output name="output" file="testMergeNotUCSC.bed"/>
</test>
<test>
<param name="input" value="Homo_sapiens.GRCh38.95_491firstLines.gtf.gz"/>
<param name="mergeTranscripts" value="--mergeTranscriptsAndOverlappingExons"/>
<param name="useGene" value="--useGene"/>
<param name="ucscformat" value=""/>
<output name="output" file="testMergeExons.bed"/>
</test>
Expand Down
105 changes: 105 additions & 0 deletions tools/fromgtfTobed12/test-data/testWithGeneIds.bed
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,105 @@
chr1 11868 14409 ENSG00000223972 0 + 11868 11868 0 3 359,109,1189 0,744,1352
chr1 12009 13670 ENSG00000223972 0 + 12009 12009 0 6 48,49,85,78,154,218 0,169,603,965,1211,1443
chr1 14403 29570 ENSG00000227232 0 - 14403 14403 0 11 98,34,152,159,198,136,137,147,99,154,37 0,601,1392,2203,2454,2829,3202,3511,3864,10334,15130
chr1 17368 17436 ENSG00000278267 0 - 17368 17368 0 1 68 0
chr1 29553 31097 ENSG00000243485 0 + 29553 29553 0 3 486,104,122 0,1010,1422
chr1 30266 31109 ENSG00000243485 0 + 30266 30266 0 2 401,134 0,709
chr1 30365 30503 ENSG00000284332 0 + 30365 30365 0 1 138 0
chr1 34553 36081 ENSG00000237613 0 - 34553 34553 0 3 621,205,361 0,723,1167
chr1 35244 36073 ENSG00000237613 0 - 35244 35244 0 2 237,353 0,476
chr1 52472 53312 ENSG00000268020 0 + 52472 52472 0 1 840 0
chr1 57597 64116 ENSG00000240361 0 + 57597 57597 0 3 56,157,1201 0,1102,5318
chr1 62948 63887 ENSG00000240361 0 + 62948 62948 0 1 939 0
chr1 65418 71585 ENSG00000186092 0 + 65564 70005 0 3 15,54,2549 0,101,3618
chr1 69054 70108 ENSG00000186092 0 + 69090 70005 0 1 1054 0
chr1 89294 120932 ENSG00000238009 0 - 89294 89294 0 4 2335,150,105,158 0,2796,23405,31480
chr1 89550 91105 ENSG00000239945 0 - 89550 89550 0 2 500,819 0,736
chr1 92229 129217 ENSG00000238009 0 - 92229 92229 0 4 11,105,212,163 0,20470,28491,36825
chr1 110952 129173 ENSG00000238009 0 - 110952 110952 0 3 405,105,119 0,1747,18102
chr1 120724 133723 ENSG00000238009 0 - 120724 120724 0 4 145,59,169,350 0,149,8330,12649
chr1 129080 133566 ENSG00000238009 0 - 129080 129080 0 2 143,193 0,4293
chr1 131024 134836 ENSG00000233750 0 + 131024 131024 0 1 3812 0
chr1 135140 135895 ENSG00000268903 0 - 135140 135140 0 1 755 0
chr1 137681 137965 ENSG00000269981 0 - 137681 137681 0 1 284 0
chr1 139789 140339 ENSG00000239906 0 - 139789 139789 0 2 58,265 0,285
chr1 141473 149707 ENSG00000241860 0 - 141473 141473 0 2 1538,3322 0,4912
chr1 142807 146831 ENSG00000241860 0 - 142807 142807 0 3 204,124,190 0,3578,3834
chr1 146385 173862 ENSG00000241860 0 - 146385 146385 0 8 124,65,529,59,66,216,132,110 0,9381,17877,19498,21714,22663,26171,27367
chr1 157783 157887 ENSG00000222623 0 - 157783 157783 0 1 104 0
chr1 160445 161525 ENSG00000241599 0 + 160445 160445 0 2 245,212 0,868
chr1 165888 168767 ENSG00000241860 0 - 165888 165888 0 3 54,66,158 0,2211,2721
chr1 182695 184174 ENSG00000279928 0 + 182695 182695 0 5 51,85,78,162,194 0,436,798,1044,1285
chr1 185216 195411 ENSG00000279457 0 - 185216 185216 0 10 134,69,153,159,202,136,137,146,112,149 0,274,1100,1912,2159,2538,2913,3222,3574,10046
chr1 187890 187958 ENSG00000273874 0 - 187890 187890 0 1 68 0
chr1 257863 264733 ENSG00000228463 0 - 257863 257863 0 2 1162,130 0,6740
chr1 257912 268816 ENSG00000228463 0 - 257912 257912 0 4 1113,85,902,150 0,3637,9390,10754
chr1 258143 359681 ENSG00000228463 0 - 258143 258143 0 4 882,902,135,337 0,98541,99905,101201
chr1 258523 268816 ENSG00000228463 0 - 258523 258523 0 3 502,902,150 0,8779,10143
chr1 258567 259024 ENSG00000228463 0 - 258567 258567 0 1 457 0
chr1 263014 297502 ENSG00000228463 0 - 263014 263014 0 4 5190,150,105,158 0,5652,26251,34330
chr1 347981 348366 ENSG00000236679 0 - 347981 347981 0 1 385 0
chr1 358856 365704 ENSG00000236601 0 + 358856 358856 0 2 73,534 0,6314
chr1 358871 365510 ENSG00000236601 0 + 358871 358871 0 2 86,340 0,6299
chr1 360056 366052 ENSG00000236601 0 + 360056 360056 0 2 112,882 0,5114
chr1 365388 366151 ENSG00000237094 0 - 365388 365388 0 2 304,133 0,630
chr1 365394 368450 ENSG00000237094 0 - 365394 365394 0 2 298,200 0,2856
chr1 365614 379972 ENSG00000237094 0 - 365614 365614 0 3 78,180,204 0,7529,14154
chr1 373181 485208 ENSG00000237094 0 - 373181 373181 0 3 142,102,169 0,6587,111858
chr1 439869 440232 ENSG00000269732 0 + 439869 439869 0 1 363 0
chr1 450702 451697 ENSG00000284733 0 - 450742 451678 0 1 995 0
chr1 476363 497259 ENSG00000237094 0 - 476363 476363 0 3 582,169,151 0,8676,20745
chr1 484831 495476 ENSG00000237094 0 - 484831 484831 0 3 377,58,200 0,10160,10445
chr1 485025 485208 ENSG00000237094 0 - 485025 485025 0 1 183 0
chr1 485065 489553 ENSG00000237094 0 - 485065 485065 0 2 143,193 0,4295
chr1 487100 489906 ENSG00000233653 0 + 487100 487100 0 2 2287,190 0,2616
chr1 491224 493241 ENSG00000250575 0 - 491224 491224 0 2 765,474 0,1543
chr1 494381 496605 ENSG00000237094 0 - 494381 494381 0 2 205,342 0,1882
chr1 494463 502508 ENSG00000237094 0 - 494463 494463 0 5 435,58,191,65,44 0,528,2645,7092,8001
chr1 494474 495368 ENSG00000237094 0 - 494474 494474 0 3 424,58,92 0,517,802
chr1 494610 499175 ENSG00000237094 0 - 494610 494610 0 3 288,58,492 0,381,4073
chr1 494770 498976 ENSG00000237094 0 - 494770 494770 0 5 128,58,191,58,293 0,221,2338,3628,3913
chr1 497133 498456 ENSG00000237094 0 - 497133 497133 0 3 166,233,58 0,939,1265
chr1 497204 502598 ENSG00000237094 0 - 497204 497204 0 6 24,233,58,65,57,134 0,868,1194,4351,4982,5260
chr1 497209 502873 ENSG00000237094 0 - 497209 497209 0 4 90,58,65,409 0,1189,4346,5255
chr1 497239 499002 ENSG00000237094 0 - 497239 497239 0 4 60,259,58,319 0,807,1159,1444
chr1 497244 502598 ENSG00000237094 0 - 497244 497244 0 5 55,233,58,65,134 0,828,1154,4311,5220
chr1 497274 498976 ENSG00000237094 0 - 497274 497274 0 2 25,578 0,1124
chr1 498280 499175 ENSG00000237094 0 - 498280 498280 0 3 25,58,492 0,118,403
chr1 498983 501607 ENSG00000237094 0 - 498983 498983 0 2 386,52 0,2572
chr1 501587 517252 ENSG00000237094 0 - 501587 501587 0 5 33,94,124,65,68 0,1274,3392,12771,15597
chr1 501603 517225 ENSG00000237094 0 - 501603 501603 0 5 17,197,124,65,70 0,861,3376,12755,15552
chr1 504469 514413 ENSG00000237094 0 - 504469 504469 0 2 464,55 0,9889
chr1 504864 522928 ENSG00000237094 0 - 504864 504864 0 4 239,65,82,70 0,9494,12320,17994
chr1 516375 516479 ENSG00000278757 0 - 516375 516375 0 1 104 0
chr1 586070 612813 ENSG00000230021 0 - 586070 586070 0 6 288,135,128,180,102,73 0,750,8558,15327,21884,26670
chr1 586277 588453 ENSG00000230021 0 - 586277 586277 0 3 81,135,337 0,543,1839
chr1 586944 720194 ENSG00000230021 0 - 586944 586944 0 4 11,105,212,163 0,116740,124766,133087
chr1 587628 594768 ENSG00000235146 0 + 587628 587628 0 2 73,534 0,6606
chr1 587667 594574 ENSG00000235146 0 + 587667 587667 0 2 62,340 0,6567
chr1 594190 633129 ENSG00000230021 0 - 594190 594190 0 5 566,180,102,88,86 0,7207,13764,34728,38853
chr1 594197 631204 ENSG00000230021 0 - 594197 594197 0 6 559,180,102,124,88,74 0,7200,13757,18543,34721,36933
chr1 594307 598551 ENSG00000230021 0 - 594307 594307 0 2 449,1253 0,2991
chr1 594307 827769 ENSG00000230021 0 - 594307 594307 0 4 449,180,212,100 0,7090,117403,233362
chr1 594307 827796 ENSG00000230021 0 - 594307 594307 0 5 449,180,102,33,127 0,7090,13647,104619,233362
chr1 594457 733064 ENSG00000230021 0 - 594457 594457 0 8 299,180,102,33,158,169,191,84 0,6940,13497,104469,117307,125574,137559,138523
chr1 601435 720200 ENSG00000230021 0 - 601435 601435 0 3 142,102,169 0,6519,118596
chr1 627376 631150 ENSG00000230021 0 - 627376 627376 0 4 447,263,88,20 0,584,1542,3754
chr1 629061 629433 ENSG00000225972 0 + 629061 629061 0 1 372 0
chr1 629639 630683 ENSG00000225630 0 + 629639 629639 0 1 1044 0
chr1 631073 632616 ENSG00000237973 0 + 631073 631073 0 1 1543 0
chr1 632324 632413 ENSG00000278791 0 - 632324 632324 0 1 89 0
chr1 632756 633438 ENSG00000229344 0 + 632756 632756 0 1 682 0
chr1 633534 633741 ENSG00000240409 0 + 633534 633534 0 1 207 0
chr1 633695 634376 ENSG00000248527 0 + 633695 633695 0 1 681 0
chr1 634375 634922 ENSG00000198744 0 + 634375 634375 0 1 547 0
chr1 674841 675265 ENSG00000268663 0 + 674841 674841 0 1 424 0
chr1 685678 686673 ENSG00000284662 0 - 685718 686654 0 1 995 0
chr1 701935 720150 ENSG00000230021 0 - 701935 701935 0 3 405,105,119 0,1749,18096
chr1 711866 732212 ENSG00000230021 0 - 711866 711866 0 3 56,169,196 0,8165,20150
chr1 720023 720206 ENSG00000230021 0 - 720023 720023 0 1 183 0
chr1 720052 724564 ENSG00000230021 0 - 720052 720052 0 2 148,207 0,4305
chr1 722091 724903 ENSG00000229376 0 + 722091 722091 0 2 2269,186 0,2626
chr1 725884 778626 ENSG00000228327 0 - 725884 725884 0 16 3920,58,191,171,197,98,124,65,157,525,59,66,216,132,110,343 0,7422,9538,17295,18310,18843,20810,30192,33082,38838,40444,42663,43612,47091,48286,52399
chr1 758232 758336 ENSG00000223181 0 - 758232 758232 0 1 104 0
chr1 760910 761989 ENSG00000229905 0 + 760910 760910 0 2 244,212 0,867
chr1 764722 774280 ENSG00000228327 0 - 764722 764722 0 5 78,104,59,66,110 0,421,1606,3825,9448