mirror of
https://github.com/galaxyproject/galaxy.git
synced 2026-09-24 16:30:27 +08:00
Merge integration branch of 'header_join' into dev
This commit is contained in:
@@ -0,0 +1,4 @@
|
||||
#chr start end gene
|
||||
chr1 10 20 geneA
|
||||
chr1 50 80 geneB
|
||||
chr5 10 40 geneL
|
||||
@@ -0,0 +1,5 @@
|
||||
#gene description
|
||||
geneA tumor-supressor
|
||||
geneB Foxp2
|
||||
geneC Gnas1
|
||||
geneE INK4a
|
||||
@@ -0,0 +1,49 @@
|
||||
chr1 147962192 147962580 CCDS989.1_cds_0_0_chr1_147962193_r 0 - chr1 147962192 147962580 NM_005997_cds_0_0_chr1_147962193_r 0 -
|
||||
chr1 147984545 147984630 CCDS990.1_cds_0_0_chr1_147984546_f 0 + chr1 147984545 147984630 BC007833_cds_0_0_chr1_147984546_f 0 +
|
||||
chr1 148078400 148078582 CCDS993.1_cds_0_0_chr1_148078401_r 0 - chr1 148078400 148078582 AJ011123_cds_0_0_chr1_148078401_r 0 -
|
||||
chr1 148185136 148185276 CCDS996.1_cds_0_0_chr1_148185137_f 0 + chr1 148185136 148185276 NM_002796_cds_0_0_chr1_148185137_f 0 +
|
||||
chr10 55251623 55253124 CCDS7248.1_cds_0_0_chr10_55251624_r 0 - chr10 55251623 55253124 AY029205_cds_0_0_chr10_55251624_r 0 -
|
||||
chr11 116124407 116124501 CCDS8374.1_cds_0_0_chr11_116124408_r 0 - chr11 116124407 116124501 AK057832_cds_0_0_chr11_116124408_r 0 -
|
||||
chr11 116206508 116206563 CCDS8377.1_cds_0_0_chr11_116206509_f 0 + chr11 116206508 116206563 NM_000040_cds_1_0_chr11_116206509_f 0 +
|
||||
chr11 116211733 116212337 CCDS8378.1_cds_0_0_chr11_116211734_r 0 - chr11 116211733 116212337 BC005380_cds_0_0_chr11_116211734_r 0 -
|
||||
chr12 38440094 38440321 CCDS8736.1_cds_0_0_chr12_38440095_r 0 - chr12 38440094 38440321 NM_052885_cds_0_0_chr12_38440095_r 0 -
|
||||
chr13 112381694 112381953 CCDS9526.1_cds_0_0_chr13_112381695_f 0 + chr13 112381694 112381953 NM_207440_cds_1_0_chr13_112381695_f 0 +
|
||||
chr14 98710240 98712285 CCDS9949.1_cds_0_0_chr14_98710241_r 0 - chr14 98710240 98712285 NM_022898_cds_0_0_chr14_98710241_r 0 -
|
||||
chr15 41486872 41487060 CCDS10096.1_cds_0_0_chr15_41486873_r 0 - chr15 41486872 41487060 BX537418_cds_0_0_chr15_41486873_r 0 -
|
||||
chr15 41673708 41673857 CCDS10097.1_cds_0_0_chr15_41673709_f 0 + chr15 41673708 41673857 AK223365_cds_0_0_chr15_41673709_f 0 +
|
||||
chr15 41679161 41679250 CCDS10098.1_cds_0_0_chr15_41679162_r 0 - chr15 41679161 41679250 NM_153700_cds_0_0_chr15_41679162_r 0 -
|
||||
chr16 142908 143003 CCDS10397.1_cds_0_0_chr16_142909_f 0 + chr16 142908 143003 NM_005332_cds_0_0_chr16_142909_f 0 +
|
||||
chr16 244413 244681 CCDS10402.1_cds_0_0_chr16_244414_f 0 + chr16 244413 244681 AK057165_cds_2_0_chr16_244414_f 0 +
|
||||
chr16 259268 259383 CCDS10403.1_cds_0_0_chr16_259269_r 0 - chr16 259268 259383 AB016929_cds_0_0_chr16_259269_r 0 -
|
||||
chr18 23786114 23786321 CCDS11891.1_cds_0_0_chr18_23786115_r 0 - chr18 23786114 23786321 NM_001792_cds_0_0_chr18_23786115_r 0 -
|
||||
chr18 59406881 59407046 CCDS11985.1_cds_0_0_chr18_59406882_f 0 + chr18 59406881 59407046 NM_012397_cds_1_0_chr18_59406882_f 0 +
|
||||
chr18 59455932 59456337 CCDS11986.1_cds_0_0_chr18_59455933_r 0 - chr18 59455932 59456337 AB046400_cds_0_0_chr18_59455933_r 0 -
|
||||
chr19 59068595 59069564 CCDS12866.1_cds_0_0_chr19_59068596_f 0 + chr19 59068595 59069564 BC013995_cds_1_0_chr19_59068596_f 0 +
|
||||
chr19 59236026 59236146 CCDS12872.1_cds_0_0_chr19_59236027_r 0 - chr19 59236026 59236146 NM_198481_cds_0_0_chr19_59236027_r 0 -
|
||||
chr19 59297998 59298008 CCDS12877.1_cds_0_0_chr19_59297999_f 0 + chr19 59297998 59298008 NM_004542_cds_0_0_chr19_59297999_f 0 +
|
||||
chr2 118288583 118288668 CCDS2120.1_cds_0_0_chr2_118288584_f 0 + chr2 118288583 118288668 NM_006773_cds_0_0_chr2_118288584_f 0 +
|
||||
chr2 220229609 220230869 CCDS2443.1_cds_0_0_chr2_220229610_r 0 - chr2 220229609 220230869 NM_024536_cds_0_0_chr2_220229610_r 0 -
|
||||
chr20 33330413 33330423 CCDS13249.1_cds_0_0_chr20_33330414_r 0 - chr20 33330413 33330423 NM_181466_cds_0_0_chr20_33330414_r 0 -
|
||||
chr20 33513606 33513792 CCDS13255.1_cds_0_0_chr20_33513607_f 0 + chr20 33513606 33513792 AF022655_cds_1_0_chr20_33513607_f 0 +
|
||||
chr21 32869641 32870022 CCDS13615.1_cds_0_0_chr21_32869642_r 0 - chr21 32869641 32870022 NM_018277_cds_3_0_chr21_32869642_r 0 -
|
||||
chr21 33321040 33322012 CCDS13620.1_cds_0_0_chr21_33321041_f 0 + chr21 33321040 33322012 NM_005806_cds_1_0_chr21_33321041_f 0 +
|
||||
chr22 30120223 30120265 CCDS13897.1_cds_0_0_chr22_30120224_f 0 + chr22 30120223 30120265 NM_004147_cds_0_0_chr22_30120224_f 0 +
|
||||
chr22 30160419 30160661 CCDS13898.1_cds_0_0_chr22_30160420_r 0 - chr22 30160419 30160661 BC032941_cds_0_0_chr22_30160420_r 0 -
|
||||
chr5 131424298 131424460 CCDS4149.1_cds_0_0_chr5_131424299_f 0 + chr5 131424298 131424460 NM_000588_cds_0_0_chr5_131424299_f 0 +
|
||||
chr5 131556601 131556672 CCDS4151.1_cds_0_0_chr5_131556602_r 0 - chr5 131556601 131556672 BC035813_cds_0_0_chr5_131556602_r 0 -
|
||||
chr5 131621326 131621419 CCDS4152.1_cds_0_0_chr5_131621327_f 0 + chr5 131621326 131621419 BC003096_cds_0_0_chr5_131621327_f 0 +
|
||||
chr6 108299600 108299744 CCDS5061.1_cds_0_0_chr6_108299601_r 0 - chr6 108299600 108299744 NM_007214_cds_0_0_chr6_108299601_r 0 -
|
||||
chr6 108594662 108594687 CCDS5063.1_cds_0_0_chr6_108594663_f 0 + chr6 108594662 108594687 NM_003269_cds_0_0_chr6_108594663_f 0 +
|
||||
chr6 108640045 108640151 CCDS5064.1_cds_0_0_chr6_108640046_r 0 - chr6 108640045 108640151 NM_003795_cds_0_0_chr6_108640046_r 0 -
|
||||
chr6 108722976 108723115 CCDS5067.1_cds_0_0_chr6_108722977_f 0 + chr6 108722976 108723115 NM_145315_cds_0_0_chr6_108722977_f 0 +
|
||||
chr7 113660517 113660685 CCDS5760.1_cds_0_0_chr7_113660518_f 0 + chr7 113660517 113660685 AF467257_cds_1_0_chr7_113660518_f 0 +
|
||||
chr7 116512159 116512389 CCDS5771.1_cds_0_0_chr7_116512160_r 0 - chr7 116512159 116512389 NM_003391_cds_0_0_chr7_116512160_r 0 -
|
||||
chr7 116714099 116714152 CCDS5773.1_cds_0_0_chr7_116714100_f 0 + chr7 116714099 116714152 NM_000492_cds_0_0_chr7_116714100_f 0 +
|
||||
chr7 116945541 116945787 CCDS5774.1_cds_0_0_chr7_116945542_r 0 - chr7 116945541 116945787 AF377960_cds_0_0_chr7_116945542_r 0 -
|
||||
chr8 118881131 118881317 CCDS6324.1_cds_0_0_chr8_118881132_r 0 - chr8 118881131 118881317 NM_000127_cds_0_0_chr8_118881132_r 0 -
|
||||
chr9 128764156 128764189 CCDS6914.1_cds_0_0_chr9_128764157_f 0 + chr9 128764156 128764189 BC051300_cds_0_0_chr9_128764157_f 0 +
|
||||
chr9 128787519 128789136 CCDS6915.1_cds_0_0_chr9_128787520_r 0 - chr9 128787519 128789136 NM_014908_cds_0_0_chr9_128787520_r 0 -
|
||||
chrX 122745047 122745924 CCDS14606.1_cds_0_0_chrX_122745048_f 0 + chrX 122745047 122745924 NM_001167_cds_1_0_chrX_122745048_f 0 +
|
||||
chrX 152648964 152649196 CCDS14733.1_cds_0_0_chrX_152648965_r 0 - chrX 152648964 152649196 NM_000425_cds_0_0_chrX_152648965_r 0 -
|
||||
chrX 152691446 152691471 CCDS14735.1_cds_0_0_chrX_152691447_f 0 + chrX 152691446 152691471 AF101728_cds_0_0_chrX_152691447_f 0 +
|
||||
chrX 152694029 152694263 CCDS14736.1_cds_0_0_chrX_152694030_r 0 - chrX 152694029 152694263 BC052303_cds_0_0_chrX_152694030_r 0 -
|
||||
@@ -0,0 +1,65 @@
|
||||
chr1 147962192 147962580 CCDS989.1_cds_0_0_chr1_147962193_r 0 - chr1 147962192 147962580 NM_005997_cds_0_0_chr1_147962193_r 0 -
|
||||
chr1 147984545 147984630 CCDS990.1_cds_0_0_chr1_147984546_f 0 + chr1 147984545 147984630 BC007833_cds_0_0_chr1_147984546_f 0 +
|
||||
chr1 148078400 148078582 CCDS993.1_cds_0_0_chr1_148078401_r 0 - chr1 148078400 148078582 AJ011123_cds_0_0_chr1_148078401_r 0 -
|
||||
chr1 148185136 148185276 CCDS996.1_cds_0_0_chr1_148185137_f 0 + chr1 148185136 148185276 NM_002796_cds_0_0_chr1_148185137_f 0 +
|
||||
chr10 55251623 55253124 CCDS7248.1_cds_0_0_chr10_55251624_r 0 - chr10 55251623 55253124 AY029205_cds_0_0_chr10_55251624_r 0 -
|
||||
chr11 116124407 116124501 CCDS8374.1_cds_0_0_chr11_116124408_r 0 - chr11 116124407 116124501 AK057832_cds_0_0_chr11_116124408_r 0 -
|
||||
chr11 116206508 116206563 CCDS8377.1_cds_0_0_chr11_116206509_f 0 + chr11 116206508 116206563 NM_000040_cds_1_0_chr11_116206509_f 0 +
|
||||
chr11 116211733 116212337 CCDS8378.1_cds_0_0_chr11_116211734_r 0 - chr11 116211733 116212337 BC005380_cds_0_0_chr11_116211734_r 0 -
|
||||
chr11 1812377 1812407 CCDS7726.1_cds_0_0_chr11_1812378_f 0 +
|
||||
chr12 38440094 38440321 CCDS8736.1_cds_0_0_chr12_38440095_r 0 - chr12 38440094 38440321 NM_052885_cds_0_0_chr12_38440095_r 0 -
|
||||
chr13 112381694 112381953 CCDS9526.1_cds_0_0_chr13_112381695_f 0 + chr13 112381694 112381953 NM_207440_cds_1_0_chr13_112381695_f 0 +
|
||||
chr14 98710240 98712285 CCDS9949.1_cds_0_0_chr14_98710241_r 0 - chr14 98710240 98712285 NM_022898_cds_0_0_chr14_98710241_r 0 -
|
||||
chr15 41486872 41487060 CCDS10096.1_cds_0_0_chr15_41486873_r 0 - chr15 41486872 41487060 BX537418_cds_0_0_chr15_41486873_r 0 -
|
||||
chr15 41673708 41673857 CCDS10097.1_cds_0_0_chr15_41673709_f 0 + chr15 41673708 41673857 AK223365_cds_0_0_chr15_41673709_f 0 +
|
||||
chr15 41679161 41679250 CCDS10098.1_cds_0_0_chr15_41679162_r 0 - chr15 41679161 41679250 NM_153700_cds_0_0_chr15_41679162_r 0 -
|
||||
chr15 41826029 41826196 CCDS10101.1_cds_0_0_chr15_41826030_f 0 +
|
||||
chr16 142908 143003 CCDS10397.1_cds_0_0_chr16_142909_f 0 + chr16 142908 143003 NM_005332_cds_0_0_chr16_142909_f 0 +
|
||||
chr16 179963 180135 CCDS10401.1_cds_0_0_chr16_179964_r 0 -
|
||||
chr16 244413 244681 CCDS10402.1_cds_0_0_chr16_244414_f 0 + chr16 244413 244681 AK057165_cds_2_0_chr16_244414_f 0 +
|
||||
chr16 259268 259383 CCDS10403.1_cds_0_0_chr16_259269_r 0 - chr16 259268 259383 AB016929_cds_0_0_chr16_259269_r 0 -
|
||||
chr18 23786114 23786321 CCDS11891.1_cds_0_0_chr18_23786115_r 0 - chr18 23786114 23786321 NM_001792_cds_0_0_chr18_23786115_r 0 -
|
||||
chr18 59406881 59407046 CCDS11985.1_cds_0_0_chr18_59406882_f 0 + chr18 59406881 59407046 NM_012397_cds_1_0_chr18_59406882_f 0 +
|
||||
chr18 59455932 59456337 CCDS11986.1_cds_0_0_chr18_59455933_r 0 - chr18 59455932 59456337 AB046400_cds_0_0_chr18_59455933_r 0 -
|
||||
chr18 59600586 59600754 CCDS11988.1_cds_0_0_chr18_59600587_f 0 +
|
||||
chr19 59068595 59069564 CCDS12866.1_cds_0_0_chr19_59068596_f 0 + chr19 59068595 59069564 BC013995_cds_1_0_chr19_59068596_f 0 +
|
||||
chr19 59236026 59236146 CCDS12872.1_cds_0_0_chr19_59236027_r 0 - chr19 59236026 59236146 NM_198481_cds_0_0_chr19_59236027_r 0 -
|
||||
chr19 59297998 59298008 CCDS12877.1_cds_0_0_chr19_59297999_f 0 + chr19 59297998 59298008 NM_004542_cds_0_0_chr19_59297999_f 0 +
|
||||
chr19 59302168 59302288 CCDS12878.1_cds_0_0_chr19_59302169_r 0 -
|
||||
chr2 118288583 118288668 CCDS2120.1_cds_0_0_chr2_118288584_f 0 + chr2 118288583 118288668 NM_006773_cds_0_0_chr2_118288584_f 0 +
|
||||
chr2 118394148 118394202 CCDS2121.1_cds_0_0_chr2_118394149_r 0 -
|
||||
chr2 220190202 220190242 CCDS2441.1_cds_0_0_chr2_220190203_f 0 +
|
||||
chr2 220229609 220230869 CCDS2443.1_cds_0_0_chr2_220229610_r 0 - chr2 220229609 220230869 NM_024536_cds_0_0_chr2_220229610_r 0 -
|
||||
chr20 33330413 33330423 CCDS13249.1_cds_0_0_chr20_33330414_r 0 - chr20 33330413 33330423 NM_181466_cds_0_0_chr20_33330414_r 0 -
|
||||
chr20 33513606 33513792 CCDS13255.1_cds_0_0_chr20_33513607_f 0 + chr20 33513606 33513792 AF022655_cds_1_0_chr20_33513607_f 0 +
|
||||
chr20 33579500 33579527 CCDS13256.1_cds_0_0_chr20_33579501_r 0 -
|
||||
chr20 33593260 33593348 CCDS13257.1_cds_0_0_chr20_33593261_f 0 +
|
||||
chr21 32707032 32707192 CCDS13614.1_cds_0_0_chr21_32707033_f 0 +
|
||||
chr21 32869641 32870022 CCDS13615.1_cds_0_0_chr21_32869642_r 0 - chr21 32869641 32870022 NM_018277_cds_3_0_chr21_32869642_r 0 -
|
||||
chr21 33321040 33322012 CCDS13620.1_cds_0_0_chr21_33321041_f 0 + chr21 33321040 33322012 NM_005806_cds_1_0_chr21_33321041_f 0 +
|
||||
chr21 33744994 33745040 CCDS13625.1_cds_0_0_chr21_33744995_r 0 -
|
||||
chr22 30120223 30120265 CCDS13897.1_cds_0_0_chr22_30120224_f 0 + chr22 30120223 30120265 NM_004147_cds_0_0_chr22_30120224_f 0 +
|
||||
chr22 30160419 30160661 CCDS13898.1_cds_0_0_chr22_30160420_r 0 - chr22 30160419 30160661 BC032941_cds_0_0_chr22_30160420_r 0 -
|
||||
chr22 30665273 30665360 CCDS13901.1_cds_0_0_chr22_30665274_f 0 +
|
||||
chr22 30939054 30939266 CCDS13903.1_cds_0_0_chr22_30939055_r 0 -
|
||||
chr5 131424298 131424460 CCDS4149.1_cds_0_0_chr5_131424299_f 0 + chr5 131424298 131424460 NM_000588_cds_0_0_chr5_131424299_f 0 +
|
||||
chr5 131556601 131556672 CCDS4151.1_cds_0_0_chr5_131556602_r 0 - chr5 131556601 131556672 BC035813_cds_0_0_chr5_131556602_r 0 -
|
||||
chr5 131621326 131621419 CCDS4152.1_cds_0_0_chr5_131621327_f 0 + chr5 131621326 131621419 BC003096_cds_0_0_chr5_131621327_f 0 +
|
||||
chr5 131847541 131847666 CCDS4155.1_cds_0_0_chr5_131847542_r 0 -
|
||||
chr6 108299600 108299744 CCDS5061.1_cds_0_0_chr6_108299601_r 0 - chr6 108299600 108299744 NM_007214_cds_0_0_chr6_108299601_r 0 -
|
||||
chr6 108594662 108594687 CCDS5063.1_cds_0_0_chr6_108594663_f 0 + chr6 108594662 108594687 NM_003269_cds_0_0_chr6_108594663_f 0 +
|
||||
chr6 108640045 108640151 CCDS5064.1_cds_0_0_chr6_108640046_r 0 - chr6 108640045 108640151 NM_003795_cds_0_0_chr6_108640046_r 0 -
|
||||
chr6 108722976 108723115 CCDS5067.1_cds_0_0_chr6_108722977_f 0 + chr6 108722976 108723115 NM_145315_cds_0_0_chr6_108722977_f 0 +
|
||||
chr7 113660517 113660685 CCDS5760.1_cds_0_0_chr7_113660518_f 0 + chr7 113660517 113660685 AF467257_cds_1_0_chr7_113660518_f 0 +
|
||||
chr7 116512159 116512389 CCDS5771.1_cds_0_0_chr7_116512160_r 0 - chr7 116512159 116512389 NM_003391_cds_0_0_chr7_116512160_r 0 -
|
||||
chr7 116714099 116714152 CCDS5773.1_cds_0_0_chr7_116714100_f 0 + chr7 116714099 116714152 NM_000492_cds_0_0_chr7_116714100_f 0 +
|
||||
chr7 116945541 116945787 CCDS5774.1_cds_0_0_chr7_116945542_r 0 - chr7 116945541 116945787 AF377960_cds_0_0_chr7_116945542_r 0 -
|
||||
chr8 118881131 118881317 CCDS6324.1_cds_0_0_chr8_118881132_r 0 - chr8 118881131 118881317 NM_000127_cds_0_0_chr8_118881132_r 0 -
|
||||
chr9 128764156 128764189 CCDS6914.1_cds_0_0_chr9_128764157_f 0 + chr9 128764156 128764189 BC051300_cds_0_0_chr9_128764157_f 0 +
|
||||
chr9 128787519 128789136 CCDS6915.1_cds_0_0_chr9_128787520_r 0 - chr9 128787519 128789136 NM_014908_cds_0_0_chr9_128787520_r 0 -
|
||||
chr9 128882427 128882523 CCDS6917.1_cds_0_0_chr9_128882428_f 0 +
|
||||
chr9 128937229 128937445 CCDS6919.1_cds_0_0_chr9_128937230_r 0 -
|
||||
chrX 122745047 122745924 CCDS14606.1_cds_0_0_chrX_122745048_f 0 + chrX 122745047 122745924 NM_001167_cds_1_0_chrX_122745048_f 0 +
|
||||
chrX 152648964 152649196 CCDS14733.1_cds_0_0_chrX_152648965_r 0 - chrX 152648964 152649196 NM_000425_cds_0_0_chrX_152648965_r 0 -
|
||||
chrX 152691446 152691471 CCDS14735.1_cds_0_0_chrX_152691447_f 0 + chrX 152691446 152691471 AF101728_cds_0_0_chrX_152691447_f 0 +
|
||||
chrX 152694029 152694263 CCDS14736.1_cds_0_0_chrX_152694030_r 0 - chrX 152694029 152694263 BC052303_cds_0_0_chrX_152694030_r 0 -
|
||||
@@ -0,0 +1,65 @@
|
||||
chr1 147962192 147962580 CCDS989.1_cds_0_0_chr1_147962193_r 0 - chr1 147962192 147962580 NM_005997_cds_0_0_chr1_147962193_r 0 -
|
||||
chr1 147984545 147984630 CCDS990.1_cds_0_0_chr1_147984546_f 0 + chr1 147984545 147984630 BC007833_cds_0_0_chr1_147984546_f 0 +
|
||||
chr1 148078400 148078582 CCDS993.1_cds_0_0_chr1_148078401_r 0 - chr1 148078400 148078582 AJ011123_cds_0_0_chr1_148078401_r 0 -
|
||||
chr1 148185136 148185276 CCDS996.1_cds_0_0_chr1_148185137_f 0 + chr1 148185136 148185276 NM_002796_cds_0_0_chr1_148185137_f 0 +
|
||||
chr10 55251623 55253124 CCDS7248.1_cds_0_0_chr10_55251624_r 0 - chr10 55251623 55253124 AY029205_cds_0_0_chr10_55251624_r 0 -
|
||||
chr11 116124407 116124501 CCDS8374.1_cds_0_0_chr11_116124408_r 0 - chr11 116124407 116124501 AK057832_cds_0_0_chr11_116124408_r 0 -
|
||||
chr11 116206508 116206563 CCDS8377.1_cds_0_0_chr11_116206509_f 0 + chr11 116206508 116206563 NM_000040_cds_1_0_chr11_116206509_f 0 +
|
||||
chr11 116211733 116212337 CCDS8378.1_cds_0_0_chr11_116211734_r 0 - chr11 116211733 116212337 BC005380_cds_0_0_chr11_116211734_r 0 -
|
||||
chr11 1812377 1812407 CCDS7726.1_cds_0_0_chr11_1812378_f 0 + ~ ~ ~ ~ ~ ~
|
||||
chr12 38440094 38440321 CCDS8736.1_cds_0_0_chr12_38440095_r 0 - chr12 38440094 38440321 NM_052885_cds_0_0_chr12_38440095_r 0 -
|
||||
chr13 112381694 112381953 CCDS9526.1_cds_0_0_chr13_112381695_f 0 + chr13 112381694 112381953 NM_207440_cds_1_0_chr13_112381695_f 0 +
|
||||
chr14 98710240 98712285 CCDS9949.1_cds_0_0_chr14_98710241_r 0 - chr14 98710240 98712285 NM_022898_cds_0_0_chr14_98710241_r 0 -
|
||||
chr15 41486872 41487060 CCDS10096.1_cds_0_0_chr15_41486873_r 0 - chr15 41486872 41487060 BX537418_cds_0_0_chr15_41486873_r 0 -
|
||||
chr15 41673708 41673857 CCDS10097.1_cds_0_0_chr15_41673709_f 0 + chr15 41673708 41673857 AK223365_cds_0_0_chr15_41673709_f 0 +
|
||||
chr15 41679161 41679250 CCDS10098.1_cds_0_0_chr15_41679162_r 0 - chr15 41679161 41679250 NM_153700_cds_0_0_chr15_41679162_r 0 -
|
||||
chr15 41826029 41826196 CCDS10101.1_cds_0_0_chr15_41826030_f 0 + ~ ~ ~ ~ ~ ~
|
||||
chr16 142908 143003 CCDS10397.1_cds_0_0_chr16_142909_f 0 + chr16 142908 143003 NM_005332_cds_0_0_chr16_142909_f 0 +
|
||||
chr16 179963 180135 CCDS10401.1_cds_0_0_chr16_179964_r 0 - ~ ~ ~ ~ ~ ~
|
||||
chr16 244413 244681 CCDS10402.1_cds_0_0_chr16_244414_f 0 + chr16 244413 244681 AK057165_cds_2_0_chr16_244414_f 0 +
|
||||
chr16 259268 259383 CCDS10403.1_cds_0_0_chr16_259269_r 0 - chr16 259268 259383 AB016929_cds_0_0_chr16_259269_r 0 -
|
||||
chr18 23786114 23786321 CCDS11891.1_cds_0_0_chr18_23786115_r 0 - chr18 23786114 23786321 NM_001792_cds_0_0_chr18_23786115_r 0 -
|
||||
chr18 59406881 59407046 CCDS11985.1_cds_0_0_chr18_59406882_f 0 + chr18 59406881 59407046 NM_012397_cds_1_0_chr18_59406882_f 0 +
|
||||
chr18 59455932 59456337 CCDS11986.1_cds_0_0_chr18_59455933_r 0 - chr18 59455932 59456337 AB046400_cds_0_0_chr18_59455933_r 0 -
|
||||
chr18 59600586 59600754 CCDS11988.1_cds_0_0_chr18_59600587_f 0 + ~ ~ ~ ~ ~ ~
|
||||
chr19 59068595 59069564 CCDS12866.1_cds_0_0_chr19_59068596_f 0 + chr19 59068595 59069564 BC013995_cds_1_0_chr19_59068596_f 0 +
|
||||
chr19 59236026 59236146 CCDS12872.1_cds_0_0_chr19_59236027_r 0 - chr19 59236026 59236146 NM_198481_cds_0_0_chr19_59236027_r 0 -
|
||||
chr19 59297998 59298008 CCDS12877.1_cds_0_0_chr19_59297999_f 0 + chr19 59297998 59298008 NM_004542_cds_0_0_chr19_59297999_f 0 +
|
||||
chr19 59302168 59302288 CCDS12878.1_cds_0_0_chr19_59302169_r 0 - ~ ~ ~ ~ ~ ~
|
||||
chr2 118288583 118288668 CCDS2120.1_cds_0_0_chr2_118288584_f 0 + chr2 118288583 118288668 NM_006773_cds_0_0_chr2_118288584_f 0 +
|
||||
chr2 118394148 118394202 CCDS2121.1_cds_0_0_chr2_118394149_r 0 - ~ ~ ~ ~ ~ ~
|
||||
chr2 220190202 220190242 CCDS2441.1_cds_0_0_chr2_220190203_f 0 + ~ ~ ~ ~ ~ ~
|
||||
chr2 220229609 220230869 CCDS2443.1_cds_0_0_chr2_220229610_r 0 - chr2 220229609 220230869 NM_024536_cds_0_0_chr2_220229610_r 0 -
|
||||
chr20 33330413 33330423 CCDS13249.1_cds_0_0_chr20_33330414_r 0 - chr20 33330413 33330423 NM_181466_cds_0_0_chr20_33330414_r 0 -
|
||||
chr20 33513606 33513792 CCDS13255.1_cds_0_0_chr20_33513607_f 0 + chr20 33513606 33513792 AF022655_cds_1_0_chr20_33513607_f 0 +
|
||||
chr20 33579500 33579527 CCDS13256.1_cds_0_0_chr20_33579501_r 0 - ~ ~ ~ ~ ~ ~
|
||||
chr20 33593260 33593348 CCDS13257.1_cds_0_0_chr20_33593261_f 0 + ~ ~ ~ ~ ~ ~
|
||||
chr21 32707032 32707192 CCDS13614.1_cds_0_0_chr21_32707033_f 0 + ~ ~ ~ ~ ~ ~
|
||||
chr21 32869641 32870022 CCDS13615.1_cds_0_0_chr21_32869642_r 0 - chr21 32869641 32870022 NM_018277_cds_3_0_chr21_32869642_r 0 -
|
||||
chr21 33321040 33322012 CCDS13620.1_cds_0_0_chr21_33321041_f 0 + chr21 33321040 33322012 NM_005806_cds_1_0_chr21_33321041_f 0 +
|
||||
chr21 33744994 33745040 CCDS13625.1_cds_0_0_chr21_33744995_r 0 - ~ ~ ~ ~ ~ ~
|
||||
chr22 30120223 30120265 CCDS13897.1_cds_0_0_chr22_30120224_f 0 + chr22 30120223 30120265 NM_004147_cds_0_0_chr22_30120224_f 0 +
|
||||
chr22 30160419 30160661 CCDS13898.1_cds_0_0_chr22_30160420_r 0 - chr22 30160419 30160661 BC032941_cds_0_0_chr22_30160420_r 0 -
|
||||
chr22 30665273 30665360 CCDS13901.1_cds_0_0_chr22_30665274_f 0 + ~ ~ ~ ~ ~ ~
|
||||
chr22 30939054 30939266 CCDS13903.1_cds_0_0_chr22_30939055_r 0 - ~ ~ ~ ~ ~ ~
|
||||
chr5 131424298 131424460 CCDS4149.1_cds_0_0_chr5_131424299_f 0 + chr5 131424298 131424460 NM_000588_cds_0_0_chr5_131424299_f 0 +
|
||||
chr5 131556601 131556672 CCDS4151.1_cds_0_0_chr5_131556602_r 0 - chr5 131556601 131556672 BC035813_cds_0_0_chr5_131556602_r 0 -
|
||||
chr5 131621326 131621419 CCDS4152.1_cds_0_0_chr5_131621327_f 0 + chr5 131621326 131621419 BC003096_cds_0_0_chr5_131621327_f 0 +
|
||||
chr5 131847541 131847666 CCDS4155.1_cds_0_0_chr5_131847542_r 0 - ~ ~ ~ ~ ~ ~
|
||||
chr6 108299600 108299744 CCDS5061.1_cds_0_0_chr6_108299601_r 0 - chr6 108299600 108299744 NM_007214_cds_0_0_chr6_108299601_r 0 -
|
||||
chr6 108594662 108594687 CCDS5063.1_cds_0_0_chr6_108594663_f 0 + chr6 108594662 108594687 NM_003269_cds_0_0_chr6_108594663_f 0 +
|
||||
chr6 108640045 108640151 CCDS5064.1_cds_0_0_chr6_108640046_r 0 - chr6 108640045 108640151 NM_003795_cds_0_0_chr6_108640046_r 0 -
|
||||
chr6 108722976 108723115 CCDS5067.1_cds_0_0_chr6_108722977_f 0 + chr6 108722976 108723115 NM_145315_cds_0_0_chr6_108722977_f 0 +
|
||||
chr7 113660517 113660685 CCDS5760.1_cds_0_0_chr7_113660518_f 0 + chr7 113660517 113660685 AF467257_cds_1_0_chr7_113660518_f 0 +
|
||||
chr7 116512159 116512389 CCDS5771.1_cds_0_0_chr7_116512160_r 0 - chr7 116512159 116512389 NM_003391_cds_0_0_chr7_116512160_r 0 -
|
||||
chr7 116714099 116714152 CCDS5773.1_cds_0_0_chr7_116714100_f 0 + chr7 116714099 116714152 NM_000492_cds_0_0_chr7_116714100_f 0 +
|
||||
chr7 116945541 116945787 CCDS5774.1_cds_0_0_chr7_116945542_r 0 - chr7 116945541 116945787 AF377960_cds_0_0_chr7_116945542_r 0 -
|
||||
chr8 118881131 118881317 CCDS6324.1_cds_0_0_chr8_118881132_r 0 - chr8 118881131 118881317 NM_000127_cds_0_0_chr8_118881132_r 0 -
|
||||
chr9 128764156 128764189 CCDS6914.1_cds_0_0_chr9_128764157_f 0 + chr9 128764156 128764189 BC051300_cds_0_0_chr9_128764157_f 0 +
|
||||
chr9 128787519 128789136 CCDS6915.1_cds_0_0_chr9_128787520_r 0 - chr9 128787519 128789136 NM_014908_cds_0_0_chr9_128787520_r 0 -
|
||||
chr9 128882427 128882523 CCDS6917.1_cds_0_0_chr9_128882428_f 0 + ~ ~ ~ ~ ~ ~
|
||||
chr9 128937229 128937445 CCDS6919.1_cds_0_0_chr9_128937230_r 0 - ~ ~ ~ ~ ~ ~
|
||||
chrX 122745047 122745924 CCDS14606.1_cds_0_0_chrX_122745048_f 0 + chrX 122745047 122745924 NM_001167_cds_1_0_chrX_122745048_f 0 +
|
||||
chrX 152648964 152649196 CCDS14733.1_cds_0_0_chrX_152648965_r 0 - chrX 152648964 152649196 NM_000425_cds_0_0_chrX_152648965_r 0 -
|
||||
chrX 152691446 152691471 CCDS14735.1_cds_0_0_chrX_152691447_f 0 + chrX 152691446 152691471 AF101728_cds_0_0_chrX_152691447_f 0 +
|
||||
chrX 152694029 152694263 CCDS14736.1_cds_0_0_chrX_152694030_r 0 - chrX 152694029 152694263 BC052303_cds_0_0_chrX_152694030_r 0 -
|
||||
@@ -0,0 +1,65 @@
|
||||
chr1 147962192 147962580 CCDS989.1_cds_0_0_chr1_147962193_r 0 - chr1 147962192 147962580 NM_005997_cds_0_0_chr1_147962193_r 0 -
|
||||
chr1 147984545 147984630 CCDS990.1_cds_0_0_chr1_147984546_f 0 + chr1 147984545 147984630 BC007833_cds_0_0_chr1_147984546_f 0 +
|
||||
chr1 148078400 148078582 CCDS993.1_cds_0_0_chr1_148078401_r 0 - chr1 148078400 148078582 AJ011123_cds_0_0_chr1_148078401_r 0 -
|
||||
chr1 148185136 148185276 CCDS996.1_cds_0_0_chr1_148185137_f 0 + chr1 148185136 148185276 NM_002796_cds_0_0_chr1_148185137_f 0 +
|
||||
chr10 55251623 55253124 CCDS7248.1_cds_0_0_chr10_55251624_r 0 - chr10 55251623 55253124 AY029205_cds_0_0_chr10_55251624_r 0 -
|
||||
chr11 116124407 116124501 CCDS8374.1_cds_0_0_chr11_116124408_r 0 - chr11 116124407 116124501 AK057832_cds_0_0_chr11_116124408_r 0 -
|
||||
chr11 116206508 116206563 CCDS8377.1_cds_0_0_chr11_116206509_f 0 + chr11 116206508 116206563 NM_000040_cds_1_0_chr11_116206509_f 0 +
|
||||
chr11 116211733 116212337 CCDS8378.1_cds_0_0_chr11_116211734_r 0 - chr11 116211733 116212337 BC005380_cds_0_0_chr11_116211734_r 0 -
|
||||
chr11 1812377 1812407 CCDS7726.1_cds_0_0_chr11_1812378_f 0 + NoChrom
|
||||
chr12 38440094 38440321 CCDS8736.1_cds_0_0_chr12_38440095_r 0 - chr12 38440094 38440321 NM_052885_cds_0_0_chr12_38440095_r 0 -
|
||||
chr13 112381694 112381953 CCDS9526.1_cds_0_0_chr13_112381695_f 0 + chr13 112381694 112381953 NM_207440_cds_1_0_chr13_112381695_f 0 +
|
||||
chr14 98710240 98712285 CCDS9949.1_cds_0_0_chr14_98710241_r 0 - chr14 98710240 98712285 NM_022898_cds_0_0_chr14_98710241_r 0 -
|
||||
chr15 41486872 41487060 CCDS10096.1_cds_0_0_chr15_41486873_r 0 - chr15 41486872 41487060 BX537418_cds_0_0_chr15_41486873_r 0 -
|
||||
chr15 41673708 41673857 CCDS10097.1_cds_0_0_chr15_41673709_f 0 + chr15 41673708 41673857 AK223365_cds_0_0_chr15_41673709_f 0 +
|
||||
chr15 41679161 41679250 CCDS10098.1_cds_0_0_chr15_41679162_r 0 - chr15 41679161 41679250 NM_153700_cds_0_0_chr15_41679162_r 0 -
|
||||
chr15 41826029 41826196 CCDS10101.1_cds_0_0_chr15_41826030_f 0 + NoChrom
|
||||
chr16 142908 143003 CCDS10397.1_cds_0_0_chr16_142909_f 0 + chr16 142908 143003 NM_005332_cds_0_0_chr16_142909_f 0 +
|
||||
chr16 179963 180135 CCDS10401.1_cds_0_0_chr16_179964_r 0 - NoChrom
|
||||
chr16 244413 244681 CCDS10402.1_cds_0_0_chr16_244414_f 0 + chr16 244413 244681 AK057165_cds_2_0_chr16_244414_f 0 +
|
||||
chr16 259268 259383 CCDS10403.1_cds_0_0_chr16_259269_r 0 - chr16 259268 259383 AB016929_cds_0_0_chr16_259269_r 0 -
|
||||
chr18 23786114 23786321 CCDS11891.1_cds_0_0_chr18_23786115_r 0 - chr18 23786114 23786321 NM_001792_cds_0_0_chr18_23786115_r 0 -
|
||||
chr18 59406881 59407046 CCDS11985.1_cds_0_0_chr18_59406882_f 0 + chr18 59406881 59407046 NM_012397_cds_1_0_chr18_59406882_f 0 +
|
||||
chr18 59455932 59456337 CCDS11986.1_cds_0_0_chr18_59455933_r 0 - chr18 59455932 59456337 AB046400_cds_0_0_chr18_59455933_r 0 -
|
||||
chr18 59600586 59600754 CCDS11988.1_cds_0_0_chr18_59600587_f 0 + NoChrom
|
||||
chr19 59068595 59069564 CCDS12866.1_cds_0_0_chr19_59068596_f 0 + chr19 59068595 59069564 BC013995_cds_1_0_chr19_59068596_f 0 +
|
||||
chr19 59236026 59236146 CCDS12872.1_cds_0_0_chr19_59236027_r 0 - chr19 59236026 59236146 NM_198481_cds_0_0_chr19_59236027_r 0 -
|
||||
chr19 59297998 59298008 CCDS12877.1_cds_0_0_chr19_59297999_f 0 + chr19 59297998 59298008 NM_004542_cds_0_0_chr19_59297999_f 0 +
|
||||
chr19 59302168 59302288 CCDS12878.1_cds_0_0_chr19_59302169_r 0 - NoChrom
|
||||
chr2 118288583 118288668 CCDS2120.1_cds_0_0_chr2_118288584_f 0 + chr2 118288583 118288668 NM_006773_cds_0_0_chr2_118288584_f 0 +
|
||||
chr2 118394148 118394202 CCDS2121.1_cds_0_0_chr2_118394149_r 0 - NoChrom
|
||||
chr2 220190202 220190242 CCDS2441.1_cds_0_0_chr2_220190203_f 0 + NoChrom
|
||||
chr2 220229609 220230869 CCDS2443.1_cds_0_0_chr2_220229610_r 0 - chr2 220229609 220230869 NM_024536_cds_0_0_chr2_220229610_r 0 -
|
||||
chr20 33330413 33330423 CCDS13249.1_cds_0_0_chr20_33330414_r 0 - chr20 33330413 33330423 NM_181466_cds_0_0_chr20_33330414_r 0 -
|
||||
chr20 33513606 33513792 CCDS13255.1_cds_0_0_chr20_33513607_f 0 + chr20 33513606 33513792 AF022655_cds_1_0_chr20_33513607_f 0 +
|
||||
chr20 33579500 33579527 CCDS13256.1_cds_0_0_chr20_33579501_r 0 - NoChrom
|
||||
chr20 33593260 33593348 CCDS13257.1_cds_0_0_chr20_33593261_f 0 + NoChrom
|
||||
chr21 32707032 32707192 CCDS13614.1_cds_0_0_chr21_32707033_f 0 + NoChrom
|
||||
chr21 32869641 32870022 CCDS13615.1_cds_0_0_chr21_32869642_r 0 - chr21 32869641 32870022 NM_018277_cds_3_0_chr21_32869642_r 0 -
|
||||
chr21 33321040 33322012 CCDS13620.1_cds_0_0_chr21_33321041_f 0 + chr21 33321040 33322012 NM_005806_cds_1_0_chr21_33321041_f 0 +
|
||||
chr21 33744994 33745040 CCDS13625.1_cds_0_0_chr21_33744995_r 0 - NoChrom
|
||||
chr22 30120223 30120265 CCDS13897.1_cds_0_0_chr22_30120224_f 0 + chr22 30120223 30120265 NM_004147_cds_0_0_chr22_30120224_f 0 +
|
||||
chr22 30160419 30160661 CCDS13898.1_cds_0_0_chr22_30160420_r 0 - chr22 30160419 30160661 BC032941_cds_0_0_chr22_30160420_r 0 -
|
||||
chr22 30665273 30665360 CCDS13901.1_cds_0_0_chr22_30665274_f 0 + NoChrom
|
||||
chr22 30939054 30939266 CCDS13903.1_cds_0_0_chr22_30939055_r 0 - NoChrom
|
||||
chr5 131424298 131424460 CCDS4149.1_cds_0_0_chr5_131424299_f 0 + chr5 131424298 131424460 NM_000588_cds_0_0_chr5_131424299_f 0 +
|
||||
chr5 131556601 131556672 CCDS4151.1_cds_0_0_chr5_131556602_r 0 - chr5 131556601 131556672 BC035813_cds_0_0_chr5_131556602_r 0 -
|
||||
chr5 131621326 131621419 CCDS4152.1_cds_0_0_chr5_131621327_f 0 + chr5 131621326 131621419 BC003096_cds_0_0_chr5_131621327_f 0 +
|
||||
chr5 131847541 131847666 CCDS4155.1_cds_0_0_chr5_131847542_r 0 - NoChrom
|
||||
chr6 108299600 108299744 CCDS5061.1_cds_0_0_chr6_108299601_r 0 - chr6 108299600 108299744 NM_007214_cds_0_0_chr6_108299601_r 0 -
|
||||
chr6 108594662 108594687 CCDS5063.1_cds_0_0_chr6_108594663_f 0 + chr6 108594662 108594687 NM_003269_cds_0_0_chr6_108594663_f 0 +
|
||||
chr6 108640045 108640151 CCDS5064.1_cds_0_0_chr6_108640046_r 0 - chr6 108640045 108640151 NM_003795_cds_0_0_chr6_108640046_r 0 -
|
||||
chr6 108722976 108723115 CCDS5067.1_cds_0_0_chr6_108722977_f 0 + chr6 108722976 108723115 NM_145315_cds_0_0_chr6_108722977_f 0 +
|
||||
chr7 113660517 113660685 CCDS5760.1_cds_0_0_chr7_113660518_f 0 + chr7 113660517 113660685 AF467257_cds_1_0_chr7_113660518_f 0 +
|
||||
chr7 116512159 116512389 CCDS5771.1_cds_0_0_chr7_116512160_r 0 - chr7 116512159 116512389 NM_003391_cds_0_0_chr7_116512160_r 0 -
|
||||
chr7 116714099 116714152 CCDS5773.1_cds_0_0_chr7_116714100_f 0 + chr7 116714099 116714152 NM_000492_cds_0_0_chr7_116714100_f 0 +
|
||||
chr7 116945541 116945787 CCDS5774.1_cds_0_0_chr7_116945542_r 0 - chr7 116945541 116945787 AF377960_cds_0_0_chr7_116945542_r 0 -
|
||||
chr8 118881131 118881317 CCDS6324.1_cds_0_0_chr8_118881132_r 0 - chr8 118881131 118881317 NM_000127_cds_0_0_chr8_118881132_r 0 -
|
||||
chr9 128764156 128764189 CCDS6914.1_cds_0_0_chr9_128764157_f 0 + chr9 128764156 128764189 BC051300_cds_0_0_chr9_128764157_f 0 +
|
||||
chr9 128787519 128789136 CCDS6915.1_cds_0_0_chr9_128787520_r 0 - chr9 128787519 128789136 NM_014908_cds_0_0_chr9_128787520_r 0 -
|
||||
chr9 128882427 128882523 CCDS6917.1_cds_0_0_chr9_128882428_f 0 + NoChrom
|
||||
chr9 128937229 128937445 CCDS6919.1_cds_0_0_chr9_128937230_r 0 - NoChrom
|
||||
chrX 122745047 122745924 CCDS14606.1_cds_0_0_chrX_122745048_f 0 + chrX 122745047 122745924 NM_001167_cds_1_0_chrX_122745048_f 0 +
|
||||
chrX 152648964 152649196 CCDS14733.1_cds_0_0_chrX_152648965_r 0 - chrX 152648964 152649196 NM_000425_cds_0_0_chrX_152648965_r 0 -
|
||||
chrX 152691446 152691471 CCDS14735.1_cds_0_0_chrX_152691447_f 0 + chrX 152691446 152691471 AF101728_cds_0_0_chrX_152691447_f 0 +
|
||||
chrX 152694029 152694263 CCDS14736.1_cds_0_0_chrX_152694030_r 0 - chrX 152694029 152694263 BC052303_cds_0_0_chrX_152694030_r 0 -
|
||||
@@ -0,0 +1,3 @@
|
||||
#chr start end gene gene description
|
||||
chr1 10 20 geneA geneA tumor-supressor
|
||||
chr1 50 80 geneB geneB Foxp2
|
||||
@@ -0,0 +1,4 @@
|
||||
#chr start end gene gene description
|
||||
chr1 10 20 geneA geneA tumor-supressor
|
||||
chr1 50 80 geneB geneB Foxp2
|
||||
chr5 10 40 geneL . .
|
||||
@@ -0,0 +1,2 @@
|
||||
chr1 10 20 geneA geneA tumor-supressor
|
||||
chr1 50 80 geneB geneB Foxp2
|
||||
+18
-2
@@ -11,6 +11,7 @@ from __future__ import print_function
|
||||
import json
|
||||
import optparse
|
||||
import os
|
||||
import re
|
||||
import struct
|
||||
import sys
|
||||
import tempfile
|
||||
@@ -284,7 +285,7 @@ def fill_empty_columns(line, split, fill_values):
|
||||
return split.join(filled_columns)
|
||||
|
||||
|
||||
def join_files(filename1, column1, filename2, column2, out_filename, split=None, buffer=1000000, keep_unmatched=False, keep_partial=False, index_depth=3, fill_options=None):
|
||||
def join_files(filename1, column1, filename2, column2, out_filename, split=None, buffer=1000000, keep_unmatched=False, keep_partial=False, keep_headers=False, index_depth=3, fill_options=None):
|
||||
# return identifier based upon line
|
||||
def get_identifier_by_line(line, column, split=None):
|
||||
if isinstance(line, str):
|
||||
@@ -294,9 +295,18 @@ def join_files(filename1, column1, filename2, column2, out_filename, split=None,
|
||||
return None
|
||||
if fill_options is None:
|
||||
fill_options = Bunch(fill_unjoined_only=True, file1_columns=None, file2_columns=None)
|
||||
keep_headers_done = False
|
||||
out = open(out_filename, 'w+b')
|
||||
index = BufferedIndex(filename2, column2, split, buffer, index_depth)
|
||||
for line1 in open(filename1, 'rb'):
|
||||
if keep_headers and not keep_headers_done:
|
||||
header1 = line1
|
||||
with open(filename2, 'r') as file2:
|
||||
header2 = file2.readline()
|
||||
header2 = re.sub(r'^#', '', header2)
|
||||
out.write("%s%s%s\n" % (header1.rstrip('\r\n'), split, header2.rstrip('\r\n')))
|
||||
keep_headers_done = True
|
||||
continue
|
||||
identifier = get_identifier_by_line(line1, column1, split)
|
||||
if identifier:
|
||||
written = False
|
||||
@@ -352,6 +362,12 @@ def main():
|
||||
dest='fill_options_file',
|
||||
type='str', default=None,
|
||||
help='Fill empty columns with a values from a JSONified file.')
|
||||
parser.add_option(
|
||||
'-H', '--keep_headers',
|
||||
action='store_true',
|
||||
dest='keep_headers',
|
||||
default=False,
|
||||
help='Keep the headers')
|
||||
|
||||
options, args = parser.parse_args()
|
||||
|
||||
@@ -383,7 +399,7 @@ def main():
|
||||
# Character for splitting fields and joining lines
|
||||
split = "\t"
|
||||
|
||||
return join_files(filename1, column1, filename2, column2, out_filename, split, options.buffer, options.keep_unmatched, options.keep_partial, options.index_depth, fill_options=fill_options)
|
||||
return join_files(filename1, column1, filename2, column2, out_filename, split, options.buffer, options.keep_unmatched, options.keep_partial, options.keep_headers, options.index_depth, fill_options=fill_options)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
+76
-30
@@ -1,6 +1,37 @@
|
||||
<tool id="join1" name="Join two Datasets" version="2.0.2">
|
||||
<tool id="join1" name="Join two Datasets" version="2.1.0">
|
||||
<description>side by side on a specified field</description>
|
||||
<command interpreter="python">join.py $input1 $input2 $field1 $field2 $out_file1 $unmatched $partial --index_depth=3 --buffer=50000000 --fill_options_file=$fill_options_file</command>
|
||||
<requirements>
|
||||
<requirement type="package" version="2.7.13">python</requirement>
|
||||
</requirements>
|
||||
<command detect_errors="aggressive">
|
||||
python '$__tool_directory__/join.py' '$input1' '$input2' $field1 $field2 '$out_file1' $unmatched $partial --index_depth=3 --buffer=50000000 --fill_options_file=$fill_options_file $header
|
||||
</command>
|
||||
<configfiles>
|
||||
<configfile name="fill_options_file"><%
|
||||
import json
|
||||
%>
|
||||
#set $__fill_options = {}
|
||||
#if $fill_empty_columns['fill_empty_columns_switch'] == 'fill_empty':
|
||||
#set $__fill_options['fill_unjoined_only'] = $fill_empty_columns['fill_columns_by'].value == 'fill_unjoined_only'
|
||||
#if $fill_empty_columns['do_fill_empty_columns']['column_fill_type'] == 'single_fill_value':
|
||||
#set $__start_fill = $fill_empty_columns['do_fill_empty_columns']['fill_value'].value
|
||||
#else:
|
||||
#set $__start_fill = ""
|
||||
#end if
|
||||
#set $__fill_options['file1_columns'] = [ __start_fill for i in range( int( $input1.metadata.columns ) ) ]
|
||||
#set $__fill_options['file2_columns'] = [ __start_fill for i in range( int( $input2.metadata.columns ) ) ]
|
||||
#if $fill_empty_columns['do_fill_empty_columns']['column_fill_type'] == 'fill_value_by_column':
|
||||
#for column_fill1 in $fill_empty_columns['do_fill_empty_columns']['column_fill1']:
|
||||
#set $__fill_options['file1_columns'][ int( column_fill1['column_number1'].value ) - 1 ] = column_fill1['fill_value1'].value
|
||||
#end for
|
||||
#for column_fill2 in $fill_empty_columns['do_fill_empty_columns']['column_fill2']:
|
||||
#set $__fill_options['file2_columns'][ int( column_fill2['column_number2'].value ) - 1 ] = column_fill2['fill_value2'].value
|
||||
#end for
|
||||
#end if
|
||||
#end if
|
||||
${json.dumps( __fill_options )}
|
||||
</configfile>
|
||||
</configfiles>
|
||||
<inputs>
|
||||
<param format="tabular" name="input1" type="data" label="Join"/>
|
||||
<param name="field1" label="using column" type="data_column" data_ref="input1" />
|
||||
@@ -48,35 +79,13 @@
|
||||
</conditional>
|
||||
</when>
|
||||
</conditional>
|
||||
<param name="header" type="select" label="Keep the header lines">
|
||||
<option value="-H">Yes</option>
|
||||
<option value="" selected="true">No</option>
|
||||
</param>
|
||||
</inputs>
|
||||
<configfiles>
|
||||
<configfile name="fill_options_file"><%
|
||||
import json
|
||||
%>
|
||||
#set $__fill_options = {}
|
||||
#if $fill_empty_columns['fill_empty_columns_switch'] == 'fill_empty':
|
||||
#set $__fill_options['fill_unjoined_only'] = $fill_empty_columns['fill_columns_by'].value == 'fill_unjoined_only'
|
||||
#if $fill_empty_columns['do_fill_empty_columns']['column_fill_type'] == 'single_fill_value':
|
||||
#set $__start_fill = $fill_empty_columns['do_fill_empty_columns']['fill_value'].value
|
||||
#else:
|
||||
#set $__start_fill = ""
|
||||
#end if
|
||||
#set $__fill_options['file1_columns'] = [ __start_fill for i in range( int( $input1.metadata.columns ) ) ]
|
||||
#set $__fill_options['file2_columns'] = [ __start_fill for i in range( int( $input2.metadata.columns ) ) ]
|
||||
#if $fill_empty_columns['do_fill_empty_columns']['column_fill_type'] == 'fill_value_by_column':
|
||||
#for column_fill1 in $fill_empty_columns['do_fill_empty_columns']['column_fill1']:
|
||||
#set $__fill_options['file1_columns'][ int( column_fill1['column_number1'].value ) - 1 ] = column_fill1['fill_value1'].value
|
||||
#end for
|
||||
#for column_fill2 in $fill_empty_columns['do_fill_empty_columns']['column_fill2']:
|
||||
#set $__fill_options['file2_columns'][ int( column_fill2['column_number2'].value ) - 1 ] = column_fill2['fill_value2'].value
|
||||
#end for
|
||||
#end if
|
||||
#end if
|
||||
${json.dumps( __fill_options )}
|
||||
</configfile>
|
||||
</configfiles>
|
||||
<outputs>
|
||||
<data format="input" name="out_file1" metadata_source="input1" />
|
||||
<data format_source="input" name="out_file1" metadata_source="input1" />
|
||||
</outputs>
|
||||
<tests>
|
||||
<test>
|
||||
@@ -128,6 +137,42 @@ ${json.dumps( __fill_options )}
|
||||
<param name="fill_value2" value="NoChrom"/>
|
||||
<output name="out_file1" file="joiner_out4.bed"/>
|
||||
</test>
|
||||
<test>
|
||||
<param name="input1" value="joiner_header_in1.tab"/>
|
||||
<param name="input2" value="joiner_header_in2.tab"/>
|
||||
<param name="field1" value="4"/>
|
||||
<param name="field2" value="1"/>
|
||||
<param name="unmatched" value=""/>
|
||||
<param name="partial" value=""/>
|
||||
<param name="header" value="-H"/>
|
||||
<param name="fill_empty_columns_switch" value="no_fill"/>
|
||||
<output name="out_file1" file="joiner_out5.tab"/>
|
||||
</test>
|
||||
<test>
|
||||
<param name="input1" value="joiner_header_in1.tab"/>
|
||||
<param name="input2" value="joiner_header_in2.tab"/>
|
||||
<param name="field1" value="4"/>
|
||||
<param name="field2" value="1"/>
|
||||
<param name="unmatched" value="Yes"/>
|
||||
<param name="partial" value="Yes"/>
|
||||
<param name="header" value="-H"/>
|
||||
<param name="fill_empty_columns_switch" value="fill_empty"/>
|
||||
<param name="fill_columns_by" value="fill_all"/>
|
||||
<param name="column_fill_type" value="single_fill_value"/>
|
||||
<param name="fill_value" value="."/>
|
||||
<output name="out_file1" file="joiner_out6.tab"/>
|
||||
</test>
|
||||
<test>
|
||||
<param name="input1" value="joiner_header_in1.tab"/>
|
||||
<param name="input2" value="joiner_header_in2.tab"/>
|
||||
<param name="field1" value="4"/>
|
||||
<param name="field2" value="1"/>
|
||||
<param name="unmatched" value=""/>
|
||||
<param name="partial" value=""/>
|
||||
<param name="header" value=""/>
|
||||
<param name="fill_empty_columns_switch" value="no_fill"/>
|
||||
<output name="out_file1" file="joiner_out7.tab"/>
|
||||
</test>
|
||||
</tests>
|
||||
<help>
|
||||
|
||||
@@ -154,7 +199,7 @@ You may choose to include lines of your first input that do not join with your s
|
||||
|
||||
Dataset1::
|
||||
|
||||
chr1 10 20 geneA
|
||||
chr1 10 20 geneA
|
||||
chr1 50 80 geneB
|
||||
chr5 10 40 geneL
|
||||
|
||||
@@ -177,4 +222,5 @@ Joining the 4th column of Dataset1 with the 1st column of Dataset2, while keepin
|
||||
chr5 10 40 geneL
|
||||
|
||||
</help>
|
||||
<citations></citations>
|
||||
</tool>
|
||||
|
||||
Reference in New Issue
Block a user