# HG changeset patch # User iuc # Date 1572627292 14400 # Node ID 6ea09f60dee99b569755a74511cf4cba9b3bb357 # Parent 69e0806b63a44bd6d3d6d8cc5b6f0a744c8f07aa "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/gffread commit 956566e1f7b4390719db56b7488a720ccad181a4" diff -r 69e0806b63a4 -r 6ea09f60dee9 cuff_macros.xml --- a/cuff_macros.xml Tue Oct 01 12:20:13 2019 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,85 +0,0 @@ - - 2.2.1 - - - - cufflinks - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - #if $in_type.set_in_type in ['BAM', 'CXB'] - #for $condition in $in_type.conditions: - #set samples = ','.join( [ str( $sample ) for $sample in $condition.samples ] ) - '$samples' - #end for - #elif $in_type.set_in_type == 'CONDITION_LIST' - #for $sample in $in_type.conditions: - '$sample' - #end for - #elif $in_type.set_in_type == 'CONDITION_REPLICATE_LIST' - #for $condition_list in $in_type.conditions: - #set samples = ','.join( [ str( $sample ) for $sample in $condition_list ] ) - '$samples' - #end for - #end if - - - #import re - #if $in_type.set_in_type in ['BAM', 'CXB'] - #set labels = '\'' + '\',\''.join( [ str( $condition.name ) for $condition in $in_type.conditions ] ) + '\'' - #elif $in_type.set_in_type in ['CONDITION_LIST', 'CONDITION_REPLICATE_LIST'] - #set labels = '\'' + '\',\''.join( map(lambda x: re.sub('[^\w\-_]', '_', x), $in_type.conditions.keys() ) ) + '\'' - #end if - --labels $labels - - - - - - - - - ## Inputs. - #for $input_file in $inputs: - '${input_file}' - #end for - #for $additional_input in $additional_inputs: - #for $input_file in $additional_input.additional_inputs: - '${input_file}' - #end for - #end for - - getattr(inputs, "__len__", [].__len__)() >= 2 - diff -r 69e0806b63a4 -r 6ea09f60dee9 gffread.xml --- a/gffread.xml Tue Oct 01 12:20:13 2019 -0400 +++ b/gffread.xml Fri Nov 01 12:54:52 2019 -0400 @@ -1,7 +1,7 @@ - + Filters and/or converts GFF3/GTF2 records - cuff_macros.xml + 0.11.4 @@ -47,7 +47,9 @@ - + + gffread + coding only: discard mRNAs that have no CDS feature (-C) - + + @@ -272,10 +276,13 @@ - + + + @@ -335,25 +343,25 @@ - + - + - + - + @@ -364,89 +372,140 @@ is a tab-delimited file providing this info - for each of the mapped sequences: -

- (useful for -A option with mRNA/EST/protein mappings) - -i discard transcripts having an intron larger than - -r only show transcripts overlapping coordinate range .. - (on chromosome/contig , strand if provided) - -R for -r option, discard all transcripts that are not fully - contained within the given range - -U discard single-exon transcripts - -C coding only: discard mRNAs that have no CDS feature - -F full GFF attribute preservation (all attributes are shown) - -G only parse additional exon attributes from the first exon - and move them to the mRNA level (useful for GTF input) - -A use the description field from and add it - as the value for a 'descr' attribute to the GFF record + gffread [-g | ][-s ] + [-o ] [-t ] [-r [[]:].. [-R]] + [-CTVNJMKQAFPGUBHZWTOLE] [-w ] [-x ] [-y ] + [-i ] [--bed] [--table ] [--sort-by ] + + Filter, convert or cluster GFF/GTF/BED records, extract the sequence of + transcripts (exon or CDS) and more. + By default (i.e. without -O) only transcripts are processed, discarding any + other non-transcript features. Default output is a simplified GFF3 with only + the basic attributes. + + is a GFF file, use '-' for stdin + + Options: - -O process also non-transcript GFF records (by default non-transcript - records are ignored) - -V discard any mRNAs with CDS having in-frame stop codons - -H for -V option, check and adjust the starting CDS phase - if the original phase leads to a translation with an - in-frame stop codon - -B for -V option, single-exon transcripts are also checked on the - opposite strand - -N discard multi-exon mRNAs that have any intron with a non-canonical - splice site consensus (i.e. not GT-AG, GC-AG or AT-AC) - -J discard any mRNAs that either lack initial START codon - or the terminal STOP codon, or have an in-frame stop codon - (only print mRNAs with a fulll, valid CDS) - --no-pseudo: filter out records matching the 'pseudo' keyword - - -M/--merge : cluster the input transcripts into loci, collapsing matching - transcripts (those with the same exact introns and fully contained) - -d : for -M option, write collapsing info to file - --cluster-only: same as --merge but without collapsing matching transcripts - -K for -M option: also collapse shorter, fully contained transcripts - with fewer introns than the container - -Q for -M option, remove the containment restriction: - (multi-exon transcripts will be collapsed if just their introns match, - while single-exon transcripts can partially overlap (80%)) - - --force-exons: make sure that the lowest level GFF features are printed as - "exon" features - -E expose (warn about) duplicate transcript IDs and other potential - problems with the given GFF/GTF records - -D decode url encoded characters within attributes - -Z merge close exons into a single exon (for intron size<4) - -w write a fasta file with spliced exons for each GFF transcript - -x write a fasta file with spliced CDS for each GFF transcript - -W for -w and -x options, also write for each fasta record the exon - coordinates projected onto the spliced sequence - -y write a protein fasta file with the translation of CDS for each record - -L Ensembl GTF to GFF3 conversion (implies -F; should be used with -m) - -m is a reference (genomic) sequence replacement table with - this format: - - For example from UCSC naming to Ensembl naming: - chr1 1 - chr2 2 - GFF records on reference sequences that are not found among the - entries in this file will be filtered out - -o the "filtered" GFF records will be written to - (use -o- for printing to stdout) - -t use in the second column of each GFF output line - -T -o option will output GTF format instead of GFF3 - + -i discard transcripts having an intron larger than + -l discard transcripts shorter than bases + -r only show transcripts overlapping coordinate range .. + (on chromosome/contig , strand if provided) + -R for -r option, discard all transcripts that are not fully + contained within the given range + -U discard single-exon transcripts + -C coding only: discard mRNAs that have no CDS features + --nc non-coding only: discard mRNAs that have CDS features + --ignore-locus : discard locus features and attributes found in the input + -A use the description field from and add it + as the value for a 'descr' attribute to the GFF record + -s is a tab-delimited file providing this info + for each of the mapped sequences: +

+ (useful for -A option with mRNA/EST/protein mappings) + + Sorting: (by default, chromosomes are kept in the order they were found) + --sort-alpha : chromosomes (reference sequences) are sorted alphabetically + --sort-by : sort the reference sequences by the order in which their + names are given in the file + + Misc options: + -F preserve all GFF attributes (for non-exon features) + --keep-exon-attrs : for -F option, do not attempt to reduce redundant + exon/CDS attributes + -G do not keep exon attributes, move them to the transcript feature + (for GFF3 output) + --keep-genes : in transcript-only mode (default), also preserve gene records + --keep-comments: for GFF3 input/output, try to preserve comments + -O process other non-transcript GFF records (by default non-transcript + records are ignored) + -V discard any mRNAs with CDS having in-frame stop codons (requires -g) + -H for -V option, check and adjust the starting CDS phase + if the original phase leads to a translation with an + in-frame stop codon + -B for -V option, single-exon transcripts are also checked on the + opposite strand (requires -g) + -P add transcript level GFF attributes about the coding status of each + transcript, including partialness or in-frame stop codons (requires -g) + --add-hasCDS : add a "hasCDS" attribute with value "true" for transcripts + that have CDS features + --adj-stop stop codon adjustment: enables -P and performs automatic + adjustment of the CDS stop coordinate if premature or downstream + -N discard multi-exon mRNAs that have any intron with a non-canonical + splice site consensus (i.e. not GT-AG, GC-AG or AT-AC) + -J discard any mRNAs that either lack initial START codon + or the terminal STOP codon, or have an in-frame stop codon + (i.e. only print mRNAs with a complete CDS) + --no-pseudo: filter out records matching the 'pseudo' keyword + --in-bed: input should be parsed as BED format (automatic if the input + filename ends with .bed*) + --in-tlf: input GFF-like one-line-per-transcript format without exon/CDS + features (see --tlf option below); automatic if the input + filename ends with .tlf) + + Clustering: + -M/--merge : cluster the input transcripts into loci, discarding + "duplicated" transcripts (those with the same exact introns + and fully contained or equal boundaries) + -d : for -M option, write duplication info to file + --cluster-only: same as -M/--merge but without discarding any of the + "duplicate" transcripts, only create "locus" features + -K for -M option: also discard as redundant the shorter, fully contained + transcripts (intron chains matching a part of the container) + -Q for -M option, no longer require boundary containment when assessing + redundancy (can be combined with -K); only introns have to match for + multi-exon transcripts, and >=80% overlap for single-exon transcripts + -Y for -M option, enforce -Q but also discard overlapping single-exon + transcripts, even on the opposite strand (can be combined with -K) + + Output options: + --force-exons: make sure that the lowest level GFF features are considered + "exon" features + --gene2exon: for single-line genes not parenting any transcripts, add an + exon feature spanning the entire gene (treat it as a transcript) + --t-adopt: try to find a parent gene overlapping/containing a transcript + that does not have any explicit gene Parent + -D decode url encoded characters within attributes + -Z merge very close exons into a single exon (when intron size<4) + -g full path to a multi-fasta file with the genomic sequences + for all input mappings, OR a directory with single-fasta files + (one per genomic sequence, with file names matching sequence names) + -w write a fasta file with spliced exons for each GFF transcript + -x write a fasta file with spliced CDS for each GFF transcript + -y write a protein fasta file with the translation of CDS for each record + -W for -w and -x options, write in the FASTA defline the exon + coordinates projected onto the spliced sequence; + for -y option, write transcript attributes in the FASTA defline + -S for -y option, use '*' instead of '.' as stop codon translation + -L Ensembl GTF to GFF3 conversion (implies -F; should be used with -m) + -m is a name mapping table for converting reference + sequence names, having this 2-column format: + + WARNING: all GFF records on reference sequences whose original IDs + are not found in the 1st column of this table will be discarded! + -t use in the 2nd column of each GFF/GTF output line + -o write the records into instead of stdout + -T main output will be GTF instead of GFF3 + --bed output records in BED format instead of default GFF3 + --tlf output "transcript line format" which is like GFF + but exons, CDS features and related data are stored as GFF + attributes in the transcript feature line, like this: + exoncount=N;exons=;CDSphase=;CDS= + is a comma-delimited list of exon_start-exon_end coordinates; + is CDS_start:CDS_end coordinates or a list like + --table output a simple tab delimited format instead of GFF, with columns + having the values of GFF attributes given in ; special + pseudo-attributes (prefixed by @) are recognized: + @chr, @start, @end, @strand, @numexons, @exons, @cds, @covlen, @cdslen + -v,-E expose (warn about) duplicate transcript IDs and other potential + problems with the given GFF/GTF records ]]> diff -r 69e0806b63a4 -r 6ea09f60dee9 test-data/Homo_sapiens.GRCh37_19.71.gff3 --- a/test-data/Homo_sapiens.GRCh37_19.71.gff3 Tue Oct 01 12:20:13 2019 -0400 +++ b/test-data/Homo_sapiens.GRCh37_19.71.gff3 Fri Nov 01 12:54:52 2019 -0400 @@ -1,4 +1,5 @@ -# gffread test-data/Homo_sapiens.GRCh37_19.71.gtf -o test-data/Homo_sapiens.GRCh37_19.71.gff3 +# gffread /tmp/tmpq6d_yfqc/files/9/2/2/dataset_922cd54b-d77c-48fb-abf7-6fc8d8fdb97c.dat -o output.gff3 +# gffread v0.11.4 ##gff-version 3 19 snRNA transcript 223158 223261 . - . ID=ENST00000410397;geneID=ENSG00000222329;gene_name=U6 19 snRNA exon 223158 223261 . - . Parent=ENST00000410397 @@ -9,55 +10,55 @@ 19 processed_pseudogene exon 239145 239247 . - . Parent=ENST00000588755 19 processed_pseudogene transcript 279495 280170 . + . ID=ENST00000589981;geneID=ENSG00000267447;gene_name=VN2R11P 19 processed_pseudogene exon 279495 280170 . + . Parent=ENST00000589981 -19 protein_coding mRNA 281043 291386 . - . ID=ENST00000269812;geneID=ENSG00000141934;gene_name=PPAP2C +19 protein_coding transcript 281043 291386 . - . ID=ENST00000269812;geneID=ENSG00000141934;gene_name=PPAP2C 19 protein_coding exon 281043 281537 . - . Parent=ENST00000269812 19 protein_coding exon 282134 282310 . - . Parent=ENST00000269812 19 protein_coding exon 282752 282809 . - . Parent=ENST00000269812 19 protein_coding exon 287474 287751 . - . Parent=ENST00000269812 19 protein_coding exon 288020 288171 . - . Parent=ENST00000269812 19 protein_coding exon 291285 291386 . - . Parent=ENST00000269812 -19 protein_coding CDS 281391 281537 . - 0 Parent=ENST00000269812 +19 protein_coding CDS 281388 281537 . - 0 Parent=ENST00000269812 19 protein_coding CDS 282134 282310 . - 0 Parent=ENST00000269812 19 protein_coding CDS 282752 282809 . - 1 Parent=ENST00000269812 19 protein_coding CDS 287474 287751 . - 0 Parent=ENST00000269812 19 protein_coding CDS 288020 288171 . - 2 Parent=ENST00000269812 19 protein_coding CDS 291285 291336 . - 0 Parent=ENST00000269812 -19 protein_coding mRNA 281345 291393 . - . ID=ENST00000434325;geneID=ENSG00000141934;gene_name=PPAP2C +19 protein_coding transcript 281345 291393 . - . ID=ENST00000434325;geneID=ENSG00000141934;gene_name=PPAP2C 19 protein_coding exon 281345 281537 . - . Parent=ENST00000434325 19 protein_coding exon 282134 282310 . - . Parent=ENST00000434325 19 protein_coding exon 282752 282809 . - . Parent=ENST00000434325 19 protein_coding exon 287474 287751 . - . Parent=ENST00000434325 19 protein_coding exon 288020 288171 . - . Parent=ENST00000434325 19 protein_coding exon 291326 291393 . - . Parent=ENST00000434325 -19 protein_coding CDS 281391 281537 . - 0 Parent=ENST00000434325 +19 protein_coding CDS 281388 281537 . - 0 Parent=ENST00000434325 19 protein_coding CDS 282134 282310 . - 0 Parent=ENST00000434325 19 protein_coding CDS 282752 282809 . - 1 Parent=ENST00000434325 19 protein_coding CDS 287474 287751 . - 0 Parent=ENST00000434325 19 protein_coding CDS 288020 288055 . - 0 Parent=ENST00000434325 -19 protein_coding mRNA 281388 291200 . - . ID=ENST00000327790;geneID=ENSG00000141934;gene_name=PPAP2C +19 protein_coding transcript 281388 291200 . - . ID=ENST00000327790;geneID=ENSG00000141934;gene_name=PPAP2C 19 protein_coding exon 281388 281537 . - . Parent=ENST00000327790 19 protein_coding exon 282134 282310 . - . Parent=ENST00000327790 19 protein_coding exon 282752 282809 . - . Parent=ENST00000327790 19 protein_coding exon 287474 287751 . - . Parent=ENST00000327790 19 protein_coding exon 288020 288171 . - . Parent=ENST00000327790 19 protein_coding exon 290952 291200 . - . Parent=ENST00000327790 -19 protein_coding CDS 281391 281537 . - 0 Parent=ENST00000327790 +19 protein_coding CDS 281388 281537 . - 0 Parent=ENST00000327790 19 protein_coding CDS 282134 282310 . - 0 Parent=ENST00000327790 19 protein_coding CDS 282752 282809 . - 1 Parent=ENST00000327790 19 protein_coding CDS 287474 287751 . - 0 Parent=ENST00000327790 19 protein_coding CDS 288020 288171 . - 2 Parent=ENST00000327790 19 protein_coding CDS 290952 291066 . - 0 Parent=ENST00000327790 -19 protein_coding mRNA 281991 287636 . - . ID=ENST00000586998;geneID=ENSG00000141934;gene_name=PPAP2C +19 protein_coding transcript 281991 287636 . - . ID=ENST00000586998;geneID=ENSG00000141934;gene_name=PPAP2C 19 protein_coding exon 281991 282310 . - . Parent=ENST00000586998 19 protein_coding exon 282752 282809 . - . Parent=ENST00000586998 19 protein_coding exon 287474 287636 . - . Parent=ENST00000586998 -19 protein_coding CDS 282125 282310 . - 0 Parent=ENST00000586998 +19 protein_coding CDS 282122 282310 . - 0 Parent=ENST00000586998 19 protein_coding CDS 282752 282809 . - 1 Parent=ENST00000586998 19 protein_coding CDS 287474 287636 . - 2 Parent=ENST00000586998 19 retained_intron transcript 287161 288530 . - . ID=ENST00000589672;geneID=ENSG00000141934;gene_name=PPAP2C 19 retained_intron exon 287161 287751 . - . Parent=ENST00000589672 19 retained_intron exon 288020 288530 . - . Parent=ENST00000589672 -19 protein_coding mRNA 287474 291382 . - . ID=ENST00000591572;geneID=ENSG00000141934;gene_name=PPAP2C +19 protein_coding transcript 287474 291382 . - . ID=ENST00000591572;geneID=ENSG00000141934;gene_name=PPAP2C 19 protein_coding exon 287474 287751 . - . Parent=ENST00000591572 19 protein_coding exon 288020 288189 . - . Parent=ENST00000591572 19 protein_coding exon 291285 291382 . - . Parent=ENST00000591572 @@ -67,7 +68,7 @@ 19 antisense transcript 305573 306467 . + . ID=ENST00000591533;geneID=ENSG00000267124;gene_name=CTD-3113P16.5 19 antisense exon 305573 305703 . + . Parent=ENST00000591533 19 antisense exon 306057 306467 . + . Parent=ENST00000591533 -19 protein_coding mRNA 305575 344793 . - . ID=ENST00000264819;geneID=ENSG00000105556;gene_name=MIER2 +19 protein_coding transcript 305575 344793 . - . ID=ENST00000264819;geneID=ENSG00000105556;gene_name=MIER2 19 protein_coding exon 305575 306711 . - . Parent=ENST00000264819 19 protein_coding exon 307119 307536 . - . Parent=ENST00000264819 19 protein_coding exon 308577 308665 . - . Parent=ENST00000264819 @@ -82,7 +83,7 @@ 19 protein_coding exon 334400 334542 . - . Parent=ENST00000264819 19 protein_coding exon 336083 336173 . - . Parent=ENST00000264819 19 protein_coding exon 344774 344793 . - . Parent=ENST00000264819 -19 protein_coding CDS 306693 306711 . - 1 Parent=ENST00000264819 +19 protein_coding CDS 306690 306711 . - 1 Parent=ENST00000264819 19 protein_coding CDS 307119 307536 . - 2 Parent=ENST00000264819 19 protein_coding CDS 308577 308665 . - 1 Parent=ENST00000264819 19 protein_coding CDS 308801 308925 . - 0 Parent=ENST00000264819 @@ -113,7 +114,7 @@ 19 retained_intron transcript 334115 344798 . - . ID=ENST00000587966;geneID=ENSG00000105556;gene_name=MIER2 19 retained_intron exon 334115 334542 . - . Parent=ENST00000587966 19 retained_intron exon 344774 344798 . - . Parent=ENST00000587966 -19 protein_coding mRNA 361750 376013 . - . ID=ENST00000342640;geneID=ENSG00000105549;gene_name=THEG +19 protein_coding transcript 361750 376013 . - . ID=ENST00000342640;geneID=ENSG00000105549;gene_name=THEG 19 protein_coding exon 361750 362426 . - . Parent=ENST00000342640 19 protein_coding exon 367065 367224 . - . Parent=ENST00000342640 19 protein_coding exon 371205 371322 . - . Parent=ENST00000342640 @@ -122,7 +123,7 @@ 19 protein_coding exon 373940 374011 . - . Parent=ENST00000342640 19 protein_coding exon 374299 374421 . - . Parent=ENST00000342640 19 protein_coding exon 375663 376013 . - . Parent=ENST00000342640 -19 protein_coding CDS 362203 362426 . - 2 Parent=ENST00000342640 +19 protein_coding CDS 362200 362426 . - 2 Parent=ENST00000342640 19 protein_coding CDS 367065 367224 . - 0 Parent=ENST00000342640 19 protein_coding CDS 371205 371322 . - 1 Parent=ENST00000342640 19 protein_coding CDS 372631 372700 . - 2 Parent=ENST00000342640 @@ -134,7 +135,7 @@ 19 retained_intron exon 362058 362426 . - . Parent=ENST00000530711 19 retained_intron exon 367065 367224 . - . Parent=ENST00000530711 19 retained_intron exon 374299 374620 . - . Parent=ENST00000530711 -19 protein_coding mRNA 362200 375970 . - . ID=ENST00000346878;geneID=ENSG00000105549;gene_name=THEG +19 protein_coding transcript 362200 375970 . - . ID=ENST00000346878;geneID=ENSG00000105549;gene_name=THEG 19 protein_coding exon 362200 362426 . - . Parent=ENST00000346878 19 protein_coding exon 367065 367224 . - . Parent=ENST00000346878 19 protein_coding exon 371205 371322 . - . Parent=ENST00000346878 @@ -142,7 +143,7 @@ 19 protein_coding exon 373470 373531 . - . Parent=ENST00000346878 19 protein_coding exon 374299 374421 . - . Parent=ENST00000346878 19 protein_coding exon 375663 375970 . - . Parent=ENST00000346878 -19 protein_coding CDS 362203 362426 . - 2 Parent=ENST00000346878 +19 protein_coding CDS 362200 362426 . - 2 Parent=ENST00000346878 19 protein_coding CDS 367065 367224 . - 0 Parent=ENST00000346878 19 protein_coding CDS 371205 371322 . - 1 Parent=ENST00000346878 19 protein_coding CDS 372631 372700 . - 2 Parent=ENST00000346878 @@ -158,10 +159,10 @@ 19 processed_transcript transcript 397589 398941 . + . ID=ENST00000591757;geneID=ENSG00000267443;gene_name=AC010641.1 19 processed_transcript exon 397589 397633 . + . Parent=ENST00000591757 19 processed_transcript exon 398690 398941 . + . Parent=ENST00000591757 -19 protein_coding mRNA 405445 409139 . - . ID=ENST00000332235;geneID=ENSG00000183186;gene_name=C2CD4C +19 protein_coding transcript 405445 409139 . - . ID=ENST00000332235;geneID=ENSG00000183186;gene_name=C2CD4C 19 protein_coding exon 405445 408401 . - . Parent=ENST00000332235 19 protein_coding exon 409006 409139 . - . Parent=ENST00000332235 -19 protein_coding CDS 407099 408361 . - 0 Parent=ENST00000332235 +19 protein_coding CDS 407096 408361 . - 0 Parent=ENST00000332235 19 retained_intron transcript 416583 419879 . - . ID=ENST00000587423;geneID=ENSG00000129946;gene_name=SHC2 19 retained_intron exon 416583 417322 . - . Parent=ENST00000587423 19 retained_intron exon 418923 419879 . - . Parent=ENST00000587423 @@ -169,7 +170,7 @@ 19 retained_intron exon 416583 417322 . - . Parent=ENST00000588376 19 retained_intron exon 418923 419056 . - . Parent=ENST00000588376 19 retained_intron exon 422146 422828 . - . Parent=ENST00000588376 -19 protein_coding mRNA 416593 460996 . - . ID=ENST00000264554;geneID=ENSG00000129946;gene_name=SHC2 +19 protein_coding transcript 416593 460996 . - . ID=ENST00000264554;geneID=ENSG00000129946;gene_name=SHC2 19 protein_coding exon 416593 417322 . - . Parent=ENST00000264554 19 protein_coding exon 418923 419056 . - . Parent=ENST00000264554 19 protein_coding exon 422146 422456 . - . Parent=ENST00000264554 @@ -183,7 +184,7 @@ 19 protein_coding exon 438970 439030 . - . Parent=ENST00000264554 19 protein_coding exon 440862 440932 . - . Parent=ENST00000264554 19 protein_coding exon 460529 460996 . - . Parent=ENST00000264554 -19 protein_coding CDS 418931 419056 . - 0 Parent=ENST00000264554 +19 protein_coding CDS 418928 419056 . - 0 Parent=ENST00000264554 19 protein_coding CDS 422146 422456 . - 2 Parent=ENST00000264554 19 protein_coding CDS 425097 425231 . - 2 Parent=ENST00000264554 19 protein_coding CDS 430684 430747 . - 0 Parent=ENST00000264554 @@ -207,14 +208,14 @@ 19 retained_intron exon 438718 438837 . - . Parent=ENST00000589922 19 retained_intron exon 438970 439030 . - . Parent=ENST00000589922 19 retained_intron exon 440862 441384 . - . Parent=ENST00000589922 -19 nonsense_mediated_decay mRNA 417200 436258 . - . ID=ENST00000590170;geneID=ENSG00000129946;gene_name=SHC2 +19 nonsense_mediated_decay transcript 417200 436258 . - . ID=ENST00000590170;geneID=ENSG00000129946;gene_name=SHC2 19 nonsense_mediated_decay exon 417200 417322 . - . Parent=ENST00000590170 19 nonsense_mediated_decay exon 418923 419056 . - . Parent=ENST00000590170 19 nonsense_mediated_decay exon 422146 422379 . - . Parent=ENST00000590170 19 nonsense_mediated_decay exon 430684 430747 . - . Parent=ENST00000590170 19 nonsense_mediated_decay exon 434709 434865 . - . Parent=ENST00000590170 19 nonsense_mediated_decay exon 436165 436258 . - . Parent=ENST00000590170 -19 nonsense_mediated_decay CDS 434765 434865 . - 2 Parent=ENST00000590170 +19 nonsense_mediated_decay CDS 434762 434865 . - 2 Parent=ENST00000590170 19 nonsense_mediated_decay CDS 436165 436258 . - 0 Parent=ENST00000590170 19 processed_transcript transcript 417200 436258 . - . ID=ENST00000591948;geneID=ENSG00000129946;gene_name=SHC2 19 processed_transcript exon 417200 417322 . - . Parent=ENST00000591948 @@ -223,7 +224,7 @@ 19 processed_transcript exon 430684 430747 . - . Parent=ENST00000591948 19 processed_transcript exon 434709 434865 . - . Parent=ENST00000591948 19 processed_transcript exon 436165 436258 . - . Parent=ENST00000591948 -19 nonsense_mediated_decay mRNA 434702 460571 . - . ID=ENST00000590222;geneID=ENSG00000129946;gene_name=SHC2 +19 nonsense_mediated_decay transcript 434702 460571 . - . ID=ENST00000590222;geneID=ENSG00000129946;gene_name=SHC2 19 nonsense_mediated_decay exon 434702 434865 . - . Parent=ENST00000590222 19 nonsense_mediated_decay exon 436165 436291 . - . Parent=ENST00000590222 19 nonsense_mediated_decay exon 436380 436431 . - . Parent=ENST00000590222 @@ -233,7 +234,7 @@ 19 nonsense_mediated_decay exon 439233 439491 . - . Parent=ENST00000590222 19 nonsense_mediated_decay exon 440862 440932 . - . Parent=ENST00000590222 19 nonsense_mediated_decay exon 460529 460571 . - . Parent=ENST00000590222 -19 nonsense_mediated_decay CDS 439401 439491 . - 1 Parent=ENST00000590222 +19 nonsense_mediated_decay CDS 439398 439491 . - 1 Parent=ENST00000590222 19 nonsense_mediated_decay CDS 440862 440932 . - 0 Parent=ENST00000590222 19 nonsense_mediated_decay CDS 460529 460571 . - 1 Parent=ENST00000590222 19 retained_intron transcript 435771 436534 . - . ID=ENST00000591388;geneID=ENSG00000129946;gene_name=SHC2 @@ -249,20 +250,20 @@ 19 processed_transcript exon 438970 439031 . - . Parent=ENST00000590113 19 rRNA transcript 453134 453245 . + . ID=ENST00000516730;geneID=ENSG00000252539;gene_name=RNA5SP462 19 rRNA exon 453134 453245 . + . Parent=ENST00000516730 -19 protein_coding mRNA 463346 474983 . - . ID=ENST00000315489;geneID=ENSG00000181781;gene_name=ODF3L2 +19 protein_coding transcript 463346 474983 . - . ID=ENST00000315489;geneID=ENSG00000181781;gene_name=ODF3L2 19 protein_coding exon 463346 464364 . - . Parent=ENST00000315489 19 protein_coding exon 467649 467762 . - . Parent=ENST00000315489 19 protein_coding exon 472394 472501 . - . Parent=ENST00000315489 19 protein_coding exon 474621 474983 . - . Parent=ENST00000315489 -19 protein_coding CDS 463847 464364 . - 2 Parent=ENST00000315489 +19 protein_coding CDS 463844 464364 . - 2 Parent=ENST00000315489 19 protein_coding CDS 467649 467762 . - 2 Parent=ENST00000315489 19 protein_coding CDS 472394 472501 . - 2 Parent=ENST00000315489 19 protein_coding CDS 474621 474747 . - 0 Parent=ENST00000315489 -19 protein_coding mRNA 463467 474880 . - . ID=ENST00000382696;geneID=ENSG00000181781;gene_name=ODF3L2 +19 protein_coding transcript 463467 474880 . - . ID=ENST00000382696;geneID=ENSG00000181781;gene_name=ODF3L2 19 protein_coding exon 463467 464364 . - . Parent=ENST00000382696 19 protein_coding exon 467649 467762 . - . Parent=ENST00000382696 19 protein_coding exon 474621 474880 . - . Parent=ENST00000382696 -19 protein_coding CDS 463847 464364 . - 2 Parent=ENST00000382696 +19 protein_coding CDS 463844 464364 . - 2 Parent=ENST00000382696 19 protein_coding CDS 467649 467762 . - 2 Parent=ENST00000382696 19 protein_coding CDS 474621 474747 . - 0 Parent=ENST00000382696 19 retained_intron transcript 464146 472631 . - . ID=ENST00000591681;geneID=ENSG00000181781;gene_name=ODF3L2 @@ -277,7 +278,7 @@ 19 antisense exon 490046 490353 . - . Parent=ENST00000592413 19 antisense exon 501541 501624 . - . Parent=ENST00000592413 19 antisense exon 507376 507813 . - . Parent=ENST00000592413 -19 protein_coding mRNA 496454 505207 . + . ID=ENST00000346144;geneID=ENSG00000099866;gene_name=MADCAM1 +19 protein_coding transcript 496454 505207 . + . ID=ENST00000346144;geneID=ENSG00000099866;gene_name=MADCAM1 19 protein_coding exon 496454 496551 . + . Parent=ENST00000346144 19 protein_coding exon 497833 498117 . + . Parent=ENST00000346144 19 protein_coding exon 498496 498825 . + . Parent=ENST00000346144 @@ -285,8 +286,8 @@ 19 protein_coding CDS 496500 496551 . + 0 Parent=ENST00000346144 19 protein_coding CDS 497833 498117 . + 2 Parent=ENST00000346144 19 protein_coding CDS 498496 498825 . + 2 Parent=ENST00000346144 -19 protein_coding CDS 504745 504963 . + 2 Parent=ENST00000346144 -19 protein_coding mRNA 496454 505347 . + . ID=ENST00000215637;geneID=ENSG00000099866;gene_name=MADCAM1 +19 protein_coding CDS 504745 504965 . + 2 Parent=ENST00000346144 +19 protein_coding transcript 496454 505347 . + . ID=ENST00000215637;geneID=ENSG00000099866;gene_name=MADCAM1 19 protein_coding exon 496454 496551 . + . Parent=ENST00000215637 19 protein_coding exon 497833 498117 . + . Parent=ENST00000215637 19 protein_coding exon 498496 498825 . + . Parent=ENST00000215637 @@ -296,18 +297,18 @@ 19 protein_coding CDS 497833 498117 . + 2 Parent=ENST00000215637 19 protein_coding CDS 498496 498825 . + 2 Parent=ENST00000215637 19 protein_coding CDS 501669 501929 . + 2 Parent=ENST00000215637 -19 protein_coding CDS 504745 504963 . + 2 Parent=ENST00000215637 -19 protein_coding mRNA 496500 504965 . + . ID=ENST00000382683;geneID=ENSG00000099866;gene_name=MADCAM1 +19 protein_coding CDS 504745 504965 . + 2 Parent=ENST00000215637 +19 protein_coding transcript 496500 504965 . + . ID=ENST00000382683;geneID=ENSG00000099866;gene_name=MADCAM1 19 protein_coding exon 496500 496551 . + . Parent=ENST00000382683 19 protein_coding exon 498496 498825 . + . Parent=ENST00000382683 19 protein_coding exon 504745 504965 . + . Parent=ENST00000382683 19 protein_coding CDS 496500 496551 . + 0 Parent=ENST00000382683 19 protein_coding CDS 498496 498825 . + 2 Parent=ENST00000382683 -19 protein_coding CDS 504745 504963 . + 2 Parent=ENST00000382683 -19 protein_coding mRNA 507299 519654 . + . ID=ENST00000359315;geneID=ENSG00000141933;gene_name=TPGS1 +19 protein_coding CDS 504745 504965 . + 2 Parent=ENST00000382683 +19 protein_coding transcript 507299 519654 . + . ID=ENST00000359315;geneID=ENSG00000141933;gene_name=TPGS1 19 protein_coding exon 507299 507844 . + . Parent=ENST00000359315 19 protein_coding exon 518889 519654 . + . Parent=ENST00000359315 19 protein_coding CDS 507507 507844 . + 0 Parent=ENST00000359315 -19 protein_coding CDS 518889 519421 . + 1 Parent=ENST00000359315 +19 protein_coding CDS 518889 519423 . + 1 Parent=ENST00000359315 19 retained_intron transcript 507500 510372 . + . ID=ENST00000588278;geneID=ENSG00000141933;gene_name=TPGS1 19 retained_intron exon 507500 510372 . + . Parent=ENST00000588278 diff -r 69e0806b63a4 -r 6ea09f60dee9 test-data/ecoli-k12.processed.gff3 --- a/test-data/ecoli-k12.processed.gff3 Tue Oct 01 12:20:13 2019 -0400 +++ b/test-data/ecoli-k12.processed.gff3 Fri Nov 01 12:54:52 2019 -0400 @@ -1,32 +1,33 @@ -# gffread /home/hxr/arbeit/galaxy/database/files/000/dataset_791.dat -F -D -E -o output.gff3 +# gffread /tmp/tmpq6d_yfqc/files/2/7/7/dataset_277f6e18-b25a-4b59-b712-49b5c202a183.dat -F -o output.gff3 +# gffread v0.11.4 ##gff-version 3 -NC_000913.3 RefSeq gene 190 255 . + . ID=gene-b0001;geneID=gene-b0001;gene_name=thrL;Dbxref=ASAP:ABE-0000006,ECOCYC:EG11277,EcoGene:EG11277,GeneID:944742;Name=thrL;gbkey=Gene;gene_biotype=protein_coding;gene_synonym=ECK0001;locus_tag=b0001;protein_id=NP_414542.1 -NC_000913.3 RefSeq CDS 190 255 . + 0 Parent=gene-b0001;Dbxref=UniProtKB/Swiss-Prot:P0AD86,Genbank:NP_414542.1,ASAP:ABE-0000006,ECOCYC:EG11277,EcoGene:EG11277,GeneID:944742;Name=NP_414542.1;gbkey=CDS;locus_tag=b0001;orig_transcript_id=gnl|b0001|mrna.b0001;product=thr operon leader peptide;transl_table=11 -NC_000913.3 RefSeq gene 337 2799 . + . ID=gene-b0002;geneID=gene-b0002;gene_name=thrA;Dbxref=ASAP:ABE-0000008,ECOCYC:EG10998,EcoGene:EG10998,GeneID:945803;Name=thrA;gbkey=Gene;gene_biotype=protein_coding;gene_synonym=ECK0002,Hs,thrA1,thrA2,thrD;locus_tag=b0002;protein_id=NP_414543.1 -NC_000913.3 RefSeq CDS 337 2799 . + 0 Parent=gene-b0002;Dbxref=UniProtKB/Swiss-Prot:P00561,Genbank:NP_414543.1,ASAP:ABE-0000008,ECOCYC:EG10998,EcoGene:EG10998,GeneID:945803;Name=NP_414543.1;gbkey=CDS;locus_tag=b0002;orig_transcript_id=gnl|b0002|mrna.b0002;product=fused aspartate kinase/homoserine dehydrogenase 1;transl_table=11 -NC_000913.3 RefSeq gene 2801 3733 . + . ID=gene-b0003;geneID=gene-b0003;gene_name=thrB;Dbxref=ASAP:ABE-0000010,ECOCYC:EG10999,EcoGene:EG10999,GeneID:947498;Name=thrB;gbkey=Gene;gene_biotype=protein_coding;gene_synonym=ECK0003;locus_tag=b0003;protein_id=NP_414544.1 -NC_000913.3 RefSeq CDS 2801 3733 . + 0 Parent=gene-b0003;Dbxref=UniProtKB/Swiss-Prot:P00547,Genbank:NP_414544.1,ASAP:ABE-0000010,ECOCYC:EG10999,EcoGene:EG10999,GeneID:947498;Name=NP_414544.1;gbkey=CDS;locus_tag=b0003;orig_transcript_id=gnl|b0003|mrna.b0003;product=homoserine kinase;transl_table=11 -NC_000913.3 RefSeq gene 3734 5020 . + . ID=gene-b0004;geneID=gene-b0004;gene_name=thrC;Dbxref=ASAP:ABE-0000012,ECOCYC:EG11000,EcoGene:EG11000,GeneID:945198;Name=thrC;gbkey=Gene;gene_biotype=protein_coding;gene_synonym=ECK0004;locus_tag=b0004;protein_id=NP_414545.1 -NC_000913.3 RefSeq CDS 3734 5020 . + 0 Parent=gene-b0004;Dbxref=UniProtKB/Swiss-Prot:P00934,Genbank:NP_414545.1,ASAP:ABE-0000012,ECOCYC:EG11000,EcoGene:EG11000,GeneID:945198;Name=NP_414545.1;gbkey=CDS;locus_tag=b0004;orig_transcript_id=gnl|b0004|mrna.b0004;product=threonine synthase;transl_table=11 -NC_000913.3 RefSeq gene 5234 5530 . + . ID=gene-b0005;geneID=gene-b0005;gene_name=yaaX;Dbxref=ASAP:ABE-0000015,ECOCYC:G6081,EcoGene:EG14384,GeneID:944747;Name=yaaX;gbkey=Gene;gene_biotype=protein_coding;gene_synonym=ECK0005;locus_tag=b0005;protein_id=NP_414546.1 -NC_000913.3 RefSeq CDS 5234 5530 . + 0 Parent=gene-b0005;Dbxref=UniProtKB/Swiss-Prot:P75616,Genbank:NP_414546.1,ASAP:ABE-0000015,ECOCYC:G6081,EcoGene:EG14384,GeneID:944747;Name=NP_414546.1;gbkey=CDS;locus_tag=b0005;orig_transcript_id=gnl|b0005|mrna.b0005;product=DUF2502 domain-containing protein YaaX;transl_table=11 -NC_000913.3 RefSeq gene 5683 6459 . - . ID=gene-b0006;geneID=gene-b0006;gene_name=yaaA;Dbxref=ASAP:ABE-0000018,ECOCYC:EG10011,EcoGene:EG10011,GeneID:944749;Name=yaaA;gbkey=Gene;gene_biotype=protein_coding;gene_synonym=ECK0006;locus_tag=b0006;protein_id=NP_414547.1 -NC_000913.3 RefSeq CDS 5683 6459 . - 0 Parent=gene-b0006;Dbxref=UniProtKB/Swiss-Prot:P0A8I3,Genbank:NP_414547.1,ASAP:ABE-0000018,ECOCYC:EG10011,EcoGene:EG10011,GeneID:944749;Name=NP_414547.1;gbkey=CDS;locus_tag=b0006;orig_transcript_id=gnl|b0006|mrna.b0006;product=peroxide stress resistance protein YaaA;transl_table=11 -NC_000913.3 RefSeq gene 6529 7959 . - . ID=gene-b0007;geneID=gene-b0007;gene_name=yaaJ;Dbxref=ASAP:ABE-0000020,ECOCYC:EG11555,EcoGene:EG11555,GeneID:944745;Name=yaaJ;gbkey=Gene;gene_biotype=protein_coding;gene_synonym=ECK0007;locus_tag=b0007;protein_id=NP_414548.1 -NC_000913.3 RefSeq CDS 6529 7959 . - 0 Parent=gene-b0007;Dbxref=UniProtKB/Swiss-Prot:P30143,Genbank:NP_414548.1,ASAP:ABE-0000020,ECOCYC:EG11555,EcoGene:EG11555,GeneID:944745;Name=NP_414548.1;gbkey=CDS;locus_tag=b0007;orig_transcript_id=gnl|b0007|mrna.b0007;product=putative transporter YaaJ;transl_table=11 -NC_000913.3 RefSeq gene 8238 9191 . + . ID=gene-b0008;geneID=gene-b0008;gene_name=talB;Dbxref=ASAP:ABE-0000027,ECOCYC:EG11556,EcoGene:EG11556,GeneID:944748;Name=talB;gbkey=Gene;gene_biotype=protein_coding;gene_synonym=ECK0008,yaaK;locus_tag=b0008;protein_id=NP_414549.1 -NC_000913.3 RefSeq CDS 8238 9191 . + 0 Parent=gene-b0008;Dbxref=UniProtKB/Swiss-Prot:P0A870,Genbank:NP_414549.1,ASAP:ABE-0000027,ECOCYC:EG11556,EcoGene:EG11556,GeneID:944748;Name=NP_414549.1;gbkey=CDS;locus_tag=b0008;orig_transcript_id=gnl|b0008|mrna.b0008;product=transaldolase B;transl_table=11 -NC_000913.3 RefSeq gene 9306 9893 . + . ID=gene-b0009;geneID=gene-b0009;gene_name=mog;Dbxref=ASAP:ABE-0000030,ECOCYC:EG11511,EcoGene:EG11511,GeneID:944760;Name=mog;gbkey=Gene;gene_biotype=protein_coding;gene_synonym=bisD,chlG,ECK0009,mogA,yaaG;locus_tag=b0009;protein_id=NP_414550.1 -NC_000913.3 RefSeq CDS 9306 9893 . + 0 Parent=gene-b0009;Dbxref=UniProtKB/Swiss-Prot:P0AF03,Genbank:NP_414550.1,ASAP:ABE-0000030,ECOCYC:EG11511,EcoGene:EG11511,GeneID:944760;Name=NP_414550.1;gbkey=CDS;locus_tag=b0009;orig_transcript_id=gnl|b0009|mrna.b0009;product=molybdopterin adenylyltransferase;transl_table=11 -NC_000913.3 RefSeq gene 9928 10494 . - . ID=gene-b0010;geneID=gene-b0010;gene_name=satP;Dbxref=ASAP:ABE-0000032,ECOCYC:EG11512,EcoGene:EG11512,GeneID:944792;Name=satP;gbkey=Gene;gene_biotype=protein_coding;gene_synonym=ECK0010,yaaH;locus_tag=b0010;protein_id=NP_414551.1 -NC_000913.3 RefSeq CDS 9928 10494 . - 0 Parent=gene-b0010;Dbxref=UniProtKB/Swiss-Prot:P0AC98,Genbank:NP_414551.1,ASAP:ABE-0000032,ECOCYC:EG11512,EcoGene:EG11512,GeneID:944792;Name=NP_414551.1;gbkey=CDS;locus_tag=b0010;orig_transcript_id=gnl|b0010|mrna.b0010;product=acetate/succinate:H(+) symporter;transl_table=11 -NC_000913.3 RefSeq gene 10643 11356 . - . ID=gene-b0011;geneID=gene-b0011;gene_name=yaaW;Dbxref=ASAP:ABE-0000037,ECOCYC:G6082,EcoGene:EG14340,GeneID:944771;Name=yaaW;gbkey=Gene;gene_biotype=protein_coding;gene_synonym=ECK0011;locus_tag=b0011;protein_id=NP_414552.1 -NC_000913.3 RefSeq CDS 10643 11356 . - 0 Parent=gene-b0011;Dbxref=UniProtKB/Swiss-Prot:P75617,Genbank:NP_414552.1,ASAP:ABE-0000037,ECOCYC:G6082,EcoGene:EG14340,GeneID:944771;Name=NP_414552.1;gbkey=CDS;locus_tag=b0011;orig_transcript_id=gnl|b0011|mrna.b0011;product=putative enzyme-specific chaperone YaaW;transl_table=11 -NC_000913.3 RefSeq gene 10830 11315 . + . ID=gene-b0012;geneID=gene-b0012;gene_name=mbiA;Dbxref=ASAP:ABE-0000040,ECOCYC:EG11509,EcoGene:EG11509,GeneID:948295;Name=mbiA;gbkey=Gene;gene_biotype=protein_coding;gene_synonym=ECK0012,htgA,htpY;locus_tag=b0012;protein_id=YP_009518733.1 -NC_000913.3 RefSeq CDS 10830 11315 . + 0 Parent=gene-b0012;Dbxref=UniProtKB/Swiss-Prot:P28697,Genbank:YP_009518733.1,ASAP:ABE-0000040,ECOCYC:EG11509,EcoGene:EG11509,GeneID:948295;Name=YP_009518733.1;gbkey=CDS;locus_tag=b0012;orig_transcript_id=gnl|b0012|mrna.CDS13;product=uncharacterized protein MbiA;transl_table=11 -NC_000913.3 RefSeq gene 11382 11786 . - . ID=gene-b0013;geneID=gene-b0013;gene_name=yaaI;Dbxref=ASAP:ABE-0000043,ECOCYC:G8202,EcoGene:EG11513,GeneID:944751;Name=yaaI;gbkey=Gene;gene_biotype=protein_coding;gene_synonym=ECK0013;locus_tag=b0013;protein_id=NP_414554.1 -NC_000913.3 RefSeq CDS 11382 11786 . - 0 Parent=gene-b0013;Dbxref=UniProtKB/Swiss-Prot:P28696,Genbank:NP_414554.1,ASAP:ABE-0000043,ECOCYC:G8202,EcoGene:EG11513,GeneID:944751;Name=NP_414554.1;gbkey=CDS;locus_tag=b0013;orig_transcript_id=gnl|b0013|mrna.b0013;product=DUF2541 domain-containing protein YaaI;transl_table=11 -NC_000913.3 RefSeq gene 12163 14079 . + . ID=gene-b0014;geneID=gene-b0014;gene_name=dnaK;Dbxref=ASAP:ABE-0000052,ECOCYC:EG10241,EcoGene:EG10241,GeneID:944750;Name=dnaK;gbkey=Gene;gene_biotype=protein_coding;gene_synonym=ECK0014,groPAB,groPC,groPF,grpC,grpF,seg;locus_tag=b0014;protein_id=NP_414555.1 -NC_000913.3 RefSeq CDS 12163 14079 . + 0 Parent=gene-b0014;Dbxref=UniProtKB/Swiss-Prot:P0A6Y8,Genbank:NP_414555.1,ASAP:ABE-0000052,ECOCYC:EG10241,EcoGene:EG10241,GeneID:944750;Name=NP_414555.1;gbkey=CDS;locus_tag=b0014;orig_transcript_id=gnl|b0014|mrna.b0014;product=chaperone protein DnaK;transl_table=11 -NC_000913.3 RefSeq gene 14168 15298 . + . ID=gene-b0015;geneID=gene-b0015;gene_name=dnaJ;Dbxref=ASAP:ABE-0000054,ECOCYC:EG10240,EcoGene:EG10240,GeneID:944753;Name=dnaJ;gbkey=Gene;gene_biotype=protein_coding;gene_synonym=ECK0015,groP,grpC;locus_tag=b0015;protein_id=NP_414556.1 -NC_000913.3 RefSeq CDS 14168 15298 . + 0 Parent=gene-b0015;Dbxref=UniProtKB/Swiss-Prot:P08622,Genbank:NP_414556.1,ASAP:ABE-0000054,ECOCYC:EG10240,EcoGene:EG10240,GeneID:944753;Name=NP_414556.1;gbkey=CDS;locus_tag=b0015;orig_transcript_id=gnl|b0015|mrna.b0015;product=chaperone protein DnaJ;transl_table=11 +NC_000913.3 RefSeq gene 190 255 . + . ID=gene-b0001;geneID=gene-b0001;gene_name=thrL;Dbxref=ASAP:ABE-0000006,ECOCYC:EG11277,EcoGene:EG11277,GeneID:944742;Name=thrL;gbkey=Gene;gene=thrL;gene_biotype=protein_coding;gene_synonym=ECK0001;locus_tag=b0001 +NC_000913.3 RefSeq CDS 190 255 . + 0 Parent=gene-b0001;Dbxref=UniProtKB/Swiss-Prot:P0AD86,Genbank:NP_414542.1,ASAP:ABE-0000006,ECOCYC:EG11277,EcoGene:EG11277,GeneID:944742;Name=NP_414542.1;gbkey=CDS;gene=thrL;locus_tag=b0001;orig_transcript_id=gnl|b0001|mrna.b0001;product=thr operon leader peptide;protein_id=NP_414542.1;transl_table=11 +NC_000913.3 RefSeq gene 337 2799 . + . ID=gene-b0002;geneID=gene-b0002;gene_name=thrA;Dbxref=ASAP:ABE-0000008,ECOCYC:EG10998,EcoGene:EG10998,GeneID:945803;Name=thrA;gbkey=Gene;gene=thrA;gene_biotype=protein_coding;gene_synonym=ECK0002,Hs,thrA1,thrA2,thrD;locus_tag=b0002 +NC_000913.3 RefSeq CDS 337 2799 . + 0 Parent=gene-b0002;Dbxref=UniProtKB/Swiss-Prot:P00561,Genbank:NP_414543.1,ASAP:ABE-0000008,ECOCYC:EG10998,EcoGene:EG10998,GeneID:945803;Name=NP_414543.1;gbkey=CDS;gene=thrA;locus_tag=b0002;orig_transcript_id=gnl|b0002|mrna.b0002;product=fused aspartate kinase/homoserine dehydrogenase 1;protein_id=NP_414543.1;transl_table=11 +NC_000913.3 RefSeq gene 2801 3733 . + . ID=gene-b0003;geneID=gene-b0003;gene_name=thrB;Dbxref=ASAP:ABE-0000010,ECOCYC:EG10999,EcoGene:EG10999,GeneID:947498;Name=thrB;gbkey=Gene;gene=thrB;gene_biotype=protein_coding;gene_synonym=ECK0003;locus_tag=b0003 +NC_000913.3 RefSeq CDS 2801 3733 . + 0 Parent=gene-b0003;Dbxref=UniProtKB/Swiss-Prot:P00547,Genbank:NP_414544.1,ASAP:ABE-0000010,ECOCYC:EG10999,EcoGene:EG10999,GeneID:947498;Name=NP_414544.1;gbkey=CDS;gene=thrB;locus_tag=b0003;orig_transcript_id=gnl|b0003|mrna.b0003;product=homoserine kinase;protein_id=NP_414544.1;transl_table=11 +NC_000913.3 RefSeq gene 3734 5020 . + . ID=gene-b0004;geneID=gene-b0004;gene_name=thrC;Dbxref=ASAP:ABE-0000012,ECOCYC:EG11000,EcoGene:EG11000,GeneID:945198;Name=thrC;gbkey=Gene;gene=thrC;gene_biotype=protein_coding;gene_synonym=ECK0004;locus_tag=b0004 +NC_000913.3 RefSeq CDS 3734 5020 . + 0 Parent=gene-b0004;Dbxref=UniProtKB/Swiss-Prot:P00934,Genbank:NP_414545.1,ASAP:ABE-0000012,ECOCYC:EG11000,EcoGene:EG11000,GeneID:945198;Name=NP_414545.1;gbkey=CDS;gene=thrC;locus_tag=b0004;orig_transcript_id=gnl|b0004|mrna.b0004;product=threonine synthase;protein_id=NP_414545.1;transl_table=11 +NC_000913.3 RefSeq gene 5234 5530 . + . ID=gene-b0005;geneID=gene-b0005;gene_name=yaaX;Dbxref=ASAP:ABE-0000015,ECOCYC:G6081,EcoGene:EG14384,GeneID:944747;Name=yaaX;gbkey=Gene;gene=yaaX;gene_biotype=protein_coding;gene_synonym=ECK0005;locus_tag=b0005 +NC_000913.3 RefSeq CDS 5234 5530 . + 0 Parent=gene-b0005;Dbxref=UniProtKB/Swiss-Prot:P75616,Genbank:NP_414546.1,ASAP:ABE-0000015,ECOCYC:G6081,EcoGene:EG14384,GeneID:944747;Name=NP_414546.1;gbkey=CDS;gene=yaaX;locus_tag=b0005;orig_transcript_id=gnl|b0005|mrna.b0005;product=DUF2502 domain-containing protein YaaX;protein_id=NP_414546.1;transl_table=11 +NC_000913.3 RefSeq gene 5683 6459 . - . ID=gene-b0006;geneID=gene-b0006;gene_name=yaaA;Dbxref=ASAP:ABE-0000018,ECOCYC:EG10011,EcoGene:EG10011,GeneID:944749;Name=yaaA;gbkey=Gene;gene=yaaA;gene_biotype=protein_coding;gene_synonym=ECK0006;locus_tag=b0006 +NC_000913.3 RefSeq CDS 5683 6459 . - 0 Parent=gene-b0006;Dbxref=UniProtKB/Swiss-Prot:P0A8I3,Genbank:NP_414547.1,ASAP:ABE-0000018,ECOCYC:EG10011,EcoGene:EG10011,GeneID:944749;Name=NP_414547.1;gbkey=CDS;gene=yaaA;locus_tag=b0006;orig_transcript_id=gnl|b0006|mrna.b0006;product=peroxide stress resistance protein YaaA;protein_id=NP_414547.1;transl_table=11 +NC_000913.3 RefSeq gene 6529 7959 . - . ID=gene-b0007;geneID=gene-b0007;gene_name=yaaJ;Dbxref=ASAP:ABE-0000020,ECOCYC:EG11555,EcoGene:EG11555,GeneID:944745;Name=yaaJ;gbkey=Gene;gene=yaaJ;gene_biotype=protein_coding;gene_synonym=ECK0007;locus_tag=b0007 +NC_000913.3 RefSeq CDS 6529 7959 . - 0 Parent=gene-b0007;Dbxref=UniProtKB/Swiss-Prot:P30143,Genbank:NP_414548.1,ASAP:ABE-0000020,ECOCYC:EG11555,EcoGene:EG11555,GeneID:944745;Name=NP_414548.1;gbkey=CDS;gene=yaaJ;locus_tag=b0007;orig_transcript_id=gnl|b0007|mrna.b0007;product=putative transporter YaaJ;protein_id=NP_414548.1;transl_table=11 +NC_000913.3 RefSeq gene 8238 9191 . + . ID=gene-b0008;geneID=gene-b0008;gene_name=talB;Dbxref=ASAP:ABE-0000027,ECOCYC:EG11556,EcoGene:EG11556,GeneID:944748;Name=talB;gbkey=Gene;gene=talB;gene_biotype=protein_coding;gene_synonym=ECK0008,yaaK;locus_tag=b0008 +NC_000913.3 RefSeq CDS 8238 9191 . + 0 Parent=gene-b0008;Dbxref=UniProtKB/Swiss-Prot:P0A870,Genbank:NP_414549.1,ASAP:ABE-0000027,ECOCYC:EG11556,EcoGene:EG11556,GeneID:944748;Name=NP_414549.1;gbkey=CDS;gene=talB;locus_tag=b0008;orig_transcript_id=gnl|b0008|mrna.b0008;product=transaldolase B;protein_id=NP_414549.1;transl_table=11 +NC_000913.3 RefSeq gene 9306 9893 . + . ID=gene-b0009;geneID=gene-b0009;gene_name=mog;Dbxref=ASAP:ABE-0000030,ECOCYC:EG11511,EcoGene:EG11511,GeneID:944760;Name=mog;gbkey=Gene;gene=mog;gene_biotype=protein_coding;gene_synonym=bisD,chlG,ECK0009,mogA,yaaG;locus_tag=b0009 +NC_000913.3 RefSeq CDS 9306 9893 . + 0 Parent=gene-b0009;Dbxref=UniProtKB/Swiss-Prot:P0AF03,Genbank:NP_414550.1,ASAP:ABE-0000030,ECOCYC:EG11511,EcoGene:EG11511,GeneID:944760;Name=NP_414550.1;gbkey=CDS;gene=mog;locus_tag=b0009;orig_transcript_id=gnl|b0009|mrna.b0009;product=molybdopterin adenylyltransferase;protein_id=NP_414550.1;transl_table=11 +NC_000913.3 RefSeq gene 9928 10494 . - . ID=gene-b0010;geneID=gene-b0010;gene_name=satP;Dbxref=ASAP:ABE-0000032,ECOCYC:EG11512,EcoGene:EG11512,GeneID:944792;Name=satP;gbkey=Gene;gene=satP;gene_biotype=protein_coding;gene_synonym=ECK0010,yaaH;locus_tag=b0010 +NC_000913.3 RefSeq CDS 9928 10494 . - 0 Parent=gene-b0010;Dbxref=UniProtKB/Swiss-Prot:P0AC98,Genbank:NP_414551.1,ASAP:ABE-0000032,ECOCYC:EG11512,EcoGene:EG11512,GeneID:944792;Name=NP_414551.1;gbkey=CDS;gene=satP;locus_tag=b0010;orig_transcript_id=gnl|b0010|mrna.b0010;product=acetate/succinate:H(+) symporter;protein_id=NP_414551.1;transl_table=11 +NC_000913.3 RefSeq gene 10643 11356 . - . ID=gene-b0011;geneID=gene-b0011;gene_name=yaaW;Dbxref=ASAP:ABE-0000037,ECOCYC:G6082,EcoGene:EG14340,GeneID:944771;Name=yaaW;gbkey=Gene;gene=yaaW;gene_biotype=protein_coding;gene_synonym=ECK0011;locus_tag=b0011 +NC_000913.3 RefSeq CDS 10643 11356 . - 0 Parent=gene-b0011;Dbxref=UniProtKB/Swiss-Prot:P75617,Genbank:NP_414552.1,ASAP:ABE-0000037,ECOCYC:G6082,EcoGene:EG14340,GeneID:944771;Name=NP_414552.1;gbkey=CDS;gene=yaaW;locus_tag=b0011;orig_transcript_id=gnl|b0011|mrna.b0011;product=putative enzyme-specific chaperone YaaW;protein_id=NP_414552.1;transl_table=11 +NC_000913.3 RefSeq gene 10830 11315 . + . ID=gene-b0012;geneID=gene-b0012;gene_name=mbiA;Dbxref=ASAP:ABE-0000040,ECOCYC:EG11509,EcoGene:EG11509,GeneID:948295;Name=mbiA;gbkey=Gene;gene=mbiA;gene_biotype=protein_coding;gene_synonym=ECK0012,htgA,htpY;locus_tag=b0012 +NC_000913.3 RefSeq CDS 10830 11315 . + 0 Parent=gene-b0012;Dbxref=UniProtKB/Swiss-Prot:P28697,Genbank:YP_009518733.1,ASAP:ABE-0000040,ECOCYC:EG11509,EcoGene:EG11509,GeneID:948295;Name=YP_009518733.1;gbkey=CDS;gene=mbiA;locus_tag=b0012;orig_transcript_id=gnl|b0012|mrna.CDS13;product=uncharacterized protein MbiA;protein_id=YP_009518733.1;transl_table=11 +NC_000913.3 RefSeq gene 11382 11786 . - . ID=gene-b0013;geneID=gene-b0013;gene_name=yaaI;Dbxref=ASAP:ABE-0000043,ECOCYC:G8202,EcoGene:EG11513,GeneID:944751;Name=yaaI;gbkey=Gene;gene=yaaI;gene_biotype=protein_coding;gene_synonym=ECK0013;locus_tag=b0013 +NC_000913.3 RefSeq CDS 11382 11786 . - 0 Parent=gene-b0013;Dbxref=UniProtKB/Swiss-Prot:P28696,Genbank:NP_414554.1,ASAP:ABE-0000043,ECOCYC:G8202,EcoGene:EG11513,GeneID:944751;Name=NP_414554.1;gbkey=CDS;gene=yaaI;locus_tag=b0013;orig_transcript_id=gnl|b0013|mrna.b0013;product=DUF2541 domain-containing protein YaaI;protein_id=NP_414554.1;transl_table=11 +NC_000913.3 RefSeq gene 12163 14079 . + . ID=gene-b0014;geneID=gene-b0014;gene_name=dnaK;Dbxref=ASAP:ABE-0000052,ECOCYC:EG10241,EcoGene:EG10241,GeneID:944750;Name=dnaK;gbkey=Gene;gene=dnaK;gene_biotype=protein_coding;gene_synonym=ECK0014,groPAB,groPC,groPF,grpC,grpF,seg;locus_tag=b0014 +NC_000913.3 RefSeq CDS 12163 14079 . + 0 Parent=gene-b0014;Dbxref=UniProtKB/Swiss-Prot:P0A6Y8,Genbank:NP_414555.1,ASAP:ABE-0000052,ECOCYC:EG10241,EcoGene:EG10241,GeneID:944750;Name=NP_414555.1;gbkey=CDS;gene=dnaK;locus_tag=b0014;orig_transcript_id=gnl|b0014|mrna.b0014;product=chaperone protein DnaK;protein_id=NP_414555.1;transl_table=11 +NC_000913.3 RefSeq gene 14168 15298 . + . ID=gene-b0015;geneID=gene-b0015;gene_name=dnaJ;Dbxref=ASAP:ABE-0000054,ECOCYC:EG10240,EcoGene:EG10240,GeneID:944753;Name=dnaJ;gbkey=Gene;gene=dnaJ;gene_biotype=protein_coding;gene_synonym=ECK0015,groP,grpC;locus_tag=b0015 +NC_000913.3 RefSeq CDS 14168 15298 . + 0 Parent=gene-b0015;Dbxref=UniProtKB/Swiss-Prot:P08622,Genbank:NP_414556.1,ASAP:ABE-0000054,ECOCYC:EG10240,EcoGene:EG10240,GeneID:944753;Name=NP_414556.1;gbkey=CDS;gene=dnaJ;locus_tag=b0015;orig_transcript_id=gnl|b0015|mrna.b0015;product=chaperone protein DnaJ;protein_id=NP_414556.1;transl_table=11