Next changeset 1:029d90b0c4f6 (2023-07-14) |
Commit message:
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/smallgenomeutilities commit f6d1be0a6643389820c4622d4cb996ac03531107 |
added:
frameshift_deletions_checks.xml macros.xml test-data/Genes_NC_045512.2.GFF3 test-data/NC_045512.2.fasta.gz test-data/REF_aln_trim.cram test-data/REF_aln_trim.cram.crai test-data/consensus.bcftools.fasta.gz test-data/frameshift_deletions_check.tsv |
b |
diff -r 000000000000 -r f079716f598c frameshift_deletions_checks.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/frameshift_deletions_checks.xml Wed May 31 17:10:11 2023 +0000 |
[ |
@@ -0,0 +1,89 @@ +<tool id="smgu_frameshift_deletions_checks" name="Frameshift Deletions Checks" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@"> + <description>reports on frameshifting indels in consensus sequence</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="xrefs"/> + <requirements> + <requirement type="package" version="@TOOL_VERSION@">smallgenomeutilities</requirement> + </requirements> + <!-- once we have version-from-git-tag in 0.4.0: <version_command>frameshift_deletion_checks --version</version_command> --> + <command detect_errors="exit_code"> + <![CDATA[ +#if $input.is_of_type("cram"): +echo 'is CRAM' >&2 && + ln -vs '$input' 'input.${input.ext}' >&2 && + ln -vs '$input.metadata.cram_index' 'input.${input.ext}.crai' >&2 && +#elif $input.is_of_type("bam"): + echo 'is BAM' && + ln -s '$input' 'input.${input.ext}' >&2 && + ln -s '$input.metadata.bam_index' 'input.${input.ext}.bai' >&2 && +#else: +# raise TypeError('Unknown input alignment type ${input.ext}') +#end if +ln -vs '$consensus' 'consensus.${consensus.ext}' >&2 && +ln -vs '$reference' 'reference.${reference.ext}' >&2 && + +frameshift_deletions_checks + --input='input.${input.ext}' + --consensus='consensus.${consensus.ext}' + --reference='reference.${reference.ext}' + --genes='$genes' + --output='$report' +#if $orf1ab != '': + --orf1ab='$orf1ab' +#end if + '$english' + $zero_based +]]> + <!-- ##cores \${GALAXY_SLOTS:-4} --> + </command> + <inputs> + <param argument="--consensus" type="data" format="fasta" label="Consensus" help="Fasta file containing the sample's consensus sequence (majority, with indels)" /> + <param argument="--input" type="data" format="bam,cram" label="Input BAM" help="Input BAM file with sample's sequencing reads, aligned against the reference" /> + <param argument="--reference" type="data" format="fasta" label="Reference" help="Fasta file containing the reference sequence (used during alignment) to compare against" /> + <param argument="--genes" type="data" format="gff" label="Genes GFF" help="GFF file listing genes positions on the reference sequence" /> + + <param argument="--english" type="boolean" truevalue="--english" falsevalue="--no-english" checked="true" optional="true" label="Write Summary Diagnosis?" help="If checked writes english summary diagnosis." /> + <param argument="--zero-based" type="boolean" truevalue="--zero-based" falsevalue="" checked="false" optional="true" label="Use 0-based Sequence Positions?" help="Use 0-based (python) instead of 1-based (standard) seq positions" /> + <param argument="--orf1ab" type="text" value="cds-YP_009724389.1" optional="true" label="ORF1AB" help="CDS ID for the full Orf1ab CDS, comprising the ribosomal shift. In the GFF this CDS should consist of 2 entries with the same CDS ID due to the partial overlap caused by the ribosomal shift at translation time."/> + </inputs> + <outputs> + <data name="report" format="tabular" /> + </outputs> + <tests> + <test> + <param name="consensus" value="consensus.bcftools.fasta.gz" /> + <param name="input" value="REF_aln_trim.cram" /> + <param name="reference" value="NC_045512.2.fasta.gz" /> + <param name="genes" value="Genes_NC_045512.2.GFF3" /> + <output name="report" value="frameshift_deletions_check.tsv" /> + </test> + </tests> + <help> + <![CDATA[ +Produces a report about frameshifting indels in a consensus sequences. + +Developed as part of the `V-pipe workflow for analysing NGS data of short viral genomes <https://github.com/cbg-ethz/V-pipe>`_. + +Columns signification: +---------------------- + +* *gene_region*: Gene in which the deletion is found according to ``--genes`` argument; +* *reads_all*: Total number of reads covering the indel; +* *reads_fwd*: Total nubmer of forward reads covering the indel; +* *reads_rev*: Total nubmer of reverse reads covering the indel; +* *deletions/insertions*: Number of reads supporting the deletion/insertion; +* *freq_del/freq_insert*: Fraction of reads supporting the deletion/insertion; +* *matches_ref*: number of reads that matche with the reference base; +* *pos_critical_inserts*: Start positions of insertions in the same gene_region that occur in > 40% of reads; +* *pos_critical_dels*: Start positions of deletions in the same gene_region that occur in > 40% of reads; +* *homopolymeric*: True if either around the start or end position of the deletion three bases are the same, which may have caused the polymerase to skip during reverse transcription of viral RNA to cDNA, e.g. AATAG; +* *ref_base*: base in the reference genome; +* *indel_position_english*: english sentence describing the indel; +* *indel_diagnosis*: english sentence with the indel diagnosis; +* *orf1ab*: CDS ID for the full Orf1ab CDS, comprising the ribosomal shift. In the GFF this CDS should consist of 2 entries with the same CDS ID due to the parital overlap caused by the ribosomal shift at translation time +]]> + </help> + <expand macro="citations"/> +</tool> |
b |
diff -r 000000000000 -r f079716f598c macros.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Wed May 31 17:10:11 2023 +0000 |
b |
@@ -0,0 +1,15 @@ +<macros> + <token name="@TOOL_VERSION@">0.3.9</token> + <token name="@VERSION_SUFFIX@">0</token> + <token name="@PROFILE@">21.09</token> + <xml name="xrefs"> + <xrefs> + <xref type="bio.tools">v-pipe</xref> + </xrefs> + </xml> + <xml name="citations"> + <citations> + <citation type="doi">10.1093/bioinformatics/btab015</citation> + </citations> + </xml> +</macros> |
b |
diff -r 000000000000 -r f079716f598c test-data/Genes_NC_045512.2.GFF3 --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/Genes_NC_045512.2.GFF3 Wed May 31 17:10:11 2023 +0000 |
b |
@@ -0,0 +1,36 @@ +##gff-version 3 +#!gff-spec-version 1.21 +#!processor NCBI annotwriter +##sequence-region NC_045512.2 1 29903 +NC_045512.2 RefSeq five_prime_UTR 1 265 . + . ID=id-NC_045512.2:1..265;gbkey=5'UTR +NC_045512.2 RefSeq gene 266 21555 . + . ID=gene-GU280_gp01;Dbxref=GeneID:43740578;Name=ORF1ab;gbkey=Gene;gene=ORF1ab;gene_biotype=protein_coding;locus_tag=GU280_gp01 +NC_045512.2 RefSeq CDS 266 13468 . + 1 ID=cds-YP_009724389.1;Parent=gene-GU280_gp01;Dbxref=Genbank:YP_009724389.1,GeneID:43740578;Name=YP_009724389.1;Note=pp1ab%3B translated by -1 ribosomal frameshift;exception=ribosomal slippage;gbkey=CDS;gene=ORF1ab;locus_tag=GU280_gp01;product=ORF1ab polyprotein;protein_id=YP_009724389.1 +NC_045512.2 RefSeq CDS 13468 21555 . + 1 ID=cds-YP_009724389.1;Parent=gene-GU280_gp01;Dbxref=Genbank:YP_009724389.1,GeneID:43740578;Name=YP_009724389.1;Note=pp1ab%3B translated by -1 ribosomal frameshift;exception=ribosomal slippage;gbkey=CDS;gene=ORF1ab;locus_tag=GU280_gp01;product=ORF1ab polyprotein;protein_id=YP_009724389.1 +NC_045512.2 RefSeq CDS 266 13483 . + 1 ID=cds-YP_009725295.1;Parent=gene-GU280_gp01;Dbxref=Genbank:YP_009725295.1,GeneID:43740578;Name=YP_009725295.1;Note=pp1a;gbkey=CDS;gene=ORF1ab;locus_tag=GU280_gp01;product=ORF1a polyprotein;protein_id=YP_009725295.1 +NC_045512.2 RefSeq stem_loop 13476 13503 . + . ID=id-GU280_gp01;Dbxref=GeneID:43740578;function=Coronavirus frameshifting stimulation element stem-loop 1;gbkey=stem_loop;gene=ORF1ab;inference=COORDINATES: profile:Rfam-release-14.1:RF00507%2CInfernal:1.1.2;locus_tag=GU280_gp01 +NC_045512.2 RefSeq stem_loop 13488 13542 . + . ID=id-GU280_gp01-2;Dbxref=GeneID:43740578;function=Coronavirus frameshifting stimulation element stem-loop 2;gbkey=stem_loop;gene=ORF1ab;inference=COORDINATES: profile:profile:Rfam-release-14.1:RF00507%2CInfernal:1.1.2;locus_tag=GU280_gp01 +NC_045512.2 RefSeq gene 21563 25384 . + . ID=gene-GU280_gp02;Dbxref=GeneID:43740568;Name=S;gbkey=Gene;gene=S;gene_biotype=protein_coding;gene_synonym=spike glycoprotein;locus_tag=GU280_gp02 +NC_045512.2 RefSeq CDS 21563 25384 . + 1 ID=cds-YP_009724390.1;Parent=gene-GU280_gp02;Dbxref=Genbank:YP_009724390.1,GeneID:43740568;Name=YP_009724390.1;Note=structural protein%3B spike protein;gbkey=CDS;gene=S;locus_tag=GU280_gp02;product=surface glycoprotein;protein_id=YP_009724390.1 +NC_045512.2 RefSeq gene 25393 26220 . + . ID=gene-GU280_gp03;Dbxref=GeneID:43740569;Name=ORF3a;gbkey=Gene;gene=ORF3a;gene_biotype=protein_coding;locus_tag=GU280_gp03 +NC_045512.2 RefSeq CDS 25393 26220 . + 1 ID=cds-YP_009724391.1;Parent=gene-GU280_gp03;Dbxref=Genbank:YP_009724391.1,GeneID:43740569;Name=YP_009724391.1;gbkey=CDS;gene=ORF3a;locus_tag=GU280_gp03;product=ORF3a protein;protein_id=YP_009724391.1 +NC_045512.2 RefSeq gene 26245 26472 . + . ID=gene-GU280_gp04;Dbxref=GeneID:43740570;Name=E;gbkey=Gene;gene=E;gene_biotype=protein_coding;locus_tag=GU280_gp04 +NC_045512.2 RefSeq CDS 26245 26472 . + 1 ID=cds-YP_009724392.1;Parent=gene-GU280_gp04;Dbxref=Genbank:YP_009724392.1,GeneID:43740570;Name=YP_009724392.1;Note=ORF4%3B structural protein%3B E protein;gbkey=CDS;gene=E;locus_tag=GU280_gp04;product=envelope protein;protein_id=YP_009724392.1 +NC_045512.2 RefSeq gene 26523 27191 . + . ID=gene-GU280_gp05;Dbxref=GeneID:43740571;Name=M;gbkey=Gene;gene=M;gene_biotype=protein_coding;locus_tag=GU280_gp05 +NC_045512.2 RefSeq CDS 26523 27191 . + 1 ID=cds-YP_009724393.1;Parent=gene-GU280_gp05;Dbxref=Genbank:YP_009724393.1,GeneID:43740571;Name=YP_009724393.1;Note=ORF5%3B structural protein;gbkey=CDS;gene=M;locus_tag=GU280_gp05;product=membrane glycoprotein;protein_id=YP_009724393.1 +NC_045512.2 RefSeq gene 27202 27387 . + . ID=gene-GU280_gp06;Dbxref=GeneID:43740572;Name=ORF6;gbkey=Gene;gene=ORF6;gene_biotype=protein_coding;locus_tag=GU280_gp06 +NC_045512.2 RefSeq CDS 27202 27387 . + 1 ID=cds-YP_009724394.1;Parent=gene-GU280_gp06;Dbxref=Genbank:YP_009724394.1,GeneID:43740572;Name=YP_009724394.1;gbkey=CDS;gene=ORF6;locus_tag=GU280_gp06;product=ORF6 protein;protein_id=YP_009724394.1 +NC_045512.2 RefSeq gene 27394 27759 . + . ID=gene-GU280_gp07;Dbxref=GeneID:43740573;Name=ORF7a;gbkey=Gene;gene=ORF7a;gene_biotype=protein_coding;locus_tag=GU280_gp07 +NC_045512.2 RefSeq CDS 27394 27759 . + 1 ID=cds-YP_009724395.1;Parent=gene-GU280_gp07;Dbxref=Genbank:YP_009724395.1,GeneID:43740573;Name=YP_009724395.1;gbkey=CDS;gene=ORF7a;locus_tag=GU280_gp07;product=ORF7a protein;protein_id=YP_009724395.1 +NC_045512.2 RefSeq gene 27756 27887 . + . ID=gene-GU280_gp08;Dbxref=GeneID:43740574;Name=ORF7b;gbkey=Gene;gene=ORF7b;gene_biotype=protein_coding;locus_tag=GU280_gp08 +NC_045512.2 RefSeq CDS 27756 27887 . + 1 ID=cds-YP_009725318.1;Parent=gene-GU280_gp08;Dbxref=Genbank:YP_009725318.1,GeneID:43740574;Name=YP_009725318.1;gbkey=CDS;gene=ORF7b;locus_tag=GU280_gp08;product=ORF7b;protein_id=YP_009725318.1 +NC_045512.2 RefSeq gene 27894 28259 . + . ID=gene-GU280_gp09;Dbxref=GeneID:43740577;Name=ORF8;gbkey=Gene;gene=ORF8;gene_biotype=protein_coding;locus_tag=GU280_gp09 +NC_045512.2 RefSeq CDS 27894 28259 . + 1 ID=cds-YP_009724396.1;Parent=gene-GU280_gp09;Dbxref=Genbank:YP_009724396.1,GeneID:43740577;Name=YP_009724396.1;gbkey=CDS;gene=ORF8;locus_tag=GU280_gp09;product=ORF8 protein;protein_id=YP_009724396.1 +NC_045512.2 RefSeq gene 28274 29533 . + . ID=gene-GU280_gp10;Dbxref=GeneID:43740575;Name=N;gbkey=Gene;gene=N;gene_biotype=protein_coding;locus_tag=GU280_gp10 +NC_045512.2 RefSeq CDS 28274 29533 . + 1 ID=cds-YP_009724397.2;Parent=gene-GU280_gp10;Dbxref=Genbank:YP_009724397.2,GeneID:43740575;Name=YP_009724397.2;Note=ORF9%3B structural protein;gbkey=CDS;gene=N;locus_tag=GU280_gp10;product=nucleocapsid phosphoprotein;protein_id=YP_009724397.2 +NC_045512.2 RefSeq gene 29558 29674 . + . ID=gene-GU280_gp11;Dbxref=GeneID:43740576;Name=ORF10;gbkey=Gene;gene=ORF10;gene_biotype=protein_coding;locus_tag=GU280_gp11 +NC_045512.2 RefSeq CDS 29558 29674 . + 1 ID=cds-YP_009725255.1;Parent=gene-GU280_gp11;Dbxref=Genbank:YP_009725255.1,GeneID:43740576;Name=YP_009725255.1;gbkey=CDS;gene=ORF10;locus_tag=GU280_gp11;product=ORF10 protein;protein_id=YP_009725255.1 +NC_045512.2 RefSeq stem_loop 29609 29644 . + . ID=id-GU280_gp11;Dbxref=GeneID:43740576;function=Coronavirus 3' UTR pseudoknot stem-loop 1;gbkey=stem_loop;gene=ORF10;inference=COORDINATES: profile::Rfam-release-14.1:RF00165%2CInfernal:1.1.2;locus_tag=GU280_gp11 +NC_045512.2 RefSeq stem_loop 29629 29657 . + . ID=id-GU280_gp11-2;Dbxref=GeneID:43740576;function=Coronavirus 3' UTR pseudoknot stem-loop 2;gbkey=stem_loop;gene=ORF10;inference=COORDINATES: profile::Rfam-release-14.1:RF00165%2CInfernal:1.1.2;locus_tag=GU280_gp11 +NC_045512.2 RefSeq three_prime_UTR 29675 29903 . + . ID=id-NC_045512.2:29675..29903;gbkey=3'UTR +NC_045512.2 RefSeq stem_loop 29728 29768 . + . ID=id-NC_045512.2:29728..29768;Note=basepair exception: alignment to the Rfam model implies coordinates 29740:29758 form a noncanonical C:T basepair%2C but the homologous positions form a highly conserved C:G basepair in other viruses%2C including SARS (NC_004718.3);function=Coronavirus 3' stem-loop II-like motif (s2m);gbkey=stem_loop;inference=COORDINATES: profile:Rfam-release-14.1:RF00164%2CInfernal:1.1.2 +### |
b |
diff -r 000000000000 -r f079716f598c test-data/NC_045512.2.fasta.gz |
b |
Binary file test-data/NC_045512.2.fasta.gz has changed |
b |
diff -r 000000000000 -r f079716f598c test-data/REF_aln_trim.cram |
b |
Binary file test-data/REF_aln_trim.cram has changed |
b |
diff -r 000000000000 -r f079716f598c test-data/REF_aln_trim.cram.crai |
b |
Binary file test-data/REF_aln_trim.cram.crai has changed |
b |
diff -r 000000000000 -r f079716f598c test-data/consensus.bcftools.fasta.gz |
b |
Binary file test-data/consensus.bcftools.fasta.gz has changed |
b |
diff -r 000000000000 -r f079716f598c test-data/frameshift_deletions_check.tsv --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/test-data/frameshift_deletions_check.tsv Wed May 31 17:10:11 2023 +0000 |
[ |
b"@@ -0,0 +1,140 @@\n+\tref_id\tstart_position\tlength\tVARIANT\tgene_region\treads_all\treads_fwd\treads_rev\tdeletions\tfreq_del\tfreq_del_fwd\tfreq_del_rev\tdeletions_fwd\tdeletions_rev\tinsertions\tfreq_insert\tfreq_insert_fwd\tfreq_insert_rev\tinsertions_fwd\tinsertions_rev\tstops\tfreq_stop\tfreq_stop_fwd\tfreq_stop_rev\tstops_fwd\tstops_rev\tmatches_ref\tpos_critical_inserts\tpos_critical_dels\thomopolymeric\tref_base\tcons_id\tvariant_position_english\tvariant_diagnosis\n+0\tNC_045512.2\t5600\t2\tdeletion\tORF1ab\t40\t40\t0\t23\t0.575\t0.575\t0\t23\t0\t0\t0.0\t0.0\t0\t0\t0\t0\t0\t0\t0\t0\t0\t17\t[21101]\t[8740, 18800]\t1\tb'T'\tNC_045512.2\tGap of 2 nucleotide(s) found at refpos 5600\tonly fwd or rev reads available, deletion supported by the majority of them; homopolymeric; neighboring indels may restore reading frame\n+1\tNC_045512.2\t5602\t3\tstopgain\tORF1ab\t40\t40\t0\t0\t0.0\t0.0\t0\t0\t0\t0\t0.0\t0.0\t0\t0\t0\t40\t1.0\t1.0\t0\t40\t0\t40\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 5602, aminoacid position 1779\tonly fwd or rev reads available, stopgain supported by the majority of them\n+2\tNC_045512.2\t5635\t3\tstopgain\tORF1ab\t40\t40\t0\t0\t0.0\t0.0\t0\t0\t0\t0\t0.0\t0.0\t0\t0\t0\t40\t1.0\t1.0\t0\t40\t0\t40\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 5635, aminoacid position 1790\tonly fwd or rev reads available, stopgain supported by the majority of them\n+3\tNC_045512.2\t5707\t3\tstopgain\tORF1ab\t63\t39\t24\t0\t0.0\t0.0\t0.0\t0\t0\t0\t0.0\t0.0\t0.0\t0\t0\t63\t1.0\t1.0\t1.0\t39\t24\t63\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 5707, aminoacid position 1814\tstopgain supported by majority of fwd and rev reads\n+4\tNC_045512.2\t5713\t3\tstopgain\tORF1ab\t72\t39\t33\t0\t0.0\t0.0\t0.0\t0\t0\t0\t0.0\t0.0\t0.0\t0\t0\t72\t1.0\t1.0\t1.0\t39\t33\t72\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 5713, aminoacid position 1816\tstopgain supported by majority of fwd and rev reads\n+5\tNC_045512.2\t5737\t3\tstopgain\tORF1ab\t79\t39\t40\t0\t0.0\t0.0\t0.0\t0\t0\t0\t0.0\t0.0\t0.0\t0\t0\t79\t1.0\t1.0\t1.0\t39\t40\t79\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 5737, aminoacid position 1824\tstopgain supported by majority of fwd and rev reads\n+6\tNC_045512.2\t5740\t3\tstopgain\tORF1ab\t79\t39\t40\t0\t0.0\t0.0\t0.0\t0\t0\t0\t0.0\t0.0\t0.0\t0\t0\t79\t1.0\t1.0\t1.0\t39\t40\t79\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 5740, aminoacid position 1825\tstopgain supported by majority of fwd and rev reads\n+7\tNC_045512.2\t5752\t3\tstopgain\tORF1ab\t79\t39\t40\t0\t0.0\t0.0\t0.0\t0\t0\t0\t0.0\t0.0\t0.0\t0\t0\t79\t1.0\t1.0\t1.0\t39\t40\t79\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 5752, aminoacid position 1829\tstopgain supported by majority of fwd and rev reads\n+8\tNC_045512.2\t5773\t3\tstopgain\tORF1ab\t78\t38\t40\t0\t0.0\t0.0\t0.0\t0\t0\t0\t0.0\t0.0\t0.0\t0\t0\t78\t1.0\t1.0\t1.0\t38\t40\t78\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 5773, aminoacid position 1836\tstopgain supported by majority of fwd and rev reads\n+9\tNC_045512.2\t5788\t3\tstopgain\tORF1ab\t74\t34\t40\t0\t0.0\t0.0\t0.0\t0\t0\t0\t0.0\t0.0\t0.0\t0\t0\t74\t1.0\t1.0\t1.0\t34\t40\t74\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 5788, aminoacid position 1841\tstopgain supported by majority of fwd and rev reads\n+10\tNC_045512.2\t5911\t3\tstopgain\tORF1ab\t45\t5\t40\t0\t0.0\t0.0\t0.0\t0\t0\t0\t0.0\t0.0\t0.0\t0\t0\t45\t1.0\t1.0\t1.0\t5\t40\t45\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 5911, aminoacid position 1882\tstopgain supported by majority of fwd and rev reads\n+11\tNC_045512.2\t6043\t3\tstopgain\tORF1ab\t10\t5\t5\t0\t0.0\t0.0\t0.0\t0\t0\t0\t0.0\t0.0\t0.0\t0\t0\t10\t1.0\t1.0\t1.0\t5\t5\t10\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 6043, aminoacid position 1926\tstopgain supported by majority of fwd and rev reads\n+12\tNC_045512.2\t6049\t3\tstopgain\tORF1ab\t10\t5\t5\t0\t0.0\t0.0\t0.0\t0\t0\t0\t0.0\t0.0\t0.0\t0\t0\t10\t1.0\t1.0\t1.0\t5\t5\t10\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 6049, aminoacid position 1928\tstopgain supported by majority of fwd and rev reads\n+13\tNC_045512.2\t6061\t3\tstopgain\tORF1ab\t10\t5\t5\t0\t0.0\t0.0\t0.0\t0\t0\t0\t0.0\t0.0\t0.0\t0\t0\t10\t1.0\t1.0\t1.0\t5\t5\t10\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 6061, aminoacid position 1932\tstopgain supported by majority of fwd and rev reads\n+14\tNC_045512.2\t6064\t3\tst"..b"C_045512.2\tEarly Stopgain found at refpos 20780, aminoacid position 6838\tonly fwd or rev reads available, stopgain supported by the majority of them\n+124\tNC_045512.2\t20783\t3\tstopgain\tORF1ab\t250\t0\t250\t0\t0.0\t0\t0.0\t0\t0\t0\t0.0\t0\t0.0\t0\t0\t250\t1.0\t0\t1.0\t0\t250\t250\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 20783, aminoacid position 6839\tonly fwd or rev reads available, stopgain supported by the majority of them\n+125\tNC_045512.2\t20819\t3\tstopgain\tORF1ab\t275\t24\t251\t0\t0.0\t0.0\t0.0\t0\t0\t0\t0.0\t0.0\t0.0\t0\t0\t275\t1.0\t1.0\t1.0\t24\t251\t275\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 20819, aminoacid position 6851\tstopgain supported by majority of fwd and rev reads\n+126\tNC_045512.2\t20828\t3\tstopgain\tORF1ab\t275\t24\t251\t0\t0.0\t0.0\t0.0\t0\t0\t0\t0.0\t0.0\t0.0\t0\t0\t274\t0.9963636363636363\t1.0\t0.9960159362549801\t24\t250\t274\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 20828, aminoacid position 6854\tstopgain supported by majority of fwd and rev reads\n+127\tNC_045512.2\t20834\t3\tstopgain\tORF1ab\t275\t24\t251\t0\t0.0\t0.0\t0.0\t0\t0\t0\t0.0\t0.0\t0.0\t0\t0\t275\t1.0\t1.0\t1.0\t24\t251\t275\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 20834, aminoacid position 6856\tstopgain supported by majority of fwd and rev reads\n+128\tNC_045512.2\t20852\t3\tstopgain\tORF1ab\t275\t24\t251\t0\t0.0\t0.0\t0.0\t0\t0\t0\t0.0\t0.0\t0.0\t0\t0\t275\t1.0\t1.0\t1.0\t24\t251\t275\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 20852, aminoacid position 6862\tstopgain supported by majority of fwd and rev reads\n+129\tNC_045512.2\t20912\t3\tstopgain\tORF1ab\t24\t24\t0\t0\t0.0\t0.0\t0\t0\t0\t0\t0.0\t0.0\t0\t0\t0\t24\t1.0\t1.0\t0\t24\t0\t24\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 20912, aminoacid position 6882\tonly fwd or rev reads available, stopgain supported by the majority of them\n+130\tNC_045512.2\t20990\t3\tstopgain\tORF1ab\t48\t24\t24\t0\t0.0\t0.0\t0.0\t0\t0\t0\t0.0\t0.0\t0.0\t0\t0\t48\t1.0\t1.0\t1.0\t24\t24\t48\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 20990, aminoacid position 6908\tstopgain supported by majority of fwd and rev reads\n+131\tNC_045512.2\t21140\t3\tstopgain\tORF1ab\t41\t17\t24\t0\t0.0\t0.0\t0.0\t0\t0\t0\t0.0\t0.0\t0.0\t0\t0\t41\t1.0\t1.0\t1.0\t17\t24\t41\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 21140, aminoacid position 6958\tstopgain supported by majority of fwd and rev reads\n+132\tNC_045512.2\t21164\t3\tstopgain\tORF1ab\t17\t17\t0\t0\t0.0\t0.0\t0\t0\t0\t0\t0.0\t0.0\t0\t0\t0\t17\t1.0\t1.0\t0\t17\t0\t17\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 21164, aminoacid position 6966\tonly fwd or rev reads available, stopgain supported by the majority of them\n+133\tNC_045512.2\t21170\t3\tstopgain\tORF1ab\t17\t17\t0\t0\t0.0\t0.0\t0\t0\t0\t0\t0.0\t0.0\t0\t0\t0\t17\t1.0\t1.0\t0\t17\t0\t17\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 21170, aminoacid position 6968\tonly fwd or rev reads available, stopgain supported by the majority of them\n+134\tNC_045512.2\t21248\t3\tstopgain\tORF1ab\t34\t17\t17\t0\t0.0\t0.0\t0.0\t0\t0\t0\t0.0\t0.0\t0.0\t0\t0\t34\t1.0\t1.0\t1.0\t17\t17\t34\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 21248, aminoacid position 6994\tstopgain supported by majority of fwd and rev reads\n+135\tNC_045512.2\t21275\t3\tstopgain\tORF1ab\t34\t17\t17\t0\t0.0\t0.0\t0.0\t0\t0\t0\t0.0\t0.0\t0.0\t0\t0\t34\t1.0\t1.0\t1.0\t17\t17\t34\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 21275, aminoacid position 7003\tstopgain supported by majority of fwd and rev reads\n+136\tNC_045512.2\t21314\t3\tstopgain\tORF1ab\t31\t14\t17\t0\t0.0\t0.0\t0.0\t0\t0\t0\t0.0\t0.0\t0.0\t0\t0\t31\t1.0\t1.0\t1.0\t14\t17\t31\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 21314, aminoacid position 7016\tstopgain supported by majority of fwd and rev reads\n+137\tNC_045512.2\t21398\t3\tstopgain\tORF1ab\t21\t4\t17\t0\t0.0\t0.0\t0.0\t0\t0\t0\t0.0\t0.0\t0.0\t0\t0\t21\t1.0\t1.0\t1.0\t4\t17\t21\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 21398, aminoacid position 7044\tstopgain supported by majority of fwd and rev reads\n+138\tNC_045512.2\t21419\t3\tstopgain\tORF1ab\t21\t4\t17\t0\t0.0\t0.0\t0.0\t0\t0\t0\t0.0\t0.0\t0.0\t0\t0\t21\t1.0\t1.0\t1.0\t4\t17\t21\t[]\t[]\t0\tb'T'\tNC_045512.2\tEarly Stopgain found at refpos 21419, aminoacid position 7051\tstopgain supported by majority of fwd and rev reads\n" |