-
Notifications
You must be signed in to change notification settings - Fork 129
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[translate] update test syntax / format
The move to "Creating files in the initial working directory" is motivated by <#1344 (comment)> and <#1176>. Additionally, I remove the pushd commands which were confusing (there were multiple!) and use variables to refer to common directories to improve readability.
- Loading branch information
1 parent
02ed067
commit 0987264
Showing
5 changed files
with
50 additions
and
43 deletions.
There are no files selected for viewing
This file was deleted.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,18 +1,21 @@ | ||
| Setup | ||
|
|
||
| $ pushd "$TESTDIR" > /dev/null | ||
| $ source _setup.sh | ||
| $ export AUGUR="${AUGUR:-$TESTDIR/../../../../bin/augur}" | ||
| $ export DATA="$TESTDIR/../data" | ||
| $ export SCRIPTS="$TESTDIR/../../../../scripts" | ||
|
|
||
| Translate amino acids for genes using a GenBank file. | ||
|
|
||
| $ ${AUGUR} translate \ | ||
| > --tree translate/data/zika/tree.nwk \ | ||
| > --ancestral-sequences translate/data/zika/nt_muts.json \ | ||
| > --reference-sequence translate/data/zika/zika_outgroup.gb \ | ||
| > --tree "$DATA/zika/tree.nwk" \ | ||
| > --ancestral-sequences "$DATA/zika/nt_muts.json" \ | ||
| > --reference-sequence "$DATA/zika/zika_outgroup.gb" \ | ||
| > --genes CA PRO \ | ||
| > --output-node-data $TMP/aa_muts.json | ||
| Validating schema of 'translate/data/zika/nt_muts.json'... | ||
| > --output-node-data aa_muts.json | ||
| Validating schema of '.+nt_muts.json'... (re) | ||
| Read in 3 features from reference sequence file | ||
| amino acid mutations written to .* (re) | ||
| $ python3 "../../scripts/diff_jsons.py" translate/data/zika/aa_muts_genbank.json $TMP/aa_muts.json | ||
|
|
||
| $ python3 "$SCRIPTS/diff_jsons.py" $DATA/zika/aa_muts_genbank.json aa_muts.json \ | ||
| > --exclude-regex-paths "root\['annotations'\]\['.+'\]\['seqid'\]" | ||
| {} |
23 changes: 12 additions & 11 deletions
23
tests/functional/translate/cram/translate-with-gff-and-gene-name.t
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,31 +1,32 @@ | ||
| Setup | ||
|
|
||
| $ pushd "$TESTDIR" > /dev/null | ||
| $ source _setup.sh | ||
| $ export AUGUR="${AUGUR:-$TESTDIR/../../../../bin/augur}" | ||
| $ export DATA="$TESTDIR/../data" | ||
| $ export SCRIPTS="$TESTDIR/../../../../scripts" | ||
|
|
||
| Translate amino acids for genes using a GFF3 file where the gene names are stored in a qualifier named "gene_name". | ||
|
|
||
| $ cat >$TMP/genemap.gff <<~~ | ||
| $ cat >genemap.gff <<~~ | ||
| > ##gff-version 3 | ||
| > ##sequence-region PF13/251013_18 1 10769 | ||
| > PF13/251013_18 GenBank gene 91 456 . + . gene_name="CA" | ||
| > PF13/251013_18 GenBank gene 457 735 . + . gene_name="PRO" | ||
| > ~~ | ||
|
|
||
| $ ${AUGUR} translate \ | ||
| > --tree translate/data/zika/tree.nwk \ | ||
| > --ancestral-sequences translate/data/zika/nt_muts.json \ | ||
| > --reference-sequence "$TMP/genemap.gff" \ | ||
| > --output-node-data $TMP/aa_muts.json | ||
| Validating schema of 'translate/data/zika/nt_muts.json'... | ||
| > --tree "${DATA}/zika/tree.nwk" \ | ||
| > --ancestral-sequences "${DATA}/zika/nt_muts.json" \ | ||
| > --reference-sequence "genemap.gff" \ | ||
| > --output-node-data aa_muts.json | ||
| Validating schema of '.+/nt_muts.json'... (re) | ||
| Read in 2 features from reference sequence file | ||
| amino acid mutations written to .* (re) | ||
|
|
||
| Other than the sequence ids which will include a temporary path, the JSONs | ||
| should be identical. | ||
|
|
||
| $ python3 "../../scripts/diff_jsons.py" \ | ||
| $ python3 "${SCRIPTS}/diff_jsons.py" \ | ||
| > --exclude-regex-paths "['seqid']" -- \ | ||
| > translate/data/zika/aa_muts_gff.json \ | ||
| > $TMP/aa_muts.json | ||
| > "${DATA}/zika/aa_muts_gff.json" \ | ||
| > aa_muts.json | ||
| {} |
24 changes: 13 additions & 11 deletions
24
tests/functional/translate/cram/translate-with-gff-and-gene.t
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,27 +1,29 @@ | ||
| Setup | ||
|
|
||
| $ pushd "$TESTDIR" > /dev/null | ||
| $ source _setup.sh | ||
| $ export AUGUR="${AUGUR:-$TESTDIR/../../../../bin/augur}" | ||
| $ export DATA="$TESTDIR/../data" | ||
| $ export SCRIPTS="$TESTDIR/../../../../scripts" | ||
|
|
||
| Translate amino acids for genes using a GFF3 file where the gene names are stored in a qualifier named "gene". | ||
|
|
||
| $ cat >$TMP/genemap.gff <<~~ | ||
| $ cat >genemap.gff <<~~ | ||
| > ##gff-version 3 | ||
| > ##sequence-region PF13/251013_18 1 10769 | ||
| > PF13/251013_18 GenBank gene 91 456 . + . gene="CA" | ||
| > PF13/251013_18 GenBank gene 457 735 . + . gene="PRO" | ||
| > ~~ | ||
|
|
||
| $ ${AUGUR} translate \ | ||
| > --tree translate/data/zika/tree.nwk \ | ||
| > --ancestral-sequences translate/data/zika/nt_muts.json \ | ||
| > --reference-sequence "$TMP/genemap.gff" \ | ||
| > --output-node-data $TMP/aa_muts.json | ||
| Validating schema of 'translate/data/zika/nt_muts.json'... | ||
| > --tree "${DATA}/zika/tree.nwk" \ | ||
| > --ancestral-sequences "${DATA}/zika/nt_muts.json" \ | ||
| > --reference-sequence genemap.gff \ | ||
| > --output-node-data aa_muts.json | ||
| Validating schema of '.+/nt_muts.json'... (re) | ||
| Read in 2 features from reference sequence file | ||
| amino acid mutations written to .* (re) | ||
| $ python3 "../../scripts/diff_jsons.py" \ | ||
|
|
||
| $ python3 "${SCRIPTS}/diff_jsons.py" \ | ||
| > --exclude-regex-paths "['seqid']" -- \ | ||
| > translate/data/zika/aa_muts_gff.json \ | ||
| > $TMP/aa_muts.json | ||
| > "${DATA}/zika/aa_muts_gff.json" \ | ||
| > aa_muts.json | ||
| {} |
25 changes: 14 additions & 11 deletions
25
tests/functional/translate/cram/translate-with-gff-and-locus-tag.t
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,23 +1,26 @@ | ||
| Setup | ||
|
|
||
| $ pushd "$TESTDIR" > /dev/null | ||
| $ source _setup.sh | ||
| $ export AUGUR="${AUGUR:-$TESTDIR/../../../../bin/augur}" | ||
| $ export DATA="$TESTDIR/../data" | ||
| $ export SCRIPTS="$TESTDIR/../../../../scripts" | ||
|
|
||
| Translate amino acids for genes using a GFF3 file where the gene names are stored in a qualifier named "locus_tag". | ||
|
|
||
| $ ${AUGUR} translate \ | ||
| > --tree translate/data/tb/tree.nwk \ | ||
| > --genes translate/data/tb/genes.txt \ | ||
| > --vcf-reference translate/data/tb/ref.fasta \ | ||
| > --ancestral-sequences translate/data/tb/nt_muts.vcf \ | ||
| > --reference-sequence translate/data/tb/Mtb_H37Rv_NCBI_Annot.gff \ | ||
| > --output-node-data $TMP/aa_muts.json \ | ||
| > --alignment-output $TMP/translations.vcf \ | ||
| > --vcf-reference-output $TMP/translations_reference.fasta | ||
| > --tree "${DATA}/tb/tree.nwk" \ | ||
| > --genes "${DATA}/tb/genes.txt" \ | ||
| > --vcf-reference "${DATA}/tb/ref.fasta" \ | ||
| > --ancestral-sequences "${DATA}/tb/nt_muts.vcf" \ | ||
| > --reference-sequence "${DATA}/tb/Mtb_H37Rv_NCBI_Annot.gff" \ | ||
| > --output-node-data aa_muts.json \ | ||
| > --alignment-output translations.vcf \ | ||
| > --vcf-reference-output translations_reference.fasta | ||
| Gene length of rrs_Rvnr01 is not a multiple of 3. will pad with N | ||
| Read in 187 specified genes to translate. | ||
| Read in 187 features from reference sequence file | ||
| 162 genes had no mutations and so have been be excluded. | ||
| amino acid mutations written to .* (re) | ||
| $ python3 "../../scripts/diff_jsons.py" translate/data/tb/aa_muts.json $TMP/aa_muts.json | ||
|
|
||
| $ python3 "${SCRIPTS}/diff_jsons.py" "${DATA}/tb/aa_muts.json" aa_muts.json \ | ||
| > --exclude-regex-paths "root\['annotations'\]\['.+'\]\['seqid'\]" | ||
| {} |