Skip to content
New issue

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

Sign up for GitHub

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

Already on GitHub? Sign in to your account

support obj ref in rec header for Genome and AMA #16

Open
wants to merge 2 commits into
base: develop
Choose a base branch
from
Open

support obj ref in rec header for Genome and AMA #16

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e50fefc
support obj ref in rec header for Genome and AMA
Aug 5, 2022
28b7cd9
support obj ref in rec header for Genome and AMA
Aug 5, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions RELEASE_NOTES.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,7 @@
### Version 1.1.2
__Changes__
- adjust fasta headers to support object ref for GenomeToFASTA() and AnnotatedMetagenomeAssembluyToFASTA()

### Version 1.1.1
__Changes__
- adjust fasta IDs to be under length threshold and return ID map
Expand Down
2 changes: 1 addition & 1 deletion kbase.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ service-language:
python

module-version:
1.1.1
1.1.2

owners:
[dylan]
Expand Down
30 changes: 17 additions & 13 deletions lib/KBaseDataObjectToFileUtils/KBaseDataObjectToFileUtilsImpl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,9 +36,9 @@ class KBaseDataObjectToFileUtils:
# state. A method could easily clobber the state set by another while
# the latter method is running.
######################################### noqa
VERSION = "1.1.1"
VERSION = "1.1.2"
GIT_URL = "https://github.com/kbaseapps/KBaseDataObjectToFileUtils"
GIT_COMMIT_HASH = "7afc08354767fb5af2e4e5e4f7ab60c8f2137b8a"
GIT_COMMIT_HASH = "e50fefcb9055647abf9b492f83b23a45b7e1af67"

#BEGIN_CLASS_HEADER
workspaceURL = None
Expand Down Expand Up @@ -572,9 +572,10 @@ def GenomeToFASTA(self, ctx, params):
case = case[0:1].upper()
short_index = 0

def record_header_sub(str, feature_id, genome_id):
def record_header_sub(str, feature_id, genome_id, genome_ref):
str = str.replace('%%feature_id%%', feature_id)
str = str.replace('%%genome_id%%', genome_id)
str = str.replace('%%genome_ref%%', genome_ref)
return str

fasta_file_path = os.path.join(dir, file)
Expand Down Expand Up @@ -634,14 +635,14 @@ def record_header_sub(str, feature_id, genome_id):
continue
else:
feature_sequence_found = True
rec_id = record_header_sub(record_id_pattern, feature['id'], genome_object['id'])
rec_id = record_header_sub(record_id_pattern, feature['id'], genome_object['id'], genome_ref)
short_id = rec_id
if id_len_limit != None and id_len_limit > 0:
if len(rec_id) >= id_len_limit:
short_index += 1
short_id = 'SID_'+str(short_index)
short_id_to_rec_id[short_id] = rec_id
rec_desc = record_header_sub(record_desc_pattern, feature['id'], genome_object['id'])
rec_desc = record_header_sub(record_desc_pattern, feature['id'], genome_object['id'], genome_ref)
seq = feature['protein_translation']
seq = seq.upper() if case == 'U' else seq.lower()

Expand Down Expand Up @@ -670,14 +671,14 @@ def record_header_sub(str, feature_id, genome_id):
self.log(invalid_msgs, "bad feature "+feature['id']+": No dna_sequence field.")
else:
feature_sequence_found = True
rec_id = record_header_sub(record_id_pattern, feature['id'], genome_object['id'])
rec_id = record_header_sub(record_id_pattern, feature['id'], genome_object['id'], genome_ref)
short_id = rec_id
if id_len_limit != None and id_len_limit > 0:
if len(rec_id) >= id_len_limit:
short_index += 1
short_id = 'SID_'+str(short_index)
short_id_to_rec_id[short_id] = rec_id
rec_desc = record_header_sub(record_desc_pattern, feature['id'], genome_object['id'])
rec_desc = record_header_sub(record_desc_pattern, feature['id'], genome_object['id'], genome_ref)
seq = feature['dna_sequence']
seq = seq.upper() if case == 'U' else seq.lower()

Expand Down Expand Up @@ -1568,9 +1569,12 @@ def AnnotatedMetagenomeAssemblyToFASTA(self, ctx, params):
case = case[0:1].upper()
short_index = 0

def record_header_sub(str, feature_id, genome_id):
def record_header_sub(str, feature_id, ama_id, ama_ref):
str = str.replace('%%feature_id%%', feature_id)
str = str.replace('%%genome_id%%', genome_id)
str = str.replace('%%genome_id%%', ama_id)
str = str.replace('%%genome_ref%%', ama_ref)
str = str.replace('%%ama_id%%', ama_id)
str = str.replace('%%ama_ref%%', ama_ref)
return str

fasta_file_path = os.path.join(dir, file)
Expand Down Expand Up @@ -1630,14 +1634,14 @@ def record_header_sub(str, feature_id, genome_id):
# continue
else:
feature_sequence_found = True
rec_id = record_header_sub(record_id_pattern, feature['id'], ama_object_name)
rec_id = record_header_sub(record_id_pattern, feature['id'], ama_object_name, ama_ref)
short_id = rec_id
if id_len_limit != None and id_len_limit > 0:
if len(rec_id) >= id_len_limit:
short_index += 1
short_id = 'SID_'+str(short_index)
short_id_to_rec_id[short_id] = rec_id
rec_desc = record_header_sub(record_desc_pattern, feature['id'], ama_object_name)
rec_desc = record_header_sub(record_desc_pattern, feature['id'], ama_object_name, ama_ref)

if feature.get('protein_translation'):
seq = feature['protein_translation']
Expand Down Expand Up @@ -1680,14 +1684,14 @@ def record_header_sub(str, feature_id, genome_id):
continue
else:
feature_sequence_found = True
rec_id = record_header_sub(record_id_pattern, feature['id'], ama_object_name)
rec_id = record_header_sub(record_id_pattern, feature['id'], ama_object_name, ama_ref)
short_id = rec_id
if id_len_limit != None and id_len_limit > 0:
if len(rec_id) >= id_len_limit:
short_index += 1
short_id = 'SID_'+str(short_index)
short_id_to_rec_id[short_id] = rec_id
rec_desc = record_header_sub(record_desc_pattern, feature['id'], ama_object_name)
rec_desc = record_header_sub(record_desc_pattern, feature['id'], ama_object_name, ama_ref)
if feature.get('dna_sequence'):
seq = feature['dna_sequence']
else:
Expand Down
Loading