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

Develop #101

Open
wants to merge 14 commits into
base: master
Choose a base branch
from
Open

Develop #101

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
14 commits
Select commit Hold shift + click to select a range
1501e1e
adding cycle options to hivtrace
stevenweaver Mar 6, 2019
94d2440
Merge branch 'develop' of github.com:veg/hivtrace into develop
stevenweaver Mar 11, 2019
ae9ea5a
Update setup.py
stevenweaver Oct 1, 2019
6b222f4
Merge branch 'master' into develop
stevenweaver Feb 10, 2020
24118ca
merge
stevenweaver Feb 10, 2020
ff79770
bump dependency
stevenweaver Feb 10, 2020
d01e04a
Merge branch 'develop' into develop
stevenweaver Feb 10, 2020
60b1e04
Merge pull request #69 from stevenweaver/develop
stevenweaver Feb 10, 2020
fee3b1b
Merge branch 'develop' into cycle-report
stevenweaver Nov 8, 2023
2cba8fa
Merge pull request #93 from veg/cycle-report
stevenweaver Nov 8, 2023
bf6fdca
merge develop
stevenweaver Mar 13, 2024
472e400
merging master
stevenweaver Mar 13, 2024
a0ba744
Merge branch 'master' of github.com:veg/hivtrace into develop
stevenweaver Mar 13, 2024
bdcc2e8
Merge branch 'master' into develop
stevenweaver Jul 12, 2024
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
32 changes: 32 additions & 0 deletions hivtrace/hivtrace.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -277,9 +277,12 @@ def hivtrace(id,
fraction,
strip_drams_flag=False,
filter_edges="no",
filter_cycles=False,
handle_contaminants="remove",
skip_alignment=False,
save_intermediate=True,
cycle_report_fn='',
attributes_file=None,
prior=None
):
"""
Expand Down Expand Up @@ -559,6 +562,12 @@ def hivtrace(id,
hivnetworkcsv_process.extend(
['-C', handle_contaminants, '-F', CONTAMINANT_ID_LIST])


if filter_cycles:
hivnetworkcsv_process.extend(['-l'])

if cycle_report_fn:
hivnetworkcsv_process.extend(['--cycle-report-file', cycle_report_fn])
if prior:
hivnetworkcsv_process.extend(
['--prior', prior])
Expand Down Expand Up @@ -714,25 +723,36 @@ def hivtrace(id,
def main():

parser = argparse.ArgumentParser(description='HIV TRACE')

parser.add_argument('-i', '--input', help='FASTA file', required=True)

parser.add_argument(
'-a',
'--ambiguities',
help='handle ambiguous nucleotides using the specified strategy',
required=True)

parser.add_argument(
'-r', '--reference', help='reference to align to', required=True)

parser.add_argument(
'-t',
'--threshold',
help='Only count edges where the distance is less than this threshold',
required=True)

parser.add_argument(
'-m', '--minoverlap', help='Minimum Overlap', required=True)

parser.add_argument('-g', '--fraction', help='Fraction', required=True)

parser.add_argument('-u', '--curate', help='Filter contaminants')

parser.add_argument(
'-f', '--filter', help='Edge filtering option', default="no", type=str)

parser.add_argument('--filter-cycles', help='Filters cycles', action='store_true')

parser.add_argument(
'-s',
'--strip_drams',
Expand All @@ -741,6 +761,7 @@ def main():
with these sites removed. It requires input/output file names along with the list of \
DRAM sites to remove: 'lewis' or 'wheeler'."
)

parser.add_argument(
'-c',
'--compare',
Expand All @@ -754,11 +775,16 @@ def main():

parser.add_argument(
'--skip-alignment', help='Skip alignment', action='store_true')

parser.add_argument('--attributes-file', help='Annotate with attributes')

parser.add_argument('--log', help='Write logs to specified directory')

parser.add_argument('-o', '--output', help='Specify output filename')
parser.add_argument('-p', '--prior', help='Prior network configuration')

parser.add_argument('--cycle-report-fn', help='cycle report output')

args = parser.parse_args()

if args.log:
Expand All @@ -779,6 +805,7 @@ def main():
COMPARE_TO_LANL = args.compare
FRACTION = args.fraction
STRIP_DRAMS = args.strip_drams
CYCLE_REPORT_FN = None
PRIOR = None

if(args.prior):
Expand All @@ -787,6 +814,9 @@ def main():
if args.output:
OUTPUT_FN = args.output

if args.cycle_report_fn:
CYCLE_REPORT_FN = args.cycle_report_fn

if STRIP_DRAMS != 'wheeler' and STRIP_DRAMS != 'lewis':
STRIP_DRAMS = False

Expand All @@ -801,9 +831,11 @@ def main():
FRACTION,
strip_drams_flag=STRIP_DRAMS,
filter_edges=args.filter,
filter_cycles=args.filter_cycles,
handle_contaminants=args.curate,
skip_alignment=args.skip_alignment,
save_intermediate=(not args.do_not_store_intermediate),
cycle_report_fn=CYCLE_REPORT_FN,
prior=PRIOR
)

Expand Down
2 changes: 1 addition & 1 deletion test/rsrc/TEST.FASTA_USER.TRACE.JSON
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1 @@
{"Degrees": {"Distribution": [4, 1], "fitted": [0.8516685221760777, 0.110011136113623], "Model": "Yule", "rho": 6.741657365453795, "rho CI": [1.457751736250405, 798.9933640071333]}, "Network Summary": {"Edges": 3, "Sequences used to make links": 5, "Clusters": 2, "Nodes": 5}, "Cluster sizes": [2, 3], "Nodes": [{"edi": null, "attributes": {"COUNTRY": "JP", "SOURCE": "TEST.FASTA_output.fasta", "YEAR_OF_SAMPLING": "2036", "ACCESSION_NUMBER": "K03455", "SUBTYPE": "Z"}, "hxb2_linked": "false", "id": "Z|JP|K03455|2036|5", "cluster": 1, "baseline": null}, {"edi": null, "attributes": {"COUNTRY": "JP", "SOURCE": "TEST.FASTA_output.fasta", "YEAR_OF_SAMPLING": "2036", "ACCESSION_NUMBER": "K03455", "SUBTYPE": "Z"}, "hxb2_linked": "false", "id": "Z|JP|K03455|2036|4", "cluster": 1, "baseline": null}, {"edi": null, "attributes": {"COUNTRY": "JP", "SOURCE": "TEST.FASTA_output.fasta", "YEAR_OF_SAMPLING": "2036", "ACCESSION_NUMBER": "K03455", "SUBTYPE": "Z"}, "hxb2_linked": "false", "id": "Z|JP|K03455|2036|3", "cluster": 2, "baseline": null}, {"edi": null, "attributes": {"COUNTRY": "JP", "SOURCE": "TEST.FASTA_output.fasta", "YEAR_OF_SAMPLING": "2036", "ACCESSION_NUMBER": "K03455", "SUBTYPE": "Z"}, "hxb2_linked": "false", "id": "Z|JP|K03455|2036", "cluster": 2, "baseline": null}, {"edi": null, "attributes": {"COUNTRY": "JP", "SOURCE": "TEST.FASTA_output.fasta", "YEAR_OF_SAMPLING": "2036", "ACCESSION_NUMBER": "K03455", "SUBTYPE": "Z"}, "hxb2_linked": "false", "id": "Z|JP|K03455|2036|2", "cluster": 2, "baseline": null}], "Directed Edges": {"Reasons for unresolved directions": {"Missing dates": 3}, "Count": 0}, "Edges": [{"removed": false, "length": 0.0101121, "directed": false, "source": 4, "support": 0.0, "sequences": ["Z|JP|K03455|2036|2", "Z|JP|K03455|2036|3"], "target": 2}, {"removed": false, "length": 0.0146112, "directed": false, "source": 3, "support": 0.0, "sequences": ["Z|JP|K03455|2036", "Z|JP|K03455|2036|3"], "target": 2}, {"removed": false, "length": 0.00230851, "directed": false, "source": 1, "support": 0.0, "sequences": ["Z|JP|K03455|2036|4", "Z|JP|K03455|2036|5"], "target": 0}], "Multiple sequences": {"Subjects with": 0, "Followup, days": null}, "HIV Stages": {"Chronic": 5, "A-3": 0, "E-2": 0, "A-2": 0, "E-1": 0, "A-1": 0, "E-3": 0}}
{"Cluster sizes": [2, 3], "Edges": [{"support": 0.0, "length": 0.0101121, "target": 2, "removed": false, "sequences": ["Z|JP|K03455|2036|2", "Z|JP|K03455|2036|3"], "source": 4, "directed": false}, {"support": 0.0, "length": 0.0146112, "target": 2, "removed": false, "sequences": ["Z|JP|K03455|2036", "Z|JP|K03455|2036|3"], "source": 3, "directed": false}, {"support": 0.0, "length": 0.00230851, "target": 0, "removed": false, "sequences": ["Z|JP|K03455|2036|4", "Z|JP|K03455|2036|5"], "source": 1, "directed": false}], "HIV Stages": {"E-1": 0, "E-3": 0, "A-3": 0, "A-2": 0, "A-1": 0, "Chronic": 5, "E-2": 0}, "Directed Edges": {"Count": 0, "Reasons for unresolved directions": {"Missing dates": 3}}, "Multiple sequences": {"Subjects with": 0, "Followup, days": null}, "Nodes": [{"edi": null, "baseline": null, "cluster": 1, "hxb2_linked": "false", "id": "Z|JP|K03455|2036|5", "attributes": {"COUNTRY": "JP", "SOURCE": "TEST.FASTA_output.fasta", "YEAR_OF_SAMPLING": "2036", "ACCESSION_NUMBER": "K03455", "SUBTYPE": "Z"}}, {"edi": null, "baseline": null, "cluster": 1, "hxb2_linked": "false", "id": "Z|JP|K03455|2036|4", "attributes": {"COUNTRY": "JP", "SOURCE": "TEST.FASTA_output.fasta", "YEAR_OF_SAMPLING": "2036", "ACCESSION_NUMBER": "K03455", "SUBTYPE": "Z"}}, {"edi": null, "baseline": null, "cluster": 2, "hxb2_linked": "false", "id": "Z|JP|K03455|2036|3", "attributes": {"COUNTRY": "JP", "SOURCE": "TEST.FASTA_output.fasta", "YEAR_OF_SAMPLING": "2036", "ACCESSION_NUMBER": "K03455", "SUBTYPE": "Z"}}, {"edi": null, "baseline": null, "cluster": 2, "hxb2_linked": "false", "id": "Z|JP|K03455|2036", "attributes": {"COUNTRY": "JP", "SOURCE": "TEST.FASTA_output.fasta", "YEAR_OF_SAMPLING": "2036", "ACCESSION_NUMBER": "K03455", "SUBTYPE": "Z"}}, {"edi": null, "baseline": null, "cluster": 2, "hxb2_linked": "false", "id": "Z|JP|K03455|2036|2", "attributes": {"COUNTRY": "JP", "SOURCE": "TEST.FASTA_output.fasta", "YEAR_OF_SAMPLING": "2036", "ACCESSION_NUMBER": "K03455", "SUBTYPE": "Z"}}], "Degrees": {"Distribution": [4, 1], "rho": 6.741657365453795, "Model": "Yule", "rho CI": [1.457751736250405, 798.9933640071333], "fitted": [0.8516685221760777, 0.110011136113623]}, "Network Summary": {"Edges": 3, "Nodes": 5, "Clusters": 2, "Sequences used to make links": 5}}