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

Jump to bottom

Handle emmtyper alt types #97

Merged
merged 3 commits into from
Nov 11, 2024
Merged

Handle emmtyper alt types #97

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
bd2a3b2
Handle alt types for emmtyper
ryanjameskennedy Nov 11, 2024
38d5d83
Handle emmtyper alt types
ryanjameskennedy Nov 11, 2024
f39d92e
Rm numpy import
ryanjameskennedy Nov 11, 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
1 change: 1 addition & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,7 @@
### Added

### Fixed
- Handle alt types for emmtyper

### Changed

Expand Down
6 changes: 3 additions & 3 deletions prp/models/typing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,9 +103,9 @@ class TypingResultEmm(RWModel):
"""Container for emmtype gene information"""

cluster_count: int
emmtype: str
emm_like_alleles: list[str]
emm_cluster: str
emmtype: str | None = None
emm_like_alleles: list[str] | None = None
emm_cluster: str | None = None


class EmmTypingMethodIndex(RWModel):
Expand Down
6 changes: 3 additions & 3 deletions prp/parse/phenotype/emmtyper.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,7 @@ def parse_emmtyper_pred(path: str) -> EmmTypingMethodIndex:
pred_result = []
df = pd.read_csv(path, sep='\t', header=None)
df.columns = ["sample_name", "cluster_count", "emmtype", "emm_like_alleles", "emm_cluster"]
df.replace(["-", ""], None, inplace=True)
df_loa = df.to_dict(orient="records")
for emmtype_array in df_loa:
emmtype_results = _parse_emmtyper_results(emmtype_array)
Expand All @@ -31,10 +32,9 @@ def parse_emmtyper_pred(path: str) -> EmmTypingMethodIndex:

def _parse_emmtyper_results(info: dict[str, Any]) -> TypingResultEmm:
"""Parse emm gene prediction results."""
emm_like_alleles = info["emm_like_alleles"].split(";")
emm_like_alleles = info["emm_like_alleles"].split(";") if not pd.isna(info["emm_like_alleles"]) else None
return TypingResultEmm(
# info
cluster_count=info["cluster_count"],
cluster_count=int(info["cluster_count"]),
emmtype=info["emmtype"],
emm_like_alleles=emm_like_alleles,
emm_cluster=info["emm_cluster"],
Expand Down
Loading