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

feat: extract additional WGS metrics #907

Merged
merged 9 commits into from
Apr 11, 2022
Merged

feat: extract additional WGS metrics #907

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
77d1552
updated extracted QC metrics for WGS
ivadym Apr 7, 2022
86f298c
changelog
ivadym Apr 7, 2022
b471dd7
add validator
ivadym Apr 7, 2022
45ae6a6
percent depulication per reads
ivadym Apr 8, 2022
358ed1b
add validation return
ivadym Apr 8, 2022
fa69e1f
typo
ivadym Apr 8, 2022
916a8a0
remove print
ivadym Apr 8, 2022
3806914
remove pct_5x
ivadym Apr 11, 2022
a19323a
changelog
ivadym Apr 11, 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
15 changes: 10 additions & 5 deletions BALSAMIC/assets/scripts/collect_qc_metrics.py
100644 → 100755
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,6 +49,7 @@ def collect_qc_metrics(

def capture_kit_resolve_type(capture_kit: str):
"""Resolves the capture_kit type (NoneType or String)"""

if capture_kit == "None":
return None
else:
Expand All @@ -67,9 +68,12 @@ def get_multiqc_data_source(multiqc_data: dict, sample: str, tool: str) -> str:
A source file that was used to produce a specific metric
"""

# Use case: splits multiqc_picard_dups into ['multiqc', 'picard', 'dup'] in order to retrieve the
# ["report_data_sources"]["Picard"]["DuplicationMetrics"] values from multiqc_data.json
subtool_name = tool[:-1].split("_")
if tool == "multiqc_general_stats":
subtool_name = ["multiqc", "FastQC", "all_sections"]
else:
# Use case: splits multiqc_picard_dups into ['multiqc', 'picard', 'dup'] in order to retrieve the
# ["report_data_sources"]["Picard"]["DuplicationMetrics"] values from multiqc_data.json
subtool_name = tool[:-1].split("_")

# Nested json fetching
for source_tool in multiqc_data["report_data_sources"]:
Expand Down Expand Up @@ -139,15 +143,16 @@ def extract(data, output_metrics, sample=None, source=None):

if isinstance(data, dict):
for k in data:
if "umi" not in k:
# Ignore UMI and reverse reads metrics
if "umi" not in k and "R_2" not in str(sample):
if k in requested_metrics:
output_metrics.append(
MetricModel(
id=sample.split("_")[1],
input=get_multiqc_data_source(
multiqc_data, sample, source
),
name=k,
name=k if "FastQC" not in k else "PERCENT_DUPLICATION",
step=source,
value=data[k],
condition=requested_metrics[k]["condition"],
Expand Down
12 changes: 11 additions & 1 deletion BALSAMIC/constants/quality_check_reporting.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -90,5 +90,15 @@
"FOLD_80_BASE_PENALTY": {"condition": {"norm": "lt", "threshold": 1.8}},
},
},
"wgs": {"FOLD_80_BASE_PENALTY": {"condition": {"norm": "lt", "threshold": 1.8}}},
"wgs": {
"MEAN_INSERT_SIZE": {"condition": None},
"MEDIAN_COVERAGE": {"condition": None},
"FastQC_mqc-generalstats-fastqc-percent_duplicates": {"condition": None},
"PCT_5X": {"condition": None},
keyvanelhami marked this conversation as resolved.
Show resolved Hide resolved
"PCT_15X": {"condition": None},
"PCT_30X": {"condition": None},
"PCT_60X": {"condition": None},
"PCT_100X": {"condition": None},
"FOLD_80_BASE_PENALTY": {"condition": {"norm": "lt", "threshold": 1.8}},
ivadym marked this conversation as resolved.
Show resolved Hide resolved
},
}
26 changes: 26 additions & 0 deletions tests/test_data/qc_files/analysis/qc/multiqc_data/multiqc_data.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,14 @@
"DuplicationMetrics": {
"concatenated_tumor_XXXXXX_R": "tests/test_data/qc_files/analysis/bam/concatenated_tumor_XXXXXX_R.sorted.mrkdup.txt"
}
},
"FastQC": {
"all_sections": {
"concatenated_tumor_XXXXXX_R_2": "tests/test_data/qc_files/analysis/fastqc/concatenated_tumor_XXXXXX_R_2_fastqc.zip",
"concatenated_normal_XXXXXX_R_1": "tests/test_data/qc_files/analysis/fastqc/concatenated_normal_XXXXXX_R_1_fastqc.zip",
"concatenated_normal_XXXXXX_R_2": "tests/test_data/qc_files/analysis/fastqc/concatenated_normal_XXXXXX_R_2_fastqc.zip",
"concatenated_tumor_XXXXXX_R_1": "tests/test_data/qc_files/analysis/fastqc/concatenated_tumor_XXXXXX_R_1_fastqc.zip"
}
}
},
"report_saved_raw_data": {
Expand Down Expand Up @@ -76,6 +84,24 @@
"READ_PAIR_DUPLICATES": 18741892.0,
"PERCENT_DUPLICATION": 0.391429
}
},
"multiqc_general_stats": {
"concatenated_tumor_XXXXXX_R_2": {
"FastQC_mqc-generalstats-fastqc-percent_duplicates": 15.03521942842923,
"FastQC_mqc-generalstats-fastqc-total_sequences": 600529762.0
},
"concatenated_normal_XXXXXX_R_1": {
"FastQC_mqc-generalstats-fastqc-percent_duplicates": 14.426654287440797,
"FastQC_mqc-generalstats-fastqc-total_sequences": 464581551.0
},
"concatenated_normal_XXXXXX_R_2": {
"FastQC_mqc-generalstats-fastqc-percent_duplicates": 14.214689357571501,
"FastQC_mqc-generalstats-fastqc-total_sequences": 464581551.0
},
"concatenated_tumor_XXXXXX_R_1": {
"FastQC_mqc-generalstats-fastqc-percent_duplicates": 15.213739762327492,
"FastQC_mqc-generalstats-fastqc-total_sequences": 600529762.0
}
}
}
}