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

separate quality measures from ancillary results #121

Merged
merged 8 commits into from
Oct 31, 2023
Merged

separate quality measures from ancillary results #121

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
af5b573
separate quality measures from ancillary results
ahwagner Oct 20, 2023
315e49f
update CAF JSON
ahwagner Oct 20, 2023
92dfdd6
remove old test suite
ahwagner Oct 21, 2023
ef92912
popMax to grpMax
ahwagner Oct 21, 2023
1db187f
add gnomad quality metrics
ahwagner Oct 26, 2023
4050031
revise supported flags
ahwagner Oct 27, 2023
0ecbf46
update CAF to support joint FAF
ahwagner Oct 27, 2023
eea47fd
restore test and update example
ahwagner Oct 27, 2023
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
5 changes: 3 additions & 2 deletions docs/Modeling/CohortFrequency/simple_result_example.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,11 +31,12 @@ alleleFrequency: 0.004783
cohort:
id: ALL
ancillaryResults:
popMaxFAF95: # Popmax Filtering AF (95% confidence)
grpMaxFAF95: # Popmax Filtering AF (95% confidence)
frequency: 0.01548
confidenceInterval: 0.95
popFreqId: 1-55051215-G-GA.AFR
groupId: 1-55051215-G-GA.AFR
homozygotes: 9 # Number of Homozygotes
qualityMeasures:
meanDepth: 32.8 # Mean depth of coverage
subcohortFrequency:
- id: 1-55051215-G-GA.AFR
Expand Down
2 changes: 1 addition & 1 deletion schema/Makefile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
.SUFFIXES:
.DELETE_ON_ERROR:

JSYAMLS:=annotation.yaml varstatement.yaml
JSYAMLS:=annotation.yaml varstatement.yaml cohortAlleleFreq.yaml
JSONS:=${JSYAMLS:.yaml=.json}

all: ${JSONS} defs
Expand Down
91 changes: 69 additions & 22 deletions schema/cohortAlleleFreq.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,6 +3,29 @@
"title": "Cohort Allele Frequency",
"type": "object",
"definitions": {
"GrpMaxFAF95": {
"type": "object",
"properties": {
"frequency": {
"type": "number"
},
"confidenceInterval": {
"type": "number",
"const": 0.95,
"default": 0.95
},
"groupId": {
"type": "string",
"description": "The genetic ancestry group from which the max frequency was calculated."
}
},
"required": [
"frequency",
"confidenceInterval",
"groupId"
],
"additionalProperties": false
},
"Allele": {
"description": "The state of a molecule at a Location.",
"type": "object",
Expand Down Expand Up @@ -318,36 +341,60 @@
"ancillaryResults": {
"type": "object",
"properties": {
"popMaxFAF95": {
"type": "object",
"properties": {
"frequency": {
"type": "number"
},
"confidenceInterval": {
"type": "number",
"const": 0.95,
"default": 0.95
},
"popFreqId": {
"type": "string"
}
},
"required": [
"frequency",
"confidenceInterval",
"popFreqId"
],
"additionalProperties": false
"grpMaxFAF95": {
"$ref": "#/definitions/GrpMaxFAF95"
},
"jointGrpMaxFAF95": {
"description": "The Group Max Filtering Allele Frequency (95% confidence interval) calculated jointly from genome and exome data.",
"$ref": "#/definitions/GrpMaxFAF95"
},
"homozygotes": {
"type": "integer"
},
"hemizygotes": {
"type": "integer"
}
},
"additionalProperties": false
},
"qualityMeasures": {
"type": "object",
"properties": {
"meanDepth": {
"type": "number"
},
"qcFilters": {
"type": "array",
"items": {
"type": "string"
}
},
"monoallelic": {
"description": "All samples are homozygous alternate for the variant.",
"type": "boolean"
},
"lowComplexityRegion": {
"description": "This flag indicates the variant is found in a low complexity region. These regions were identified with the symmetric DUST algorithm at a score threshold of 30.",
"type": "boolean"
},
"lowConfidenceLossOfFunctionError": {
"description": "Low confidence in predicted Loss of Function (pLoF), where variant is determined by LOFTEE to be unlikely loss of function for a transcript.",
"type": "boolean"
},
"lossOfFunctionWarning": {
"description": "A warning provided by LOFTEE to use caution when interpreting the transcript or variant.",
"type": "boolean"
},
"noncodingTranscriptError": {
"description": "Marked in a putative loss of function category by VEP (essential splice, stop-gained, or frameshift) but appears on a non-protein-coding transcript.",
"type": "boolean"
},
"heterozygousSkewedAlleleCount": {
"description": "The count of individuals called as heterozygous for this variant with a skewed allele balance, indicating some of these individuals may be miscalled homozygous alternative allele.",
"type": "integer"
}
},
"additonalProperties": false
"additionalProperties": false
},
"subcohortFrequency": {
"type": "array",
Expand Down
67 changes: 53 additions & 14 deletions schema/cohortAlleleFreq.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,21 @@ $schema: http://json-schema.org/draft-07/schema
title: Cohort Allele Frequency
type: object
definitions:
GrpMaxFAF95:
type: object
properties:
frequency:
type: number
confidenceInterval:
type: number
const: 0.95
default: 0.95
groupId:
type: string
description: >-
The genetic ancestry group from which the max frequency was calculated.
required: [ frequency, confidenceInterval, groupId ]
additionalProperties: false
Allele:
description: The state of a molecule at a Location.
type: object
Expand Down Expand Up @@ -239,30 +254,54 @@ properties:
ancillaryResults:
type: object
properties:
popMaxFAF95:
type: object
properties:
frequency:
type: number
confidenceInterval:
type: number
const: 0.95
default: 0.95
popFreqId:
type: string
required: [frequency, confidenceInterval, popFreqId]
additionalProperties: false
grpMaxFAF95:
$ref: '#/definitions/GrpMaxFAF95'
jointGrpMaxFAF95:
description: >-
The Group Max Filtering Allele Frequency (95% confidence interval) calculated jointly
from genome and exome data.
$ref: '#/definitions/GrpMaxFAF95'
homozygotes:
type: integer
hemizygotes:
type: integer
additionalProperties: false
qualityMeasures:
theferrit32 marked this conversation as resolved.
Show resolved Hide resolved
type: object
properties:
meanDepth:
type: number
qcFilters:
type: array
items:
type: string
monoallelic:
description: >-
All samples are homozygous alternate for the variant.
type: boolean
lowComplexityRegion:
description: >-
This flag indicates the variant is found in a low complexity region. These regions were identified
with the symmetric DUST algorithm at a score threshold of 30.
type: boolean
lowConfidenceLossOfFunctionError:
description: >-
Low confidence in predicted Loss of Function (pLoF), where variant is determined by LOFTEE
to be unlikely loss of function for a transcript.
type: boolean
lossOfFunctionWarning:
description: >-
A warning provided by LOFTEE to use caution when interpreting the transcript or variant.
type: boolean
noncodingTranscriptError:
description: >-
Marked in a putative loss of function category by VEP (essential splice, stop-gained, or frameshift)
but appears on a non-protein-coding transcript.
type: boolean
heterozygousAlleleBalanceFlagged:
heterozygousSkewedAlleleCount:
description: >-
The count of individuals called as heterozygous for this variant with a skewed allele balance,
indicating some of these individuals may be miscalled homozygous alternative allele.
type: integer
additionalProperties: false
subcohortFrequency:
Expand Down
Loading