| - **Pre-processing**: Phasing, QC, variant filtering, variant annotation of the reference panel 
| The preprocessing mode is responsible to the preparation of the multiple input file that will be used by the phasing process. 
| The phasing mode is the core mode of this pipeline. 
| The simulation mode is used to create artificial low informative genetic information from high density data. This allow to compare the imputed result to a *truth* and therefore evaluate the quality of the imputation. 
| This mode compare two vcf together to compute a summary of the differences between them. 
| This final process unable to loop the whole pipeline for increasing the performance of the imputation. To do so it filter out the best imputed position and rerun the analysis using this positions. |
+
## Pipeline output
To see the results of an example test run with a full size dataset refer to the [results](https://nf-co.re/phaseimpute/results) tab on the nf-core website pipeline page.
@@ -90,8 +107,10 @@ We thank the following people for their extensive assistance in the development
If you would like to contribute to this pipeline, please see the [contributing guidelines](.github/CONTRIBUTING.md).
+For further information or help, don't hesitate to get in touch on the [Slack `#phaseimpute` channel](https://nfcore.slack.com/channels/phaseimpute) (you can join with [this invite](https://nf-co.re/join/slack)).
For further information or help, don't hesitate to get in touch on the [Slack `#phaseimpute` channel](https://nfcore.slack.com/channels/phaseimpute) (you can join with [this invite](https://nf-co.re/join/slack)).
+## Citations
## Citations
diff --git a/assets/chr_rename.txt b/assets/chr_rename.txt
new file mode 100644
index 00000000..a85016b6
--- /dev/null
+++ b/assets/chr_rename.txt
@@ -0,0 +1,39 @@
+chr1 1
+chr2 2
+chr3 3
+chr4 4
+chr5 5
+chr6 6
+chr7 7
+chr8 8
+chr9 9
+chr10 10
+chr11 11
+chr12 12
+chr13 13
+chr14 14
+chr15 15
+chr16 16
+chr17 17
+chr18 18
+chr19 19
+chr20 20
+chr21 21
+chr22 22
+chr23 23
+chr24 24
+chr25 25
+chr26 26
+chr27 27
+chr28 28
+chr29 29
+chr30 30
+chr31 31
+chr32 32
+chr33 33
+chr34 34
+chr35 35
+chr36 36
+chr37 37
+chr38 38
+chr39 X
diff --git a/assets/regionsheet.csv b/assets/regionsheet.csv
new file mode 100644
index 00000000..030c9ba1
--- /dev/null
+++ b/assets/regionsheet.csv
@@ -0,0 +1,2 @@
+chr,start,end
+20,20000000,2200000
diff --git a/assets/samplesheet.csv b/assets/samplesheet.csv
index 5f653ab7..441a688f 100644
--- a/assets/samplesheet.csv
+++ b/assets/samplesheet.csv
@@ -1,3 +1,3 @@
-sample,fastq_1,fastq_2
-SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A1_S1_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A1_S1_L002_R2_001.fastq.gz
-SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz,
+sample,BAM,BAI
+1_BAM_1X,/path/to/.bam,/path/to/.bai
+1_BAM_SNP,/path/to/.bam,/path/to/.bai
diff --git a/assets/schema_input.json b/assets/schema_input.json
index 6a7e788c..ce442280 100644
--- a/assets/schema_input.json
+++ b/assets/schema_input.json
@@ -1,7 +1,7 @@
{
"$schema": "http://json-schema.org/draft-07/schema",
"$id": "https://raw.githubusercontent.com/nf-core/phaseimpute/master/assets/schema_input.json",
- "title": "nf-core/phaseimpute pipeline - params.input schema",
+ "title": "nf-core/phaseimpute pipeline - params.input",
"description": "Schema for the file provided with params.input",
"type": "array",
"items": {
@@ -13,21 +13,17 @@
"errorMessage": "Sample name must be provided and cannot contain spaces",
"meta": ["id"]
},
- "fastq_1": {
+ "BAM": {
"type": "string",
- "format": "file-path",
- "exists": true,
- "pattern": "^\\S+\\.f(ast)?q\\.gz$",
- "errorMessage": "FastQ file for reads 1 must be provided, cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
+ "pattern": "^\\S+\\.bam$",
+ "errorMessage": "BAM file must be provided, cannot contain spaces and must have extension '.bam'"
},
- "fastq_2": {
+ "BAI": {
+ "errorMessage": "BAI file must be provided, cannot contain spaces and must have extension '.bai'",
"type": "string",
- "format": "file-path",
- "exists": true,
- "pattern": "^\\S+\\.f(ast)?q\\.gz$",
- "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
+ "pattern": "^\\S+\\.bai$"
}
},
- "required": ["sample", "fastq_1"]
+ "required": ["sample", "BAM", "BAI"]
}
}
diff --git a/assets/schema_input_region.json b/assets/schema_input_region.json
new file mode 100644
index 00000000..6c871b1a
--- /dev/null
+++ b/assets/schema_input_region.json
@@ -0,0 +1,35 @@
+{
+ "$schema": "http://json-schema.org/draft-07/schema",
+ "$id": "https://raw.githubusercontent.com/nf-core/phaseimpute/master/assets/schema_input.json",
+ "title": "nf-core/phaseimpute pipeline - params.input_region schema",
+ "description": "Schema for the file provided with params.input_region",
+ "type": "array",
+ "items": {
+ "type": "object",
+ "properties": {
+ "chr": {
+ "anyOf": [
+ {
+ "type": "string",
+ "pattern": "^\\S+$"
+ },
+ {
+ "type": "integer",
+ "pattern": "^\\d+$"
+ }
+ ]
+ },
+ "start": {
+ "type": "integer",
+ "pattern": "^\\d+$",
+ "errorMessage": "Region start name must be provided, cannot contain spaces and must be numeric"
+ },
+ "end": {
+ "type": "integer",
+ "pattern": "^\\d+$",
+ "errorMessage": "Region end name must be provided, cannot contain spaces and must be numeric"
+ }
+ },
+ "required": ["chr", "start", "end"]
+ }
+}
diff --git a/conf/modules.config b/conf/modules.config
index e3ea8fa6..f30dbfa6 100644
--- a/conf/modules.config
+++ b/conf/modules.config
@@ -18,10 +18,6 @@ process {
saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
]
- withName: FASTQC {
- ext.args = '--quiet'
- }
-
withName: CUSTOM_DUMPSOFTWAREVERSIONS {
publishDir = [
path: { "${params.outdir}/pipeline_info" },
@@ -39,4 +35,116 @@ process {
]
}
+ // Simulate workflow
+ withName: VIEW_REGION {
+ ext.args = [
+ ].join(' ')
+ ext.prefix = { "${meta.id}_R${meta.region}" }
+ }
+ withName: VIEW_DEPTH {
+ ext.args = [
+ ].join(' ')
+ ext.prefix = { "${meta.id}_D${meta.depth}" }
+ }
+
+ // Panel preparation workflow
+ withName: VIEW_VCF_REGION {
+ ext.args = [
+ "-Oz",
+ "--no-version"
+ ].join(' ')
+ ext.prefix = { "${meta.id}_${meta.region}" }
+ }
+
+ withName: BCFTOOLS_ANNOTATE {
+ ext.args = [
+ "-Oz",
+ "--no-version"
+ ].join(' ')
+ ext.prefix = { "${meta.id}_chrDel_${meta.region}" }
+ }
+
+ withName: VIEW_VCF_SNPS {
+ ext.args = [
+ "-m 2",
+ "-M 2",
+ "-v snps",
+ "--no-version"
+ ].join(' ')
+ ext.prefix = { "${meta.id}_SPNS" }
+ }
+ withName: BCFTOOLS_NORM{
+ ext.args = [
+ "-m",
+ "-any",
+ "--no-version"
+ ].join(' ')
+ ext.prefix = { "${meta.id}_norm" }
+ }
+ withName: VIEW_VCF_SITES {
+ ext.args = [
+ "-G",
+ "-m 2",
+ "-M 2",
+ "-v snps",
+ "--no-version"
+ ].join(' ')
+ ext.prefix = { "${meta.id}_SITES" }
+ }
+ withName: BCFTOOLS_QUERY {
+ ext.args = [
+ "-f'%CHROM\t%POS\t%REF,%ALT\n'",
+ ].join(' ')
+ ext.prefix = { "${meta.id}_SITES_TSV" }
+ }
+ withName: TABIX_TABIX {
+ ext.args = [
+ "-s1",
+ "-b2",
+ "-e2"
+ ].join(' ')
+ ext.prefix = { "${meta.id}_SITES_TSV" }
+ }
+ withName: BEDTOOLS_MAKEWINDOWS {
+ ext.args = [
+ '-w 60000',
+ '-s 40000'
+ ].join(' ')
+ ext.prefix = { "${meta.id}_chunks" }
+ }
+ withName: BCFTOOLS_MPILEUP {
+ ext.args = [
+ "-I",
+ "-E",
+ "-a 'FORMAT/DP'"
+ ].join(' ')
+ ext.args2 = [
+ "-Aim",
+ "-C alleles"
+ ].join(' ')
+ }
+
+ withName: GLIMPSE_PHASE {
+ ext.args = [
+ "--impute-reference-only-variants"
+ ].join(' ')
+ ext.prefix = { "${meta.id}" }
+ ext.suffix = "bcf"
+ }
+ withName: GLIMPSE_CHUNK {
+ ext.args = [
+ "--window-size 200000",
+ "--buffer-size 20000"
+ ].join(' ')
+ ext.prefix = { "${meta.id}" }
+ }
+ withName: GLIMPSE_LIGATE {
+ ext.prefix = { "${meta.id}_D${meta.depth}_P${meta.panel}" }
+ }
+ withName: GLIMPSE_CONCORDANCE {
+ ext.prefix = { "${meta.id}_D${meta.depth}_P${meta.panel}_R${meta.region}" }
+ }
+ withName: ADD_COLUMNS {
+ ext.prefix = { "${meta.id}_D${meta.depth}_P${meta.panel}_R${meta.region}_SNP" }
+ }
}
diff --git a/conf/test_full.config b/conf/test_full.config
index 90d800db..cb2a0fae 100644
--- a/conf/test_full.config
+++ b/conf/test_full.config
@@ -17,8 +17,21 @@ params {
// Input data for full size test
// TODO nf-core: Specify the paths to your full test data ( on nf-core/test-datasets or directly in repositories, e.g. SRA)
// TODO nf-core: Give any required params for the test so that command line flags are not needed
- input = 'https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_full_illumina_amplicon.csv'
// Genome references
- genome = 'R64-1-1'
+ map = "/groups/dog/llenezet/test-datasets/data/genetic_maps.b38/chr21.b38.gmap.gz"
+ genome = "GRCh38"
+ fasta = "/groups/dog/llenezet/script/phaseimpute/data/genome.fa"
+
+ // Resources increase incompatible with Github Action
+ max_cpus = 12
+ max_memory = '50.GB'
+ max_time = '6.h'
+
+ // Input data
+ input = "tests/csv/sample_sim.csv"
+ panel = "tests/csv/panel.csv"
+ input_region_string = "all"
+ outdir = "results/test_full"
+ step = "simulate"
}
diff --git a/conf/test_panelprep.config b/conf/test_panelprep.config
new file mode 100644
index 00000000..32a78c5a
--- /dev/null
+++ b/conf/test_panelprep.config
@@ -0,0 +1,33 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ Nextflow config file for running minimal tests
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ Defines input files and everything required to run a fast and simple pipeline test.
+
+ Use as follows:
+ nextflow run nf-core/phaseimpute -profile test_panelprep,$group
\n" + summary_section += "| Process Name | +Software | +Version | +
|---|---|---|
| {process if (i == 0) else ''} | +{tool} | +{version} | +