Merge pull request #281 from caraiz2001/dev-ratio

Coda workflow.
Files that are unique to the coda workflow have been added to the corresponding folders (conf, modules, subworkflows...). Files that are present in the pipeline have been added as ***_coda to avoid overwriting the original ones (modules_coda.config, nextflow_coda.config, main_coda.nf... etc).

assets/schema_tools.json

@@ -0,0 +1,61 @@
+{
+    "$schema": "http://json-schema.org/draft-07/schema",
+    "title": "nf-core/differentialabundance - params.tools schema",
+    "description": "Schema for the file provided with params.tools",
+    "type": "array",
+    "items": {
+        "type": "object",
+        "properties": {
+            "pathway_name": {
+                "type": "string",
+                "meta": ["pathway_name"]
+            },
+            "diff_method": {
+                "type": "string",
+                "errorMessage": "choose propd, DESeq2 or none",
+                "meta": ["diff_method"]
+            },
+            "args_diff": {
+                "type": "string",
+                "meta": ["args_diff"]
+            },
+            "enr_diff_method": {
+                "type": "string",
+                "meta": ["enr_diff_method"],
+                "errorMessage": "choose grea, gsea or none"
+            },
+            "args_enr_diff": {
+                "type": "string",
+                "meta": ["args_enr_diff"]
+            },
+            "cor_method": {
+                "type": "string",
+                "meta": ["cor_method"],
+                "errorMessage": "choose correlation,proportionality, partial correlation or none"
+            },
+            "args_cor": {
+                "type": "string",
+                "meta": ["args_cor"]
+            },
+            "enr_cor_method": {
+                "type": "string",
+                "meta": ["enr_cor_method"],
+                "errorMessage": "choose grea or none"
+            },
+            "args_enr_cor": {
+                "type": "string",
+                "meta": ["args_enr_cor"]
+            },
+            "sel_method": {
+                "type": "string",
+                "meta": ["sel_method"],
+                "errorMessage": "choose filtervar or none"
+            },
+            "args_sel": {
+                "type": "string",
+                "meta": ["args_sel"]
+            }
+        },
+        "required": []
+    }
+}

assets/tools_samplesheet.csv

@@ -0,0 +1,6 @@
+pathway_name,diff_method,args_diff,enr_diff_method,args_enr_diff,cor_method,args_cor,enr_cor_method,args_enr_cor,sel_method,args_sel
+diff_prop,propd, --adjacency true --permutation 100 --fixseed true, , ,,, , ,,
+filtered_pcor,propd, --adjacency true --permutation 100 --fixseed true, , ,propr,  --permutation 10 --adjacency true --cutoff_min 0.005 --cutoff_max 0.5 --cutoff_interval 0.01 --metric pcor.bshrink, , , filtervar,
+prop,, , , ,propr,  --cutoff_min 0.05 --cutoff_max 0.95 --cutoff_interval 0.05 --fixseed true --metric rho --permutation 100 --adjacency true, , , ,
+diff_grea,propd,--group_col fase --adjacency true --permutation 10,grea, --permutation 10, , , , ,,
+deseq2,deseq2,,gsea,,,,,,,

conf/crg.config

@@ -0,0 +1,41 @@
+params {
+    config_profile_name = 'CRG profile'
+    config_profile_description = 'Configuration to run on CRG cluster'
+
+    max_cpus = 64
+    max_memory = 100.GB
+    max_time   = 48.h
+}
+
+
+process {
+    executor = 'crg'
+    //maxRetries = params.max_retries
+    //errorStrategy = params.err_start
+
+    withLabel:process_low {
+        queue = 'cn-el7,short-centos79'
+        cpus   = { check_max( 2                  , 'cpus'    ) }
+        memory = { check_max( 12.GB * task.attempt, 'memory'  ) }
+        time   = { check_max( 4.h  * task.attempt, 'time'    ) }
+    }
+    withLabel:process_medium{
+        queue = 'cn-el7,short-centos79'
+        cpus   = { check_max( 6                  , 'cpus'    ) }
+        memory = { check_max( 36.GB * task.attempt, 'memory'  ) }
+        time   = { check_max( 8.h  * task.attempt, 'time'    ) }
+    }
+    withLabel:process_high {
+        queue = 'cn-el7,long-centos79'
+        cpus   = { check_max( 12                  , 'cpus'    ) }
+        memory = { check_max( 56.GB * task.attempt, 'memory'  ) }
+        time   = { check_max( 12.h  * task.attempt, 'time'    ) }
+
+    }
+}
+
+
+singularity {
+    enabled  = true
+    cacheDir = 'singularity_cache'
+}

conf/modules_coda.config

@@ -0,0 +1,45 @@
+process {
+    withName: "PROPR"{
+        ext.args = { "${meta.args_cor}" == "null" ? '' : "${meta.args_cor}" }
+        publishDir = [
+            path: { "${params.outdir}/correlation_analysis/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+    withName: "PROPD"{
+        ext.args = { "${meta.args_diff}" == "null" ? '' : "${meta.args_diff}" }
+        publishDir = [
+            path: { "${params.outdir}/differential_analysis/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
+    withName: "FILTERVAR"{
+        ext.args = { "${meta.args_cor}" == "null" ? '' : "${meta.args_cor}" }
+        publishDir = [
+            path: { "${params.outdir}/variable_selection/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
+    withName: "GREA_DIFF"{
+        ext.args = { "${meta.args_enr_diff}" == "null" ? '' : "${meta.args_enr_diff}" }
+        publishDir = [
+            path: { "${params.outdir}/enrichment_differential/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
+    withName: "GREA_COR"{
+        ext.args = { "${meta.args_enr_cor}" == "null" ? '' : "${meta.args_enr_cor}" }
+        publishDir = [
+            path: { "${params.outdir}/enrichment_correlation/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+}

main_coda.nf

@@ -0,0 +1,40 @@
+// include { PROPR_PROPR        } from '../../../modules/nf-core/propr/propr/main'
+// include { PROPR_PROPD        } from '../../../modules/nf-core/propr/propd/main'
+// include { PROPR_GREA         } from '../../../modules/nf-core/propr/grea/main'
+// include { MYGENE             } from '../../../modules/nf-core/mygene/main'
+include { EXPERIMENTAL        } from './subworkflows/experimental/main.nf'
+include { fromSamplesheet } from 'plugin/nf-validation'
+
+
+// These are local files from my Bachelor Thesis project, I am creating the ch_samples_and_matrix
+// manually for testing but it should be be provided by the processing section of nf-core/differentialabundance
+Counts_ch = Channel.fromPath("../YMC/counts_sin0.csv")
+
+Sample_ch = Channel.fromPath("../YMC/samplesheet_RCvsOX.csv")
+    .map{ it -> [[id: 'YMC'], it]}
+
+ch_samples_and_matrix = Sample_ch.combine(Counts_ch)
+
+// Convert the samplesheet.csv in a channel with the proper format
+ch_tools = Channel.fromSamplesheet('tools')
+
+
+// TO DO: This should be modified to run one path per default, not all
+if (params.pathway == "all") {
+    ch_tools
+        .set{ ch_tools_single }
+} else {
+    ch_tools
+        .filter{
+            it[0]["pathway_name"] == params.pathway // TO DO: change pathway to path also in the tools_samplesheet file
+        }
+        //.view()
+        .set{ ch_tools_single }
+}
+ch_tools_single.view()
+
+workflow {
+    EXPERIMENTAL(ch_samples_and_matrix, ch_tools_single)
+    EXPERIMENTAL.out.output.view()
+}
+

modules.json

@@ -60,6 +60,26 @@
                         "git_sha": "9326d73af3fbe2ee90d9ce0a737461a727c5118e",
                         "installed_by": ["modules"]
                     },
+                    "mygene": {
+                        "branch": "master",
+                        "git_sha": "82024cf6325d2ee194e7f056d841ecad2f6856e9",
+                        "installed_by": ["modules"]
+                    },
+                    "propr/grea": {
+                        "branch": "master",
+                        "git_sha": "71b1180a5a3de6398eb0eb4d55424cbda36f52d8",
+                        "installed_by": ["modules"]
+                    },
+                    "propr/propd": {
+                        "branch": "master",
+                        "git_sha": "08b360512467e8e7079f995bb7c981a7c204d00f",
+                        "installed_by": ["modules"]
+                    },
+                    "propr/propr": {
+                        "branch": "master",
+                        "git_sha": "132fa6c9bd2515807f6a1cdec1ad7d03c817bcc9",
+                        "installed_by": ["modules"]
+                    },
                     "proteus/readproteingroups": {
                         "branch": "master",
                         "git_sha": "a069b29783583c219c1f23ed3dcf64a5aee1340b",

modules/local/filtervar/main.nf

@@ -0,0 +1,23 @@
+process FILTERVAR {
+    tag "$meta.id"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/r-propr:5.0.3':
+        'quay.io/biocontainers/r-propr:5.0.3' }"
+
+    input:
+    tuple val(meta), path(count), path(adj_matrix)
+
+    output:
+    tuple val(meta), path("*.count_filtered.tsv"),  emit: count
+    path "*.R_sessionInfo.log",                     emit: session_info
+    path "versions.yml",                            emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    template 'filtervar.R'
+}