From 3e411cc6888cd926f8f2fe6c3c46128d284c5e04 Mon Sep 17 00:00:00 2001
From: "Thomas A. Christensen II" <25492070+MillironX@users.noreply.github.com>
Date: Thu, 19 Oct 2023 11:38:43 -0500
Subject: [PATCH] refactor: Switch to SRA direct download for samples

---
 assets/schema_input.json |  8 ++++----
 main.nf                  | 11 ++++++++---
 2 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/assets/schema_input.json b/assets/schema_input.json
index 80cf68b..fbcd887 100644
--- a/assets/schema_input.json
+++ b/assets/schema_input.json
@@ -12,12 +12,12 @@
         "pattern": "^\\S+$",
         "errorMessage": "Sample name must be provided and cannot contain spaces"
       },
-      "fastq_1": {
+      "sra": {
         "type": "string",
-        "pattern": "^\\S+\\.f(ast)?q\\.gz$",
-        "errorMessage": "FastQ file for reads 1 must be provided, cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
+        "pattern": "^(((SR|ER|DR)[APRSX])|(SAM(N|EA|D))|(PRJ(NA|EB|DB))|(GS[EM])|(syn))(\\d+)$",
+        "errorMessage": "Please provide a valid SRA, ENA, DDBJ or GEO identifier"
       }
     },
-    "required": ["sample", "fastq_1"]
+    "required": ["sample", "sra"]
   }
 }
diff --git a/main.nf b/main.nf
index 17096eb..1510ff6 100755
--- a/main.nf
+++ b/main.nf
@@ -1,9 +1,10 @@
 #!/usr/bin/env nextflow
 
-include { validateParameters } from 'plugin/nf-validation'
+include { validateParameters; fromSamplesheet } from 'plugin/nf-validation'
 
 include { CLIQUESNV } from './modules/cliquesnv'
 include { EFETCH } from './modules/efetch'
+include { FASTERQ_DUMP } from './modules/fasterq_dump'
 include { HAPLINK_HAPLOTYPES as HAPLINK_ML_HAPLOTYPES } from './modules/haplink/haplotypes'
 include { HAPLINK_HAPLOTYPES as HAPLINK_RAW_HAPLOTYPES } from './modules/haplink/haplotypes'
 include { HAPLINK_SEQUENCES } from './modules/haplink/sequences'
@@ -20,8 +21,12 @@ workflow {
     validateParameters()
 
     Channel
-        .fromPath("*.fastq.gz")
-        .map { file -> tuple(file.simpleName, file) }
+        .fromSamplesheet("input")
+        .set { ch_sras }
+
+    FASTERQ_DUMP( ch_sras )
+    FASTERQ_DUMP
+        .out
         .set { ch_input }
 
     EFETCH("${params.reference}")