Merge pull request #9 from moka-guys/v1.4.0_attempt2

V1.4.0 attempt2 (#9)

Author: RachelDuffin

Readme.md

@@ -1,6 +1,5 @@
-# FastQC Reads Quality Control Github release v1.3
+# FastQC Reads Quality Control  v1.4.0
 ## What does this app do?
-
 This app generates a QC report on reads data.
 
 ## What are typical use cases for this app?
@@ -10,26 +9,24 @@ reads to draw biological conclusions, you should always perform some simple qual
 that the raw data looks good and there are no problems or biases in your data which may affect how you can usefully use it."
 
 ## What data are required for this app to run?
-
-This app requires reads data, in any of the following formats:
-
+This can take one or more sets of compatible reads data, in any of the following formats:
 - Gzipped FASTQ files (`*.fq.gz` or `*.fastq.gz`)
 - BAM files (`*.bam`)
 
-## What does this app output?
+It also can take a number of files and settings that are used by fastqc including:
+- Custom contaminants - optional - A file containing custom contaminant sequences to screen overrepresented sequences against. If left empty, a default set of contaminants will be used. 
+- Custom adapters - optional - Custom adapter sequences which will be explicity searched against the library. If left empty, a default set of adapters will be used. 
+- Custom limits - optional - Criteria used to determine the warn/error limits for the various modules, or selectively remove some modules from the output altogether.
+-Input format - default = auto - String describing the format of the input file. By default FastQC will try to automatically detect the format based on the input filename. You can override this by choosing a specific format (fastq, bam, or bam_mapped). 
+- kmer_size - The kmer size that the kmer analysis module will use. This module reports overrepresented k-mers (sequences of size 'k'). This size must be between 2 and 10
+- Disable grouping of bases past 50bp? - default = true -  Disable grouping of bases for reads >50bp. All reports will show data for every base in the read. - extra_options - Extra command-line options that will be passed directly to the fastqc invocation. Example: --nofilter
 
-This app outputs an HTML report that illustrates several metrics. For detailed information about the analysis modules included
-in the report, consult the FastQC manual at:
 
-http://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/
+## What does this app output?
+This app outputs an HTML report and a machine-readable text file for each sample.
+Results are output to a subfolder `QC` 
 
-The QC stats are also output as a machine-readable text file.
 
 ## How does this app work?
+This app runs a dockerised version of fastqc, release [v0.11.9](https://github.com/moka-guys/fastqc/releases/tag/v0.11.9)
 
-This app runs FastQC, which analyzes the read data using various modules. The app returns the QC stats text file, exactly as
-generated by FastQC.
-
-
-## Custom modifications
-Output files are saved to a subfolder 'QC' within any specified output folder

dxapp.json

@@ -1,21 +1,21 @@
 {
-  "name": "fastqc_v1.3",
-  "title": "FastQC Reads Quality Control v1.3",
-  "summary": "v1.3 - Generates a QC report on reads data",
+  "name": "fastqc_v1.4.0",
+  "title": "FastQC Reads Quality Control v1.4.0",
+  "summary": "v1.4.0 - Generates a QC report on reads data",
   "tags": [
     "Read QC",
     "Statistics"
   ],
   "properties": {
-    "github release": "v1.3"
+    "github release": "v1.4.0"
   },
   "dxapi": "1.0.0",
   "inputSpec": [
     {
       "name": "reads",
       "label": "Reads",
-      "help": "A file containing the reads to be checked. Accepted formats are gzipped-FASTQ and BAM.",
-      "class": "file",
+      "help": "one or more files containing the reads to be checked. Accepted formats are gzipped-FASTQ and BAM.",
+      "class": "array:file",
       "patterns": ["*.fq.gz", "*.fastq.gz", "*.sam", "*.bam"]
     },
     {
@@ -86,47 +86,40 @@
       "name": "report_html",
       "label": "FastQC Report",
       "help": "An html file archive containing the report as generated by FastQC.",
-      "class": "file",
+      "class": "array:file",
       "patterns": ["*.stats-fastqc.html"]
     },
     {
       "name": "stats_txt",
       "label": "FastQC Stats",
       "help": "A text file containing the machine-readable statistics as generated by FastQC.",
-      "class": "file",
+      "class": "array:file",
       "patterns": ["*.stats-fastqc.txt"]
     }
   ],
   "runSpec": {
-    "execDepends": [
-      {
-        "name": "openjdk-7-jre-headless"
-      }
-    ],
-    "systemRequirementsByRegion": {
-      "aws:us-east-1": {
-        "main": {
-          "instanceType": "mem1_ssd1_x4"
-        }
-      }
-    },
-    "systemRequirements": {
-      "main": {
-        "instanceType": "mem1_ssd1_x4"
-      }
-    },
+    "execDepends": [],
     "file": "src/code.sh",
-    "release": "14.04",
+    "release": "20.04",
+    "version": "0",
     "interpreter": "bash",
     "distribution": "Ubuntu"
   },
-  "details": {
-    "upstreamUrl": "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/",
-    "upstreamVersion": "0.11.3",
-    "upstreamLicenses": [
-      "GPLv3"
+  "access": {
+    "network": [
+      "*"
     ],
-    "upstreamAuthor": "Simon Andrews",
-    "whatsNew": "* 2.2.0: Updated to FastQC 0.11.3; changed default instance type\n* 2.1.0: Updated to FastQC 0.11.2; changed default values for the 'kmer_size' and 'nogroup' parameters\n* 2.0.1: Fixed error when mid line is null\n* 2.0.0: Changing output spec to TXT and HTML files"
+    "project": "CONTRIBUTE",
+    "allProjects": "VIEW"
+  },
+  "ignoreReuse": false,
+  "regionalOptions": {
+    "aws:us-east-1": {
+      "systemRequirements": {
+        "main": {
+          "instanceType": "mem1_ssd1_v2_x2"
+        }
+      }
+    }
   }
 }