Added fastq_trim_fastp_fastqc

README.md

@@ -73,7 +73,6 @@ Prepare an `assemblysheet.csv` file with following columns representing target a
 - `fasta:` FASTA file
 - `gff3 [Optional]:` GFF3 annotation file if available
 - `monoploid_ids [Optional]:` A txt file listing the IDs used to calculate LAI in monoploid mode if necessary
-- `hic_reads [Optional]:` A SRA id such as 'SRR8238190' or path to paired reads such as 'PG_PETUNIA_HiC_CGYCF_CACTCA_L001_R{1,2}.fastq.gz'
 - `synteny_labels [Optional]:` A two column tsv file listing fasta sequence ids (first column) and labels for the synteny plots (second column) when performing synteny analysis
 
 Now, you can run the pipeline using:

assets/assemblysheet.csv

@@ -1,2 +1,2 @@
-tag,fasta,gff3,monoploid_ids,hic_reads,synteny_labels
-FI1,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/003/814/445/GCA_003814445.1_ASM381444v1/GCA_003814445.1_ASM381444v1_genomic.fna.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/003/814/445/GCA_003814445.1_ASM381444v1/GCA_003814445.1_ASM381444v1_genomic.gff.gz,,,
+tag,fasta,gff3,monoploid_ids,synteny_labels
+FI1,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/003/814/445/GCA_003814445.1_ASM381444v1/GCA_003814445.1_ASM381444v1_genomic.fna.gz,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/003/814/445/GCA_003814445.1_ASM381444v1/GCA_003814445.1_ASM381444v1_genomic.gff.gz,,

assets/schema_input.json

@@ -35,23 +35,6 @@
                     }
                 ]
             },
-            "hic_reads": {
-                "errorMessage": "HiC reads should either be provided as a SRA ID or as a path to paired reads with pattern '*R{1,2}.(fastq|fq).gz'",
-                "anyOf": [
-                    {
-                        "type": "string",
-                        "pattern": "^SR\\w+$"
-                    },
-                    {
-                        "type": "string",
-                        "pattern": "^\\S+R\\{1,2\\}\\.f(ast)?q\\.gz$"
-                    },
-                    {
-                        "type": "string",
-                        "maxLength": 0
-                    }
-                ]
-            },
             "synteny_labels": {
                 "errorMessage": "Synteny labels tsv path cannot contain spaces and must have extension '.tsv'",
                 "anyOf": [

modules.json

@@ -90,6 +90,16 @@
                         "git_sha": "89ff95427f695086369d7927a3c17cea2a37a382",
                         "installed_by": ["modules"]
                     },
+                    "fastp": {
+                        "branch": "master",
+                        "git_sha": "003920c7f9a8ae19b69a97171922880220bedf56",
+                        "installed_by": ["fastq_trim_fastp_fastqc"]
+                    },
+                    "fastqc": {
+                        "branch": "master",
+                        "git_sha": "f4ae1d942bd50c5c0b9bd2de1393ce38315ba57c",
+                        "installed_by": ["fastq_trim_fastp_fastqc"]
+                    },
                     "gunzip": {
                         "branch": "master",
                         "git_sha": "3a5fef109d113b4997c9822198664ca5f2716208",
@@ -133,6 +143,11 @@
                         "branch": "master",
                         "git_sha": "2b21fbeb20ad9f17612f4a3dd7b12971513f08d5",
                         "installed_by": ["subworkflows"]
+                    },
+                    "fastq_trim_fastp_fastqc": {
+                        "branch": "master",
+                        "git_sha": "cfd937a668919d948f6fcbf4218e79de50c2f36f",
+                        "installed_by": ["subworkflows"]
                     }
                 }
             }