From acad9ac7e5eb850361a4797000199641ef29b3e9 Mon Sep 17 00:00:00 2001
From: Olga Botvinnik <olga.botvinnik@gmail.com>
Date: Mon, 24 Jun 2019 17:50:36 -0700
Subject: [PATCH] Try to clean up czb update

---
 conf/czbiohub_aws.config | 123 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 123 insertions(+)
 create mode 100644 conf/czbiohub_aws.config

diff --git a/conf/czbiohub_aws.config b/conf/czbiohub_aws.config
new file mode 100644
index 0000000..5c47c12
--- /dev/null
+++ b/conf/czbiohub_aws.config
@@ -0,0 +1,123 @@
+/*
+ * -------------------------------------------------
+ *  Nextflow config file for Chan Zuckerberg Biohub
+ * -------------------------------------------------
+ * Defines reference genomes, using iGenome paths
+ * Imported under the default 'standard' Nextflow
+ * profile in nextflow.config
+ */
+
+ //Profile config names for nf-core/configs
+ params {
+   config_profile_description = 'Chan Zuckerberg Biohub AWS Batch profile provided by nf-core/configs.'
+   config_profile_contact = 'Olga Botvinnik (@olgabot)'
+   config_profile_url = 'https://www.czbiohub.org/'
+ }
+
+docker {
+  enabled = true
+}
+
+process {
+  executor = 'awsbatch'
+  queue = 'nextflow'
+  errorStrategy = 'ignore'
+}
+
+workDir = "s3://czb-nextflow/intermediates/"
+
+aws.region = 'us-west-2'
+executor.awscli = '/home/ec2-user/miniconda/bin/aws'
+params.tracedir = './'
+
+params {
+  saveReference = true
+
+  // Largest SPOT instances available on AWS: https://ec2instances.info/
+  max_memory = 1952.GB
+  max_cpus = 96
+  max_time = 240.h
+
+  seq_center = "czbiohub"
+
+  // illumina iGenomes reference file paths on CZ Biohub reference s3 bucket
+  // No final slash because it's added later
+  igenomes_base = "s3://czbiohub-reference/igenomes"
+
+  // GENCODE (human + mouse) reference file paths on CZ Biohub reference s3 bucket
+  // No final slash because it's added later
+  gencode_base = "s3://czbiohub-reference/gencode"
+  transgenes_base = "s3://czbiohub-reference/transgenes"
+
+  // AWS configurations
+  awsregion = "us-west-2"
+  awsqueue = "nextflow"
+
+  igenomesIgnore = true
+
+  fc_extra_attributes = 'gene_name'
+  fc_group_features = 'gene_id'
+  fc_group_features_type = 'gene_type'
+
+  // GENCODE GTF and fasta files
+  genomes {
+    'GRCh38' {
+      fasta             = "${params.gencode_base}/human/v30/GRCh38.p12.genome.ERCC92.fa"
+      gtf               = "${params.gencode_base}/human/v30/gencode.v30.annotation.ERCC92.gene_type.gtf"
+      transcript_fasta  = "${params.gencode_base}/human/v30/gencode.v30.transcripts.ERCC92.fa"
+      star              = "${params.gencode_base}/human/v30/STARIndex/"
+    }
+    'GRCm38' {
+      fasta             = "${params.gencode_base}/mouse/vM21/GRCm38.p6.genome.ERCC92.fa"
+      gtf               = "${params.gencode_base}/mouse/vM21/gencode.vM21.annotation.ERCC92.gene_type.gtf"
+      transcript_fasta  = "${params.gencode_base}/mouse/vM21/gencode.vM21.transcripts.ERCC92.fa"
+    }
+  }
+
+  transgenes {
+    'ChR2' {
+      fasta   = "${params.transgenes_base}/ChR2/ChR2.fa"
+      gtf     = "${params.transgenes_base}/ChR2/ChR2.gtf"
+    }
+    'Cre' {
+      fasta   = "${params.transgenes_base}/Cre/Cre.fa"
+      gtf     = "${params.transgenes_base}/Cre/Cre.gtf"
+    }
+    'ERCC' {
+      fasta   = "${params.transgenes_base}/ERCC92/ERCC92.fa"
+      gtf     = "${params.transgenes_base}/ERCC92/ERCC92.gtf"
+    }
+    'GCaMP6m' {
+      fasta   = "${params.transgenes_base}/GCaMP6m/GCaMP6m.fa"
+      gtf     = "${params.transgenes_base}/GCaMP6m/GCaMP6m.gtf"
+    }
+    'GFP' {
+      fasta   = "${params.transgenes_base}/Gfp/Gfp.fa"
+      gtf     = "${params.transgenes_base}/Gfp/Gfp.gtf"
+    }
+    'NpHR' {
+      fasta   = "${params.transgenes_base}/NpHR/NpHR.fa"
+      gtf     = "${params.transgenes_base}/NpHR/NpHR.gtf"
+    }
+    'RCaMP' {
+      fasta   = "${params.transgenes_base}/RCaMP/RCaMP.fa"
+      gtf     = "${params.transgenes_base}/RCaMP/RCaMP.gtf"
+    }
+    'RGECO' {
+      fasta   = "${params.transgenes_base}/RGECO/RGECO.fa"
+      gtf     = "${params.transgenes_base}/RGECO/RGECO.gtf"
+    }
+    'Tdtom' {
+      fasta   = "${params.transgenes_base}/Tdtom/Tdtom.fa"
+      gtf     = "${params.transgenes_base}/Tdtom/Tdtom.gtf"
+    }
+    'Car-T' {
+      fasta   = "${params.transgenes_base}/car-t/car-t.fa"
+      gtf     = "${params.transgenes_base}/car-t/car-t.gtf"
+    }
+    'zsGreen' {
+      fasta   = "${params.transgenes_base}/zsGreen/zsGreen.fa"
+      gtf     = "${params.transgenes_base}/zsGreen/zsGreen.gtf"
+    }
+  }
+}