Merge pull request #34 from uclahs-cds/cz-update-docker-nonroot

Fixed the issue that docker was running as root

Author: Chenghao Zhu

README.md

@@ -115,7 +115,7 @@ After marking dup BAM files, the BAM files are then indexed by utilizing Picard
 | `temp_dir` | yes | path | Absolute path to the directory where the nextflow's intermediate files are saved. |
 | `save_intermediate_files` | yes | boolean | Save intermediate files. If yes, not only the final BAM, but also the unmerged, unsorted, and duplicates unmarked BAM files will also be saved. |
 | `cache_intermediate_pipeline_steps` | yes | boolean | Enable cahcing to resume pipeline and the end of the last successful process completion when a pipeline fails (if true the default submission script must be modified). |
-| `max_number_of_parallel_jobs` | yes | int | The maximum number of jobs or steps of the pipeline that can be ran in parallel. |
+| `max_number_of_parallel_jobs` | no | int | The maximum number of jobs or steps of the pipeline that can be ran in parallel. Default is 1. Be very cautious setting this to any value larger than 1, as it may cause out-of-memory error. It may be helpful when running on a big memory computing node. |
 | `bwa_mem_number_of_cpus` | no | int | Number of cores to use for BWA-MEM2. If not set, this will be calculated to ensure at least 2.5Gb memory per core. |
 | `blcds_registered_dataset_input` | yes | boolean | Input FASTQs are from the Boutros Lab data registry. |
 | `blcds_registered_dataset_output` | yes | boolean | Enable saving final files including BAM and BAM index, and logging files directory to the Boutros Lab Data registry. |

pipeline/config/align-DNA.config

@@ -19,9 +19,6 @@ params {
     save_intermediate_files = false
     cache_intermediate_pipeline_steps = false
 
-    // resource configuraton for entire pipeline
-    max_number_of_parallel_jobs = 1
-
     // uncomment to manually set ncpus for bwa-mem2
     // bwa_mem_number_of_cpus = 60
 

pipeline/config/methods.config

@@ -4,15 +4,21 @@ manifest {
     name = "align-DNA"
     author = "Benjamin Carlin"
     description = "alignment pipeline for paired fastqs DNA samples"
-    version = "6.0.1"
+    version = "6.0.2"
 }
 
 params {
+    // resource configuraton for entire pipeline
+    max_number_of_parallel_jobs = 1
+
+    // tools and their versions
     bwa_version = "bwa-mem2-2.1"
 }
 
 docker {
     enabled = true
+    sudo = false
+    runOptions = "-u \$(id -u):\$(id -g)"
 }
 
 methods {
@@ -32,14 +38,15 @@ methods {
             def pattern = ~/^(?<baseDir>(?<mntDir>\/\w+)\/data\/(?<diseaseId>\w+)\/(?<datasetId>\w+)\/(?<patientId>\w+)\/(?<sampleId>[A-Za-z0-9-]+)\/(?<analyte>.+)\/(?<technology>.+))\/raw\/FASTQ\/.+$/
 
             // First check if all input fastq files are from the same sample_id
-            base_dirs = fastqs.each {
+            // TODO: figure out why .each {} does not work any more.
+            def base_dirs = []
+            fastqs.each {
                 def matcher = it =~ pattern
                 if (!matcher.matches()) {
                     throw new Exception("The input path ${it} isn't a valid blcds-registered path.")
                 }
-                return matcher.group("baseDir")
+                base_dirs.push(matcher.group("baseDir"))
             }
-            .unique(false)
 
             if (base_dirs.size() > 1) {
                 throw new Exception(