Release version 1.1.0 (#12)

* Create dev branch

* Add rule and sample info to slurm log files

* Fix SnpSift_dbnsfp log writing

* Fix SnpSift_dbsnp log writing

* Fix bcftools_view_multiallelicsites log writing

* Fix SnpSift_filter_proband log writing

* Add pipeline tests (#7)

* Add test dataset

* Add info on test dataset

* Automate setting up to run test dataset

* Docs (#8)

* minor changes to runscripts

* update docs to state of human_genomics_pipeline docs

* woops

* probably an overstatement for this pipeline

* forgot to update

* add description of pipeline steps

* add more info

* update

* Functionize code (#9)

* remove unnecessary code

* put code into functions to avoid global variables

* forgot to add some stuff to README

* snakemake doesn't allow functions for outputs - fix

* update rulegraphs

* fix typo

* improve config (#10)

* remove need for user to write flag stuff in config

* forgot to remove hardcoding again woops

* Speedups (#11)

* use parabricks for filtering in cohort analyses

* update rulegraphs

* pbrun vqsr can't take files named g.vcf

* update readme with parabricks + add equivalent commands

* improve readme

* improve readme

* improve docs and fixes

* add link to discusions

* fix spaces

* rename test files to work with updated pipeline

* backwards compatability with older human_genomics_pipeline runs

Author: leahkemp

README.md

@@ -1,7 +1,8 @@
-{
-    "__default__" :
-    {
-        "account" : "",
-        "partition" : ""
-    }
+{
+    "__default__" :
+    {
+        "account" : "",
+        "partition" : "",
+        "output" : "logs/slurm-%j_{rule}_{wildcards.sample}.out"
+    }
 }

config/cluster.json

@@ -35,32 +35,77 @@ WES:
 ##############################
 
 # Number of threads to use per rule/sample for multithreaded rules, multithreading will significantly speed up these rules (diminishing speed gains beyond 8 threads)
-THREADS:
+THREADS: 
 
 # Maximum memory usage per rule/sample (eg. '40g' for 40 gigabytes, this should suffice for exomes)
 MAXMEMORY: ""
 
 # Maximum number of GPU's to be used per rule/sample for gpu-accelerated runs (eg `1` for 1 GPU)
-GPU:
+GPU: 
 
 ##############################
 ###### Variant filtering #####
 ##############################
 
-# Resources used to filter indels and SNP's...
-FILTERING:
-  # ...for analysis of single samples
-  SINGLE: ""
-
-  # ...for analysis of cohorts
-  COHORT:
-    INDELS: ""
-    SNPS: ""
-
-  # Tranche filtering level/truth sensitivity
-  TRANCHE: 
-    SNPS: ""
-    INDELS: ""
+# Tranche filtering level/truth sensitivity
+TRANCHE:
+  SNPS: ""
+  INDELS: ""
+
+###############################################
+###### Variant filtering - SINGLE SAMPLES #####
+###############################################
+
+# Filtering for single sample analyses
+# If NOT analysing single sample data, leave this section blank
+# (see more about these settings for gatk FilterVariantTranches at https://gatk.broadinstitute.org/hc/en-us/articles/360042479092-FilterVariantTranches)
+
+SINGLE:
+
+  # Provide a list of resources
+  RESOURCES:
+    - 
+    - 
+
+################################################
+###### Variant filtering - COHORT ANALYSIS #####
+################################################
+
+# Filtering for cohort analyses
+# If NOT analysing cohorts, leave this section blank
+# (see more about these settings for gatk VariantRecalibrator at https://gatk.broadinstitute.org/hc/en-us/articles/360042914791-VariantRecalibrator)
+
+COHORT:
+
+  # For indels...
+  INDELS:
+
+    # ...provide a list of resources
+    RESOURCES:
+      - 
+      - 
+      - 
+
+    # ...provide associated machine learning parameters
+    PARAMS:
+      - 
+      - 
+      - 
+
+  # For SNP's...
+  SNPS:
+
+    # ...provide a list of resources
+    RESOURCES:
+    - 
+    - 
+    - 
+
+    # ...provide associated machine learning parameters
+    PARAMS:
+    - 
+    - 
+    - 
 
 ##############################
 ####### VCF annotation #######