Merge branch 'dev' of https://github.com/fmalmeida/MpGAP into add-hif…

…iasm-assembler
fmalmeida · Feb 27, 2024 · ed0719c · ed0719c
2 parents 142b4ac + d27c7d6
commit ed0719c
Show file tree

Hide file tree

Showing 270 changed files with 1,790,689 additions and 8,742 deletions.
diff --git a/conf/singularity.config b/conf/singularity.config
@@ -4,7 +4,7 @@ docker.enabled          = false
 singularity.enabled     = true
 singularity.autoMounts  = true
 process {
-    withName:  '.*' {
-        container = "fmalmeida/mpgap@sha256:28223374b5500b09ae467064d825b44d086c99f1ade6afa80dbf8fd0053d760e"
+    withName: '.*' {
+        container = "docker://fmalmeida/mpgap@sha256:28223374b5500b09ae467064d825b44d086c99f1ade6afa80dbf8fd0053d760e"
     }
 }
diff --git a/docs/assets/defaults.config b/docs/assets/defaults.config
@@ -83,6 +83,15 @@ params {
 // Sometimes the pipeline may crash because to much variation was found exceeding the limit
   nanopolish_max_haplotypes = 1000
 
+// BUSCO dataset. The pipeline runs BUSCO after assemblies and the user can select on of the
+// available BUSCO datasets listed in their website: https://busco.ezlab.org/busco_userguide.html#running-busco
+//
+// If blank, bacteria_odb10 will be used
+//
+// If unsure you can set the param to 'auto' which will tell BUSCO to automatically select the most
+// appropriate one (it takes a little bit more of time and space).
+  busco_lineage = null
+
 
             /*
              * Advanced parameters
@@ -103,10 +112,10 @@ params {
                                               // If you don't need this comparison and don't want to polish the raw assembly,
                                               // use this parameter.
 
-  skip_spades    = false                      // Hybrid and shortreads only assemblies
+  skip_spades = false                         // Hybrid and shortreads only assemblies
   spades_additional_parameters = null         // Must be given as shown in Spades manual. E.g. " --meta --plasmids "
 
-  skip_shovill   = false                      // Paired shortreads only assemblies
+  skip_shovill = false                        // Paired shortreads only assemblies
   shovill_additional_parameters = null        // Must be given as shown in Shovill manual. E.g. " --depth 15 "
                                               // The pipeline already executes shovill with spades, skesa and megahit, so please, do not use it with shovill's ``--assembler`` parameter.
 
@@ -116,24 +125,27 @@ params {
   skip_megahit = false                        // Shortreads only assemblies
   megahit_additional_parameters = null        // Must be given as shown in Megahit manual. E.g. " --presets meta-large "
 
-  skip_haslr     = false                      // Hybrid assemblies
+  skip_haslr = false                          // Hybrid assemblies
   haslr_additional_parameters = null          // Must be given as shown in Haslr manual. E.g. " --cov-lr 30 "
 
-  skip_canu      = false                      // Longreads only assemblies
+  skip_canu = false                           // Longreads only assemblies
   canu_additional_parameters = null           // Must be given as shown in Canu manual. E.g. " correctedErrorRate=0.075 corOutCoverage=200 "
 
-  skip_flye      = false                      // Longreads only assemblies
+  skip_flye = false                           // Longreads only assemblies
   flye_additional_parameters = null           // Must be given as shown in Flye manual. E.g. " --meta --iterations 4 "
 
-  skip_raven     = false                      // Longreads only assemblies
+  skip_raven = false                          // Longreads only assemblies
   raven_additional_parameters = null          // Must be given as shown in Raven manual. E.g. " --polishing-rounds 4 "
 
-  skip_wtdbg2    = false                      // Longreads only assemblies
+  skip_wtdbg2 = false                         // Longreads only assemblies
   wtdbg2_additional_parameters = null         // Must be given as shown in wtdbg2 manual. E.g. " --tidy-reads 5000 "
 
-  skip_shasta    = false                      // Nanopore longreads only assemblies
+  skip_shasta = false                         // Nanopore longreads only assemblies
   shasta_additional_parameters = null         // Must be given as shown in shasta manual. E.g. " --Reads.minReadLength 5000 "
 
+  skip_pilon = false                          // Skip pilon polisher when performing hybrid assembly strategy 2
+  skip_polypolish = false                     // Skip polypolisher polisher when performing hybrid assembly strategy 2
+
 
             /*
              * Resources controlling parameters

diff --git a/docs/assets/flye_medaka/basic_stats/GC_content_plot.pdf b/docs/assets/flye_medaka/basic_stats/GC_content_plot.pdf
diff --git a/docs/assets/flye_medaka/basic_stats/Nx_plot.pdf b/docs/assets/flye_medaka/basic_stats/Nx_plot.pdf
diff --git a/docs/assets/flye_medaka/basic_stats/cumulative_plot.pdf b/docs/assets/flye_medaka/basic_stats/cumulative_plot.pdf
diff --git a/docs/assets/flye_medaka/basic_stats/flye_medaka_consensus_GC_content_plot.pdf b/docs/assets/flye_medaka/basic_stats/flye_medaka_consensus_GC_content_plot.pdf
diff --git a/docs/assets/flye_medaka/busco_stats/run_flye_medaka/logs/bbtools_err.log b/docs/assets/flye_medaka/busco_stats/run_flye_medaka/logs/bbtools_err.log
diff --git a/docs/assets/flye_medaka/busco_stats/run_flye_medaka/logs/bbtools_out.log b/docs/assets/flye_medaka/busco_stats/run_flye_medaka/logs/bbtools_out.log
@@ -0,0 +1,35 @@
+A	C	G	T	N	IUPAC	Other	GC	GC_stdev
+0.2522	0.2477	0.2473	0.2528	0.0000	0.0000	0.0000	0.4950	0.0892
+
+Main genome scaffold total:         	84
+Main genome contig total:           	84
+Main genome scaffold sequence total:	29332743
+Main genome contig sequence total:  	29332743  	0.000% gap
+Main genome scaffold N/L50:         	6/2285407
+Main genome contig N/L50:           	6/2285407
+Main genome scaffold N/L90:         	16/666409
+Main genome contig N/L90:           	16/666409
+Max scaffold length:                	3009410
+Max contig length:                  	3009410
+Number of scaffolds > 50 KB:        	23
+% main genome in scaffolds > 50 KB: 	97.65%
+
+
+Minimum 	Number        	Number        	Total         	Total         	Scaffold
+Scaffold	of            	of            	Scaffold      	Contig        	Contig  
+Length  	Scaffolds     	Contigs       	Length        	Length        	Coverage
+--------	--------------	--------------	--------------	--------------	--------
+    All 	            84	            84	      29332743	      29332743	 100.00%
+    500 	            84	            84	      29332743	      29332743	 100.00%
+   1000 	            77	            77	      29327738	      29327738	 100.00%
+   2500 	            61	            61	      29301361	      29301361	 100.00%
+   5000 	            54	            54	      29274410	      29274410	 100.00%
+  10000 	            44	            44	      29200110	      29200110	 100.00%
+  25000 	            34	            34	      29029000	      29029000	 100.00%
+  50000 	            23	            23	      28643628	      28643628	 100.00%
+ 100000 	            23	            23	      28643628	      28643628	 100.00%
+ 250000 	            20	            20	      28213368	      28213368	 100.00%
+ 500000 	            17	            17	      27062076	      27062076	 100.00%
+1000000 	            12	            12	      23363975	      23363975	 100.00%
+2500000 	             3	             3	       8216853	       8216853	 100.00%
+