From 53357faff6d5c52129a2cde37ab30cf99573dd9c Mon Sep 17 00:00:00 2001
From: James Fellows Yates <jfy133@gmail.com>
Date: Mon, 29 Nov 2021 10:39:26 +0100
Subject: [PATCH] Minor QoL updates

---
 CHANGELOG.md                                  |  6 +++++-
 docs/images/usage/eager2_metromap_complex.svg | 14 +++++++-------
 docs/output.md                                |  4 ++--
 main.nf                                       |  4 ++--
 4 files changed, 16 insertions(+), 12 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index ea88da141..595c0132a 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -3,16 +3,20 @@
 The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html).
 
-## [dev]
+## 2.4.1[dev]
 
 ### `Added`
 
 - [#805](https://github.com/nf-core/eager/issues/805) Changes to bam_trim options to allow flexible trimming by library strandedness (in addition to UDG treatment).
 - [#808](https://github.com/nf-core/eager/issues/808) Retain read group information across bam merges. Sample set to sample name (rather than library name) in bwa output 'RG' readgroup tag.
 - Map and base quality filters prior to genotyping with pileupcaller can now be specified.
+- [#774](https://github.com/nf-core/eager/issues/774) Added support for multi-threaded Bowtie2 build reference genome indexing
+- [#804](https://github.com/nf-core/eager/issues/804) Improved output documentation description to add how 'cluster factor' is calculated
 
 ### `Fixed`
 
+- [#803](https://github.com/nf-core/eager/issues/803) Fixed mistake in metro-map diagram (`samtools index` is now correctly `samtools faidx`)
+
 ### `Dependencies`
 
 ### `Deprecated`
diff --git a/docs/images/usage/eager2_metromap_complex.svg b/docs/images/usage/eager2_metromap_complex.svg
index 0dd3c4985..18b2f1e95 100644
--- a/docs/images/usage/eager2_metromap_complex.svg
+++ b/docs/images/usage/eager2_metromap_complex.svg
@@ -5,7 +5,7 @@
    viewBox="0 0 316.84646 170.04657"
    version="1.1"
    id="svg8"
-   inkscape:version="1.1 (1:1.1+202105261517+ce6663b3b7)"
+   inkscape:version="1.1.1 (1:1.1+202109281949+c3084ef5ed)"
    sodipodi:docname="eager2_metromap_complex.svg"
    inkscape:export-filename="/home/jfellows/Documents/git/nf-core/eager/docs/images/usage/eager2_metromap_complex.png"
    inkscape:export-xdpi="300"
@@ -145,9 +145,9 @@
      borderopacity="1.0"
      inkscape:pageopacity="0.0"
      inkscape:pageshadow="2"
-     inkscape:zoom="0.3238356"
-     inkscape:cx="406.07024"
-     inkscape:cy="-143.59138"
+     inkscape:zoom="0.4579727"
+     inkscape:cx="677.98801"
+     inkscape:cy="506.58042"
      inkscape:document-units="mm"
      inkscape:current-layer="layer1"
      inkscape:document-rotation="0"
@@ -155,9 +155,9 @@
      inkscape:snap-bbox="true"
      inkscape:bbox-nodes="true"
      inkscape:window-width="1920"
-     inkscape:window-height="1016"
+     inkscape:window-height="1043"
      inkscape:window-x="0"
-     inkscape:window-y="27"
+     inkscape:window-y="0"
      inkscape:window-maximized="1"
      inkscape:snap-bbox-midpoints="false"
      inkscape:snap-global="true"
@@ -967,7 +967,7 @@
          x="143.71013"
          y="116.57104"
          style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:3.52777px;font-family:'Maven Pro';-inkscape-font-specification:'Maven Pro';text-align:center;text-anchor:middle;stroke-width:0.264583"
-         id="tspan1556">index</tspan></text>
+         id="tspan1556">faidx</tspan></text>
     <circle
        style="fill:#ffffff;fill-rule:evenodd;stroke:#000000;stroke-width:1;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:1"
        id="path12-3-5-93-2"
diff --git a/docs/output.md b/docs/output.md
index 77bbab0e3..8adcea4f2 100644
--- a/docs/output.md
+++ b/docs/output.md
@@ -77,8 +77,8 @@ The possible columns displayed by default are as follows:
 * **Endogenous DNA (%)** This is from the endorS.py tool. It displays a percentage of mapped reads over total reads that went into mapped (i.e. the percentage DNA content of the library that matches the reference). Assuming a perfect ancient sample with no modern contamination, this would be the amount of true ancient DNA in the sample. However this value _most likely_ include contamination and will not entirely be the true 'endogenous' content.
 * **Reads Mapped** This is from Samtools. This is the raw number of preprocessed reads mapped to your reference genome _after_ map quality filtering (note the column name does not distinguish itself from prior-map quality filtering, but the post-filter column is always second)
 * **Endogenous DNA Post (%)** This is from the endorS.py tool. It displays a percentage of mapped reads _after_ BAM filtering (i.e. for mapping quality and/or bam-level length filtering) over total reads that went into mapped (i.e. the percentage DNA content of the library that matches the reference). This column will only be displayed if BAM filtering is turned on and is based on the original mapping for total reads, and mapped reads as calculated from the post-filtering BAM.
-* **ClusterFactor** This is from DeDup. This is a value representing the how many duplicates in the library exist for each unique read. A cluster factor close to one replicates a highly complex library and could be sequenced further. Generally with a value of more than 2 you will not be gaining much more information by sequencing deeper.
-* **Dups** This is from Picard's markDuplicates. It represents the percentage of reads in your library that were exact duplicates of other reads in your database. The lower the better, as high duplication rate means lots of sequencing of the same information (and therefore is not time or cost effective).
+* **ClusterFactor** This is from **DeDup only**. This is a value representing the how many duplicates in the library exist for each unique read. This ratio is calculated as `reads_before_deduplication / reads_after_deduplication`.  A cluster factor close to one indicates a highly complex library and could be sequenced further. Generally with a value of more than 2 you will not be gaining much more information by sequencing deeper.
+* **Dups** This is from **Picard's markDuplicates only**. It represents the percentage of reads in your library that were exact duplicates of other reads in your database. The lower the better, as high duplication rate means lots of sequencing of the same information (and therefore is not time or cost effective).
 * **X Prime Y>Z N base** These columns are from DamageProfiler. The prime numbers represent which end of the reads the damage is referring to. The Y>Z is the type of substitution (C>T is the true damage, G>A is the complementary). You should see for no- and half-UDG treatment a decrease in frequency from the 1st to 2nd base.
 * **Mean Read Length** This is from DamageProfiler. This is the mean length of all de-duplicated mapped reads. Ancient DNA normally will have a mean between 30-75, however this can vary.
 * **Median Read Length** This is from DamageProfiler. This is the median length of all de-duplicated mapped reads. Ancient DNA normally will have a mean between 30-75, however this can vary.
diff --git a/main.nf b/main.nf
index 4ffa0e873..804b44609 100644
--- a/main.nf
+++ b/main.nf
@@ -497,7 +497,7 @@ if( !params.bwa_index && params.fasta && (params.mapper == 'bwaaln' || params.ma
 // bowtie2 Index
 if( !params.bt2_index && params.fasta && params.mapper == "bowtie2"){
   process makeBT2Index {
-    label 'sc_medium'
+    label 'mc_medium'
     tag "${fasta}"
     publishDir path: "${params.outdir}/reference_genome/bt2_index", mode: params.publish_dir_mode, saveAs: { filename -> 
             if (params.save_reference) filename 
@@ -515,7 +515,7 @@ if( !params.bt2_index && params.fasta && params.mapper == "bowtie2"){
 
     script:
     """
-    bowtie2-build $fasta $fasta
+    bowtie2-build --threads ${task.cpus} $fasta $fasta
     mkdir BT2Index && mv ${fasta}* BT2Index
     """
     }