Use pigz whenever available

lib/miga/version.rb

@@ -12,15 +12,15 @@ module MiGA
   # - String indicating release status:
   #   - rc* release candidate, not released as gem
   #   - [0-9]+ stable release, released as gem
-  VERSION = [1.3, 15, 1].freeze
+  VERSION = [1.3, 15, 2].freeze
 
   ##
   # Nickname for the current major.minor version.
   VERSION_NAME = 'mezzotint'
 
   ##
   # Date of the current gem relese.
-  VERSION_DATE = Date.new(2024, 5, 6)
+  VERSION_DATE = Date.new(2024, 5, 21)
 
   ##
   # References of MiGA

manual/part2/requirements/apt-get.md

@@ -4,7 +4,7 @@
 
 If you prefer to see code in action, the full installation process
 with apt-get is available as a
-[Notebook in Google Colab](https://colab.research.google.com/gist/lmrodriguezr/78f2f48eadce96bc2dd526fd194fb00a/miga_1-2_apt_installation.ipynb).
+[Notebook in Google Colab](https://colab.research.google.com/gist/lmrodriguezr/78f2f48eadce96bc2dd526fd194fb00a).
 
 ## Packages
 
@@ -13,7 +13,7 @@ Run:
 ```bash
 sudo apt-get update
 sudo apt-get install \
-  ruby ruby-sqlite3 r-base sqlite3 python3-pip \
+  ruby ruby-sqlite3 r-base sqlite3 python3-pip pigz \
   libcurl4-openssl-dev zlib1g zlib1g-dev \
   ncbi-blast+ hmmer bedtools idba prodigal mcl barrnap \
   diamond-aligner trnascan-se fastp fastani seqtk

manual/part2/requirements/brew.md

@@ -2,7 +2,7 @@
 
 If you prefer to see code in action, the full installation process
 with homebrew is available as a
-[Notebook in Google Colab](https://colab.research.google.com/drive/1d4bRsudagAeYqzgmWRicv18c8Y17XEFM).
+[Notebook in Google Colab](https://colab.research.google.com/gist/lmrodriguezr/5b77ae113e92f2efee5060902eb78a16).
 
 # Installing requirements using Homebrew
 
@@ -36,11 +36,18 @@ Now that you have Homebrew, execute:
 brew tap brewsci/bio
 # In Linux, replace 'temurin' with 'openjdk'
 brew install \
-    r sqlite3 python temurin \
+    r sqlite3 python numpy pigz temurin \
     blast hmmer bedtools prodigal gmp idba mcl krona \
     barrnap diamond fastani faqcs falco seqtk fastp trnascan
 ```
 
+Additionally, recent changes in `pip` might break some installations, and
+as such we recommend pre-installing python packages in a brew environment:
+
+```bash
+pip install --break-system-packages pyhmmer pyrodigal
+```
+
 We also recommend installing the `sqlite3` gem beforehand using the brew
 libraries, to avoid headaches down the road (but this is optional):
 

manual/part2/requirements/conda.md

@@ -9,7 +9,7 @@ If you don't have Conda, you can follow the
 
 If you prefer to see code in action, the full installation process
 with conda is available as a
-[Notebook in Google Colab](https://colab.research.google.com/gist/lmrodriguezr/c973df8d63c1b0d2c6ebddc39f3d92fd/miga_1-2_conda_installation.ipynb).
+[Notebook in Google Colab](https://colab.research.google.com/gist/lmrodriguezr/c973df8d63c1b0d2c6ebddc39f3d92fd).
 
 ## Note for macOS users
 

scripts/cds.bash

@@ -64,7 +64,7 @@ fi
 
 # Gzip
 for ext in gff3 faa fna ; do
-  [[ -e "$DATASET.$ext" ]] && gzip -9 -f "$DATASET.$ext"
+  [[ -e "$DATASET.$ext" ]] && gzip -9f "$DATASET.$ext"
 done
 
 # Finalize

scripts/miga.bash

@@ -15,6 +15,11 @@ function exists { [[ -e "$1" ]] ; }
 # Evaluates if the first passed argument is a function
 function fx_exists { [[ $(type -t "$1") == "function" ]] ; }
 
+# Override gzip with pigz (if available)
+if which -s pigz ; then
+  function gzip { pigz -p ${CORES:-2} "$@" ; }
+fi
+
 # Initiate a project-wide run
 function miga_start_project_step {
   local dir="$1"

scripts/mytaxa.bash

@@ -86,12 +86,10 @@ else
     ktImportText -o "$DATASET.html" -n biota "$DATASET.mytaxa.krona,$DATASET"
 
     # Gzip and cleanup
-    [[ -e "../../../06.cds/$DATASET.gff2" ]] \
-      && gzip -9 -f "../../../06.cds/$DATASET.gff2"
-    [[ -e "../../../06.cds/$DATASET.gff3" ]] \
-      && gzip -9 -f "../../../06.cds/$DATASET.gff3"
-    gzip -9 -f "$DATASET.mytaxain"
-    gzip -9 -f "$DATASET.blast"
+    for i in "../../../06.cds/$DATASET.gff2" "../../../06.cds/$DATASET.gff3" \
+             "$DATASET.mytaxain" "$DATASET.blast" ; do
+      [[ -e $i ]] && gzip -9f $i
+    done
     rm "$DATASET.daa"
   fi
 

scripts/mytaxa_scan.bash

@@ -72,7 +72,7 @@ else
         awk "NR==$win" "$DATASET.wintax.genes" | tr "\\t" "\\n" \
           > "$DATASET.reg/$i.ids"
         if [[ "$FAA" == *.gz ]] ; then
-          gzip -c -d "$FAA" \
+          gzip -cd "$FAA" \
             | FastA.filter.pl -q "$DATASET.reg/$i.ids" /dev/stdin \
             > "$DATASET.reg/$i.faa"
         else
@@ -81,8 +81,7 @@ else
         fi
       done
       # Archive regions
-      tar -cf "$DATASET.reg.tar" "$DATASET.reg"
-      gzip -9 "$DATASET.reg.tar"
+      tar -c "$DATASET.reg" | gzip -9c > "$DATASET.reg.tar.gz"
       rm -r "$DATASET.reg"
     fi
 
@@ -91,7 +90,7 @@ else
       [[ -e "$DATASET.$x" ]] && rm "$DATASET.$x"
     done
     [[ -s "$DATASET.mytaxa" && ! -s "$DATASET.mytaxa.gz" ]] \
-      && gzip -9 -f "$DATASET.mytaxa"
+      && gzip -9f "$DATASET.mytaxa"
   fi
 
 fi

scripts/ssu.bash

@@ -59,7 +59,7 @@ if [[ -s $fa ]] ; then
 
   # Gzip
   for x in gff ssu.all.fa rdp.tsv trna.txt ; do
-    [[ -e "${DATASET}.${x}" ]] && gzip -9 -f "${DATASET}.${x}"
+    [[ -e "${DATASET}.${x}" ]] && gzip -9f "${DATASET}.${x}"
   done
 fi
 

scripts/trimmed_reads.bash

@@ -30,7 +30,8 @@ FastQ.tag.rb -i "$in1" -p "$b-" -s "/1" -o "$b.1.fastq.gz"
 [[ -e "$in2" ]] && FastQ.tag.rb -i "$in2" -p "$b-" -s "/2" -o "$b.2.fastq.gz"
 
 # Multitrim
-CMD="multitrim.py --zip gzip --level 9 --threads $CORES -o $b"
+CMD="multitrim.py --level 9 --threads $CORES -o $b"
+which -s pigz && CMD="$CMD --zip pigz"
 if [[ -s "$b.2.fastq.gz" ]] ; then
   # Paired
   $CMD -1 "$b.1.fastq.gz" -2 "$b.2.fastq.gz"