Merge pull request #167 from TobyBaril/v5.1.0

Updates for Earl Grey 5.1.0

README.md

@@ -191,13 +191,13 @@ If you would like to try Earl Grey, or prefer to use it in a browser, you can do
 
 NOTE: This pipeline is currently running with Dfam 3.7 curated elements only. We are working on updating to Dfam 3.8 for a future release. If required, you can modify the conda installation of RepeatMasker within the conda environment (do at your own risk!)
 
-Earl Grey version 5.0.3 (latest stable release) with all required and configured dependencies is found in the `toby_baril_bio` and `biooconda` conda channels. To install, simply run the following depending on your installation:
+Earl Grey version 5.1.0 (latest stable release) with all required and configured dependencies is found in the `toby_baril_bio` and `biooconda` conda channels. To install, simply run the following depending on your installation:
 ```
 # With conda
-conda create -n earlgrey -c conda-forge -c bioconda earlgrey=5.0.3
+conda create -n earlgrey -c conda-forge -c bioconda earlgrey=5.1.0
 
 # With mamba
-mamba create -n earlgrey -c conda-forge -c bioconda earlgrey=5.0.3
+mamba create -n earlgrey -c conda-forge -c bioconda earlgrey=5.1.0
 ```
 
 # Recommended Installation with Conda or Mamba on ARM-based Mac Systems (M chips)
@@ -371,7 +371,7 @@ brewIntel install coreutils
 
 Change TEstrainer_for_earlGrey.sh for the macOS version:
 ```
-nano $(which earlGrey | gsed 's|bin.*|share/earlgrey-5.0.3-0/scripts/TEstrainer/TEstrainer_for_earlGrey.sh|g')
+nano $(which earlGrey | gsed 's|bin.*|share/earlgrey-5.1.0-0/scripts/TEstrainer/TEstrainer_for_earlGrey.sh|g')
 
 # delete everything in this file.
 ```
@@ -582,12 +582,12 @@ Save the file with `CTRL+X` then press `Y` when asked to overwrite the file.
 
 Make sure the updated file is executable:
 ```
-chmod a+x $(which earlGrey | gsed 's|bin.*|share/earlgrey-5.0.3-0/scripts/TEstrainer/TEstrainer_for_earlGrey.sh|g')
+chmod a+x $(which earlGrey | gsed 's|bin.*|share/earlgrey-5.1.0-0/scripts/TEstrainer/TEstrainer_for_earlGrey.sh|g')
 ```
 
 Edit the script directory path in this file by running the following:
 ```
-gsed -i "s|INSERT_FILENAME_HERE|$(which earlGrey | gsed 's:bin.*:share/earlgrey-5.0.3-0/scripts/TEstrainer/scripts/:g')|g" $(which earlGrey | gsed 's|bin.*|share/earlgrey-5.0.3-0/scripts/TEstrainer/TEstrainer_for_earlGrey.sh|g')
+gsed -i "s|INSERT_FILENAME_HERE|$(which earlGrey | gsed 's:bin.*:share/earlgrey-5.1.0-0/scripts/TEstrainer/scripts/:g')|g" $(which earlGrey | gsed 's|bin.*|share/earlgrey-5.1.0-0/scripts/TEstrainer/TEstrainer_for_earlGrey.sh|g')
 ```
 
 Edit famdb.py for use with our environment:
@@ -597,12 +597,12 @@ gsed -i 's/python3/python/g' $(which earlGrey | gsed 's|bin.*|share/RepeatMasker
 
 Edit LTR_FINDER_PARALLEL to be compatible with zsh
 ```
-gsed -i "s|\`timeout $timeout|\`gtimeout $timeout|g" $(which earlGrey | gsed 's|bin.*|share/earlgrey-5.0.3-0/scripts/LTR_FINDER_parallel|g')
+gsed -i "s|\`timeout $timeout|\`gtimeout $timeout|g" $(which earlGrey | gsed 's|bin.*|share/earlgrey-5.1.0-0/scripts/LTR_FINDER_parallel|g')
 ```
 
 Install LTR_Finder from source
 ```
-cd $(which earlGrey | gsed 's|bin.*|share/earlgrey-5.0.3-0/scripts/bin|g')
+cd $(which earlGrey | gsed 's|bin.*|share/earlgrey-5.1.0-0/scripts/bin|g')
 git clone https://github.com/xzhub/LTR_Finder
 cd ./LTR_Finder/source
 make
@@ -611,14 +611,14 @@ cp * ../../LTR_FINDER.x86_64-1.0.7/
 
 Edit rcMergeRepeatsLoose:
 ```
-gsed -i 's|sed|gsed|g' $(which earlGrey | gsed 's|bin.*|share/earlgrey-5.0.3-0/scripts/rcMergeRepeatsLoose|g')
+gsed -i 's|sed|gsed|g' $(which earlGrey | gsed 's|bin.*|share/earlgrey-5.1.0-0/scripts/rcMergeRepeatsLoose|g')
 var=$(which earlGrey | gsed "s/earlGrey/Rscript/g")
-gsed -i "s|Rscript|${var}|g" $(which earlGrey | gsed 's|bin.*|share/earlgrey-5.0.3-0/scripts/rcMergeRepeatsLoose|g')
+gsed -i "s|Rscript|${var}|g" $(which earlGrey | gsed 's|bin.*|share/earlgrey-5.1.0-0/scripts/rcMergeRepeatsLoose|g')
 ```
 
 Edit main earlGrey script:
 ```
-gsed -i "s|Rscript|${var}|g" $(which earlGrey | gsed 's|bin.*|share/earlgrey-5.0.3-0/earlGrey|g')
+gsed -i "s|Rscript|${var}|g" $(which earlGrey | gsed 's|bin.*|share/earlgrey-5.1.0-0/earlGrey|g')
 ```
 
 Add an important directory to PERL5LIB (for RepeatMasker)
@@ -635,7 +635,7 @@ You are ready to go! Just remember to activate the _intel_ terminal, then the co
 In this case, we need to bind a system directory to the docker container. In the line below, we are binding a directory call `host_data` that is found on our current path to `/data/` in the docker container. Please replace the file path before `:` to the directory you wish to bind to `/data/` in the container. This container must be run in interactive mode the first time you use it.
 
 ```
-docker run -it -v `pwd`/host_data/:/data/ quay.io/biocontainers/earlgrey:5.0.3--h4ac6f70_0
+docker run -it -v `pwd`/host_data/:/data/ quay.io/biocontainers/earlgrey:5.1.0--h4ac6f70_0
 ```
 
 ## If you are running the container for the first time, you need to enable Earl Grey to configure the Dfam libraries correctly in interactive mode.
@@ -647,7 +647,7 @@ earlGrey -g /data/genome.fasta -s test_genome -t 8 -o /data/
 ```
 
 ## If you need the container to run offline and/or without interactive mode
-I try to keep an up-to-date container in docker hub, but this might not always be the case depending on if I have had time to build and upload a new image. Currently, there is an image with Dfam 3.7 curated elements only, and this is version 5.0.3. You can use this image by pulling the container:
+I try to keep an up-to-date container in docker hub, but this might not always be the case depending on if I have had time to build and upload a new image. Currently, there is an image with Dfam 3.7 curated elements only, and this is version 5.1.0. You can use this image by pulling the container:
 
 ```
 # Interactive mode

earlGrey

@@ -3,7 +3,7 @@
 usage()
 {
 	echo "	#############################
-	earlGrey version 5.0.3
+	earlGrey version 5.1.0
 	Required Parameters:
 		-g == genome.fasta
 		-s == species name

earlGreyAnnotationOnly

@@ -3,7 +3,7 @@
 usage()
 {
 	echo "	#############################
-	earlGrey version 5.0.3 (AnnotationOnly)
+	earlGrey version 5.1.0 (AnnotationOnly)
 	Required Parameters:
 		-g == genome.fasta
 		-s == species name

earlGreyLibConstruct

@@ -3,7 +3,7 @@
 usage()
 {
         echo "  #############################
-        earlGrey version 5.0.3 (Library Construction Only)
+        earlGrey version 5.1.0 (Library Construction Only)
         Required Parameters:
                 -g == genome.fasta
                 -s == species name

scripts/divergenceCalc/divergence_calc.py

@@ -28,7 +28,7 @@
 parser.add_argument('-t', '--cores', type=int, default=4,
                     help='Number of cores')
 parser.add_argument('-k', '--timeout', type=int, default=30,
-                    help='Seconds after which water will be cancelled and repeat treated as unalignable')
+                    help='Seconds after which matcher will be cancelled and repeat treated as unalignable')
 
 args = parser.parse_args()
 
@@ -131,27 +131,27 @@ def outer_func(genome_path, temp_dir, timeoutSeconds, gff):
             if exists(query_path) is True and getsize(query_path) > 0:
                 # Set path to subject sequence
                 subject_path=temp_dir+"/split_library/"+repeat_family+".fasta"
-                # Run water, with timeout exception
-                test_command = shlex.split("water "+query_path+" "+subject_path+" -gapopen 10 -gapextend 0.5 -outfile "+query_path+".water -aformat fasta")
+                # Run matcher, with timeout exception
+                test_command = shlex.split("matcher "+query_path+" "+subject_path+" -outfile "+query_path+".matcher -aformat fasta")
                 # Run test and kill if it takes more than 10 seconds
                 alignment_p = subprocess.Popen(test_command, stdout=subprocess.DEVNULL, stderr=subprocess.STDOUT)
                 try:
                     alignment_p.wait(timeoutSeconds)
                 except subprocess.TimeoutExpired:
-                    # if water fails to complete before timeout, kill and move on
+                    # if matcher fails to complete before timeout, kill and move on
                     with open(failed_file_name, "a") as failed_file:
                         failed_file.write(seqnames+":"+start+"-"+end+"_"+strand+"_"+repeat_family+"\n")
                     alignment_p.kill()
 
-            if exists(query_path+".water") is False or getsize(query_path+".water") == 0:
+            if exists(query_path+".matcher") is False or getsize(query_path+".matcher") == 0:
                 # If no alignment is possible, set distances to NA and alignment length to 0
                 Kdist = "NA"
                 os.remove(query_path)
-                if exists(query_path+".water") is True:
-                    os.remove(query_path+".water")
+                if exists(query_path+".matcher") is True:
+                    os.remove(query_path+".matcher")
             else:
                 # Read in alignments
-                aln = list(SeqIO.parse(query_path+".water", 'fasta'))
+                aln = list(SeqIO.parse(query_path+".matcher", 'fasta'))
                 ref_seq, gen_seq = str(aln[0].seq).upper(), str(aln[1].seq).upper()
                 # Check ref and genome sequence are same length, set Kdist to NA if not
                 if len(ref_seq) == len(gen_seq):
@@ -163,7 +163,7 @@ def outer_func(genome_path, temp_dir, timeoutSeconds, gff):
                 else:
                     Kdist = "NA"
                 # Delete temporary files
-                os.remove(query_path+".water")
+                os.remove(query_path+".matcher")
                 os.remove(query_path)
             # Make line for temporary file and write to file
             tmp_holder = row[1].to_list()[1:]