added CLGs for #27

.gitignore

@@ -23,4 +23,5 @@ __pycache__
 *.check
 *.hmm
 *.rbh
-LG_db/*/
+LG_db/*/
+._*

Makefile

@@ -2,18 +2,24 @@ all: BCnS_ALG UnicellLG UnicellLGOrthofinder
 
 BCnS_ALG: LG_db/BCnS_LGs.tar.gz
 	cd LG_db; \
-	tar -xzvf BCnS_LGs.tar.gz; \
+	tar --skip-old-files -xzvf BCnS_LGs.tar.gz; \
 	cd BCnS_LGs; \
-	snakemake --cores 1
+	snakemake
 
 UnicellLG: LG_db/UnicellMetazoanLgs.tar.gz
 	cd LG_db; \
-	tar -xzvf UnicellMetazoanLgs.tar.gz; \
+	tar --skip-old-files -xzvf UnicellMetazoanLgs.tar.gz; \
 	cd UnicellMetazoanLgs; \
-	snakemake --cores 1 
+	snakemake
 
 UnicellLGOrthofinder: LG_db/UnicellMetazoanLgsOrthofinder.tar.gz
 	cd LG_db; \
-	tar -xzvf UnicellMetazoanLgsOrthofinder.tar.gz; \
+	tar --skip-old-files -xzvf UnicellMetazoanLgsOrthofinder.tar.gz; \
 	cd UnicellMetazoanLgsOrthofinder; \
-	snakemake --cores 1
+	snakemake
+
+CLG_v1.0: LG_db/CLG_v1.0.tar.gz
+	cd LG_db; \
+	tar --skip-old-files -xzvf CLG_v1.0.tar.gz; \
+	cd CLG_v1.0; \
+	snakemake

Makefile_1core

@@ -0,0 +1,26 @@
+CORES=	1	
+all: BCnS_ALG UnicellLG UnicellLGOrthofinder
+
+BCnS_ALG: LG_db/BCnS_LGs.tar.gz
+	cd LG_db; \
+	tar --skip-old-files -xzvf BCnS_LGs.tar.gz; \
+	cd BCnS_LGs; \
+	snakemake --cores $(CORES)
+
+UnicellLG: LG_db/UnicellMetazoanLgs.tar.gz
+	cd LG_db; \
+	tar --skip-old-files -xzvf UnicellMetazoanLgs.tar.gz; \
+	cd UnicellMetazoanLgs; \
+	snakemake --cores $(CORES)
+
+UnicellLGOrthofinder: LG_db/UnicellMetazoanLgsOrthofinder.tar.gz
+	cd LG_db; \
+	tar --skip-old-files -xzvf UnicellMetazoanLgsOrthofinder.tar.gz; \
+	cd UnicellMetazoanLgsOrthofinder; \
+	snakemake --cores $(CORES)
+
+CLG_v1.0: LG_db/CLG_v1.0.tar.gz
+	cd LG_db; \
+	tar --skip-old-files -xzvf CLG_v1.0.tar.gz; \
+	cd CLG_v1.0; \
+	snakemake --cores $(CORES)

docs/CHANGELOG.md

@@ -1,4 +1,6 @@
 # In this document we will log changes to include with release notes.
 - v0.3.1 - Published on ?? (Pending)
   - Removed redundant files from the package (specifically the genome_rearrangement_simulation2 and 3 files.)
+  - Added the Simakov et al 2020 CLGs to the software.
+  - Added another makefile that has a variable number of cores.
 - v0.3.0 - Published on Feb 25th, 2023

docs/README.md

@@ -10,6 +10,10 @@
 ```sh
 #install
 git clone https://github.com/conchoecia/odp.git
+# NOTE: The make step will automatically use all of the cores on
+#       your current machine. If using a slurm cluster be sure to
+#       request all of the threads on that node. If you need to use
+#       fewer cores, run `make -f Makefile_1core` instead.
 cd odp && make
 # make a config.yaml file for your odp analysis
 cp odp/example_configs/CONFIG_odp.yaml ./config.yaml
@@ -33,6 +37,7 @@ snakemake -r -p --snakefile odp/scripts/odp
     - [Help generating `.chrom` files](#chromhelp)
   - [Use cases](#cases)
     - [Make macrosynteny plots between two or more genomes](#macrosynuse)
+    - [If you want to analyze chordate linkage groups](#CLGs)
     - [Find and characterize ancestral linkage groups](#ALGanalysis)
       - [ALGs part 1 - Ortholog finding in 3+ species](#nwayreciprocalbest)
       - [ALGs part 2 - Find significantly numerous groups of orthologs](#groupby)
@@ -242,6 +247,17 @@ Run the pipeline with the command `snakemake -r -p --snakefile odp/scripts/odp`.
     - `synteny_nocolor`
       - Two-species synteny plots appear here regardless of what is in `LG_db`.
 
+### <a name="CLGs"></a> If you want to analyze chordate linkage groups
+
+The preinstalled ALGs are the Bilaterian-Cnidarian-Sponge Linkage Groups (BCnS
+LGs) that are discussed in [Simakov et al.(2022)](https://www.science.org/doi/full/10.1126/sciadv.abi5884). If you want to
+analyze your genomes in the context of the Chordate Linkage Groups (CLGs), then
+please compile them first by running this command. Be warned that this will take
+a long time as there are 25 thousand gene groups for which HMMs must be built.
+By default this command will use all of the threads available on the machine you
+are using: `make CLGs_v1.0`. To use only one core, run `make -f Makefile_1core
+CLGs_v1.0`.
+
 ### <a name="ALGanalysis"></a>Find and characterize ancestral linkage groups
 
 Finding ancestral linkage groups of proteins for a group of species is a useful