Merge pull request #2 from fmalmeida/dev

merge dev to master
fmalmeida · Dec 19, 2022 · e1c52c2 · e1c52c2
2 parents 24eb1da + 0e95997
commit e1c52c2
Show file tree

Hide file tree

Showing 17 changed files with 384 additions and 92 deletions.
diff --git a/.gitignore b/.gitignore
@@ -1,2 +1,3 @@
+tests
 test
 docs/_site
diff --git a/docs/quickstart.rst b/docs/quickstart.rst
@@ -13,17 +13,17 @@ To keep things simple and reproducible, let's work with the reference *E. coli*
 
 .. code-block:: bash
 
-   ## download ecoli genome Sakai
-   wget \
-    https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/008/865/GCF_000008865.2_ASM886v2/GCF_000008865.2_ASM886v2_genomic.fna.gz \
-    -O ecoli_sakai.fna.gz && \
-   gzip -d ecoli_sakai.fna.gz
-
-   ## download ecoli genome K12
-   wget \
-    https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/005/845/GCF_000005845.2_ASM584v2/GCF_000005845.2_ASM584v2_genomic.fna.gz \
-    -O ecoli_k12.fna.gz && \
-  gzip -d ecoli_k12.fna.gz
+    ## download ecoli genome Sakai
+    wget \
+      https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/008/865/GCF_000008865.2_ASM886v2/GCF_000008865.2_ASM886v2_genomic.fna.gz \
+      -O ecoli_sakai.fna.gz && \
+    gzip -d ecoli_sakai.fna.gz
+
+    ## download ecoli genome K12
+    wget \
+      https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/005/845/GCF_000005845.2_ASM584v2/GCF_000005845.2_ASM584v2_genomic.fna.gz \
+      -O ecoli_k12.fna.gz && \
+    gzip -d ecoli_k12.fna.gz
 
 Prepare input
 """""""""""""
@@ -36,15 +36,15 @@ We can prepare this csv with:
 
 .. code-block:: bash
 
-   echo "ecoli_k12.fna,K12,purple" > input.fofn
-   echo "ecoli_sakai.fna,SAKAI,lorange" >> input.fofn
+    echo "ecoli_k12.fna,K12,purple" > input.fofn
+    echo "ecoli_sakai.fna,SAKAI,lorange" >> input.fofn
 
 The file must look like this (input.fofn):
 
 .. code-block:: bash
 
-   ecoli_k12.fna,K12,purple
-   ecoli_sakai.fna,SAKAI,lorange
+    ecoli_k12.fna,K12,purple
+    ecoli_sakai.fna,SAKAI,lorange
 
 Create the circos plot
 """"""""""""""""""""""
@@ -58,8 +58,8 @@ With that, we can finally create a minimal circos configuration file and plots h
 
 .. code-block:: bash
 
-   # run easy_circos
-   plot_circos --fofn input.fofn
+    # run easy_circos
+    plot_circos --fofn input.fofn
 
 This will create all the circos configuration files and required data files under the ``results`` folder (Can be changed with ``--outdir``). See the created plot:
 

diff --git a/recipe/bin/GCcalc.py b/recipe/bin/GCcalc.py
diff --git a/recipe/bin/plot_circos b/recipe/bin/plot_circos
@@ -32,6 +32,8 @@ export INTRACHR_FILE="links_concatenated_colored_no_intrachr.txt"
 export INTRACHR_SHOW="no"
 export GCWINDOW=5000
 export GCSTEP=5000
+export BACANNOT="no"
+export SKIP_LINKS="no"
 
 ######################################
 ### Function to filter FASTA files ###
@@ -82,6 +84,7 @@ source ${SCRIPT_DIR}/../src/tiles.sh
 ### Function to create circos.conf file ###
 ###########################################
 source ${SCRIPT_DIR}/../src/write_circos.sh
+source ${SCRIPT_DIR}/../src/write_circos_bacannot.sh
 
 ###############################
 ### Function to plot circos ###
@@ -223,6 +226,14 @@ case $ARGS in
       gff2tiles
       exit
       ;;
+    --bacannot)
+      export BACANNOT="yes"
+      shift
+      ;;
+    --skip_links)
+      export SKIP_LINKS="yes"
+      shift
+      ;;
     *)
       printf "******************************\n"
       printf "Error: Invalid argument $1\n"

diff --git a/recipe/bin/removesmalls.pl b/recipe/bin/removesmalls.pl
diff --git a/recipe/cmd_build.sh b/recipe/cmd_build.sh
@@ -3,4 +3,4 @@ conda build purge-all
 conda clean -afy
 
 # build package
-conda-build --user falmeida . -c conda-forge -c r -c defaults -c bioconda -c falmeida -c anaconda
+conda-build --user falmeida . -c conda-forge -c r -c defaults -c bioconda -c falmeida -c anaconda $@
diff --git a/recipe/meta.yaml b/recipe/meta.yaml
@@ -1,5 +1,5 @@
 {% set name = "easy_circos" %}
-{% set version = "0.2" %}
+{% set version = "0.3" %}
 
 package:
   name: "{{ name|lower }}"

diff --git a/recipe/src/find_links.sh b/recipe/src/find_links.sh
@@ -4,8 +4,8 @@ find_links()
 mkdir -p ${RESULTS}/all_vs_all_blast
 
 # concatenate genomes
-cat ${RESULTS}/filtered/* >> ${RESULTS}/all_vs_all_blast/concatenated_genomes.fasta ;
-export CONCAT_FASTA=${RESULTS}/all_vs_all_blast/concatenated_genomes.fasta
+cat ${RESULTS}/filtered/* >> ${RESULTS}/concatenated_genomes.fasta ;
+export CONCAT_FASTA=${RESULTS}/concatenated_genomes.fasta
 export BLAST_DB=${RESULTS}/all_vs_all_blast/blast_db
 
 # Run blast

diff --git a/recipe/src/gc_skew.sh b/recipe/src/gc_skew.sh
@@ -1,6 +1,6 @@
 gc_skew()
 {
 # exec GCcalc.py
-$CONDA_PREFIX/bin/python3 $CONDA_PREFIX/bin/GCcalc.py -f ${RESULTS}/all_vs_all_blast/concatenated_genomes.fasta -w $GCWINDOW -s $GCSTEP | \
+$CONDA_PREFIX/bin/python3 $CONDA_PREFIX/bin/GCcalc.py -f ${RESULTS}/concatenated_genomes.fasta -w $GCWINDOW -s $GCSTEP | \
     cut -f 1,2,3,5 | awk '{ if ($4 > 0) print $0 "\t" "color=dblue"; else print $0 "\t" "color=red"}' > ${RESULTS}/conf/GC_skew.txt
 }
diff --git a/recipe/src/gff2labels.sh b/recipe/src/gff2labels.sh
@@ -25,5 +25,5 @@ gff2labels()
           }
         } ;
       }
-    }' $GFF
+    }' <( sed 's/ /__/g' $GFF )
 }
diff --git a/recipe/src/gff2tiles.sh b/recipe/src/gff2tiles.sh
@@ -1,6 +1,6 @@
 gff2tiles()
 {
-  # use awk to parse gff and create labels based on user desire
+  # use awk to parse gff and create tiles based on user desire
   echo -e "#chr\tstart\tend\toptions\tcomment"
   awk \
     -v pattern="$PATTERN" \
@@ -18,5 +18,5 @@ gff2tiles()
           print $1,$4,$5,"color="color_val,"# attributes: "s
         } ;
       }
-    }' $GFF
+    }' <( sed 's/ /__/g' $GFF )
 }
diff --git a/recipe/src/help.sh b/recipe/src/help.sh
@@ -5,80 +5,86 @@ cat << EOF
 Simple script to create a circos plot between FASTA files.
 Copyright, Felipe Almeida <[email protected]>, 2021
 
- Syntax:
+    Syntax:
 
-  # To draw circos
-  plot_circos.sh [-h] [--fofn <file> --outdir <outdir> --minlen <int> --minid <int>
-                       --linklen <int> --show_intrachr --gc_window <int> --gc_step <int>
-                       --labels <file> --tiles <files> ]
+    # To draw circos
+    plot_circos.sh [-h] [ options ]
 
-  # To use helpful scripts
-  plot_circos [ --gff2labels <FEATURES> <PATTERN> <ATTRIBUTE> <COLOR> <GFF> ]
-  plot_circos [ --gff2tiles  <FEATURES> <PATTERN> <COLOR> <GFF> ]
+    # To use helpful scripts
+    plot_circos [ --gff2labels <FEATURES> <PATTERN> <ATTRIBUTE> <COLOR> <GFF> ]
+    plot_circos [ --gff2tiles  <FEATURES> <PATTERN> <COLOR> <GFF> ]
 
 
- Options:
+    Options:
 
- # Help
- -h/--help                           Print this help
+    # Help
+    -h/--help                           Print this help
 
- # Threads for blastn
- --threads                           Number of threads to use [Default: 1]
+    # Threads for blastn
+    --threads                           Number of threads to use [Default: 1]
 
- # Output
- --outdir                            Path to output directory [Default: ./results]
+    # Output
+    --outdir                            Path to output directory [Default: ./results]
 
- # Input file of file names
- # CSV: fasta path,prefix,color
- --fofn                              File of file names containing list of fastas to
-                                     draw circos plot.
+    # Input file of file names
+    # CSV: fasta path,prefix,color
+    --fofn                              File of file names containing list of fastas to draw circos plot.
 
- # Input min. length
- --minlen                            Min size of contigs to consider for plot [Default: 10000]
+    # Input min. length
+    --minlen                            Min size of contigs to consider for plot [Default: 10000]
 
- # Links (blastn) min. percentage id
- --minid                             Min. percentage id to filter the results of blastn to draw links [Default: 85]
- --linklen                           Min. link (blastn hit) length to display in plot [Default: 5000]
- --show_intrachr                     Tells the program to create a conf file showing intra chr links [Default: false]
-                                     Mandatory if using only one FASTA, otherwise, links will not be shown.
+    # Links (blastn) min. percentage id
+    --skip_links                        Do not compute blast and do not draw links.
+                                        Useful for when only desiring the configs. [Default: false]
 
- # GC skew config
- --gc_window                         GC skew window size [Default: 5000]
- --gc_step                           GC skew step size [Default: 5000]
+    --minid                             Min. percentage id to filter the results of blastn to draw links [Default: 85]
 
- # Labels config
- --labels                            TSV file containing the label definitions for plotting. The file must contain
-                                     4 or 5 columns as shown at http://circos.ca/documentation/tutorials/2d_tracks/text_1/lesson,
-                                     "DATA FORMAT" section. The first column must be the name (ID) of the contig.
-                                     Checkout the "--gff2labels" script (below).
+    --linklen                           Min. link (blastn hit) length to display in plot [Default: 5000]
+    
+    --show_intrachr                     Tells the program to create a conf file showing intra chr links [Default: false]
+                                        Mandatory if using only one FASTA, otherwise, links will not be shown.
 
- # Tiles config
- --tiles                             TSV file containing the tile definitions for plotting. The file must contain
-                                     3 or 4 columns as shown at http://circos.ca/documentation/tutorials/configuration/data_files.
-                                     The first column must be the name (ID) of the contig.
-                                     Checkout the "--gff2tiles" script (below).
+    # GC skew config
+    --gc_window                         GC skew window size [Default: 5000]
+    
+    --gc_step                           GC skew step size [Default: 5000]
 
+    # Labels config
+    --labels                            TSV file containing the label definitions for plotting. The file must contain
+                                        4 or 5 columns as shown at http://circos.ca/documentation/tutorials/2d_tracks/text_1/lesson,
+                                        "DATA FORMAT" section. The first column must be the name (ID) of the contig.
+                                        Checkout the "--gff2labels" script (below).
 
- # Helpful scripts!
- # See the examples in our quickstart: https://easy-circos.readthedocs.io/en/latest/quickstart.html
- --gff2labels                        A useful script that allows you to filter a GFF file and create a "circos label file"
-                                     with desired inputs. Eg. "plot_circos --gff2labels CDS arcA ID red ecoli_k12.gff". This
-                                     command will get each line where the feature (3rd column) is a CDS and that has the
-                                     "acrA" (in the complete line) pattern to write the "circos labels file" using the ID
-                                     attributes column as label (string as found in the gff), giving these features
-                                     a "red" color option.
+    # Tiles config
+    --tiles                             TSV file containing the tile definitions for plotting. The file must contain
+                                        3 or 4 columns as shown at http://circos.ca/documentation/tutorials/configuration/data_files.
+                                        The first column must be the name (ID) of the contig.
+                                        Checkout the "--gff2tiles" script (below).
 
-                                     For <FEATURES> and <PATTERN> users can use "" to match anything, and "|" to match
-                                     more than one string. E.g. plot_circos --gff2labels "" "acrA|mdt" ID red ecoli_k12.gff
 
- --gff2tiles                         A useful script that allows you to filter a GFF file and create a "circos tiles file"
-                                     with desired inputs. Eg. "plot_circos --gff2tiles CDS arcA red ecoli_k12.gff". This
-                                     command will get each line where the feature (3rd column) is a CDS and that has the
-                                     "acrA" (in the complete line) pattern to write the "circos tiles file" giving these
-                                     features a "red" color option.
+    # Helpful scripts!
+    # See the examples in our quickstart: https://easy-circos.readthedocs.io/en/latest/quickstart.html
+    --gff2labels                        A useful script that allows you to filter a GFF file and create a "circos label file"
+                                        with desired inputs. Eg. "plot_circos --gff2labels CDS arcA ID red ecoli_k12.gff". This
+                                        command will get each line where the feature (3rd column) is a CDS and that has the
+                                        "acrA" (in the complete line) pattern to write the "circos labels file" using the ID
+                                        attributes column as label (string as found in the gff), giving these features
+                                        a "red" color option.
 
-                                     For <FEATURES> and <PATTERN> users can use "" to match anything, and "|" to match
-                                     more than one string. E.g. plot_circos --gff2tiles "" "acrA|mdt" red ecoli_k12.gff.
+                                        For <FEATURES> and <PATTERN> users can use "" to match anything, and "|" to match
+                                        more than one string. E.g. plot_circos --gff2labels "" "acrA|mdt" ID red ecoli_k12.gff
+
+    --gff2tiles                         A useful script that allows you to filter a GFF file and create a "circos tiles file"
+                                        with desired inputs. Eg. "plot_circos --gff2tiles CDS arcA red ecoli_k12.gff". This
+                                        command will get each line where the feature (3rd column) is a CDS and that has the
+                                        "acrA" (in the complete line) pattern to write the "circos tiles file" giving these
+                                        features a "red" color option.
+
+                                        For <FEATURES> and <PATTERN> users can use "" to match anything, and "|" to match
+                                        more than one string. E.g. plot_circos --gff2tiles "" "acrA|mdt" red ecoli_k12.gff.
+    
+    --bacannot                          It also writes the customized configs for bacannot annotations.
+                                        Only useful inside bacannot pipelines.
 
 
 EOF

diff --git a/recipe/src/parse_links.sh b/recipe/src/parse_links.sh
@@ -19,3 +19,13 @@ done<"$FOFN"
 # create additional file whithout intrachr links
 awk -F'\t' '{ if ($1 != $4) { print } }' ${RESULTS}/conf/links_concatenated_colored.txt > ${RESULTS}/conf/links_concatenated_colored_no_intrachr.txt ;
 }
+
+empty_links()
+{
+  # concatenate genomes
+  cat ${RESULTS}/filtered/* >> ${RESULTS}/concatenated_genomes.fasta ;
+  export CONCAT_FASTA=${RESULTS}/concatenated_genomes.fasta
+  export BLAST_DB=${RESULTS}/all_vs_all_blast/blast_db
+
+  touch ${RESULTS}/conf/links_concatenated_colored.txt ${RESULTS}/conf/links_concatenated_colored_no_intrachr.txt 
+}
diff --git a/recipe/src/tiles.sh b/recipe/src/tiles.sh
@@ -11,7 +11,7 @@ read -r -d '' TILES_CONF << EOM
 # to understand its configuration read: http://circos.ca/documentation/tutorials/2d_tracks/tiles/configuration
 <plot>
 type              = tile
-layers_overflow   = grow
+layers_overflow   = collapse
 file              = circos_tiles.txt
 r1                = 0.85r
 r0                = 0.75r

diff --git a/recipe/src/workflow.sh b/recipe/src/workflow.sh
@@ -12,14 +12,27 @@ workflow()
   karyotype       ;
 
   # Step 3
+  if [ "$SKIP_LINKS" = "no" ]
+  then
   echo " # Finding links (all vs all blastn)!"
   find_links      ;
   parse_links     ;
+  else
+  echo " # Skipping links (all vs all blastn)!"
+  empty_links     ;
+  fi
 
   # Step 4
   echo " # Removing duplicate lines in conf files!"
   dedup           ;
+  if [ "$SKIP_LINKS" = "no" ]
+  then
   check_links     ;
+  export DEFAULT_LINE="chromosomes_display_default = no"
+  else
+  export DEFAULT_LINE="chromosomes_display_default = yes"
+  export CUSTOM_CHR_LINE=""
+  fi
 
   # Step 5
   echo " # Computing GC Skew!"
@@ -47,11 +60,19 @@ workflow()
 
   # Step 6
   echo " # Wrinting circos conf file!"
-  write_circos > ${RESULTS}/conf/circos.conf ;
+  if [ "$BACANNOT" == "no" ]
+  then
+  write_circos          > ${RESULTS}/conf/circos.conf ;
+  else
+  write_circos_bacannot > ${RESULTS}/conf/circos.conf ;
+  fi
 
   # Step 7
+  if [ "$BACANNOT" == "no" ]
+  then
   echo " # Plotting circos!"
   plot_circos     ;
+  fi
 
   # Bye
   echo ${BYE}
-Original file line number
+Diff line change
@@ Expand Up / @@ -25,5 +25,5 @@ gff2labels() @@
               }
             } ;
           }
-        }' $GFF
+        }' <( sed 's/ /__/g' $GFF )
     }