v1.7.2

yjx1217 · Mar 20, 2023 · a33c4e2 · a33c4e2
1 parent 8b90d42
commit a33c4e2
Show file tree

Hide file tree

Showing 14 changed files with 28 additions and 15 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -5,6 +5,11 @@ All notable changes to this project will be documented in this file.
 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).
 
+## [1.7.2] - 2023-03-20
+### Changed
+- Better support for historical PacBio RSII reads.
+- Cleaner TE output in the final annotation GFF3 file.
+
 ## [1.7.1] - 2023-01-28
 ### Fixed
 - A bug leading to the loss of detailed TE subtype info in the final annotation GFF3 file.

diff --git a/Example_Outputs/CPG_1a.nuclear_genome.tidy.cds.fa.gz b/Example_Outputs/CPG_1a.nuclear_genome.tidy.cds.fa.gz
diff --git a/Example_Outputs/CPG_1a.nuclear_genome.tidy.fa.gz b/Example_Outputs/CPG_1a.nuclear_genome.tidy.fa.gz
diff --git a/Example_Outputs/CPG_1a.nuclear_genome.tidy.gff3.gz b/Example_Outputs/CPG_1a.nuclear_genome.tidy.gff3.gz
diff --git a/Example_Outputs/CPG_1a.nuclear_genome.tidy.pep.fa.gz b/Example_Outputs/CPG_1a.nuclear_genome.tidy.pep.fa.gz
diff --git a/Manual_20230128.docx → Manual_20230320.docx b/Manual_20230128.docx → Manual_20230320.docx
diff --git a/Project_Template/00.Long_Reads/LRSDAY.00.Long_Reads_Preprocessing.sh b/Project_Template/00.Long_Reads/LRSDAY.00.Long_Reads_Preprocessing.sh
@@ -13,7 +13,7 @@ reads_type="nanopore-raw" # The long reads data type: "pacbio-raw" or "pacbio-co
 run_filtering="yes" # Whether to filter and downsample the reads: "yes" or "no". Default = "yes".
 genome_size="12500000" # The haploid genome size (in bp) of sequenced organism. Default = "12500000" (i.e. 12.5 Mb for the budding yeast S. cereviaie genome). This is used to calculate targeted sequencing coverage after read filtering (see below). 
 post_filtering_coverage="60" # Targeted sequencing coverage after read filtering and downsampling. Default = "60" (i.e. 60x coverage).
-threads=24 # The number of threads to use. Default = "4".
+threads=4 # The number of threads to use. Default = "4".
 
 #######################################
 # process the pipeline

diff --git a/Project_Template/00.Long_Reads/LRSDAY.00.PacBio.RSII_bax2bam.sh b/Project_Template/00.Long_Reads/LRSDAY.00.PacBio.RSII_bax2bam.sh
@@ -13,12 +13,14 @@ pacbio_RSII_bax_fofn_file="./pacbio_fofn_files/$prefix.RSII_bax.fofn" # The fofn
 #######################################
 # process the pipeline
 
-source $miniconda2_dir/activate $conda_pacbio_dir/../../conda_pacbio_env
-$conda_pacbio_dir/bax2bam \
+#source $miniconda2_dir/activate $conda_pacbio_dir/../../conda_pacbio_env
+
+$bax2bam_dir/bax2bam \
     --fofn=$pacbio_RSII_bax_fofn_file \
     -o ./pacbio_fofn_files/$prefix.bax2bam \
     --subread \
-    --pulsefeatures=DeletionQV,DeletionTag,InsertionQV,IPD,MergeQV,SubstitutionQV,PulseWidth,SubstitutionTag
+    --pulsefeatures=DeletionQV,DeletionTag,InsertionQV,IPD,MergeQV,SubstitutionQV,PulseWidth,SubstitutionTag \
+    --allowUnrecognizedChemistryTriple
 
 cd pacbio_fofn_files
 rm $prefix.bax2bam.scraps.bam

diff --git a/Project_Template/11.TE_Annotation/LRSDAY.11.TE_Annotation.sh b/Project_Template/11.TE_Annotation/LRSDAY.11.TE_Annotation.sh
@@ -111,13 +111,14 @@ $bedtools_dir/bedtools intersect -v -a $prefix.TY_soloLTR.refined.nr.gff -b $pre
 
 cat $prefix.TY.complete_plus_truncated.final.gff $prefix.TY.soloLTR.final.gff > $prefix.TY.all.final.gff
 
-#perl $LRSDAY_HOME/scripts/tidy_maker_gff3.pl -r ./../$prefix.genome.fa -i $prefix.TY.all.final.gff -o $prefix.TE.gff3 -t $prefix 
-perl $LRSDAY_HOME/scripts/tidy_TE_gff3.pl -r ./../$prefix.genome.fa -i $prefix.TY.all.final.gff -o ./../$prefix.nuclear_genome.TE.gff3 -t $prefix 
+perl $LRSDAY_HOME/scripts/tidy_TE_gff3.pl -r ./../$prefix.genome.fa -i $prefix.TY.all.final.gff -o $prefix.nuclear_genome.TE.raw.gff3 -t $prefix 
+perl $LRSDAY_HOME/scripts/adjust_TY_annotation_for_gff3.pl -i $prefix.nuclear_genome.TE.raw.gff3 -o ./../$prefix.nuclear_genome.TE.gff3 
 
 
 if [[ $debug == "no" ]]
 then
     rm $prefix.*.final.gff
+    rm $prefix.nuclear_genome.TE.raw.gff3
 fi
 
 cd ..

diff --git a/README.md b/README.md
@@ -22,7 +22,8 @@ Jia-Xing Yue & Gianni Liti. (2018) Long-read sequencing data analysis for yeasts
 Jia-Xing Yue, Jing Li, Louise Aigrain, Johan Hallin, Karl Persson, Karen Oliver, Anders Bergström, Paul Coupland, Jonas Warringer, Marco Cosentino Lagomarsino, Gilles Fischer, Richard Durbin, Gianni Liti. (2017) Contrasting evolutionary genome dynamics between domesticated and wild yeasts. *Nature Genetics*, 49:913-924.
 
 ## Release history
-* v1.7.1 Released on 2022/01/28
+* v1.7.2 Released on 2023/03/20
+* v1.7.1 Released on 2023/01/28
 * v1.7.0 Released on 2022/12/31
 * v1.6.0 Released on 2019/10/03
 * v1.5.0 Released on 2019/05/13

diff --git a/install_dependencies.sh b/install_dependencies.sh
@@ -164,7 +164,7 @@ SHASTA_DOWNLOAD_URL="https://github.com/paoloshasta/shasta/releases/download/${S
 # for assembly polishing
 
 PB_ASSEMBLY_VERSION="0.0.8" #
-BAX2BAM_VERSION="0.0.11" #
+BAX2BAM_VERSION="0.0.9" #
 PBMM2_VERSION="1.9.0" #
 
 NANOPOLISH_VERSION="0.14.0" # released on 2021.04.06
@@ -572,7 +572,8 @@ then
 	clean "$build_dir/bax2bam_conda_env"
 	$miniconda2_dir/conda create -y -p $build_dir/bax2bam_conda_env 
 	source $miniconda2_dir/activate $build_dir/bax2bam_conda_env
-	$miniconda2_dir/conda install -y -c bioconda bax2bam=${BAX2BAM_VERSION}
+	#$miniconda2_dir/conda install -y -c bioconda bax2bam=${BAX2BAM_VERSION}
+	$miniconda2_dir/conda install -y -c "bioconda/label/cf201901" bax2bam 
 	source $miniconda2_dir/deactivate
 	note_installed $bax2bam_dir
     fi

diff --git a/pipelines/LRSDAY.00.Long_Reads_Preprocessing.sh b/pipelines/LRSDAY.00.Long_Reads_Preprocessing.sh
@@ -13,7 +13,7 @@ reads_type="nanopore-raw" # The long reads data type: "pacbio-raw" or "pacbio-co
 run_filtering="yes" # Whether to filter and downsample the reads: "yes" or "no". Default = "yes".
 genome_size="12500000" # The haploid genome size (in bp) of sequenced organism. Default = "12500000" (i.e. 12.5 Mb for the budding yeast S. cereviaie genome). This is used to calculate targeted sequencing coverage after read filtering (see below). 
 post_filtering_coverage="60" # Targeted sequencing coverage after read filtering and downsampling. Default = "60" (i.e. 60x coverage).
-threads=24 # The number of threads to use. Default = "4".
+threads=4 # The number of threads to use. Default = "4".
 
 #######################################
 # process the pipeline

diff --git a/pipelines/LRSDAY.00.PacBio.RSII_bax2bam.sh b/pipelines/LRSDAY.00.PacBio.RSII_bax2bam.sh
@@ -13,12 +13,14 @@ pacbio_RSII_bax_fofn_file="./pacbio_fofn_files/$prefix.RSII_bax.fofn" # The fofn
 #######################################
 # process the pipeline
 
-source $miniconda2_dir/activate $conda_pacbio_dir/../../conda_pacbio_env
-$conda_pacbio_dir/bax2bam \
+#source $miniconda2_dir/activate $conda_pacbio_dir/../../conda_pacbio_env
+
+$bax2bam_dir/bax2bam \
     --fofn=$pacbio_RSII_bax_fofn_file \
     -o ./pacbio_fofn_files/$prefix.bax2bam \
     --subread \
-    --pulsefeatures=DeletionQV,DeletionTag,InsertionQV,IPD,MergeQV,SubstitutionQV,PulseWidth,SubstitutionTag
+    --pulsefeatures=DeletionQV,DeletionTag,InsertionQV,IPD,MergeQV,SubstitutionQV,PulseWidth,SubstitutionTag \
+    --allowUnrecognizedChemistryTriple
 
 cd pacbio_fofn_files
 rm $prefix.bax2bam.scraps.bam

diff --git a/pipelines/LRSDAY.11.TE_Annotation.sh b/pipelines/LRSDAY.11.TE_Annotation.sh
@@ -111,13 +111,14 @@ $bedtools_dir/bedtools intersect -v -a $prefix.TY_soloLTR.refined.nr.gff -b $pre
 
 cat $prefix.TY.complete_plus_truncated.final.gff $prefix.TY.soloLTR.final.gff > $prefix.TY.all.final.gff
 
-#perl $LRSDAY_HOME/scripts/tidy_maker_gff3.pl -r ./../$prefix.genome.fa -i $prefix.TY.all.final.gff -o $prefix.TE.gff3 -t $prefix 
-perl $LRSDAY_HOME/scripts/tidy_TE_gff3.pl -r ./../$prefix.genome.fa -i $prefix.TY.all.final.gff -o ./../$prefix.nuclear_genome.TE.gff3 -t $prefix 
+perl $LRSDAY_HOME/scripts/tidy_TE_gff3.pl -r ./../$prefix.genome.fa -i $prefix.TY.all.final.gff -o $prefix.nuclear_genome.TE.raw.gff3 -t $prefix 
+perl $LRSDAY_HOME/scripts/adjust_TY_annotation_for_gff3.pl -i $prefix.nuclear_genome.TE.raw.gff3 -o ./../$prefix.nuclear_genome.TE.gff3 
 
 
 if [[ $debug == "no" ]]
 then
     rm $prefix.*.final.gff
+    rm $prefix.nuclear_genome.TE.raw.gff3
 fi
 
 cd ..