Skip to content

Commit

Permalink
add --skip_ani_screen to the new version of gtdbtk
Browse files Browse the repository at this point in the history
  • Loading branch information
@Hydro3639
Hydro3639 authored Oct 17, 2023
1 parent 3664452 commit 883cb11
Showing 1 changed file with 17 additions and 17 deletions.
34 changes: 17 additions & 17 deletions bin/nanophase.iso
View file
Original file line number Diff line number Diff line change
Expand Up @@ -202,7 +202,7 @@ long_read_assembly(){
mv $OutDIR/01-LongAssemblies/tmp/assembly.fasta $OutDIR/01-LongAssemblies/tmp/assembly_info.txt $OutDIR/01-LongAssemblies/tmp/flye.log $OutDIR/01-LongAssemblies

if [ -f $OutDIR/01-LongAssemblies/assembly.fasta -a -f $OutDIR/01-LongAssemblies/assembly_info.txt ]; then
echo "`datetime.DONE` long-read assembly finished sucessfully: detailed log file is $OutDIR/01-LongAssemblies/flye.log"
echo "`datetime.DONE` long-read assembly finished successfully: detailed log file is $OutDIR/01-LongAssemblies/flye.log"
rm -rf $OutDIR/01-LongAssemblies/tmp
else
echo "`datetime.ERROR` Something wrong with long-read assembly, terminating..."
Expand All @@ -212,7 +212,7 @@ long_read_assembly(){

if [ -f $OutDIR/01-LongAssemblies/assembly.fasta -a -f $OutDIR/01-LongAssemblies/assembly_info.txt ]; then
echo "`datetime.INFO` long-read assembly has been found in the folder: $OutDIR/01-LongAssemblies/. Now go to the next stage: generating LongBins...
Note: plese ensure flye assembly finished sucessfully in the previous run, if not, please remove this folder using the command 'rm -rf $OutDIR/$OutDIR/01-LongAssemblies/' and re-run nanophase command"
Note: please ensure flye assembly finished successfully in the previous run, if not, please remove this folder using the command 'rm -rf $OutDIR/$OutDIR/01-LongAssemblies/' and re-run nanophase command"
else
if [[ -d $OutDIR/01-LongAssemblies ]]; then
echo "`datetime.INFO` Long-read assembly re-starts"
Expand All @@ -234,7 +234,7 @@ racon_polishing(){
minimap2 -x map-ont -d $OutDIR/02-LongBins/bin.fasta.mni $OutDIR/02-LongBins/bin.raw.fasta >$OutDIR/03-Polishing/Racon/racon.polish.log 2>&1 && minimap2 -ax map-ont -t $N_threads $OutDIR/02-LongBins/bin.fasta.mni $ONT_seqs > $OutDIR/03-Polishing/Racon/overlaps.racon.sam 2>>$OutDIR/03-Polishing/Racon/racon.polish.log && racon -t $N_threads $ONT_seqs $OutDIR/03-Polishing/Racon/overlaps.racon.sam $OutDIR/02-LongBins/bin.raw.fasta > $OutDIR/03-Polishing/Racon/bin-racon.fasta 2>>$OutDIR/03-Polishing/Racon/racon.polish.log

if [[ -s $OutDIR/03-Polishing/Racon/bin-racon.fasta ]]; then
echo "`datetime.DONE` racon polishing finished sucessfully: detailed log file is $OutDIR/03-Polishing/Racon/racon.polish.log"
echo "`datetime.DONE` racon polishing finished successfully: detailed log file is $OutDIR/03-Polishing/Racon/racon.polish.log"
rm -rf $OutDIR/02-LongBins/bin.fasta.mni && rm -rf $OutDIR/03-Polishing/Racon/overlaps.racon.sam
else
echo "`datetime.ERROR` Something wrong with racon polishing, terminating..."
Expand Down Expand Up @@ -262,7 +262,7 @@ medaka_consensus -m $medaka_model -i $ONT_seqs -d $OutDIR/03-Polishing/Racon/bin
mv $OutDIR/03-Polishing/medaka/tmp/consensus.fasta $OutDIR/03-Polishing/medaka/bin-medaka.fasta

if [[ -s $OutDIR/03-Polishing/medaka/bin-medaka.fasta ]]; then
echo "`datetime.DONE` medaka polishing finished sucessfully: detailed log file is $OutDIR/03-Polishing/medaka/medaka.polish.log"
echo "`datetime.DONE` medaka polishing finished successfully: detailed log file is $OutDIR/03-Polishing/medaka/medaka.polish.log"
rm -rf $OutDIR/03-Polishing/medaka/tmp/ && rm -rf $OutDIR/03-Polishing/Racon/bin-racon.fasta.*
else
echo "`datetime.ERROR` Something wrong with medaka polishing, terminating..."
Expand All @@ -274,7 +274,7 @@ if [[ -s $OutDIR/03-Polishing/medaka/bin-medaka.fasta ]]; then
if [[ $Type == hybrid ]]; then
echo "`datetime.INFO` medaka polishing has been finished. Now go to the next stage: polypolish polishing"
else
echo "`datetime.INFO` medaka polishing has been finished. Now go to the next stage: bin quality assessement and genome classification"
echo "`datetime.INFO` medaka polishing has been finished. Now go to the next stage: bin quality assessment and genome classification"
fi
else
if [[ -d $OutDIR/03-Polishing/medaka ]]; then
Expand All @@ -301,21 +301,21 @@ genome_stats(){

sed -n '/------------/,$p' $OutDIR/03-Polishing/Final-bins/checkm.log | tail -n+4 | head -n -1 | grep -v '\----------------------------' | awk '{print $1"\t"$13"\t"$14"\t"$15}' > $OutDIR/03-Polishing/Final-bins/tmp.genome.completeness
if [[ -s $OutDIR/03-Polishing/Final-bins/tmp.genome.completeness ]]; then
echo "`datetime.DONE` genome quality assessment finished sucessfully"
echo "`datetime.DONE` genome quality assessment finished successfully"
else
echo "`datetime.ERROR` Something wrong with checkm process, terminating..."
exit 1; >&2
fi

## Taxa info
echo "`datetime.TASK` Genome taxa classification starts"
gtdbtk classify_wf --genome_dir $OutDIR/03-Polishing/Final-bins/ -x fasta --out_dir $OutDIR/03-Polishing/Final-bins/tmp --cpus $N_threads >/dev/null 2>&1
gtdbtk classify_wf --genome_dir $OutDIR/03-Polishing/Final-bins/ -x fasta --out_dir $OutDIR/03-Polishing/Final-bins/tmp --cpus $N_threads --skip_ani_screen >/dev/null 2>&1
echo "`cat $OutDIR/03-Polishing/Final-bins/tmp/gtdbtk.log`"
echo "`datetime.DONE` genome classification done"

cat $OutDIR/03-Polishing/Final-bins/tmp/classify/gtdbtk.*summary.tsv | grep -v '^user_genome' | awk -F"\t" '{print $2}' > $OutDIR/03-Polishing/Final-bins/tmp.taxa
if [[ -s $OutDIR/03-Polishing/Final-bins/tmp.taxa ]]; then
echo "`datetime.DONE` GTDB::Taxa finished sucessfully"
echo "`datetime.DONE` GTDB::Taxa finished successfully"
else
echo "`datetime.ERROR` Something wrong with GTDB:Taxa process, terminating..."
exit 1; >&2
Expand Down Expand Up @@ -369,9 +369,9 @@ sr_polypolish_polca_polishing(){
polypolish_polishing(){
bwa index $OutDIR/03-Polishing/medaka/bin-medaka.fasta >$OutDIR/03-Polishing/Polypolish/polypolish.polish.log 2>&1 && bwa mem -t $N_threads -a $OutDIR/03-Polishing/medaka/bin-medaka.fasta $SR1_seqs > $OutDIR/03-Polishing/Polypolish/bin_alignments_1.sam 2>>$OutDIR/03-Polishing/Polypolish/polypolish.polish.log && bwa mem -t $N_threads -a $OutDIR/03-Polishing/medaka/bin-medaka.fasta $SR2_seqs > $OutDIR/03-Polishing/Polypolish/bin_alignments_2.sam 2>>$OutDIR/03-Polishing/Polypolish/polypolish.polish.log && polypolish_insert_filter.py --in1 $OutDIR/03-Polishing/Polypolish/bin_alignments_1.sam --in2 $OutDIR/03-Polishing/Polypolish/bin_alignments_2.sam --out1 $OutDIR/03-Polishing/Polypolish/bin_filtered_1.sam --out2 $OutDIR/03-Polishing/Polypolish/bin_filtered_2.sam 2>>$OutDIR/03-Polishing/Polypolish/polypolish.polish.log && polypolish $OutDIR/03-Polishing/medaka/bin-medaka.fasta $OutDIR/03-Polishing/Polypolish/bin_filtered_1.sam $OutDIR/03-Polishing/Polypolish/bin_filtered_2.sam > $OutDIR/03-Polishing/Polypolish/bin-polypolish.fasta 2>>$OutDIR/03-Polishing/Polypolish/polypolish.polish.log && rm -rf $OutDIR/03-Polishing/Polypolish/*sam && rm -rf $OutDIR/03-Polishing/medaka/bin-medaka.fasta.*

## Check if the polypolish finished sucessfully
## Check if the polypolish finished successfully
if [[ -s $OutDIR/03-Polishing/Polypolish/bin-polypolish.fasta ]]; then
echo "`datetime.INFO` polypolish polishing finished sucessfully: detailed log file is $OutDIR/03-Polishing/Polypolish/polypolish.polish.log"
echo "`datetime.INFO` polypolish polishing finished successfully: detailed log file is $OutDIR/03-Polishing/Polypolish/polypolish.polish.log"
else
echo "`datetime.ERROR` Something wrong with polypolish polishing, terminating..."
exit 1; >&2
Expand Down Expand Up @@ -399,7 +399,7 @@ if [[ $sr_suffix == fa ]] || [[ $sr_suffix == fa.gz ]]; then
## clean: add ow=t allow overwritting and fake q
reformat.sh ow=t in=$SR1_seqs in2=$SR2_seqs out=$OutDIR/03-Polishing/POLCA/tmp/sr_1.fq out2=$OutDIR/03-Polishing/POLCA/tmp/sr_2.fq qfake=30 >$OutDIR/03-Polishing/POLCA/polca.polish.log 2>&1
if [[ -s $OutDIR/03-Polishing/POLCA/tmp/sr_1.fq ]] && [[ -s $OutDIR/03-Polishing/POLCA/tmp/sr_2.fq ]]; then
echo "`datetime.DONE` fa2fq process finished sucessfully"
echo "`datetime.DONE` fa2fq process finished successfully"
else
echo "`datetime.ERROR` Something wrong with fa2fq process, terminating..."
exit 1; >&2
Expand All @@ -423,7 +423,7 @@ if [[ ! -s $Polish_Path/POLCA/tmp/bin-polypolish.fasta.PolcaCorrected.fa ]]; the
echo "`datetime.INFO` Seems POLCA polishing did not improve the genome quality, so using polypolish-polished bins instead"
cp $Polish_Path/Polypolish/bin-polypolish.fasta $Polish_Path/POLCA/bin-polca.fasta
else
echo "`datetime.DONE` POLCA-polishing has been finished sucessfully: detailed log file is $Polish_Path/POLCA/polca.polish.log"
echo "`datetime.DONE` POLCA-polishing has been finished successfully: detailed log file is $Polish_Path/POLCA/polca.polish.log"
mv $Polish_Path/POLCA/tmp/bin-polypolish.fasta.PolcaCorrected.fa $Polish_Path/POLCA/bin-polca.fasta
fi

Expand All @@ -432,7 +432,7 @@ rm -rf $Polish_Path/POLCA/tmp && rm -rf $Polish_Path/Polypolish/bin-polypolish.f
}

if [[ -s $OutDIR/03-Polishing/POLCA/bin-polca.fasta ]]; then
echo "`datetime.INFO` polca polishing has been finished. Now go to the next stage: bin quality assessement and genome classification"
echo "`datetime.INFO` polca polishing has been finished. Now go to the next stage: bin quality assessment and genome classification"
else
if [[ -d $OutDIR/03-Polishing/POLCA ]]; then
echo "`datetime.INFO` polca polishing re-starts"
Expand All @@ -458,21 +458,21 @@ genome_stats(){

sed -n '/------------/,$p' $OutDIR/03-Polishing/Final-bins/checkm.log | tail -n+4 | head -n -1 | grep -v '\----------------------------' | awk '{print $1"\t"$13"\t"$14"\t"$15}' > $OutDIR/03-Polishing/Final-bins/tmp.genome.completeness
if [[ -s $OutDIR/03-Polishing/Final-bins/tmp.genome.completeness ]]; then
echo "`datetime.DONE` genome quality assessment finished sucessfully"
echo "`datetime.DONE` genome quality assessment finished successfully"
else
echo "`datetime.ERROR` Something wrong with checkm process, terminating..."
exit 1; >&2
fi

## Taxa info
echo "`datetime.TASK` Genome taxa classification starts"
gtdbtk classify_wf --genome_dir $OutDIR/03-Polishing/Final-bins/ -x fasta --out_dir $OutDIR/03-Polishing/Final-bins/tmp --cpus $N_threads >/dev/null 2>&1
gtdbtk classify_wf --genome_dir $OutDIR/03-Polishing/Final-bins/ -x fasta --out_dir $OutDIR/03-Polishing/Final-bins/tmp --cpus $N_threads --skip_ani_screen >/dev/null 2>&1
echo "`cat $OutDIR/03-Polishing/Final-bins/tmp/gtdbtk.log`"
echo "`datetime.DONE` genome classification done"

cat $OutDIR/03-Polishing/Final-bins/tmp/classify/gtdbtk.*summary.tsv | grep -v '^user_genome' | awk -F"\t" '{print $2}' > $OutDIR/03-Polishing/Final-bins/tmp.taxa
if [[ -s $OutDIR/03-Polishing/Final-bins/tmp.taxa ]]; then
echo "`datetime.DONE` GTDB:Taxa was finished sucessfully"
echo "`datetime.DONE` GTDB:Taxa was finished successfully"
else
echo "`datetime.ERROR` Something wrong with GTDB:Taxa process, terminating..."
exit 1; >&2
Expand Down Expand Up @@ -522,7 +522,7 @@ fi
if [[ $Type = long_read_only ]]; then
echo "`datetime.INFO` long_read_only model was selected, only Nanopore long reads will be used"
if [[ -f $SR1_seqs ]] || [[ -f $SR2_seqs ]]; then
echo "`datetime.ERROR` It seems you are using long_read_only model, but provided short reads at the same time. If short reads were involved, please use [--hybrid] parameter, or remove short reads in the command; terminating..."
echo "`datetime.ERROR` It seems you are using the long_read_only model, but provided short reads at the same time. If short reads were involved, please use [--hybrid] parameter, or remove short reads in the command; terminating..."
show_help; exit 1; fi
long_read_check
## long-read-only model
Expand Down

0 comments on commit 883cb11

Please sign in to comment.