add profiling cmd (#7)

* init minimap2_processing

* fix test-1

* input -> artifact_id

* return filepath vs template

* adding tests

Author: antgonza

data/templates/0.mapping_minimap2_db.sbatch

@@ -8,10 +8,12 @@
 #SBATCH -o {{output}}/step-1/logs/%x-%A_%a.out
 #SBATCH -e {{output}}/step-1/logs/%x-%A_%a.out
 #SBATCH --array {{array_params}}
+
 source ~/.bashrc
+set -e
 conda activate {{conda_environment}}
-
 cd {{output}}/step-1
+
 step=${SLURM_ARRAY_TASK_ID}
 input=$(head -n $step {{output}}/sample_list.txt | tail -n 1)
 

data/templates/1.hifiasm-meta_new.sbatch

@@ -10,9 +10,8 @@
 #SBATCH --array {{array_params}}
 
 source ~/.bashrc
-
+set -e
 conda activate {{conda_environment}}
-
 cd {{output}}/step-1
 
 step=${SLURM_ARRAY_TASK_ID} ##1000_2, 1000_1

data/templates/2.get-circular-genomes.sbatch

@@ -10,6 +10,7 @@
 #SBATCH --array {{array_params}}
 
 source ~/.bashrc
+set -e
 conda activate {{conda_environment}}
 cd {{output}}
 

data/templates/3.minimap2_assembly.sbatch

@@ -10,8 +10,8 @@
 #SBATCH --array {{array_params}}
 
 source ~/.bashrc
+set -e
 conda activate {{conda_environment}}
-
 cd {{output}}
 
 step=${SLURM_ARRAY_TASK_ID}

data/templates/4.metawrap_binning_new.sbatch

@@ -10,7 +10,7 @@
 #SBATCH --array {{array_params}}
 
 source ~/.bashrc
-
+set -e
 conda activate {{conda_environment}}
 cd {{output}}
 
@@ -35,4 +35,4 @@ Fasta_to_Contig2Bin.sh -i ./concoct_bins -e fa > ${sample_name}.concoct.tsv
 Fasta_to_Contig2Bin.sh -i ./maxbin2_bins -e fa > ${sample_name}.maxbin2.tsv
 Fasta_to_Contig2Bin.sh -i ./metabat2_bins -e fa > ${sample_name}.metabat2.tsv
 
-DAS_Tool --bins=${sample_name}.concoct.tsv,${sample_name}.maxbin2.tsv,${sample_name}.metabat2.tsv --contigs={{output}}/step-2/${sample_name}_noLCG.fa --outputbasename={{output}}/${folder}/${sample_name}/${sample_name} --labels=CONCOCT,MaxBin,MetaBAT --threads={{nprocs}} --search_engine=diamond --dbDirectory=${DAS_db} --write_bins
+DAS_Tool --bins=${sample_name}.concoct.tsv,${sample_name}.maxbin2.tsv,${sample_name}.metabat2.tsv --contigs={{output}}/step-2/${sample_name}_noLCG.fa --outputbasename={{output}}/${folder}/${sample_name}/${sample_name} --labels=CONCOCT,MaxBin,MetaBAT --threads={{nprocs}} --search_engine=diamond --dbDirectory=${DAS_db} --write_bins

data/templates/5.DAS_Tools_prepare_batch3_test.sbatch

@@ -10,6 +10,7 @@
 #SBATCH --array {{array_params}}
 
 source ~/.bashrc
+set -e
 conda activate {{conda_environment}}
 cd {{output}}
 

data/templates/6.MAG_rename.sbatch

@@ -11,9 +11,8 @@
 
 
 source ~/.bashrc
-
+set -e
 conda activate {{conda_environment}}
-
 cd {{output}}
 
 step=${SLURM_ARRAY_TASK_ID}

data/templates/7.checkm_batch.sbatch

@@ -0,0 +1,32 @@
+#!/bin/bash
+#SBATCH -J {{job_name}}
+#SBATCH -p qiita
+#SBATCH -N {{node_count}}
+#SBATCH -n {{nprocs}}
+#SBATCH --time {{wall_time_limit}}
+#SBATCH --mem {{mem_in_gb}}G
+#SBATCH -o {{output}}/minimap2/logs/%x-%A_%a.out
+#SBATCH -e {{output}}/minimap2/logs/%x-%A_%a.out
+#SBATCH --array {{array_params}}
+
+source ~/.bashrc
+set -e
+conda activate {{conda_environment}}
+mkdir -p {{output}}/alignments
+cd {{output}}/
+db=/ddn_scratch/qiita_t/working_dir/tmp/db/WoLr2.mmi
+
+step=${SLURM_ARRAY_TASK_ID}
+input=$(head -n $step {{output}}/sample_list.txt | tail -n 1)
+
+sample_name=`echo $input | awk '{print $1}'`
+filename=`echo $input | awk '{print $2}'`
+
+fn=`basename ${filename}`
+
+minimap2 -x map-hifi -t {{nprocs}} -a \
+       --secondary=no --MD --eqx ${db} \
+       ${filename} | \
+   samtools sort -@ {{nprocs}} - | \
+   awk 'BEGIN { FS=OFS="\t" } /^@/ { print; next } { $10="*"; $11="*" } 1' | \
+   xz -1 -T1 > {{output}}/alignments/${sample_name}.sam.xz

data/templates/woltka_minimap2.sbatch

@@ -0,0 +1,49 @@
+#!/bin/bash
+#SBATCH -J {{job_name}}
+#SBATCH -p qiita
+#SBATCH -N {{node_count}}
+#SBATCH -n {{nprocs}}
+#SBATCH --time {{wall_time_limit}}
+#SBATCH --mem {{mem_in_gb}}G
+#SBATCH -o {{output}}/merge/logs/%x-%A_%a.out
+#SBATCH -e {{output}}/merge/logs/%x-%A_%a.out
+
+source ~/.bashrc
+set -e
+conda activate {{conda_environment}}
+cd {{output}}/
+tax=/projects/wol/qiyun/wol2/databases/minimap2/WoLr2.tax
+coords=/projects/wol/qiyun/wol2/databases/minimap2/WoLr2.coords
+len_map=/projects/wol/qiyun/wol2/databases/minimap2/WoLr2/length.map
+functional_dir=/projects/wol/qiyun/wol2/databases/minimap2/WoLr2/
+
+mkdir -p {{output}}/coverages/
+
+for f in `ls alignments/*.sam.xz`; do
+    sn=`basename ${f/.sam.xz/}`;
+    of={{output}}/bioms/${sn};
+    mkdir -p ${of};
+    echo "woltka classify -i ${f} -o ${of}/none.biom --no-demux --lineage ${tax} --rank none --outcov {{output}}/coverages/";
+    echo "woltka classify -i ${f} -o ${of}/per-gene.biom --no-demux -c ${coords}";
+done | parallel -j {{node_count}}
+wait
+
+for f in `ls bioms/*/per-gene.biom`; do
+    dn=`dirname ${f}`;
+    sn=`basename ${sn}`;
+    echo "woltka collapse -i ${f} -m ${functional_dir}/orf-to-ko.map.xz -o ${dn}/ko.biom; " \
+        "woltka collapse -i ${dn}/ko.biom -m ${functional_dir}/ko-to-ec.map -o ${dn}/ec.biom; " \
+        "woltka collapse -i ${dn}/ko.biom -m ${functional_dir}/ko-to-reaction.map -o ${dn}/reaction.biom; " \
+        "woltka collapse -i ${dn}/reaction.biom -m ${functional_dir}/reaction-to-module.map -o ${dn}/module.biom; " \
+        "woltka collapse -i ${dn}/module.biom -m ${functional_dir}/module-to-pathway.map -o ${dn}/pathway.biom;"
+done | parallel -j {{node_count}}
+wait
+
+# MISSING:
+# merge bioms!
+
+find {{output}}/coverages/ -iname "*.cov" > {{output}}/cov_files.txt
+micov consolidate --paths {{output}}/cov_files.txt --lengths ${len_map} --output {{output}}/coverages.tgz
+
+cd alignments
+tar -cvf ../alignments.tar *.sam.xz