Develop

src/analysis/persephone/SeqC_pipeline/.dockerignore

@@ -1,5 +1,5 @@
-**/*.log
-Dockerfile
-.git
-.gitignore
+**/*.log
+Dockerfile
+.git
+.gitignore
 .env

src/analysis/persephone/SeqC_pipeline/.gitignore

@@ -1,8 +1,8 @@
-/seqc_proc/{DEPO_demo,DEPO_proc,REPO_host,REPO_tool}/
-/seqc_input/
-/seqc_output/
+/seqc_proc/{DEPO_demo,DEPO_proc,REPO_host,REPO_tool}/*
+/seqc_input/*
+/seqc_output/*
 .DS_Store
-#/DB/REPO_tool/kraken/taxonomy/nucl_{gb,wgs}.accession2taxid.gz
-#/DB/REPO_host
+# Retain core directories
+!/seqc_{input,output,proc}/.gitkeep
 #echo .DS_Store >> ~/.gitignore_global
 #git config --global core.excludesfile ~/.gitignore_global

src/analysis/persephone/SeqC_pipeline/BASH_seqc_makedb.sh

@@ -3,7 +3,7 @@
 # Title: make pipeline DBs
 # Program by: Wiley Barton - 2022.02.07
 # Modified for conda/docker pipeline - 2024.02.22
-# last update - 2025.02.10
+# last update - 2025.05.05
 # Modified code sources:
 #   check volume size: https://stackoverflow.com/questions/8110530/check-free-disk-space-for-current-partition-in-bash
 #   semi-array in env var: https://unix.stackexchange.com/questions/393091/unable-to-use-an-array-as-environment-variable
@@ -22,6 +22,8 @@
 #    link dled genomes between kraken
 #    clear reduntancy with db build via drop of accession from get list
 #   better compression: tar pigball: tar cvf - /data/share/kdb_a2a/ | pigz --best - > /data/share/kdb_a2a.tar.gz
+#   evaluate and implement zenodo_get: pip3 install zenodo_get, zenodo_get -r 14888918
+#   update hsap genome to: https://huttenhower.sph.harvard.edu/kneadData_databases/Homo_sapiens_hg39_T2T_Bowtie2_v0.1.tar.gz
 #======================================================================================================#
 # Set vars
 v_debug=0
@@ -37,6 +39,8 @@ v_vol_free=$(( $(stat --file-system --format="%a*%S" /) ))
 v_vol_mb=1048576
 # size of 1 gigabyte GB
 v_vol_gb=1073741824
+# size of 1 GB in MB
+v_vol_gm=1000
 # fixed used size
 #v_vol_used=$(printf %.0f $(echo "${v_vol_gb} * 161.4" | bc -l))
 v_vol_used=0
@@ -65,36 +69,40 @@ varr_db_path[$vn]=${varr_db_path[0]}'/REPO_host/hsap_contam/bowtie2'
 varr_db_gets[$vn]='wget --no-check-certificate http://huttenhower.sph.harvard.edu/kneadData_databases/Homo_sapiens_hg37_and_human_contamination_Bowtie2_v0.1.tar.gz -O '${varr_db_path[$vn]}'/hsap_hg37_contam.tar.gz'
 varr_db_pack[$vn]=${varr_db_pack[0]}${varr_db_path[$vn]}'/hsap_hg37_contam.tar.gz'' --directory '${varr_db_path[$vn]}
 # check - if size > 1 then assume preexisting
-if [[ "$(du ${varr_db_path[$vn]} 2> /dev/null | cut --fields 1 | tail -1)" -gt 1 ]];then 
-varr_db_check[$vn]=1
-else
-varr_db_check[$vn]=0
-fi
+# TODO - set to compression size as min threshold
 varr_db_size[$vn]=7.4
+# Pull current size
+vt_L=$(du -BM ${varr_db_path[$vn]} 2> /dev/null | cut --fields 1 | tail -1 | sed 's|M||g')
+# Pull expected size
+vt_R=$(printf %.0f $(echo "${v_vol_gm} * ${varr_db_size[$vn]}" | bc -l))
+# test and set accordingly
+[[ ${vt_L} -gt ${vt_R} ]] && varr_db_check[$vn]=1 || varr_db_check[$vn]=0
+# OoD ifelse approach
+#if [[ "$(du -BM ${varr_db_path[$vn]} 2> /dev/null | cut --fields 1 | tail -1)" -gt "${varr_db_size[$vn]}" ]];then 
+#varr_db_check[$vn]=1
+#else
+#varr_db_check[$vn]=0
+#fi
 # host - ncbi-bt2 - btau - 3.7G ~ 30min w/ 6 threads
 ((vn++))
 varr_db_name[$vn]='host_kd_btau'
 varr_db_path[$vn]=${varr_db_path[0]}'/REPO_host/btau'
 varr_db_gets[$vn]='datasets download genome accession GCF_002263795.3 --include genome --filename '${varr_db_path[$vn]}'/btau_ARS-UCD2.0.zip && unzip -qq '${varr_db_path[$vn]}'/btau_ARS-UCD2.0.zip -d '${varr_db_path[$vn]}' && micromamba run -n env_s1_kneaddata bowtie2-build --threads '${venv_cpu_max}' '${varr_db_path[$vn]}'/ncbi_dataset/data/GCF_002263795.3/GCF_002263795.3_ARS-UCD2.0_genomic.fna '${varr_db_path[$vn]}'/bowtie2/btau_ucd2'
-if [[ "$(du ${varr_db_path[$vn]} 2> /dev/null | cut --fields 1 | tail -1)" -gt 1 ]];then 
-varr_db_check[$vn]=1
-else
-varr_db_check[$vn]=0
-fi
 varr_db_size[$vn]=3.7
+vt_L=$(du -BM ${varr_db_path[$vn]} 2> /dev/null | cut --fields 1 | tail -1 | sed 's|M||g')
+vt_R=$(printf %.0f $(echo "${v_vol_gm} * ${varr_db_size[$vn]}" | bc -l))
+[[ ${vt_L} -gt ${vt_R} ]] && varr_db_check[$vn]=1 || varr_db_check[$vn]=0
 # host - bowtie2 - mmus 3.5G
 ((vn++))
 varr_db_name[$vn]='host_kd_mmus'
 varr_db_path[$vn]=${varr_db_path[0]}'/REPO_host/mmus/bowtie2'
 #varr_db_gets[3]='micromamba run -n env_s1 kneaddata_database --download mouse_C57BL bowtie2 '${varr_db_path[3]}'/C57BL.tar.gz'
 varr_db_gets[$vn]='wget --no-check-certificate http://huttenhower.sph.harvard.edu/kneadData_databases/mouse_C57BL_6NJ_Bowtie2_v0.1.tar.gz -O '${varr_db_path[$vn]}'/C57BL.tar.gz'
 varr_db_pack[$vn]=${varr_db_pack[0]}${varr_db_path[$vn]}'/C57BL.tar.gz'' --directory '${varr_db_path[$vn]}
-if [[ "$(du ${varr_db_path[$vn]} 2> /dev/null | cut --fields 1 | tail -1)" -gt 1 ]];then 
-varr_db_check[$vn]=1
-else
-varr_db_check[$vn]=0
-fi
 varr_db_size[$vn]=3.5
+vt_L=$(du -BM ${varr_db_path[$vn]} 2> /dev/null | cut --fields 1 | tail -1 | sed 's|M||g')
+vt_R=$(printf %.0f $(echo "${v_vol_gm} * ${varr_db_size[$vn]}" | bc -l))
+[[ ${vt_L} -gt ${vt_R} ]] && varr_db_check[$vn]=1 || varr_db_check[$vn]=0
 # Tool repo
 #checkm2 - 2.9G
 ((vn++))
@@ -105,12 +113,10 @@ varr_db_gets[$vn]='micromamba run -n env_s3_checkm2 checkm2 database --download
 varr_db_pack[$vn]=''
 #varr_db_gets[4]='wget https://zenodo.org/records/5571251/files/checkm2_database.tar.gz -O '${varr_db_path[4]}'/CheckM2_database.tar.gz'
 #varr_db_pack[4]=${varr_db_pack[0]}${varr_db_path[4]}'/CheckM2_database.tar.gz'' --directory '${varr_db_path[4]}
-if [[ "$(du ${varr_db_path[$vn]} 2> /dev/null | cut --fields 1 | tail -1)" -gt 1 ]];then 
-varr_db_check[$vn]=1
-else
-varr_db_check[$vn]=0
-fi
 varr_db_size[$vn]=2.9
+vt_L=$(du -BM ${varr_db_path[$vn]} 2> /dev/null | cut --fields 1 | tail -1 | sed 's|M||g')
+vt_R=$(printf %.0f $(echo "${v_vol_gm} * ${varr_db_size[$vn]}" | bc -l))
+[[ ${vt_L} -gt ${vt_R} ]] && varr_db_check[$vn]=1 || varr_db_check[$vn]=0
 #NCBI
 # taxdump - 0.5G (493M)
 ((vn++))
@@ -120,62 +126,52 @@ varr_db_path[$vn]=${varr_db_path[0]}'/REPO_tool/ncbi_NR'
 varr_db_gets[$vn]='wget --no-check-certificate https://ftp.ncbi.nlm.nih.gov/pub/taxonomy/taxdump.tar.gz -O '${varr_db_path[$vn]}'/taxdump.tar.gz'
 varr_db_pack[$vn]=${varr_db_pack[0]}${varr_db_path[$vn]}'/taxdump.tar.gz --directory '${varr_db_path[$vn]}
 #mkdir taxonomy && tar -xxvf taxdump.tar.gz -C taxonomy && mv ./taxonomy/ /DB/DEPO_demo/REPO_tool/ncbi_NR
-if [[ "$(du ${varr_db_path[$vn]} 2> /dev/null | cut --fields 1 | tail -1)" -gt 1 ]];then 
-varr_db_check[$vn]=1
-else
-varr_db_check[$vn]=0
-fi
 varr_db_size[$vn]=0.5
+vt_L=$(du -BM ${varr_db_path[$vn]} 2> /dev/null | cut --fields 1 | tail -1 | sed 's|M||g')
+vt_R=$(printf %.0f $(echo "${v_vol_gm} * ${varr_db_size[$vn]}" | bc -l))
+[[ ${vt_L} -gt ${vt_R} ]] && varr_db_check[$vn]=1 || varr_db_check[$vn]=0
 # kraken/bracken
 ## premade - pluspf smol - 8G
 ((vn++))
 varr_db_name[$vn]='tool_k2_std8'
 varr_db_path[$vn]=${varr_db_path[0]}'/REPO_tool/kraken'
 varr_db_gets[$vn]='wget --no-check-certificate https://genome-idx.s3.amazonaws.com/kraken/k2_pluspf_08gb_20240605.tar.gz -O '${varr_db_path[$vn]}'/kdb_std8.tar.gz'
 varr_db_pack[$vn]=${varr_db_pack[0]}${varr_db_path[$vn]}'/kdb_std8.tar.gz --directory '${varr_db_path[$vn]}'/kdb_std8'
-if [[ "$(du ${varr_db_path[$vn]}/kdb_std8 2> /dev/null | cut --fields 1 | tail -1)" -gt 1 ]];then 
-varr_db_check[$vn]=1
-else
-varr_db_check[$vn]=0
-fi
 varr_db_size[$vn]=8
+vt_L=$(du -BM ${varr_db_path[$vn]} 2> /dev/null | cut --fields 1 | tail -1 | sed 's|M||g')
+vt_R=$(printf %.0f $(echo "${v_vol_gm} * ${varr_db_size[$vn]}" | bc -l))
+[[ ${vt_L} -gt ${vt_R} ]] && varr_db_check[$vn]=1 || varr_db_check[$vn]=0
 # custom agora/apollo - apollo @ 4.5G
 ## apollo
 ((vn++))
 varr_db_name[$vn]='tool_k2_apollo'
 varr_db_path[$vn]=${varr_db_path[0]}'/REPO_tool/kraken/kdb_apollo'
 varr_db_gets[$vn]='wget --no-check-certificate https://zenodo.org/records/14884732/files/kdb_apollo.tar.gz -O '${varr_db_path[$vn]}'.tar.gz'
 varr_db_pack[$vn]='tar -I pigz -xvf '${varr_db_path[$vn]}'.tar.gz --directory '${varr_db_path[0]}'/REPO_tool/kraken/'
-if [[ "$(du ${varr_db_path[$vn]} 2> /dev/null | cut --fields 1 | tail -1)" -gt 1 ]];then 
-varr_db_check[$vn]=1
-else
-varr_db_check[$vn]=0
-fi
 varr_db_size[$vn]=4.5
+vt_L=$(du -BM ${varr_db_path[$vn]} 2> /dev/null | cut --fields 1 | tail -1 | sed 's|M||g')
+vt_R=$(printf %.0f $(echo "${v_vol_gm} * ${varr_db_size[$vn]}" | bc -l))
+[[ ${vt_L} -gt ${vt_R} ]] && varr_db_check[$vn]=1 || varr_db_check[$vn]=0
 ## agora2 - 50G (clean?) TODO confirm
 ((vn++))
 varr_db_name[$vn]='tool_k2_agora'
 varr_db_path[$vn]=${varr_db_path[0]}'/REPO_tool/kraken/kdb_agora'
 varr_db_gets[$vn]='wget --no-check-certificate https://zenodo.org/records/14884741/files/kdb_agora.tar.gz -O '${varr_db_path[$vn]}'.tar.gz'
 varr_db_pack[$vn]='tar -I pigz -xvf '${varr_db_path[$vn]}'.tar.gz --directory '${varr_db_path[0]}'/REPO_tool/kraken/'
-if [[ "$(du ${varr_db_path[$vn]} 2> /dev/null | cut --fields 1 | tail -1)" -gt 1 ]];then 
-varr_db_check[$vn]=1
-else
-varr_db_check[$vn]=0
-fi
 varr_db_size[$vn]=50
+vt_L=$(du -BM ${varr_db_path[$vn]} 2> /dev/null | cut --fields 1 | tail -1 | sed 's|M||g')
+vt_R=$(printf %.0f $(echo "${v_vol_gm} * ${varr_db_size[$vn]}" | bc -l))
+[[ ${vt_L} -gt ${vt_R} ]] && varr_db_check[$vn]=1 || varr_db_check[$vn]=0
 ## agora2 and apollo - 154G pre 69 post - 84G genomes - TODO ADJUST FOR FINAL BUILD 238
 ((vn++))
 varr_db_name[$vn]='tool_k2_agora2apollo'
 varr_db_path[$vn]=${varr_db_path[0]}'/REPO_tool/kraken/kdb_a2a'
 varr_db_gets[$vn]='wget --no-check-certificate https://zenodo.org/records/14888918/files/kdb_a2a.tar.gz -O '${varr_db_path[$vn]}'.tar.gz'
 varr_db_pack[$vn]='tar -I pigz -xvf '${varr_db_path[$vn]}'.tar.gz --directory '${varr_db_path[0]}'/REPO_tool/kraken/'
-if [[ "$(du ${varr_db_path[$vn]} 2> /dev/null | cut --fields 1 | tail -1)" -gt 1 ]];then 
-varr_db_check[$vn]=1
-else
-varr_db_check[$vn]=0
-fi
 varr_db_size[$vn]=69
+vt_L=$(du -BM ${varr_db_path[$vn]} 2> /dev/null | cut --fields 1 | tail -1 | sed 's|M||g')
+vt_R=$(printf %.0f $(echo "${v_vol_gm} * ${varr_db_size[$vn]}" | bc -l))
+[[ ${vt_L} -gt ${vt_R} ]] && varr_db_check[$vn]=1 || varr_db_check[$vn]=0
 ##smol demo - actual size needed
 ((vn++))
 varr_db_name[$vn]='tool_k2_demo'
@@ -186,6 +182,9 @@ else
 varr_db_check[$vn]=0
 fi
 varr_db_size[$vn]=8
+vt_L=$(du -BM ${varr_db_path[$vn]} 2> /dev/null | cut --fields 1 | tail -1 | sed 's|M||g')
+vt_R=$(printf %.0f $(echo "${v_vol_gm} * ${varr_db_size[$vn]}" | bc -l))
+[[ ${vt_L} -gt ${vt_R} ]] && varr_db_check[$vn]=1 || varr_db_check[$vn]=0
 # humann
 func_help () {
 # Help content
@@ -523,6 +522,15 @@ func_makedb_krak () {
         #create fail log if missing
         printf 'NCBI_ID\tno_attempts\n' > ${v_dir_k2_genm}/log_fail.txt
     fi
+    # remove elements from array eg uncultured taxa
+    varr_drop=(77133)
+    for v_grab in "${varr_drop[@]}";do
+        for vi in "${!varr_taxid_uniq[@]}";do
+            if [[ ${varr_taxid_uniq[vi]} = $v_grab ]];then
+                unset 'varr_taxid_uniq[vi]'
+            fi
+        done
+    done
     #remove whitespace
     varr_taxid_uniq=( $(printf '%s\n' "${varr_taxid_uniq[@]}") )
     for v_i in "${!varr_taxid_uniq[@]}";do

src/analysis/persephone/SeqC_pipeline/BASH_seqc_mama.sh

@@ -3,7 +3,8 @@
 # Title: mama script: take run commands, est db link, run stepgen
 # Program by: Wiley Barton - 2022.02.27
 # Modified for conda/docker pipeline - 2024.02.22
-# last update - 2025.01.30
+# Version for Persephone
+# last update - 2025.05.13
 # Modified code sources:
 #   https://stackoverflow.com/questions/2043453/executing-multi-line-statements-in-the-one-line-command-line
 # Notes: generate bash files according to user input for the completion of pipeline
@@ -36,6 +37,7 @@
 #  flesh out func_demo to build complete demo run within /DB/DEPO_demo
 #  auto compile file list from input dir in absence of provided list
 #  expand splash to include system params: cpu, mem, du of key directories
+# implement pv for progress bar... tar -I pigz -xvf stuff.tar.gz | pv
 #refs
 # prodigal:https://bmcbioinformatics.biomedcentral.com/articles/10.1186/1471-2105-11-119#citeas
 # https://www.cyberciti.biz/tips/bash-shell-parameter-substitution-2.html
@@ -53,6 +55,8 @@ var_rep_len=${#var_rep_ary[@]}
 #size check -db
 v_vol_real=$(du -bs $v_dir_db | cut -f1 )
 v_vol_none=60000
+#system max cpu
+v_sys_mem=$(nproc)
 v_scrp_check=0
 #var_rep_ary[var_rep_len]='x/y/z/cat'*'.kitty'
 #var_rep_out=${var_rep_ary[@]}
@@ -136,7 +140,7 @@ func_help () {
 	printf " -o OUTPUT: Directory to contain final output (/path/to/output)\n"
 	printf " -r BrANCH: Branch of pipeline to use, one of SR, MAG, ALL\n\t(default: SR)\n"
 	printf " -c COMMS : Commands applied to step\n"
-	printf " -s STEPS : Steps of pipeline to run with '0' complete run \n\t(steps=( $( eval echo {1..9} ) ))\n"
+	printf " -s STEPS : Steps of pipeline to run with '0' complete run \n\t(alt. -s 2 -3)\n"
 	printf " -e HeAD  : Head of files, from first char to start of variable region\n"
 	printf "\tsample_01.fastq\n\t...\n\tsample_10.fastq\n\t^^^^^^^\n"
 	printf " -t TAIL  : File tail, ~extension, constant across all input\n"
@@ -1309,7 +1313,7 @@ if [[ ${v_scrp_check} -eq 1 ]];then
 					vopt_step=( $( eval echo {1..6} ) )
 				fi
 			else
-				vopt_step=${OPTARG}
+				vopt_step+=("$OPTARG")
 				vopt_part=1
 			fi
 			if ((vopt_dbug));then
@@ -1518,6 +1522,7 @@ if (( ${vopt_log} ));then
 		fi
 		printf 'Input file type: %s\n%s\n' "${vopt_file_type}" "${v_logblock1}" >> ${v_logfile}
 		# Check zip status - CRIT - extend to .tar files in dir
+		#	pot. just exclude .tar
 		vt_L=$( printf '%s\n' "${v_file_in_good[@]}" | grep -E "\.gz|gzip$" | wc -l )
 		vt_R='0'
 		if [[ ${vt_L} -gt ${vt_R} ]];then
@@ -1724,12 +1729,21 @@ for istep in "${vopt_step[@]}";do
 			vin_head=''
 			vin_tail=''
 		fi
+		# proc check - ensure that too many processes are not called
+		if [[ -z ${venv_proc_max} ]];then
+			venv_proc_max=$(( ${venv_cpu_max} / 2 ))
+		fi
+		if [[ $(printf %.0f $(echo "${venv_cpu_max} * ${venv_proc_max}" | bc -l)) -gt "${v_sys_mem}" ]];then
+			vt="${venv_proc_max}"
+			while [[ $(printf %.0f $(echo "${venv_cpu_max} * ${vt}" | bc -l)) -gt "${v_sys_mem}" ]];do
+				((vt--))
+				#printf 'in%s\n' "${vt}"
+			done
+			#printf 'out%s\n' "${vt}"
+			venv_proc_max="${vt}"
+		fi
 		if [[ ${vopt_com_log} -eq 0 ]];then
 			#insert as awk print block - ex: vopt_com='{ printf "--output-format tsv --output-basename %s",va_nID }'
-			#improve with adjustment to :--processes <1>
-			if [[ -z ${venv_proc_max} ]];then
-				venv_proc_max=$(( ${venv_cpu_max} / 2 ))
-			fi
 			vin_com='{ printf " --remove-intermediate-output --reference-db %s --threads %s --processes %s --max-memory %sg --trimmomatic /opt/conda/envs/env_s1_kneaddata/share/trimmomatic --reorder","'${vin_host_rm}'",'${venv_cpu_max}','${venv_proc_max}','${venv_mem_max}' }'
 		fi
 		#WORKING EX
@@ -1757,6 +1771,9 @@ for istep in "${vopt_step[@]}";do
 			v_drop_exit=${v_drop_exit}' '${vout_sX}/${v_drop_catch}
 		fi
 		# exit logging
+		# TODO more elaborate permissions transfer approach
+		# pot. grab user ID at start and set ownership directly
+		chmod -R +777 ${vout_sX}/*
 		v_print_size=$( du -sh ${vout_sX} | cut -f 1 )
 		v_print_count=$( find ${vout_sX} | wc -l )
 		printf 'Step product location:\t%s\nStep run script location:\t%s\nStep output size(disk use):\t%s\nStep output count(files):\t%s\n%s\n' \
@@ -1986,7 +2003,7 @@ for istep in "${vopt_step[@]}";do
 					v_k2mpa_out=${v_kjoin_out/out/mpa_out_RA}
 					cat ${v_kjoin_out/out/mpa_out} | cut --fields 2${v_bk_col_frac} > "${v_k2mpa_out}"
 					#drop col type for match with meta data
-					sed -i "1 s/_$v_match//" "${v_k2mpa_out}"
+					sed -i "1,1s/_$v_match//g" "${v_k2mpa_out}"
 					#counts
 					v_match='num'
 					v_bk_cols=( $( head ${v_kjoin_out/out/mpa_out} -n 1 ) )
@@ -2006,7 +2023,7 @@ for istep in "${vopt_step[@]}";do
 					v_k2mpa_out=${v_kjoin_out/out/mpa_out_RC}
 					cat ${v_kjoin_out/out/mpa_out} | cut --fields 2${v_bk_col_num} > "${v_k2mpa_out}"
 					#drop col type for match with meta data
-					sed -i "1 s/_$v_match//" "${v_k2mpa_out}"
+					sed -i "1,1s/_$v_match//g" "${v_k2mpa_out}"
 					#default mars input is now "${v_k2mpa_out}" = /DB/DEPO_proc/step2_kraken/KB_S_mpa_out_RC.txt
 					vout_sX=${vout_s2}
 					# step keep-clean
@@ -2016,10 +2033,13 @@ for istep in "${vopt_step[@]}";do
 						v_drop_catch='*_{k2,bracken}_*{.txt,.fastq}'
 						eval "rm ${vout_sX}/${v_drop_catch}" 2> /dev/null
 						#statment for final drop
-						v_drop_catch='KB_*.txt'
+						v_drop_catch='KB_S_{taxid,out,mpa_out}.txt'
 						v_drop_exit=${v_drop_exit}' '${vout_sX}/${v_drop_catch}
 					fi
 					# exit logging
+					# TODO more elaborate permissions transfer approach
+					# pot. grab user ID at start and set ownership directly
+					chmod -R +777 ${vout_sX}/*
 					v_print_size=$( du -sh ${vout_sX} | cut -f 1 )
 					v_print_count=$( find ${vout_sX} | wc -l  )
 					printf 'Step product location:\t%s\nStep run script location:\t%s\nStep output size(disk use):\t%s\nStep output count(files):\t%s\n%s\n' \
@@ -2204,6 +2224,9 @@ for istep in "${vopt_step[@]}";do
 					vout_s3=${vin_O_dir}/${v_exit_dir}
 					# exit logging
 					vout_sX=${vout_s3}
+					# TODO more elaborate permissions transfer approach
+					# pot. grab user ID at start and set ownership directly
+					chmod -R +777 ${vout_sX}/*
 					v_print_size=$( du -sh ${vout_sX} | cut -f 1 )
 					v_print_count=$( find ${vout_sX} | wc -l  )
 					printf 'Step product location:\t%s\nStep run script location:\t%s\nStep output size(disk use):\t%s\nStep output count(files):\t%s\n%s\n' \
@@ -2582,6 +2605,9 @@ if (( ${vopt_log} ));then
 	# Relocate taxonomy output
 	v_drop_catch='KB_S_mpa_out_{RC,RA}.txt'
 	eval "mv ${vout_s2}/${v_drop_catch} /home/seqc_user/seqc_project/final_reports/" 2> /dev/null
+	# TODO more elaborate permissions transfer approach
+	# pot. grab user ID at start and set ownership directly
+	chmod -R +777 /home/seqc_user/seqc_project/final_reports
 fi
 if (( ${vopt_log} ));then
 	printf 'SeqC Stuff ENDS @: %s\n' "$(date +"%Y.%m.%d %H.%M.%S (%Z)")"
@@ -2665,7 +2691,7 @@ if [[ ${v_scrp_check} -eq 0 ]];then
 	#startup splash - ascii gen from: https://patorjk.com/software/taag, standard,slant,alpha,isometric1,impossible
 	#https://medium.com/@Frozenashes/making-a-custom-startup-message-for-a-linux-shell-using-bashrc-and-bash-scripting-280268fdaa17
 	func_splash() {
-  	#if null create
+	#if null create
 		if [[ -z "${VEN_SPLASH}" ]]; then
 			echo "VEN_SPLASH="\"1\" >> /etc/environment
 			echo "export VEN_SPLASH=1" >>  /root/.bashrc
@@ -2701,7 +2727,7 @@ if [[ ${v_scrp_check} -eq 0 ]];then
   ___\:::\   \:::\    \/::::::\   \:::\    \/:::/    / \:::\    \/:::/    / \:::\    \
  /\   \:::\   \:::\____\::/\:::\   \:::\____\::/____/   \:::\____\::/    /   \:::\____\
 /::\   \:::\   \::/    /:/__\:::\   \::/    /:|    |    |:::|    |::____/     \::/    /
-\:::\   \:::\   \/____/::\   \:::\   \/____/::|____|    |:::|____/::\    \     \/____/
+\:::\   \:::\   \/____/::\   \:::\   \/____/::|____|    |:::|____|::\    \     \/____/
  \:::\   \:::\____\   \:::\   \:::\____\   |:::\   _\___/:::/    /:::\    \
   \:::\  /:::/    /    \:::\   \::/    /    \:::\ |::| /:::/    / \:::\    \
    \:::\/:::/    /______\:::\   \/____/______\:::\|::|/:::/    /___\:::\    \    _____    _____       ______