/srv/GT/analysis/course_sushi/public/gstore/projects/p1001/o35755_Canu_2025-09-03--15-03-37/scripts/Assemble_mut22_ventricles_100k_1.sh_sushiID1633_2025-09-03--15-03-50_o.log
--------------------------------------------------
Job runs on fgcz-c-095
at /scratch/o35755_Canu_2025-09-03--15-03-37_mut22_temp3572097
Starting EzAppCanu o35755_Canu_2025-09-03--15-03-37_mut22_temp3572097 2025-09-03 15:03:56
EXECUTED CMD: canu -p mut22 -d mut22 genomeSize=5000k maxMemory=30 maxThreads=8 useGrid=false -pacbio-raw /srv/GT/analysis/course_sushi/public/gstore/projects/p1001/ventricles_100k/MutantSample_2_R1.fastq.gz 1> mut22_canu.log
ezRun tag: 9a33c060b4f013d968058b2834d6f6bc1492ad87
ezRun github link: https://github.com/uzh/ezRun/tree/9a33c060b4f013d968058b2834d6f6bc1492ad87
R version 4.5.0 (2025-04-11)
Platform: x86_64-pc-linux-gnu
Running under: Debian GNU/Linux 12 (bookworm)
Matrix products: default
BLAS: /usr/lib/x86_64-linux-gnu/blas/libblas.so.3.11.0
LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.11.0 LAPACK version 3.11.0
locale:
[1] LC_CTYPE=C.UTF-8 LC_NUMERIC=C LC_TIME=C.UTF-8
[4] LC_COLLATE=C.UTF-8 LC_MONETARY=C.UTF-8 LC_MESSAGES=C.UTF-8
[7] LC_PAPER=C.UTF-8 LC_NAME=C LC_ADDRESS=C
[10] LC_TELEPHONE=C LC_MEASUREMENT=C.UTF-8 LC_IDENTIFICATION=C
time zone: Europe/Berlin
tzcode source: system (glibc)
attached base packages:
[1] stats4 stats graphics grDevices utils datasets methods
[8] base
other attached packages:
[1] ezRun_3.21.1 lubridate_1.9.4 forcats_1.0.0
[4] stringr_1.5.1 dplyr_1.1.4 purrr_1.0.4
[7] readr_2.1.5 tidyr_1.3.1 tibble_3.2.1
[10] ggplot2_3.5.2 tidyverse_2.0.0 GenomicRanges_1.60.0
[13] Biostrings_2.76.0 GenomeInfoDb_1.44.0 XVector_0.48.0
[16] IRanges_2.42.0 S4Vectors_0.46.0 BiocGenerics_0.54.0
[19] generics_0.1.4 data.table_1.17.4
loaded via a namespace (and not attached):
[1] gtable_0.3.6 jsonlite_2.0.0 compiler_4.5.0
[4] crayon_1.5.3 tidyselect_1.2.1 dichromat_2.0-0.1
[7] scales_1.4.0 R6_2.6.1 GenomeInfoDbData_1.2.14
[10] pillar_1.10.2 RColorBrewer_1.1-3 tzdb_0.5.0
[13] rlang_1.1.6 stringi_1.8.7 timechange_0.3.0
[16] cli_3.6.5 withr_3.0.2 magrittr_2.0.3
[19] grid_4.5.0 hms_1.1.3 lifecycle_1.0.4
[22] vctrs_0.6.5 glue_1.8.0 farver_2.1.2
[25] httr_1.4.7 tools_4.5.0 pkgconfig_2.0.3
[28] UCSC.utils_1.4.0
Finished EzAppCanu o35755_Canu_2025-09-03--15-03-37_mut22_temp3572097 2025-09-03 15:03:57
___STDOUT_END___
/srv/GT/analysis/course_sushi/public/gstore/projects/p1001/o35755_Canu_2025-09-03--15-03-37/scripts/Assemble_mut22_ventricles_100k_1.sh_sushiID1633_2025-09-03--15-03-50_e.log
--------------------------------------------------
+ set -o pipefail
+ umask 0002
+ SCRATCH_DIR=/scratch/o35755_Canu_2025-09-03--15-03-37_mut22_temp3572097
+ GSTORE_DIR=/srv/GT/analysis/course_sushi/public/gstore/projects
+ INPUT_DATASET=/srv/GT/analysis/course_sushi/public/gstore/projects/p1001/o35755_Canu_2025-09-03--15-03-37/input_dataset.tsv
+ LAST_JOB=TRUE
++ hostname
+ echo 'Job runs on fgcz-c-095'
+ echo 'at /scratch/o35755_Canu_2025-09-03--15-03-37_mut22_temp3572097'
+ mkdir /scratch/o35755_Canu_2025-09-03--15-03-37_mut22_temp3572097
+ cd /scratch/o35755_Canu_2025-09-03--15-03-37_mut22_temp3572097
+ source /usr/local/ngseq/etc/lmod_profile
+++ eval 'echo /usr/local/ngseq/etc/modules:/etc/fgcz-envmods/lmod:/etc/lmod/modules:/usr/share/lmod/lmod/modulefiles'
++++ echo /usr/local/ngseq/etc/modules:/etc/fgcz-envmods/lmod:/etc/lmod/modules:/usr/share/lmod/lmod/modulefiles
++ export MODULEPATH=/usr/local/ngseq/etc/modules:/usr/local/ngseq/etc/modules:/etc/fgcz-envmods/lmod:/etc/lmod/modules:/usr/share/lmod/lmod/modulefiles
++ MODULEPATH=/usr/local/ngseq/etc/modules:/usr/local/ngseq/etc/modules:/etc/fgcz-envmods/lmod:/etc/lmod/modules:/usr/share/lmod/lmod/modulefiles
++ source /usr/share/lmod/lmod/init/profile
+++ '[' -z '' ']'
+++ LMOD_ALLOW_ROOT_USE=yes
+++ '[' -n '' ']'
+++ '[' yes '!=' yes ']'
+++ '[' -z /usr/share/modulefiles ']'
+++ findExec READLINK_CMD /bin/readlink readlink
+++ Nm=READLINK_CMD
+++ confPath=/bin/readlink
+++ execNm=readlink
+++ eval READLINK_CMD=/bin/readlink
++++ READLINK_CMD=/bin/readlink
+++ '[' '!' -x /bin/readlink ']'
+++ unset Nm confPath execNm
+++ findExec PS_CMD /bin/ps ps
+++ Nm=PS_CMD
+++ confPath=/bin/ps
+++ execNm=ps
+++ eval PS_CMD=/bin/ps
++++ PS_CMD=/bin/ps
+++ '[' '!' -x /bin/ps ']'
+++ unset Nm confPath execNm
+++ findExec EXPR_CMD /usr/bin/expr expr
+++ Nm=EXPR_CMD
+++ confPath=/usr/bin/expr
+++ execNm=expr
+++ eval EXPR_CMD=/usr/bin/expr
++++ EXPR_CMD=/usr/bin/expr
+++ '[' '!' -x /usr/bin/expr ']'
+++ unset Nm confPath execNm
+++ findExec BASENAME_CMD /usr/bin/basename basename
+++ Nm=BASENAME_CMD
+++ confPath=/usr/bin/basename
+++ execNm=basename
+++ eval BASENAME_CMD=/usr/bin/basename
++++ BASENAME_CMD=/usr/bin/basename
+++ '[' '!' -x /usr/bin/basename ']'
+++ unset Nm confPath execNm
+++ unset -f findExec
+++ '[' -f /proc/3572097/exe ']'
++++ /bin/readlink /proc/3572097/exe
+++ my_shell=/usr/bin/bash
++++ /usr/bin/expr /usr/bin/bash : '-*\(.*\)'
+++ my_shell=/usr/bin/bash
++++ /usr/bin/basename /usr/bin/bash
+++ my_shell=bash
+++ case ${my_shell} in
+++ '[' -f /usr/share/lmod/lmod/init/bash ']'
+++ . /usr/share/lmod/lmod/init/bash
++++ '[' -z '' ']'
++++ case "$-" in
++++ __lmod_vx=x
++++ '[' -n x ']'
++++ set +x
Shell debugging temporarily silenced: export LMOD_SH_DBG_ON=1 for this output (/usr/share/lmod/lmod/init/bash)
Shell debugging restarted
++++ unset __lmod_vx
+++ unset my_shell PS_CMD EXPR_CMD BASENAME_CMD MODULEPATH_INIT LMOD_ALLOW_ROOT_USE READLINK_CMD
++ export NGSEQ=/usr/local/ngseq
++ NGSEQ=/usr/local/ngseq
++ export ngsrc=/usr/local/ngseq/srcm
++ ngsrc=/usr/local/ngseq/srcm
++ export ngpkg=/usr/local/ngseq/packages
++ ngpkg=/usr/local/ngseq/packages
++ export ngmdf=/usr/local/ngseq/etc/modules
++ ngmdf=/usr/local/ngseq/etc/modules
++ '[' -d /usr/local/ngseq/. ']'
++ PATH=/usr/local/ngseq/bin:/home/trxcopy/.conda/envs/gi_sushi_jobmanager_2024/bin:/misc/ngseq12/miniforge3/condabin:/usr/local/ngseq/packages/Dev/Ruby/3.3.7/bin:/usr/local/ngseq/bin:/usr/local/bin:/usr/bin:/bin:/usr/local/games:/usr/games
++ export PATH
++ LD_LIBRARY_PATH=/usr/local/ngseq/lib:/usr/local/ngseq/lib:/usr/local/ngseq/lib
++ export LD_LIBRARY_PATH
++ alias 'lmodInit=. /usr/local/ngseq/etc/lmod_profile'
+ module add Assembly/Canu/2.2 Dev/R/4.5.0 Dev/jdk/21
+ local __lmod_my_status
+ local __lmod_sh_dbg
+ '[' -z '' ']'
+ case "$-" in
+ __lmod_sh_dbg=x
+ '[' -n x ']'
+ set +x
Shell debugging temporarily silenced: export LMOD_SH_DBG_ON=1 for Lmod's output
Shell debugging restarted
+ return 0
+ R --vanilla --slave
Loading required package: data.table
Loading required package: Biostrings
Loading required package: BiocGenerics
Loading required package: generics
Attaching package: ‘generics’
The following objects are masked from ‘package:base’:
as.difftime, as.factor, as.ordered, intersect, is.element, setdiff,
setequal, union
Attaching package: ‘BiocGenerics’
The following objects are masked from ‘package:stats’:
IQR, mad, sd, var, xtabs
The following objects are masked from ‘package:base’:
anyDuplicated, aperm, append, as.data.frame, basename, cbind,
colnames, dirname, do.call, duplicated, eval, evalq, Filter, Find,
get, grep, grepl, is.unsorted, lapply, Map, mapply, match, mget,
order, paste, pmax, pmax.int, pmin, pmin.int, Position, rank,
rbind, Reduce, rownames, sapply, saveRDS, table, tapply, unique,
unsplit, which.max, which.min
Loading required package: S4Vectors
Loading required package: stats4
Attaching package: ‘S4Vectors’
The following objects are masked from ‘package:data.table’:
first, second
The following object is masked from ‘package:utils’:
findMatches
The following objects are masked from ‘package:base’:
expand.grid, I, unname
Loading required package: IRanges
Attaching package: ‘IRanges’
The following object is masked from ‘package:data.table’:
shift
Loading required package: XVector
Loading required package: GenomeInfoDb
Attaching package: ‘Biostrings’
The following object is masked from ‘package:base’:
strsplit
Loading required package: GenomicRanges
Loading required package: tidyverse
── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr 1.1.4 ✔ readr 2.1.5
✔ forcats 1.0.0 ✔ stringr 1.5.1
✔ ggplot2 3.5.2 ✔ tibble 3.2.1
✔ lubridate 1.9.4 ✔ tidyr 1.3.1
✔ purrr 1.0.4
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ lubridate::%within%() masks IRanges::%within%()
✖ dplyr::between() masks data.table::between()
✖ dplyr::collapse() masks Biostrings::collapse(), IRanges::collapse()
✖ dplyr::combine() masks BiocGenerics::combine()
✖ purrr::compact() masks XVector::compact()
✖ dplyr::desc() masks IRanges::desc()
✖ tidyr::expand() masks S4Vectors::expand()
✖ dplyr::filter() masks stats::filter()
✖ dplyr::first() masks S4Vectors::first(), data.table::first()
✖ lubridate::hour() masks data.table::hour()
✖ lubridate::isoweek() masks data.table::isoweek()
✖ dplyr::lag() masks stats::lag()
✖ dplyr::last() masks data.table::last()
✖ lubridate::mday() masks data.table::mday()
✖ lubridate::minute() masks data.table::minute()
✖ lubridate::month() masks data.table::month()
✖ ggplot2::Position() masks BiocGenerics::Position(), base::Position()
✖ lubridate::quarter() masks data.table::quarter()
✖ purrr::reduce() masks GenomicRanges::reduce(), IRanges::reduce()
✖ dplyr::rename() masks S4Vectors::rename()
✖ lubridate::second() masks S4Vectors::second(), data.table::second()
✖ lubridate::second<-() masks S4Vectors::second<-()
✖ dplyr::slice() masks XVector::slice(), IRanges::slice()
✖ purrr::transpose() masks data.table::transpose()
✖ lubridate::wday() masks data.table::wday()
✖ lubridate::week() masks data.table::week()
✖ lubridate::yday() masks data.table::yday()
✖ lubridate::year() masks data.table::year()
ℹ Use the conflicted package () to force all conflicts to become errors
unknown param: partition
unknown param: sushi_app
unknown param: isLastJob
-- canu 2.2
--
-- CITATIONS
--
-- For 'standard' assemblies of PacBio or Nanopore reads:
-- Koren S, Walenz BP, Berlin K, Miller JR, Phillippy AM.
-- Canu: scalable and accurate long-read assembly via adaptive k-mer weighting and repeat separation.
-- Genome Res. 2017 May;27(5):722-736.
-- http://doi.org/10.1101/gr.215087.116
--
-- Read and contig alignments during correction and consensus use:
-- Šošic M, Šikic M.
-- Edlib: a C/C ++ library for fast, exact sequence alignment using edit distance.
-- Bioinformatics. 2017 May 1;33(9):1394-1395.
-- http://doi.org/10.1093/bioinformatics/btw753
--
-- Overlaps are generated using:
-- Berlin K, et al.
-- Assembling large genomes with single-molecule sequencing and locality-sensitive hashing.
-- Nat Biotechnol. 2015 Jun;33(6):623-30.
-- http://doi.org/10.1038/nbt.3238
--
-- Myers EW, et al.
-- A Whole-Genome Assembly of Drosophila.
-- Science. 2000 Mar 24;287(5461):2196-204.
-- http://doi.org/10.1126/science.287.5461.2196
--
-- Corrected read consensus sequences are generated using an algorithm derived from FALCON-sense:
-- Chin CS, et al.
-- Phased diploid genome assembly with single-molecule real-time sequencing.
-- Nat Methods. 2016 Dec;13(12):1050-1054.
-- http://doi.org/10.1038/nmeth.4035
--
-- Contig consensus sequences are generated using an algorithm derived from pbdagcon:
-- Chin CS, et al.
-- Nonhybrid, finished microbial genome assemblies from long-read SMRT sequencing data.
-- Nat Methods. 2013 Jun;10(6):563-9
-- http://doi.org/10.1038/nmeth.2474
--
-- CONFIGURE CANU
--
-- Detected Java(TM) Runtime Environment '21.0.4' (from '/usr/local/ngseq/packages/Dev/jdk/21/bin/java') without -d64 support.
--
-- WARNING:
-- WARNING: Failed to run gnuplot using command 'gnuplot'.
-- WARNING: Plots will be disabled.
-- WARNING:
--
--
-- Detected 8 CPUs and 30720 gigabytes of memory on the local machine.
--
-- Detected Slurm with 'sinfo' binary in /usr/bin/sinfo.
-- Slurm disabled by useGrid=false
--
-- Local machine mode enabled; grid support not detected or not allowed.
--
-- Job limits:
-- 30 gigabytes memory (maxMemory option).
-- 8 CPUs (maxThreads option).
--
-- (tag)Concurrency
-- (tag)Threads |
-- (tag)Memory | |
-- (tag) | | | total usage algorithm
-- ------- ---------- -------- -------- -------------------- -----------------------------
-- Local: meryl 12.000 GB 4 CPUs x 2 jobs 24.000 GB 8 CPUs (k-mer counting)
-- Local: hap 8.000 GB 4 CPUs x 2 jobs 16.000 GB 8 CPUs (read-to-haplotype assignment)
-- Local: cormhap 6.000 GB 8 CPUs x 1 job 6.000 GB 8 CPUs (overlap detection with mhap)
-- Local: obtovl 4.000 GB 8 CPUs x 1 job 4.000 GB 8 CPUs (overlap detection)
-- Local: utgovl 4.000 GB 8 CPUs x 1 job 4.000 GB 8 CPUs (overlap detection)
-- Local: cor -.--- GB 4 CPUs x - jobs -.--- GB - CPUs (read correction)
-- Local: ovb 4.000 GB 1 CPU x 7 jobs 28.000 GB 7 CPUs (overlap store bucketizer)
-- Local: ovs 8.000 GB 1 CPU x 3 jobs 24.000 GB 3 CPUs (overlap store sorting)
-- Local: red 15.000 GB 4 CPUs x 2 jobs 30.000 GB 8 CPUs (read error detection)
-- Local: oea 8.000 GB 1 CPU x 3 jobs 24.000 GB 3 CPUs (overlap error adjustment)
-- Local: bat 16.000 GB 4 CPUs x 1 job 16.000 GB 4 CPUs (contig construction with bogart)
-- Local: cns -.--- GB 4 CPUs x - jobs -.--- GB - CPUs (consensus)
--
-- Found untrimmed raw PacBio CLR reads in the input files.
--
-- Generating assembly 'mut22' in '/scratch/o35755_Canu_2025-09-03--15-03-37_mut22_temp3572097/mut22':
-- genomeSize:
-- 5000000
--
-- Overlap Generation Limits:
-- corOvlErrorRate 0.2400 ( 24.00%)
-- obtOvlErrorRate 0.0450 ( 4.50%)
-- utgOvlErrorRate 0.0450 ( 4.50%)
--
-- Overlap Processing Limits:
-- corErrorRate 0.2500 ( 25.00%)
-- obtErrorRate 0.0450 ( 4.50%)
-- utgErrorRate 0.0450 ( 4.50%)
-- cnsErrorRate 0.0750 ( 7.50%)
--
-- Stages to run:
-- correct raw reads.
-- trim corrected reads.
-- assemble corrected and trimmed reads.
--
--
-- BEGIN CORRECTION
----------------------------------------
-- Starting command on Wed Sep 3 15:03:57 2025 with 520.484 GB free disk space
cd .
./mut22.seqStore.sh \
> ./mut22.seqStore.err 2>&1
-- Finished on Wed Sep 3 15:03:57 2025 (fast as lightning) with 520.484 GB free disk space
----------------------------------------
--
-- ERROR: Read coverage (0) lower than allowed.
-- ERROR: minInputCoverage = 10
-- ERROR:
-- ERROR: This could be caused by an incorrect genomeSize.
-- ERROR:
-- ERROR: You can force Canu to continue by decreasing parameter
-- ERROR: minInputCoverage. Be warned that the quality of corrected
-- ERROR: reads and/or contiguity of contigs will be poor.
--
ABORT:
ABORT: canu 2.2
ABORT: Don't panic, but a mostly harmless error occurred and Canu stopped.
ABORT: Try restarting. If that doesn't work, ask for help.
ABORT:
Error in ezSystem(cmd) :
canu -p mut22 -d mut22 genomeSize=5000k maxMemory=30 maxThreads=8 useGrid=false -pacbio-raw /srv/GT/analysis/course_sushi/public/gstore/projects/p1001/ventricles_100k/MutantSample_2_R1.fastq.gz 1> mut22_canu.log
failed
Calls: -> withCallingHandlers -> runMethod -> ezSystem
error exists: gxtx_data_mngt@fgcz.system
mail sent to: gxtx_data_mngt@fgcz.system
Execution halted
___STDERR_END___