config: updated GDB

config/GDB/config.yaml

@@ -3,9 +3,9 @@
 
 # Steps to be done
 # steps: ["preprocessing", "assembly", "mapping", "annotation", "analysis", "taxonomy"]
-steps: ["preprocessing"]
-steps_annotation: ["diamond", "rgi", "plasflow", "minced", "barrnap"] # prodigal is run in any case
-steps_analysis: ["quast", "cdhit", "mash_dist"]
+steps: ["preprocessing", "assembly", "polishing"]
+steps_annotation: ["rgi", "plasflow", "minced", "barrnap"] # prodigal is run in any case
+steps_analysis: ["quast", "cdhit", "diamond", "mash"]
 steps_taxonomy: ["kraken2", "kaiju"]
 
 ############################################################
@@ -49,9 +49,7 @@ data:
 ##############################
 # Preprocessing
 
-# TODO: installation ???
-# Preprocessing: LR: Basecalling
-# XXX
+# https://community.nanoporetech.com/protocols/Guppy-protocol/v/GPB_2003_v1_revT_14Dec2018
 guppy:
     config: "dna_r9.4.1_450bps_modbases_dam-dcm-cpg_hac.cfg"
     gpu:
@@ -66,49 +64,31 @@ guppy:
         gpu_device: "cuda:0"
         threads: 20
 
-# Preprocessing: SR
 # https://github.com/OpenGene/fastp
 fastp:
     threads: 10
     min_length: 40
 
-# FastQ QC
 # https://www.bioinformatics.babraham.ac.uk/projects/fastqc/
 fastqc:
     threads: 10
-    params: "-q -f fastq"
 
 ##############################
 # Assembly
 
 # List of assemblers for different read types: assembler names MUST be UNIQUE
-# Allowed values:
-#   SR: megahit, metaspades
-#   Hy: metaspadeshybrid (metaspades w/ LR), operams
-#   LR: flye, wtdbg2, canu
-#   HyHy: imp3 (IMP3 assembly using LR and SR from metaT and metaG), assembly is not part of the pipeline
-#   Polishing w/ SR: suffix "_sr" for hybrid and LR assemblers
 assemblers:
     sr: ["megahit", "metaspades"]
-    lr: ["flye", "wtdbg2", "canu", "flye_sr", "wtdbg2_sr", "canu_sr"]
-    hy: ["metaspadeshybrid", "operams", "metaspadeshybrid_sr", "operams_sr"]
-    hyhy: ["imp3"]
+    lr: ["flye", "canu"]
+    hy: ["metaspadeshybrid", "operamsmegahit", "operamsmetaspades"]
 
 # https://github.com/fenderglass/Flye
 flye:
     threads: 10
-    genome_size: "1g"
-
-# https://github.com/ruanjue/wtdbg2
-wtdbg2:
-    threads: 10
-    bin: "/scratch/users/sbusi/tools/wtdbg2/"
-    genome_size: "1g"
 
 # https://canu.readthedocs.io/en/latest/
 canu:
     threads: 24
-    # mem: "64g"
     genome_size: "1g"
 
 # https://github.com/ablab/spades
@@ -119,14 +99,12 @@ metaspades:
 megahit:
     threads: 10
 
-# TODO: installation
 # https://github.com/CSB5/OPERA-MS
 operams:
     threads: 10
-    bin: "/home/users/sbusi/apps/miniconda3/envs/operams/OPERA-MS/OPERA-MS.pl"
 
 ##############################
-# Long-read assembly polishing
+# Assembly polishing
 
 # https://nanoporetech.github.io/medaka/index.html
 medaka:
@@ -140,14 +118,10 @@ racon:
 ##############################
 # Mapping
 
-# Mapper
 # http://bio-bwa.sourceforge.net/
 bwa:
     threads: 10
-    long_reads_index:
-        opts: "-aY -A 5 -B 11 -O 2,1 -E 4,3 -k 8 -W 16 -w 40 -r 1 -D 0 -y 20 -L 30,30 -T 2.5"
 
-# SAM utils
 # http://www.htslib.org/doc/samtools.html
 samtools:
     sort:
@@ -157,35 +131,28 @@ samtools:
 ##############################
 # Annotation
 
-# Sequence search
 # https://github.com/bbuchfink/diamond
 diamond:
     threads: 20
     db: "nr_uniprot_trembl.dmnd" # file name in "dbs" folder
 
-# CRISPR
 # https://github.com/dnasko/CASC
 casc:
     threads: 10
 
-# CRISPR
 # https://github.com/ctSkennerton/minced
 # minced:
 
-# Plasmid prediction
 # https://github.com/smaegol/PlasFlow
-plasflow:
-    threshold: 0.7 # class. prob. threshold
-    minlen: 1000 # rm contigs with length below this threshold
+# plasflow:
+#     threshold: 0.7 # class. prob. threshold
+#     minlen: 1000 # rm contigs with length below this threshold
 
-# AMR prediction
 # https://github.com/arpcard/rgi
 rgi:
     threads: 5
     db_url: "https://card.mcmaster.ca/latest/data"
-    alignment_tool: "DIAMOND"
 
-# rRNA genes prediction
 # https://github.com/tseemann/barrnap
 barrnap:
     threads: 5
@@ -221,17 +188,17 @@ bbmap:
 quast:
     threads: 10
 
-# Sequence search and clustering
-# https://github.com/soedinglab/MMseqs2
-# mmseqs2:
-    # threads: 30
-    # createdb: "--dbtype 2 --shuffle -v"
-    # easycluster: "--kmer-per-seq-scale 0.5 --cov-mode 0 -c 0.5 --min-seq-id 0.9"
-    # easylinclust: "--kmer-per-seq-scale 0.5 --cov-mode 0 -c 0.5 --min-seq-id 0.9"
-    # path: "/home/users/sbusi/apps/mmseqs/bin"
-    # createdb: "/home/users/sbusi/apps/mmseqs/bin/mmseqs createdb"
-    # rbh: "/home/users/sbusi/apps/mmseqs/bin/mmseqs rbh"
-    # convertalis: "/home/users/sbusi/apps/mmseqs/bin/mmseqs convertalis"
+# https://github.com/marbl/mash
+mash:
+    threads: 10
+
+# https://github.com/marbl/MashMap
+mashmap:
+    threads: 10
+
+# https://github.com/ParBLiSS/FastANI
+fastani:
+    threads: 10
 
 ##############################
 # Taxonomy
@@ -242,10 +209,6 @@ kraken2:
     threads: 10
     db: # dir. name in "dbs" folder
         maxikraken: "maxikraken2_1903_140GB"
-    class:
-        sr: "--gzip-compressed --paired"
-        lr: ""
-        contigs: ""
 
 # http://kaiju.binf.ku.dk/
 # http://kaiju.binf.ku.dk/server
@@ -257,33 +220,6 @@ kaiju:
         kaiju_db_nr_euk: "kaiju_db_nr_euk_2020-05-25"
     ranks: ["phylum", "class", "order", "family", "genus", "species"]
 
-# XXX
+# https://github.com/Ecogenomics/GTDBTk
 GTDBTK: # dir. name in "dbs" folder
     DATA: "gtdbtk_release89"
-
-##############################
-# MISC
-
-# https://github.com/marbl/mash
-mash:
-    threads: 10
-
-##############################
-# Binning
-
-# DAS_Tool:
-#     path: "/home/users/sbusi/apps/DAS_Tool-master"
-#     bin: "/home/users/sbusi/apps/DAS_Tool-master/src/"
-#     db: "/home/users/sbusi/apps/DAS_Tool-master/db/"
-#     Rscript: "/home/users/sbusi/apps/miniconda3/envs/dastool/bin/"
-# # Rscript: "/home/users/sbusi/apps/miniconda3/envs/dastool/bin/"
-# # dastool_database: "/home/users/sbusi/apps/DAS_Tool-master/db/"
-
-##############################
-# ???
-# nonpareil:
-#     memory: 4096
-#     threads: 14
-
-# rebaler:
-#     threads: 28

config/GDB/sbatch.sh

@@ -18,6 +18,6 @@ ONTP_SLURM="config/GDB/slurm.yaml"
 ONTP_CLUSTER="sbatch -p {cluster.partition} -q {cluster.qos} {cluster.explicit} -N {cluster.nodes} -n {cluster.n} -c {threads} -t {cluster.time} --job-name={cluster.job-name}"
 
 conda activate ${ONTP_ENV} && \
-snakemake -s workflow/Snakefile -rp --jobs 10 --local-cores 1 \
+snakemake -s workflow/Snakefile -rp --jobs 5 --local-cores 1 \
 --configfile ${ONTP_CONFIG} --use-conda --conda-prefix ${CONDA_PREFIX}/pipeline \
 --cluster-config ${ONTP_SLURM} --cluster "${ONTP_CLUSTER}"

config/GDB/slurm.yaml

@@ -28,7 +28,7 @@ fastp_sr:
     explicit: ""
 
 rm_rrna_bbmap:
-    time: "00-6:00:00"
+    time: "00-4:00:00"
     partition: "batch"
     qos: "qos-batch"
     nodes: 1
@@ -68,14 +68,6 @@ assembly_lr_flye:
     n: 1
     explicit: ""
 
-assembly_lr_wtdbg2:
-    time: "00-8:00:00"
-    partition: "bigmem"
-    qos: "qos-bigmem"
-    nodes: 1
-    n: 1
-    explicit: ""
-
 assembly_lr_canu:
     time: "05-00:00:00"
     partition: "bigmem"
@@ -109,17 +101,35 @@ assembly_hy_metaspades:
     explicit: ""
 
 assembly_hy_operams:
-    time: "00-4:00:00"
+    time: "00-12:00:00"
     partition: "bigmem"
     qos: "qos-bigmem"
     nodes: 1
     n: 1
     explicit: ""
 
-filter_contigs:
-    time: "00-00:30:00"
-    partition: "batch"
-    qos: "qos-batch"
+# Assembly polishing
+
+polishing_racon_lr:
+    time: "00-6:00:00"
+    partition: "bigmem"
+    qos: "qos-bigmem"
+    nodes: 1
+    n: 1
+    explicit: ""
+
+polishing_racon_sr:
+    time: "00-6:00:00"
+    partition: "bigmem"
+    qos: "qos-bigmem"
+    nodes: 1
+    n: 1
+    explicit: ""
+
+polishing_medaka_lr:
+    time: "01-00:00:00"
+    partition: "bigmem"
+    qos: "qos-bigmem"
     nodes: 1
     n: 1
     explicit: ""
@@ -173,23 +183,6 @@ mapping_bwa_mem_assembly_hyhy:
     n: 1
     explicit: ""
 
-# Assembly polishing
-polishing_racon_lr:
-    time: "00-18:00:00"
-    partition: "bigmem"
-    qos: "qos-bigmem"
-    nodes: 1
-    n: 1
-    explicit: ""
-
-polishing_racon_sr:
-    time: "00-18:00:00"
-    partition: "bigmem"
-    qos: "qos-bigmem"
-    nodes: 1
-    n: 1
-    explicit: ""
-
 # Annotation
 annotation_prodigal:
     time: "00-2:00:00"