diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000000000000000000000000000000000000..112189a0a6a312add8be1f3a52ad5d3f87026b5f
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,7 @@
+figures/output/**
+figures/data/nanostats_summary.tsv
+figures/data/crispr_summary.tsv
+**/.snakemake/
+slurm-*.out
+*.tmp
+*.log
\ No newline at end of file
diff --git a/2019_GDB/config/CONFIG.yaml b/2019_GDB/config/CONFIG.yaml
index aab8911bf4efe9daef1f357fbf111082335ffbd0..ee71f60ae41e9575d056363f158c8e7a1093e954 100755
--- a/2019_GDB/config/CONFIG.yaml
+++ b/2019_GDB/config/CONFIG.yaml
@@ -1,13 +1,23 @@
-# steps: "assembly_annotation mapping metaT mmseq binning taxonomy analysis"
-steps: "binning taxonomy analysis"
+steps: ["assembly_annotation", "mapping", "metaT", "mmseq", "binning", "taxonomy", "analysis"]
+
+# analysis_steps: ["cdhit", "mappability", "crispr", "plasmids", "amr"]
+analysis_steps: ["cdhit", "mappability", "crispr", "plasmids", "amr"]
+
+# working directory containing all relevant data,
+# i.e. prefix for data, results, DBs etc.
+work_dir: "/scratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB"
data_dir: "data"
results_dir: "results"
db_dir: "dbs"
+
runs:
first: "S1_SizeSelected"
second: "S3_Gtube"
# third: "20181108_0827_test"
-assemblers: ["flye"]
+
+# assemblers: ["flye"]
+assemblers: ["flye", "megahit", "metaspades", "metaspades_hybrid"]
+
p7zip:
bin: "/home/users/claczny/apps/software/p7zip_16.02/bin/7za"
threads: 4
@@ -18,8 +28,10 @@ ont_fast5_api:
threads: 8
flowcell: "FLO-MIN106"
kit: "SQK-LSK109"
+
#barcodes: ["barcode06", "barcode07", "barcode08", "barcode09", "barcode10"]
barcodes: ["no_barcode"]
+
guppy_cpu:
path: "/scratch/users/claczny/ont/apps/software/ont-guppy-cpu-3.1.5_linux64/bin"
bin: "/scratch/users/claczny/ont/apps/software/ont-guppy-cpu-3.1.5_linux64/bin/guppy_basecaller"
@@ -45,10 +57,13 @@ guppy_barcoder:
version: "3.4.5+fb1fbfb"
records_per_fastq: 8000
threads: 8
+
nanostats:
+
short_reads_prefix: "/scratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/data/raw/short_reads"
#short_reads_prefix: "/mnt/isilon/projects/lcsb_sequencing/transfer/bioecosystem/Rashi/2019/Apr/fastq"
metaT_prefix: "/scratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/data/metaT"
+
fastp:
min_length: 40
minimap2:
@@ -97,10 +112,9 @@ metaspades:
threads: 28
mmseq2:
threads: 24
+
# Define sample names
-#samples: ["flye", "megahit", "metaspades_hybrid"]
-# samples: ["flye", "megahit"]
-# samples: ["metaspades_hybrid"]
+samples: ["ONT3_MG_xx_Rashi_S11"]
binning_samples: ["flye", "megahit", "bwa_sr_metaspades_hybrid", "bwa_lr_metaspades_hybrid", "bwa_merged_metaspades_hybrid", "mmi_sr_metaspades_hybrid", "mmi_lr_metaspades_hybrid", "mmi_merged_metaspades_hybrid"]
# Hybrid assembler
@@ -120,10 +134,11 @@ kraken2_database: "/scratch/users/bkunath/Kraken2/maxikraken2_1903_140GB/"
# Path to DAS_Tool
DAS_Tool:
- path: "/home/users/sbusi/apps/DAS_Tool-master"
- bin: "/home/users/sbusi/apps/DAS_Tool-master/src/"
+ path: "/home/users/sbusi/apps/DAS_Tool-master"
+ bin: "/home/users/sbusi/apps/DAS_Tool-master/src/"
# Path to DAS_Tool database
+# TODO: mv to DAS_Tool
dastool_database: "/home/users/sbusi/apps/DAS_Tool-master/db/"
# Mapping options
@@ -145,18 +160,29 @@ GTDBTK:
DATA: "/home/users/sbusi/apps/db/gtdbtk/release89"
# Rscript path
+# TODO: mv to DAS_Tool
Rscript: "/home/users/sbusi/apps/miniconda3/envs/dastool/bin/"
+# XXX
mmseqs:
- 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"
+ 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"
-# Paths to CASC and minced for CRISPR
+# CRISPR
CASC:
PATH: "$PATH:/mnt/lscratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/crispr/bin"
PERL5LIB: "/mnt/lscratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/crispr/lib/site_perl"
-
minced:
PATH: "$PATH:/mnt/lscratch/users/sbusi/ONT/cedric_ont_basecalling/2019_GDB/crispr/minced/"
+
+# Plasmid prediction
+plasflow:
+ threshold: 0.7 # class. prob. threshold
+ minlen: 1000 # rm contigs with length below this threshold
+
+# AMR prediction
+rgi:
+ db_url: "https://card.mcmaster.ca/latest/data"
+ alignment_tool: "DIAMOND" # DIAMOND or BLAST
diff --git a/2019_GDB/envs/plasflow.yaml b/2019_GDB/envs/plasflow.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..ecce806232735d371ddb0e63b73190603af06c87
--- /dev/null
+++ b/2019_GDB/envs/plasflow.yaml
@@ -0,0 +1,90 @@
+channels:
+ # for PlasFlow
+ - smaegol
+ # rest
+ - bioconda
+ - conda-forge
+ - defaults
+dependencies:
+ - _libgcc_mutex=0.1=conda_forge
+ - _openmp_mutex=4.5=1_llvm
+ - _r-mutex=1.0.1=anacondar_1
+ - backports=1.0=py_2
+ - backports.weakref=1.0rc1=py35_1
+ - bioconductor-biocgenerics=0.22.0=r3.3.2_0
+ - bioconductor-biostrings=2.42.1=r3.3.2_0
+ - bioconductor-iranges=2.8.2=r3.3.2_0
+ - bioconductor-s4vectors=0.12.2=r3.3.2_0
+ - bioconductor-xvector=0.14.1=r3.3.2_0
+ - bioconductor-zlibbioc=1.20.0=r3.3.2_1
+ - biopython=1.68=py35_0
+ - blas=2.16=openblas
+ - bleach=1.5.0=py35_0
+ - bzip2=1.0.8=h516909a_2
+ - ca-certificates=2020.4.5.1=hecc5488_0
+ - cairo=1.14.6=4
+ - certifi=2018.8.24=py35_1001
+ - curl=7.52.1=0
+ - fontconfig=2.12.1=6
+ - freetype=2.7=1
+ - gettext=0.19.8.1=hc5be6a0_1002
+ - glib=2.51.4=0
+ - graphite2=1.3.13=he1b5a44_1001
+ - gsl=2.6=h294904e_0
+ - harfbuzz=1.4.3=0
+ - html5lib=0.9999999=py35_0
+ - icu=58.2=hf484d3e_1000
+ - jpeg=9c=h14c3975_1001
+ - libblas=3.8.0=16_openblas
+ - libcblas=3.8.0=16_openblas
+ - libffi=3.2.1=he1b5a44_1007
+ - libgcc=7.2.0=h69d50b8_2
+ - libgcc-ng=9.2.0=h24d8f2e_2
+ - libgfortran-ng=7.3.0=hdf63c60_5
+ - libiconv=1.15=h516909a_1006
+ - liblapack=3.8.0=16_openblas
+ - liblapacke=3.8.0=16_openblas
+ - libopenblas=0.3.9=h5ec1e0e_0
+ - libpng=1.6.28=1
+ - libstdcxx-ng=9.2.0=hdf63c60_2
+ - libtiff=4.0.7=0
+ - libxml2=2.9.5=0
+ - llvm-openmp=10.0.0=hc9558a2_0
+ - markdown=3.2.1=py_0
+ - mmtf-python=1.0.2=py35_0
+ - mock=2.0.0=py35_0
+ - msgpack-python=0.5.6=py35h2d50403_3
+ - ncurses=5.9=10
+ - numpy=1.15.2=py35h99e49ec_0
+ - numpy-base=1.15.2=py35h2f8d375_0
+ - olefile=0.46=py_0
+ - openssl=1.0.2u=h516909a_0
+ - pandas=0.23.4=py35hf8a1672_0
+ - pango=1.40.4=0
+ - pbr=5.4.2=py_0
+ - pcre=8.44=he1b5a44_0
+ - pillow=4.3.0=py35_0
+ - pip=20.0.2=py_2
+ - pixman=0.34.0=h14c3975_1003
+ - protobuf=3.4.0=py35_0
+ - python=3.5.4=0
+ - python-dateutil=2.8.1=py_0
+ - pytz=2019.3=py_0
+ - r-base=3.3.2=5
+ - readline=6.2=0
+ - reportlab=3.4.0=py35_0
+ - rpy2=2.7.8=py35r3.3.2_1
+ - scikit-learn=0.20.0=py35h22eb022_1
+ - scipy=1.1.0=py35he2b7bc3_1
+ - setuptools=40.4.3=py35_0
+ - six=1.14.0=py_1
+ - sqlite=3.13.0=1
+ - tensorflow=1.3.0=py35_0
+ - tk=8.5.19=2
+ - webencodings=0.5.1=py_1
+ - werkzeug=1.0.1=pyh9f0ad1d_0
+ - wheel=0.34.2=py_1
+ - xz=5.2.5=h516909a_0
+ - zlib=1.2.8=3
+ # PlasFlow: should be installed from smaegol, NOT from pip
+ - plasflow=1.1.0
diff --git a/2019_GDB/envs/rgi.yaml b/2019_GDB/envs/rgi.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..ad8e7f7fe6c0d133aaf98add13916b798eb2787f
--- /dev/null
+++ b/2019_GDB/envs/rgi.yaml
@@ -0,0 +1,139 @@
+channels:
+ - conda-forge
+ - bioconda
+ - defaults
+dependencies:
+ - _libgcc_mutex=0.1=conda_forge
+ - _openmp_mutex=4.5=1_llvm
+ - bamtools=2.5.1=he860b03_5
+ - bedtools=2.29.2=hc088bd4_0
+ - biopython=1.72=py36h14c3975_1000
+ - blast=2.9.0=pl526h3066fca_4
+ - bowtie2=2.3.5.1=py36he513fc3_0
+ - bwa=0.7.17=hed695b0_7
+ - bzip2=1.0.8=h516909a_2
+ - ca-certificates=2020.4.5.1=hecc5488_0
+ - certifi=2020.4.5.1=py36h9f0ad1d_0
+ - curl=7.69.1=h33f0ec9_0
+ - cycler=0.10.0=py_2
+ - diamond=0.8.36=h8b12597_4
+ - entrez-direct=13.3=pl526h375a9b1_0
+ - expat=2.2.9=he1b5a44_2
+ - filetype=1.0.7=pyh9f0ad1d_0
+ - freetype=2.10.2=he06d7ca_0
+ - htslib=1.9=h4da6232_3
+ - icu=64.2=he1b5a44_1
+ - kiwisolver=1.2.0=py36hdb11119_0
+ - krb5=1.17.1=h2fd8d38_0
+ - ld_impl_linux-64=2.34=h53a641e_4
+ - libblas=3.8.0=16_openblas
+ - libcblas=3.8.0=16_openblas
+ - libcurl=7.69.1=hf7181ac_0
+ - libdeflate=1.6=h516909a_0
+ - libedit=3.1.20191231=h46ee950_0
+ - libffi=3.2.1=he1b5a44_1007
+ - libgcc-ng=9.2.0=h24d8f2e_2
+ - libgfortran-ng=7.5.0=hdf63c60_6
+ - liblapack=3.8.0=16_openblas
+ - libopenblas=0.3.9=h5ec1e0e_0
+ - libpng=1.6.37=hed695b0_1
+ - libssh2=1.9.0=hab1572f_2
+ - libstdcxx-ng=9.2.0=hdf63c60_2
+ - llvm-openmp=10.0.0=hc9558a2_0
+ - matplotlib-base=3.2.1=py36hb8e4980_0
+ - ncurses=6.1=hf484d3e_1002
+ - numpy=1.18.4=py36h7314795_0
+ - oligoarrayaux=3.8=hc9558a2_0
+ - openssl=1.1.1g=h516909a_0
+ - pandas=1.0.4=py36h830a2c2_0
+ - patsy=0.5.1=py_0
+ - pcre=8.44=he1b5a44_0
+ - perl=5.26.2=h516909a_1006
+ - perl-app-cpanminus=1.7044=pl526_1
+ - perl-archive-tar=2.32=pl526_0
+ - perl-base=2.23=pl526_1
+ - perl-business-isbn=3.004=pl526_0
+ - perl-business-isbn-data=20140910.003=pl526_0
+ - perl-carp=1.38=pl526_3
+ - perl-common-sense=3.74=pl526_2
+ - perl-compress-raw-bzip2=2.087=pl526he1b5a44_0
+ - perl-compress-raw-zlib=2.087=pl526hc9558a2_0
+ - perl-constant=1.33=pl526_1
+ - perl-data-dumper=2.173=pl526_0
+ - perl-digest-hmac=1.03=pl526_3
+ - perl-digest-md5=2.55=pl526_0
+ - perl-encode=2.88=pl526_1
+ - perl-encode-locale=1.05=pl526_6
+ - perl-exporter=5.72=pl526_1
+ - perl-exporter-tiny=1.002001=pl526_0
+ - perl-extutils-makemaker=7.36=pl526_1
+ - perl-file-listing=6.04=pl526_1
+ - perl-file-path=2.16=pl526_0
+ - perl-file-temp=0.2304=pl526_2
+ - perl-html-parser=3.72=pl526h6bb024c_5
+ - perl-html-tagset=3.20=pl526_3
+ - perl-html-tree=5.07=pl526_1
+ - perl-http-cookies=6.04=pl526_0
+ - perl-http-daemon=6.01=pl526_1
+ - perl-http-date=6.02=pl526_3
+ - perl-http-message=6.18=pl526_0
+ - perl-http-negotiate=6.01=pl526_3
+ - perl-io-compress=2.087=pl526he1b5a44_0
+ - perl-io-html=1.001=pl526_2
+ - perl-io-socket-ssl=2.066=pl526_0
+ - perl-io-zlib=1.10=pl526_2
+ - perl-json=4.02=pl526_0
+ - perl-json-xs=2.34=pl526h6bb024c_3
+ - perl-libwww-perl=6.39=pl526_0
+ - perl-list-moreutils=0.428=pl526_1
+ - perl-list-moreutils-xs=0.428=pl526_0
+ - perl-lwp-mediatypes=6.04=pl526_0
+ - perl-lwp-protocol-https=6.07=pl526_4
+ - perl-mime-base64=3.15=pl526_1
+ - perl-mozilla-ca=20180117=pl526_1
+ - perl-net-http=6.19=pl526_0
+ - perl-net-ssleay=1.88=pl526h90d6eec_0
+ - perl-ntlm=1.09=pl526_4
+ - perl-parent=0.236=pl526_1
+ - perl-pathtools=3.75=pl526h14c3975_1
+ - perl-scalar-list-utils=1.52=pl526h516909a_0
+ - perl-socket=2.027=pl526_1
+ - perl-storable=3.15=pl526h14c3975_0
+ - perl-test-requiresinternet=0.05=pl526_0
+ - perl-time-local=1.28=pl526_1
+ - perl-try-tiny=0.30=pl526_1
+ - perl-types-serialiser=1.0=pl526_2
+ - perl-uri=1.76=pl526_0
+ - perl-www-robotrules=6.02=pl526_3
+ - perl-xml-namespacesupport=1.12=pl526_0
+ - perl-xml-parser=2.44_01=pl526ha1d75be_1002
+ - perl-xml-sax=1.02=pl526_0
+ - perl-xml-sax-base=1.09=pl526_0
+ - perl-xml-sax-expat=0.51=pl526_3
+ - perl-xml-simple=2.25=pl526_1
+ - perl-xsloader=0.24=pl526_0
+ - pip=20.1.1=py_1
+ - prodigal=2.6.3=h516909a_2
+ - pyahocorasick=1.4.0=py36h8c4c3a4_1
+ - pyfaidx=0.5.8=py_1
+ - pyparsing=2.4.7=pyh9f0ad1d_0
+ - python=3.6.10=h8356626_1011_cpython
+ - python-dateutil=2.8.1=py_0
+ - python_abi=3.6=1_cp36m
+ - pytz=2020.1=pyh9f0ad1d_0
+ - readline=8.0=hf8c457e_0
+ - rgi=5.1.0=py_1
+ - samtools=1.9=h10a08f8_12
+ - scipy=1.4.1=py36h2d22cac_3
+ - seaborn=0.10.1=py_0
+ - setuptools=47.1.1=py36h9f0ad1d_0
+ - six=1.15.0=pyh9f0ad1d_0
+ - sqlite=3.30.1=hcee41ef_0
+ - statsmodels=0.11.1=py36h8c4c3a4_1
+ - tbb=2020.1=hc9558a2_0
+ - tk=8.6.10=hed695b0_0
+ - tornado=6.0.4=py36h8c4c3a4_1
+ - wheel=0.34.2=py_1
+ - xz=5.2.5=h516909a_0
+ - zlib=1.2.11=h516909a_1006
+
diff --git a/2019_GDB/envs/snakemake.yaml b/2019_GDB/envs/snakemake.yaml
index f6777ba72734cfc1b550a27bf4a7066179256100..b728fca61b3108cda90d81c0fcda0358a297957c 100755
--- a/2019_GDB/envs/snakemake.yaml
+++ b/2019_GDB/envs/snakemake.yaml
@@ -1,4 +1,4 @@
-name: snakemake
+name: ONT_pilot
channels:
- conda-forge
- bioconda
@@ -169,5 +169,3 @@ dependencies:
- zipp=2.1.0
- zlib=1.2.11
- zstd=1.4.4
-prefix: /home/users/sbusi/apps/miniconda3/envs/snakemake
-
diff --git a/2019_GDB/rules/ANALYSIS_RULES b/2019_GDB/rules/ANALYSIS_RULES
index 9e8b8cfc2baab4c8388e8c60cd6f16965d3fd4f4..67402f7bce2ab2bd4095fd66ff0fa0c98459a10d 100755
--- a/2019_GDB/rules/ANALYSIS_RULES
+++ b/2019_GDB/rules/ANALYSIS_RULES
@@ -6,22 +6,6 @@
# 5. CRISPRS - via 'minced' and 'CASC'
# 6. Plasmids
-import os
-from tempfile import TemporaryDirectory
-
-configfile: "config/CONFIG.yaml"
-DATA_DIR = config["data_dir"]
-RESULTS_DIR = config["results_dir"]
-DB_DIR=config["db_dir"]
-BARCODES=config["barcodes"]
-# ASSEMBLERS=config["assemblers"]
-MAPPERS=["bwa", "mmi"]
-# SAMPLES=config["samples"]
-SAMPLES=["ONT3_MG_xx_Rashi_S11"]
-BINNING_SAMPLES=config["binning_samples"]
-HYBRID_ASSEMBLER=config["hybrid_assembler"]
-
-
############################################
######## Partial_vs_unique_ORFs ############
############################################
@@ -190,3 +174,122 @@ rule minced:
date) &> >(tee {log})
"""
+############
+# PlasFlow #
+############
+# Filter input FASTA by seq. length
+rule plasflow_input:
+ input:
+ os.path.join(RESULTS_DIR, "assembly/{assembly}.fa")
+ output:
+ temp(os.path.join(RESULTS_DIR, "analysis/plasflow/{assembly}.fna"))
+ log:
+ os.path.join(RESULTS_DIR, "analysis/plasflow/{assembly}.fna.log")
+ params:
+ script=os.path.join(SRC_DIR, "filter_fasta_by_length.pl"),
+ minlen=config["plasflow"]["minlen"]
+ message:
+ "Plasmid prediction w/ PlasFlow: {input}"
+ shell:
+ # script from PathoFact
+ "{params.script} {params.minlen} {input} > {output} 2> {log}"
+
+# Run PlasFlow
+rule plasflow:
+ input:
+ os.path.join(RESULTS_DIR, "analysis/plasflow/{assembly}.fna")
+ output:
+ os.path.join(RESULTS_DIR, "analysis/plasflow/{assembly}.tsv")
+ log:
+ os.path.join(RESULTS_DIR, "analysis/plasflow/{assembly}.tsv.log")
+ params:
+ threshold=config["plasflow"]["threshold"]
+ conda:
+ os.path.join(ENV_DIR, "plasflow.yaml")
+ message:
+ "Plasmid prediction w/ PlasFlow: {input}"
+ shell:
+ "PlasFlow.py --input {input} --output {output}.tmp --threshold {params.threshold} &> {log} && "
+ "cut -f3,4,6- {output}.tmp > {output} && "
+ "rm {output}.tmp*"
+
+#######
+# RGI #
+#######
+# RGI input: proteins
+# NOTE: remove stop codon symbol "*"
+# NOTE: one rule per assembly to have a workaround for the issue with file paths
+# should be resolved properly later
+rule rgi_input_flye:
+ input:
+ os.path.abspath(os.path.join(RESULTS_DIR, "annotation/proteins/flye/lr/merged/no_barcode/assembly.faa"))
+ output:
+ temp(os.path.join(RESULTS_DIR, "analysis/rgi/flye.faa"))
+ shell:
+ "sed 's/\*$//' {input} > {output}"
+
+rule rgi_input_metaspades_hybrid:
+ input:
+ os.path.abspath(os.path.join(RESULTS_DIR, "annotation/proteins/metaspades_hybrid/lr_no_barcode-sr_ONT3_MG_xx_Rashi_S11/contigs.faa"))
+ output:
+ temp(os.path.join(RESULTS_DIR, "analysis/rgi/metaspades_hybrid.faa"))
+ shell:
+ "sed 's/\*$//' {input} > {output}"
+
+rule rgi_input_metaspades:
+ input:
+ os.path.abspath(os.path.join(RESULTS_DIR, "annotation/proteins/metaspades/ONT3_MG_xx_Rashi_S11/final.contigs.faa"))
+ output:
+ temp(os.path.join(RESULTS_DIR, "analysis/rgi/metaspades.faa"))
+ shell:
+ "sed 's/\*$//' {input} > {output}"
+
+rule rgi_input_megahit:
+ input:
+ os.path.abspath(os.path.join(RESULTS_DIR, "annotation/proteins/megahit/ONT3_MG_xx_Rashi_S11/final.contigs.faa"))
+ output:
+ temp(os.path.join(RESULTS_DIR, "analysis/rgi/megahit.faa"))
+ shell:
+ "sed 's/\*$//' {input} > {output}"
+
+# RGI DBs
+rule rgi_db:
+ output:
+ archive=temp(os.path.join(DB_DIR, "rgi/card-data.tar.bz2")),
+ json=os.path.join(DB_DIR, "rgi/card.json")
+ log:
+ os.path.join(DB_DIR, "rgi/rgi.log")
+ params:
+ db_url=config["rgi"]["db_url"]
+ message:
+ "Download RGI DB data"
+ shell:
+ "wget -O {output.archive} {params.db_url} --no-check-certificate &> {log} && "
+ "tar -C $(dirname {output.archive}) -xvf {output.archive} &>> {log}"
+
+# Run RGI: proteins
+rule rgi_prot:
+ input:
+ faa=os.path.join(RESULTS_DIR, "analysis/rgi/{assembly}.faa"),
+ db=os.path.join(DB_DIR, "rgi/card.json")
+ output:
+ os.path.join(RESULTS_DIR, "analysis/rgi/{assembly}.txt")
+ log:
+ os.path.join(RESULTS_DIR, "analysis/rgi/{assembly}.log")
+ threads: 10
+ params:
+ alignment_tool=config["rgi"]["alignment_tool"],
+ obname=lambda wildcards, output: os.path.splitext(output[0])[0]
+ conda:
+ os.path.join(ENV_DIR, "rgi.yaml")
+ message:
+ "AMR prediction w/ RGI: {input}"
+ shell:
+ # NOTE: to make sure that the correct DB is used
+ "rgi clean --local &> {log} && "
+ "rgi load --card_json {input.db} --local &>> {log} && "
+ "rgi database --version --local &>> {log} && "
+ # NOTE: https://github.com/arpcard/rgi/issues/93: KeyError: 'snp'
+ # need to run the CMD twice
+ "rgi main --input_sequence {input.faa} --output_file {params.obname} --input_type protein --local -a {params.alignment_tool} --clean -n {threads} &>> {log} || "
+ "rgi main --input_sequence {input.faa} --output_file {params.obname} --input_type protein --local -a {params.alignment_tool} --clean -n {threads} &>> {log}"
diff --git a/2019_GDB/rules/ASSEMBLY_ANNOTATION_RULES b/2019_GDB/rules/ASSEMBLY_ANNOTATION_RULES
index a3c1c5ad6bfb285ccce509d897491ce28df6fe86..1af624b0792a6756142270085e3bacb822a2eb86 100755
--- a/2019_GDB/rules/ASSEMBLY_ANNOTATION_RULES
+++ b/2019_GDB/rules/ASSEMBLY_ANNOTATION_RULES
@@ -1,26 +1,5 @@
# For running the ASSEMBLY and ANNOTATION workflow for ONT data
-import os
-from tempfile import TemporaryDirectory
-
-configfile: "config/CONFIG.yaml"
-DATA_DIR = config["data_dir"]
-RESULTS_DIR = config["results_dir"]
-DB_DIR=config["db_dir"]
-RUNS=[config["runs"]["first"],
- config["runs"]["second"]]
-# config["runs"]["third"]]
-BARCODES=config["barcodes"]
-SAMPLES=["ONT3_MG_xx_Rashi_S11"]
-sr_sample=["ONT3_MG_xx_Rashi_S11"]
-# SAMPLES_ALL=config["samples"]
-REFERENCES=["igc", "hg38"]
-IGC_URI=config["igc"]["uri"]
-HG38_URI=config["hg38"]["uri"]
-ASSEMBLERS=config["assemblers"]
-MAPPERS=["bwa_mem", "minimap2"]
-
-
######
# RULES
######
diff --git a/2019_GDB/rules/BINNING_RULES b/2019_GDB/rules/BINNING_RULES
index 0b38b5ca3cae6fec3c80ce5339bfe5754e0e6fc2..102adaa745ab032644a8a701eb1072f72da07f95 100755
--- a/2019_GDB/rules/BINNING_RULES
+++ b/2019_GDB/rules/BINNING_RULES
@@ -1,21 +1,5 @@
# Rules for BINNING workflow, i.e. generating MAGs from assemblies
-import os
-from tempfile import TemporaryDirectory
-
-configfile: "config/CONFIG.yaml"
-DATA_DIR = config["data_dir"]
-RESULTS_DIR = config["results_dir"]
-DB_DIR=config["db_dir"]
-BARCODES=config["barcodes"]
-ASSEMBLERS=config["assemblers"]
-MAPPERS=["bwa", "mmi"]
-#SAMPLES=config["samples"]
-SAMPLES=["flye", "megahit", "metaspades_hybrid"]
-BINNING_SAMPLES=config["binning_samples"]
-HYBRID_ASSEMBLER=config["hybrid_assembler"]
-
-
###################
# Preparing files #
###################
diff --git a/2019_GDB/rules/MAPPING_RULES b/2019_GDB/rules/MAPPING_RULES
index 0827a17e3002a22c9942fee6e9baeee8892a7282..83af0b7785c4dc8334457ca7b95e8c022f86b5a6 100755
--- a/2019_GDB/rules/MAPPING_RULES
+++ b/2019_GDB/rules/MAPPING_RULES
@@ -1,23 +1,5 @@
# Rule for running the mapping "workflow" for ONT analsyes
-#shell.executable("/bin/bash")
-#shell.prefix("source ~/.bashrc; ")
-import os
-from tempfile import TemporaryDirectory
-
-configfile: "config/CONFIG.yaml"
-DATA_DIR = config["data_dir"]
-RESULTS_DIR = config["results_dir"]
-DB_DIR=config["db_dir"]
-BARCODES=config["barcodes"]
-ASSEMBLERS=config["assemblers"]
-MAPPERS=["bwa", "mmi"]
-#SAMPLES=config["samples"]
-SAMPLES=["flye", "megahit", "metaspades_hybrid"]
-BINNING_SAMPLES=config["binning_samples"]
-HYBRID_ASSEMBLER=config["hybrid_assembler"]
-
-
#######################
## Mapping to hybrid ##
#######################
diff --git a/2019_GDB/rules/METAT_RULES b/2019_GDB/rules/METAT_RULES
index 636ea21c9649bfa82c31e132d14e56d9b5dca24f..157930ad403f26e60a1bddc302db83d62c1453ea 100755
--- a/2019_GDB/rules/METAT_RULES
+++ b/2019_GDB/rules/METAT_RULES
@@ -1,20 +1,5 @@
# Rules for mapping the metaT reads to the different assemblies
-import os
-from tempfile import TemporaryDirectory
-
-configfile: "config/CONFIG.yaml"
-DATA_DIR = config["data_dir"]
-RESULTS_DIR = config["results_dir"]
-DB_DIR=config["db_dir"]
-ASSEMBLERS=config["assemblers"]
-MAPPERS=["bwa", "mmi"]
-# SAMPLES=config["samples"]
-SAMPLES=["flye", "megathit", "metaspades_hybrid"]
-BINNING_SAMPLES=config["binning_samples"]
-HYBRID_ASSEMBLER=config["hybrid_assembler"]
-
-
###########
## metaT ##
###########
diff --git a/2019_GDB/rules/MMSEQ_RULES b/2019_GDB/rules/MMSEQ_RULES
index 98a5c84caf8b5afc9cad24746e34a3bd642fb61e..93d1c2787a2b345ac73d4a868701ad40cbddd3a8 100755
--- a/2019_GDB/rules/MMSEQ_RULES
+++ b/2019_GDB/rules/MMSEQ_RULES
@@ -1,21 +1,5 @@
# For running the MMSEQ2 comparison of proteins after assemblies are run through prokka/prodigal
-import os
-from tempfile import TemporaryDirectory
-
-configfile: "config/CONFIG.yaml"
-DATA_DIR = config["data_dir"]
-RESULTS_DIR = config["results_dir"]
-DB_DIR=config["db_dir"]
-BARCODES=config["barcodes"]
-ASSEMBLERS=config["assemblers"]
-MAPPERS=["bwa", "mm"]
-# SAMPLES=config["samples"]
-SAMPLES=["flye", "megahit", "metaspades_hybrid"]
-BINNING_SAMPLES=config["binning_samples"]
-HYBRID_ASSEMBLER=config["hybrid_assembler"]
-
-
#############################
######## MMSEQ2 ############
#############################
diff --git a/2019_GDB/rules/PLOT_RULES b/2019_GDB/rules/PLOT_RULES
index fdbb71a6d52dfb2bb6515d45020fe5d7a0cb8823..88b0e1b22f4280e42129d0a19003eaef35089c81 100755
--- a/2019_GDB/rules/PLOT_RULES
+++ b/2019_GDB/rules/PLOT_RULES
@@ -1,29 +1,12 @@
# For running the MMSEQ2 comparison of proteins after assemblies are run through prokka/prodigal
-import os
-#from tempfile import TemporaryDirectory
-
-configfile: "config/CONFIG.yaml"
-#DATA_DIR = config["data_dir"]
-RESULTS_DIR = config["results_dir"]
-#DB_DIR=config["db_dir"]
-BARCODES=config["barcodes"]
-#ASSEMBLERS=config["assemblers"]
-#MAPPERS=["bwa", "mm"]
-## SAMPLES=config["samples"]
-#SAMPLES=["flye", "megahit", "metaspades_hybrid"]
-#BINNING_SAMPLES=config["binning_samples"]
-#HYBRID_ASSEMBLER=config["hybrid_assembler"]
-SR_PREFIX="ONT3_MG_xx_Rashi_S11"
-
-
#############################
###### IGC COVERAGE ########
#############################
rule all:
input:
- expand("{results_dir}/plots/genomecov/{sr_prefix}_vs_{lr_prefix}-x-{reference}_coverage.html", results_dir=RESULTS_DIR, sr_prefix=SR_PREFIX, lr_prefix=BARCODES, reference="igc"),
- expand("{results_dir}/plots/annotation/diamond/lr_{lr_prefix}-sr{sr_prefix}-gene_length_ratio.html", results_dir=RESULTS_DIR, sr_prefix=SR_PREFIX, lr_prefix=BARCODES)
+ expand("{results_dir}/plots/genomecov/{sr_prefix}_vs_{lr_prefix}-x-{reference}_coverage.html", results_dir=RESULTS_DIR, sr_prefix=SAMPLES, lr_prefix=BARCODES, reference="igc"),
+ expand("{results_dir}/plots/annotation/diamond/lr_{lr_prefix}-sr{sr_prefix}-gene_length_ratio.html", results_dir=RESULTS_DIR, sr_prefix=SAMPLES, lr_prefix=BARCODES)
rule igc_correlation_plot:
diff --git a/2019_GDB/rules/TAXONOMY_RULES b/2019_GDB/rules/TAXONOMY_RULES
index bdc76d9ea6e1a0525b9cc1f371079a86246c51c0..a10e690b81ec8c02f0d893276200cd2e65a710ca 100755
--- a/2019_GDB/rules/TAXONOMY_RULES
+++ b/2019_GDB/rules/TAXONOMY_RULES
@@ -1,21 +1,5 @@
# For running the contamination check and taxonomy on the generated MAGs
-import os
-from tempfile import TemporaryDirectory
-
-configfile: "config/CONFIG.yaml"
-DATA_DIR = config["data_dir"]
-RESULTS_DIR = config["results_dir"]
-DB_DIR=config["db_dir"]
-BARCODES=config["barcodes"]
-ASSEMBLERS=config["assemblers"]
-MAPPERS=["bwa", "mmi"]
-#SAMPLES=config["samples"]
-SAMPLES=["flye", "megahit", "metaspades_hybrid"]
-BINNING_SAMPLES=config["binning_samples"]
-HYBRID_ASSEMBLER=config["hybrid_assembler"]
-
-
#####################################
######## GTDBTK & CHECKM ############
#####################################
diff --git a/2019_GDB/rules/checkpoint_ASSEMBLY_ANNOTATION_RULES b/2019_GDB/rules/checkpoint_ASSEMBLY_ANNOTATION_RULES
index 24bdf257b4c009cc7dc8701b8a261d38adaa29b3..c33efa4ebcd0263f9f6e37a0fc4d4e12d7fa065a 100755
--- a/2019_GDB/rules/checkpoint_ASSEMBLY_ANNOTATION_RULES
+++ b/2019_GDB/rules/checkpoint_ASSEMBLY_ANNOTATION_RULES
@@ -1,26 +1,5 @@
# For running the ASSEMBLY and ANNOTATION workflow for ONT data
-import os
-from tempfile import TemporaryDirectory
-
-configfile: "config/CONFIG.yaml"
-DATA_DIR = config["data_dir"]
-RESULTS_DIR = config["results_dir"]
-DB_DIR=config["db_dir"]
-RUNS=[config["runs"]["first"],
- config["runs"]["second"]]
-# config["runs"]["third"]]
-BARCODES=config["barcodes"]
-SAMPLES=["ONT3_MG_xx_Rashi_S11"]
-sr_sample=["ONT3_MG_xx_Rashi_S11"]
-# SAMPLES_ALL=config["samples"]
-REFERENCES=["igc", "hg38"]
-IGC_URI=config["igc"]["uri"]
-HG38_URI=config["hg38"]["uri"]
-ASSEMBLERS=config["assemblers"]
-MAPPERS=["bwa_mem", "minimap2"]
-
-
######
# RULES
######
diff --git a/2019_GDB/scripts/filter_fasta_by_length.pl b/2019_GDB/scripts/filter_fasta_by_length.pl
new file mode 100755
index 0000000000000000000000000000000000000000..1643e1bc2b13f4299570475ed8b6e05eb4b9c30f
--- /dev/null
+++ b/2019_GDB/scripts/filter_fasta_by_length.pl
@@ -0,0 +1,21 @@
+#!/usr/bin/env perl
+
+# from https://www.biostars.org/p/79202/#79467
+
+use strict;
+use warnings;
+
+my $minlen = shift or die "Error: `minlen` parameter not provided\n";
+{
+ local $/=">";
+ while(<>) {
+ chomp;
+ next unless /\w/;
+ s/>$//gs;
+ my @chunk = split /\n/;
+ my $header = shift @chunk;
+ my $seqlen = length join "", @chunk;
+ print ">$_" if($seqlen >= $minlen);
+ }
+ local $/="\n";
+}
diff --git a/2019_GDB/updated_SNAKEFILE b/2019_GDB/updated_SNAKEFILE
index 7290cb83f562164795ef3eacfc9bdd2f00f4a4f3..26e428dc5c38e225945172bb35e332c2e0aa64d3 100755
--- a/2019_GDB/updated_SNAKEFILE
+++ b/2019_GDB/updated_SNAKEFILE
@@ -1,14 +1,51 @@
# File for running ONT analyses
-# default configuration file
+##############################
+# MODULES
+import os
+from tempfile import TemporaryDirectory
+
+##############################
+# CONFIG
configfile:"config/CONFIG.yaml"
+# Paths
+SRC_DIR = srcdir("scripts")
+ENV_DIR = srcdir("envs")
+DATA_DIR = config["data_dir"]
+RESULTS_DIR = config["results_dir"]
+DB_DIR = config["db_dir"]
+
+# Steps
+STEPS = config['steps']
+ANALYSIS_STEPS = config["analysis_steps"]
+
+# Input
+BARCODES = config["barcodes"]
+RUNS = [
+ config["runs"]["first"],
+ config["runs"]["second"],
+# config["runs"]["third"]
+]
+SAMPLES = config["samples"]
+BINNING_SAMPLES = config["binning_samples"]
+
+# References
+IGC_URI = config["igc"]["uri"]
+HG38_URI = config["hg38"]["uri"]
+REFERENCES = ["igc", "hg38"]
+
+# Tools
+ASSEMBLERS = config["assemblers"]
+HYBRID_ASSEMBLER = config["hybrid_assembler"]
+MAPPERS = ["bwa", "mmi"]
+
# default executable for snakmake
shell.executable("bash")
-# input settings
-RUNS=config['runs']['first']
-STEPS=config['steps']
+# working directory
+workdir:
+ config["work_dir"]
# include rules for the workflows based on "steps" in the CONFIG.yaml file
# ONT analyses workflow
@@ -56,9 +93,21 @@ if 'taxonomy' in STEPS:
if 'analysis' in STEPS:
include: "workflows/analysis.smk"
- TARGETS += ["cdhit_analysis.done",
- "mappability_index.done",
- "crispr_analysis.done"]
+ # CD-HIT
+ if "cdhit" in ANALYSIS_STEPS:
+ TARGETS.append("cdhit_analysis.done")
+ # Mappability
+ if "mappability" in ANALYSIS_STEPS:
+ TARGETS.append("mappability_index.done")
+ # CRISPR
+ if "crispr" in ANALYSIS_STEPS:
+ TARGETS.append("crispr_analysis.done")
+ # Plasmid prediction
+ if "plasmids" in ANALYSIS_STEPS:
+ TARGETS.append("plasmids_analysis.done")
+ # AMR prediction
+ if "amr" in ANALYSIS_STEPS:
+ TARGETS.append("amr_analysis.done")
#else:
# raise Exception('You are not serious. No input data')
diff --git a/2019_GDB/workflows/analysis.smk b/2019_GDB/workflows/analysis.smk
index 690ebb537a185dfa3f6f07095135e898197f5141..064d6ba49dcfaa7968b3e702f0f176d681996b52 100755
--- a/2019_GDB/workflows/analysis.smk
+++ b/2019_GDB/workflows/analysis.smk
@@ -1,21 +1,5 @@
# For running the ANALYSIS "workflow"
-import os
-from tempfile import TemporaryDirectory
-
-configfile: "config/CONFIG.yaml"
-DATA_DIR = config["data_dir"]
-RESULTS_DIR = config["results_dir"]
-DB_DIR=config["db_dir"]
-BARCODES=config["barcodes"]
-#ASSEMBLERS=config["assemblers"]
-MAPPERS=["bwa", "mmi"]
-# SAMPLES=config["samples"]
-#SAMPLES=["flye", "megahit", "metaspades_hybrid"]
-BINNING_SAMPLES=config["binning_samples"]
-HYBRID_ASSEMBLER=config["hybrid_assembler"]
-
-
# specify which rules to run
include:
'../rules/ANALYSIS_RULES'
@@ -44,3 +28,15 @@ rule CRISPR:
expand(os.path.join(RESULTS_DIR, "analysis/crispr/minced/{assembly}.txt"), assembly=["flye", "megahit", "metaspades", "metaspades_hybrid"])
output:
touch('crispr_analysis.done')
+
+rule PLASMIDS:
+ input:
+ expand(os.path.join(RESULTS_DIR, "analysis/plasflow/{assembly}.tsv"), assembly=ASSEMBLERS)
+ output:
+ touch('plasmids_analysis.done')
+
+rule AMR:
+ input:
+ expand(os.path.join(RESULTS_DIR, "analysis/rgi/{assembly}.txt"), assembly=ASSEMBLERS)
+ output:
+ touch('amr_analysis.done')
diff --git a/2019_GDB/workflows/assembly_annotation.smk b/2019_GDB/workflows/assembly_annotation.smk
index 51cd000b216a52a1f5a1771d17f69e9a17248b6a..f26ad8f0b3442f60d6cc65469a526d036add908f 100755
--- a/2019_GDB/workflows/assembly_annotation.smk
+++ b/2019_GDB/workflows/assembly_annotation.smk
@@ -1,25 +1,5 @@
# For running the ASSEMBLY and ANNOTATION part of the ONT pipeline
-import os
-from tempfile import TemporaryDirectory
-
-configfile: "config/CONFIG.yaml"
-DATA_DIR = config["data_dir"]
-RESULTS_DIR = config["results_dir"]
-DB_DIR=config["db_dir"]
-RUNS=[config["runs"]["first"],
- config["runs"]["second"]]
-# config["runs"]["third"]]
-##RUNS=config["runs"]["third"]
-BARCODES=config["barcodes"]
-SAMPLES=["ONT3_MG_xx_Rashi_S11"]
-# SAMPLES_ALL=config["samples"]
-REFERENCES=["igc", "hg38"]
-IGC_URI=config["igc"]["uri"]
-HG38_URI=config["hg38"]["uri"]
-ASSEMBLERS=config["assemblers"]
-MAPPERS=["bwa_mem", "minimap2"]
-
# specify which rules to run
include:
'../rules/ASSEMBLY_ANNOTATION_RULES'
@@ -46,8 +26,8 @@ rule BASECALL_MERGE_QC:
expand(os.path.join(RESULTS_DIR, "qc/lr/merged/{barcode}/{barcode}NanoStats.txt"), barcode=BARCODES),
expand(os.path.join(RESULTS_DIR, "qc/lr/{run}/{barcode}/{barcode}NanoStats.txt"), run=RUNS, barcode=BARCODES),
# expand(os.path.join(RESULTS_DIR, "preprocessing/sr/{sr_sample}_R1_001.fastp.fq.gz"), sr_sample=["ONT3_MG_xx_Rashi_S11"]),
- expand(os.path.join(RESULTS_DIR, "preprocessing/sr/{sr_sample}.fastp.{report_type}"), sr_sample="ONT3_MG_xx_Rashi_S11", report_type=["html", "json"]),
- expand(os.path.join(RESULTS_DIR, "qc/sr/fastqc/{sr_sample}/{sr_sample}_R{orientation}_001.fastp.fastqc.html"), sr_sample="ONT3_MG_xx_Rashi_S11", orientation=["1", "2"])
+ expand(os.path.join(RESULTS_DIR, "preprocessing/sr/{sr_sample}.fastp.{report_type}"), sr_sample=SAMPLES, report_type=["html", "json"]),
+ expand(os.path.join(RESULTS_DIR, "qc/sr/fastqc/{sr_sample}/{sr_sample}_R{orientation}_001.fastp.fastqc.html"), sr_sample=SAMPLES, orientation=["1", "2"])
output: "basecall_merge_qc.done"
shell:
"""
@@ -67,8 +47,8 @@ rule BASECALL_MERGE_QC_NO_MOD:
rule COVERAGE_OF_REFERENCES:
input:
- expand(os.path.join(RESULTS_DIR, "genomecov/sr/minimap2/{sr_sample}-x-{reference}.avg_cov.txt"), sr_sample="ONT3_MG_xx_Rashi_S11", reference=REFERENCES),
- expand(os.path.join(RESULTS_DIR, "genomecov/sr/bwa_mem/{sr_sample}-x-{reference}.avg_cov.txt"), sr_sample="ONT3_MG_xx_Rashi_S11", reference=REFERENCES),
+ expand(os.path.join(RESULTS_DIR, "genomecov/sr/minimap2/{sr_sample}-x-{reference}.avg_cov.txt"), sr_sample=SAMPLES, reference=REFERENCES),
+ expand(os.path.join(RESULTS_DIR, "genomecov/sr/bwa_mem/{sr_sample}-x-{reference}.avg_cov.txt"), sr_sample=SAMPLES, reference=REFERENCES),
expand(os.path.join(RESULTS_DIR, "genomecov/lr/merged/{barcode}/{barcode}-x-{reference}.avg_cov.txt"), barcode=BARCODES, reference=REFERENCES)
output: "coverage_of_references.done"
shell:
@@ -123,11 +103,11 @@ rule ASSEMBLE_AND_COVERAGE:
#expand(os.path.join(RESULTS_DIR, "genomecov/lr/bwa_mem/{barcode}_reads-x-lr_{barcode}_sr_{sample}-{assembler}_contigs.avg_cov.txt"), barcode=BARCODES, sample=SAMPLES, assembler="operams"),
expand(os.path.join(RESULTS_DIR, "assembly/flye/lr/merged/{barcode}/assembly.fna"), barcode=BARCODES),
# short reads on short read contigs
- expand(os.path.join(RESULTS_DIR, "genomecov/sr/bwa_mem/{sr_sample}_reads-x-{sr_sample}-{assembler}_contigs.avg_cov.txt"), sr_sample="ONT3_MG_xx_Rashi_S11", assembler=["megahit", "metaspades"]),
+ expand(os.path.join(RESULTS_DIR, "genomecov/sr/bwa_mem/{sr_sample}_reads-x-{sr_sample}-{assembler}_contigs.avg_cov.txt"), sr_sample=SAMPLES, assembler=["megahit", "metaspades"]),
# assemble short reads with metaspades
- # expand(os.path.join(RESULTS_DIR, "assembly/metaspades/{sr_sample}/contigs.fna"), sr_sample="ONT3_MG_xx_Rashi_S11"),
+ # expand(os.path.join(RESULTS_DIR, "assembly/metaspades/{sr_sample}/contigs.fna"), sr_sample=SAMPLES),
# long reads on short read contigs
- expand(os.path.join(RESULTS_DIR, "genomecov/lr/bwa_mem/{barcode}_reads-x-{sr_sample}-{assembler}_contigs.avg_cov.txt"), barcode=BARCODES, sr_sample="ONT3_MG_xx_Rashi_S11", assembler="megahit")
+ expand(os.path.join(RESULTS_DIR, "genomecov/lr/bwa_mem/{barcode}_reads-x-{sr_sample}-{assembler}_contigs.avg_cov.txt"), barcode=BARCODES, sr_sample=SAMPLES, assembler="megahit")
output: "assemble_and_coverage.done"
shell:
"""
diff --git a/2019_GDB/workflows/binning.smk b/2019_GDB/workflows/binning.smk
index d94542207bf225f5d493fa3a4a4d1e78cda72fd5..0ebf77a44b05cbcd1dc0f5421146f0a5c67d575e 100755
--- a/2019_GDB/workflows/binning.smk
+++ b/2019_GDB/workflows/binning.smk
@@ -1,21 +1,5 @@
# For running the BINNING "workflow"
-import os
-from tempfile import TemporaryDirectory
-
-configfile: "config/CONFIG.yaml"
-DATA_DIR = config["data_dir"]
-RESULTS_DIR = config["results_dir"]
-DB_DIR=config["db_dir"]
-BARCODES=config["barcodes"]
-ASSEMBLERS=config["assemblers"]
-MAPPERS=["bwa", "mmi"]
-#SAMPLES=config["samples"]
-SAMPLES=["flye", "megahit", "metaspades_hybrid"]
-BINNING_SAMPLES=config["binning_samples"]
-HYBRID_ASSEMBLER=config["hybrid_assembler"]
-
-
# specify which rules to run
include:
'../rules/BINNING_RULES'
diff --git a/2019_GDB/workflows/checkpoint_assembly_annotation.smk b/2019_GDB/workflows/checkpoint_assembly_annotation.smk
index 3e43d008e09d33697493a568d0cc9ac4e0a3229c..0e23f32b93e29da637220463b5e184b15fa3bafc 100755
--- a/2019_GDB/workflows/checkpoint_assembly_annotation.smk
+++ b/2019_GDB/workflows/checkpoint_assembly_annotation.smk
@@ -1,25 +1,5 @@
# For running the ASSEMBLY and ANNOTATION part of the ONT pipeline
-import os
-from tempfile import TemporaryDirectory
-
-configfile: "config/CONFIG.yaml"
-DATA_DIR = config["data_dir"]
-RESULTS_DIR = config["results_dir"]
-DB_DIR=config["db_dir"]
-RUNS=[config["runs"]["first"],
- config["runs"]["second"]]
-# config["runs"]["third"]]
-##RUNS=config["runs"]["third"]
-BARCODES=config["barcodes"]
-SAMPLES=["ONT3_MG_xx_Rashi_S11"]
-# SAMPLES_ALL=config["samples"]
-REFERENCES=["igc", "hg38"]
-IGC_URI=config["igc"]["uri"]
-HG38_URI=config["hg38"]["uri"]
-ASSEMBLERS=config["assemblers"]
-MAPPERS=["bwa_mem", "minimap2"]
-
# specify which rules to run
include:
'../rules/checkpoint_ASSEMBLY_ANNOTATION_RULES'
diff --git a/2019_GDB/workflows/mapping.smk b/2019_GDB/workflows/mapping.smk
index d6f22292e7015f580e950836429b73e6c0d0be8b..8b9716973b3b1c9819f512f67de27ad23672149c 100755
--- a/2019_GDB/workflows/mapping.smk
+++ b/2019_GDB/workflows/mapping.smk
@@ -1,22 +1,5 @@
# Workflow for running mapping steps of different assemblers, and mappers for the Binning workflow
-#shell.executable("/bin/bash")
-##shell.prefix("source ~/.bashrc; ")
-import os
-from tempfile import TemporaryDirectory
-
-configfile: "config/CONFIG.yaml"
-DATA_DIR = config["data_dir"]
-RESULTS_DIR = config["results_dir"]
-DB_DIR=config["db_dir"]
-BARCODES=config["barcodes"]
-ASSEMBLERS=config["assemblers"]
-MAPPERS=["bwa", "mmi"]
-#SAMPLES=config["samples"]
-SAMPLES=["flye", "megahit", "metaspades_hybrid"]
-BINNING_SAMPLES=config["binning_samples"]
-HYBRID_ASSEMBLER=config["hybrid_assembler"]
-
# specify which rules to run
include:
'../rules/MAPPING_RULES'
diff --git a/2019_GDB/workflows/metat.smk b/2019_GDB/workflows/metat.smk
index a19965eba9c462fbbae63ce4ea01d9ba0b2c8ddd..4854a12e4b563ec54245b3e0e52bfe611c3fb36d 100755
--- a/2019_GDB/workflows/metat.smk
+++ b/2019_GDB/workflows/metat.smk
@@ -1,20 +1,5 @@
# Workflow for running mapping metaT reads to different assemblies using different mappers for the Binning workflow
-import os
-from tempfile import TemporaryDirectory
-
-configfile: "config/CONFIG.yaml"
-DATA_DIR = config["data_dir"]
-RESULTS_DIR = config["results_dir"]
-DB_DIR=config["db_dir"]
-BARCODES=config["barcodes"]
-ASSEMBLERS=config["assemblers"]
-MAPPERS=["bwa", "mmi"]
-#Â SAMPLES=config["samples"]
-SAMPLES=["flye", "megahit", "metaspades_hybrid"]
-BINNING_SAMPLES=config["binning_samples"]
-HYBRID_ASSEMBLER=config["hybrid_assembler"]
-
# specify which rules to run
include:
'../rules/METAT_RULES'
diff --git a/2019_GDB/workflows/mmseq.smk b/2019_GDB/workflows/mmseq.smk
index 2ba8f8319a62aaf682ff9bc92d22b12a4fcc54e4..272a754fd6a94be274e360e79a11e87d10228bfc 100755
--- a/2019_GDB/workflows/mmseq.smk
+++ b/2019_GDB/workflows/mmseq.smk
@@ -1,21 +1,5 @@
# For running the MMSEQ2 "workflow"
-import os
-from tempfile import TemporaryDirectory
-
-configfile: "config/CONFIG.yaml"
-DATA_DIR = config["data_dir"]
-RESULTS_DIR = config["results_dir"]
-DB_DIR=config["db_dir"]
-BARCODES=config["barcodes"]
-ASSEMBLERS=config["assemblers"]
-MAPPERS=["bwa", "mmi"]
-# SAMPLES=config["samples"]
-SAMPLES=["flye", "megahit", "metaspades_hybrid"]
-BINNING_SAMPLES=config["binning_samples"]
-HYBRID_ASSEMBLER=config["hybrid_assembler"]
-
-
# specify which rules to run
include:
'../rules/MMSEQ_RULES'
@@ -23,7 +7,7 @@ include:
# Rule all for running the MMSEQ2 analyses on the proteins after assembly
rule MMSEQ:
input:
- expand(os.path.join(RESULTS_DIR, "annotation/mmseq2/{assembler}_db"), assembler=["flye", "megahit", "metaspades_hybrid", "metaspades"]),
+ expand(os.path.join(RESULTS_DIR, "annotation/mmseq2/{assembler}_db"), assembler=ASSEMBLERS),
expand(os.path.join(RESULTS_DIR, "annotation/mmseq2/flye_megahit_rbh")),
expand(os.path.join(RESULTS_DIR, "annotation/mmseq2/flye_metaspades_hybrid_rbh")),
expand(os.path.join(RESULTS_DIR, "annotation/mmseq2/megahit_metaspades_hybrid_rbh")),
diff --git a/2019_GDB/workflows/taxonomy.smk b/2019_GDB/workflows/taxonomy.smk
index 733d1ef2433b6e555a7cb4caca5268884339ca7a..6b9e5dde5c7e0b9d7acf945e4e519a76cf3d799d 100755
--- a/2019_GDB/workflows/taxonomy.smk
+++ b/2019_GDB/workflows/taxonomy.smk
@@ -1,21 +1,5 @@
# For running the TAXONOMY "workflow"
-import os
-from tempfile import TemporaryDirectory
-
-configfile: "config/CONFIG.yaml"
-DATA_DIR = config["data_dir"]
-RESULTS_DIR = config["results_dir"]
-DB_DIR=config["db_dir"]
-BARCODES=config["barcodes"]
-ASSEMBLERS=config["assemblers"]
-MAPPERS=["bwa", "mmi"]
-#SAMPLES=config["samples"]
-SAMPLES=["flye", "megahit", "metaspades_hybrid"]
-BINNING_SAMPLES=config["binning_samples"]
-HYBRID_ASSEMBLER=config["hybrid_assembler"]
-
-
# specify which rules to run
include:
'../rules/TAXONOMY_RULES'