def __init__(self, args=None, run=terminal.Run(), progress=terminal.Progress()):
self.init_workflow_super_class(args, workflow_name='pangenomics')
# initialize the base class
ContigsDBWorkflow.__init__(self)
self.rules.extend(['anvi_gen_genomes_storage',
'anvi_pan_genome'])
self.general_params.extend(["project_name",
"fasta_txt",
"internal_genomes",
"external_genomes"])
self.dirs_dict.update({"FASTA_DIR": "01_FASTA",
"CONTIGS_DIR": "02_CONTIGS",
"PAN_DIR": "03_PAN"})
self.default_config.update({"fasta_txt": "fasta.txt",
"anvi_pan_genome": {"threads": 7}})
pan_params = ["--project-name", "--genome-names", "--skip-alignments",\
"--align-with", "--exclude-partial-gene-calls", "--use-ncbi-blast",\
"--minbit", "--mcl-inflation", "--min-occurrence",\
"--min-percent-identity", "--sensitive", "--description",\
"--overwrite-output-destinations", "--skip-hierarchical-clustering",\
"--enforce-hierarchical-clustering", "--distance", "--linkage"]
self.rule_acceptable_params_dict['anvi_pan_genome'] = pan_params
storage_params = ["--gene-caller"]
self.rule_acceptable_params_dict['anvi_gen_genomes_storage'] = storage_params
def __init__(self, args, run=terminal.Run(), progress=terminal.Progress()):
self.args = args
self.run = run
self.progress = progress
# know thyself.
self.name = 'pangenomics'
# initialize the base class
ContigsDBWorkflow.__init__(self)
self.rules.extend(['gen_external_genome_file',
'anvi_gen_genomes_storage',
'anvi_pan_genome'])
self.general_params.extend(["project_name", "fasta_txt"])
self.dirs_dict.update({"FASTA_DIR": "01_FASTA",
"CONTIGS_DIR": "02_CONTIGS",
"PAN_DIR": "03_PAN"})
self.default_config.update({"fasta_txt": "fasta.txt",
"anvi_pan_genome": {"threads": 20}})
pan_params = ["--project-name", "--genome-names", "--skip-alignments",\
"--align-with", "--exclude-partial-gene-calls", "--use-ncbi-blast",\
"--minbit", "--mcl-inflation", "--min-occurrence",\
"--min-percent-identity", "--sensitive", "--description",\
"--overwrite-output-destinations", "--skip-hierarchical-clustering",\
"--enforce-hierarchical-clustering", "--distance", "--linkage"]
self.rule_acceptable_params_dict['anvi_pan_genome'] = pan_params
storage_params = ["--internal-genomes", "--external-genomes", "--gene-caller"]
self.rule_acceptable_params_dict['anvi_gen_genomes_storage'] = storage_params
def __init__(self, args=None, run=terminal.Run(), progress=terminal.Progress()):
self.init_workflow_super_class(args, workflow_name='phylogenomics')
# initialize the base class
ContigsDBWorkflow.__init__(self)
self.input_for_anvi_get_sequences_for_hmm_hits = {}
self.internal_genomes_file = ''
self.external_genomes_file = ''
# initialize the base class
self.rules.extend(['anvi_get_sequences_for_hmm_hits', 'trimal', 'iqtree'])
self.general_params.extend(['project_name', 'internal_genomes', 'external_genomes'])
self.dirs_dict.update({"PHYLO_DIR": "01_PHYLOGENOMICS"})
self.default_config.update({'anvi_get_sequences_for_hmm_hits': {'--return-best-hit': True,
'--align-with': 'famsa',
'--concatenate-genes': True,
'--get-aa-sequences': True,
'--hmm-sources': 'Campbell_et_al'},
'trimal': {'-gt': 0.5},
'iqtree': {'threads': 8, '-m': 'WAG', '-bb': 1000}})
get_sequences_params = ['--return-best-hit', \
'--separator', '--align-with', '--min-num-bins-gene-occurs', \
'--max-num-genes-missing-from-bin', '--concatenate-genes', \
'--get-aa-sequences', '--gene-names', '--hmm-sources']
self.rule_acceptable_params_dict['anvi_get_sequences_for_hmm_hits'] = get_sequences_params
self.rule_acceptable_params_dict['trimal'] = ['-gt', 'additional_params']
self.rule_acceptable_params_dict['iqtree'] = ['-m', '-bb', 'additional_params']
def __init__(self,
args=None,
run=terminal.Run(),
progress=terminal.Progress()):
self.init_workflow_super_class(args, workflow_name='phylogenomics')
# initialize the base class
ContigsDBWorkflow.__init__(self)
self.input_for_anvi_get_sequences_for_hmm_hits = {}
self.internal_genomes_file = ''
self.external_genomes_file = ''
self.phylogenomics_sequence_file = None
self.project_name = None
self.use_hmms_for_phylogeny = True
# initialize the base class
self.rules.extend(
['anvi_get_sequences_for_hmm_hits', 'trimal', 'iqtree'])
self.general_params.extend(
['project_name', 'internal_genomes', 'external_genomes'])
self.dirs_dict.update({"PHYLO_DIR": "01_PHYLOGENOMICS"})
self.default_config.update({
'anvi_get_sequences_for_hmm_hits': {
'--return-best-hit': True,
'--align-with': 'famsa',
'--concatenate-genes': True,
'--get-aa-sequences': True,
'--hmm-sources': 'Bacteria_71'
},
'trimal': {
'-gt': 0.5
},
'iqtree': {
'threads': 8,
'-m': 'WAG',
'-bb': 1000
}
})
get_sequences_params = ['--return-best-hit', \
'--separator', '--align-with', '--min-num-bins-gene-occurs', \
'--max-num-genes-missing-from-bin', '--concatenate-genes', \
'--get-aa-sequences', '--gene-names', '--hmm-sources']
self.rule_acceptable_params_dict[
'anvi_get_sequences_for_hmm_hits'] = get_sequences_params
self.rule_acceptable_params_dict['trimal'] = [
'-gt', 'additional_params'
]
self.rule_acceptable_params_dict['iqtree'] = [
'-m', '-bb', 'additional_params'
]
def __init__(self):
ContigsDBWorkflow.__init__(self, config)
self.rules = ['iu_gen_configs', 'iu_filter_quality_minoche', 'gen_qc_report', 'gzip_fastqs',\
'fq2fa', 'merge_fastas_for_co_assembly', 'megahit', 'anvi_script_anvi_script_reformat_fasta',\
'anvi_gen_contigs_database', 'export_gene_calls', 'centrifuge',\
'anvi_import_taxonomy', 'anvi_run_hmms', 'anvi_run_ncbi_cogs',\
'bowtie_build', 'bowtie', 'samtools_view', 'anvi_init_bam',\
'anvi_profile', 'annotate_contigs_database', 'anvi_merge']
rule_acceptable_params_dict = {}
# defining the accesible params per rule
rule_acceptable_params_dict['iu_gen_configs'] = [
"--r1-prefix", "--r2-prefix"
]
rule_acceptable_params_dict['iu_filter_quality_minoche'] = [
'visualize_quality_curves', 'ignore_deflines', 'limit_num_pairs',
'print_qual_scores', 'store_read_fate'
]
rule_acceptable_params_dict['gzip_fastqs'] = ["run"]
rule_acceptable_params_dict['megahit'] = []
rule_acceptable_params_dict['anvi_script_reformat_fasta'] = []
rule_acceptable_params_dict['anvi_gen_contigs_database'] = []
rule_acceptable_params_dict['export_gene_calls'] = []
rule_acceptable_params_dict['centrifuge'] = []
rule_acceptable_params_dict['anvi_import_taxonomy'] = []
rule_acceptable_params_dict['anvi_run_hmms'] = []
rule_acceptable_params_dict['anvi_run_ncbi_cogs'] = []
rule_acceptable_params_dict['bowtie_build'] = []
rule_acceptable_params_dict['bowtie'] = []
rule_acceptable_params_dict['samtools_view'] = []
rule_acceptable_params_dict['anvi_init_bam'] = []
rule_acceptable_params_dict['anvi_profile'] = []
rule_acceptable_params_dict['annotate_contigs_database'] = []
rule_acceptable_params_dict['anvi_merge'] = []
self.rule_acceptable_params_dict = rule_acceptable_params_dict
def __init__(self, config):
ContigsDBWorkflow.__init__(self, config)
self.rules.extend([
'gen_external_genome_file', 'anvi_gen_genomes_storage',
'anvi_pan_genome'
])
self.general_params.extend(["project_name", "samples_txt"])
pan_params = ["--project-name", "--output-dir", "--genome-names", "--skip-alignments",\
"--align-with", "--exclude-partial-gene-calls", "--use-ncbi-blast",\
"--minbit", "--mcl-inflation", "--min-occurrence",\
"--min-percent-identity", "--sensitive", "--description",\
"--overwrite-output-destinations", "--skip-hierarchical-clustering",\
"--enforce-hierarchical-clustering", "--distance", "--linkage"]
self.rule_acceptable_params_dict['anvi_pan_genome'] = pan_params
storage_params = [
"--internal-genomes", "--external-genomes", "--gene-caller"
]
self.rule_acceptable_params_dict[
'anvi_gen_genomes_storage'] = storage_params
def __init__(self, args, run=terminal.Run(), progress=terminal.Progress()):
self.args = args
self.run = run
self.progress = progress
# know thyself.
self.name = 'metagenomics'
self.samples_information = {}
self.kraken_annotation_dict = {}
self.run_metaspades = None
self.use_scaffold_from_metaspades = None
self.remove_short_reads_based_on_references = None
self.references_for_removal_txt = None
self.references_for_removal = {}
self.references_mode = None
self.fasta_txt_file = None
self.samples_txt_file = None
self.sample_names = None
self.group_sizes = None
# initialize the base class
ContigsDBWorkflow.__init__(self)
self.rules.extend(['iu_gen_configs', 'iu_filter_quality_minoche', 'gen_qc_report', 'gzip_fastqs',\
'merge_fastqs_for_co_assembly', 'megahit', 'merge_fastas_for_co_assembly',\
'anvi_gen_contigs_database', 'anvi_export_gene_calls', 'centrifuge',\
'anvi_import_taxonomy', 'anvi_run_hmms', 'anvi_run_ncbi_cogs',\
'bowtie_build', 'bowtie', 'samtools_view', 'anvi_init_bam', 'idba_ud',\
'anvi_profile', 'annotate_contigs_database', 'anvi_merge', 'import_percent_of_reads_mapped',\
'krakenhll', 'krakenhll_mpa_report', 'import_kraken_hll_taxonomy', 'metaspades',\
'remove_short_reads_based_on_references'])
self.general_params.extend(['samples_txt', "references_mode", "all_against_all",\
"kraken_txt"])
rule_acceptable_params_dict = {}
# defining the accesible params per rule
rule_acceptable_params_dict['iu_gen_configs'] = ["--r1-prefix", "--r2-prefix"]
rule_acceptable_params_dict['iu_filter_quality_minoche'] = ['run', '--visualize-quality-curves', '--ignore-deflines', '--limit-num-pairs', '--print-qual-scores', '--store-read-fate']
rule_acceptable_params_dict['gzip_fastqs'] = ["run"]
rule_acceptable_params_dict['metaspades'] = ["run", "additional_params", "use_scaffolds"]
rule_acceptable_params_dict['megahit'] = ["run", "--min-contig-len", "--min-count", "--k-min",
"--k-max", "--k-step", "--k-list",
"--no-mercy", "--no-bubble", "--merge-level",
"--prune-level", "--prune-depth", "--low-local-ratio",
"--max-tip-len", "--no-local", "--kmin-1pass",
"--presets", "--memory", "--mem-flag",
"--use-gpu", "--gpu-mem", "--keep-tmp-files",
"--tmp-dir", "--continue", "--verbose"]
rule_acceptable_params_dict['idba_ud'] = ["run", "--mink", "--maxk", "--step", "--inner_mink",
"--inner_step", "--prefix", "--min_count",
"--min_support", "--seed_kmer", "--min_contig",
"--similar", "--max_mismatch", "--min_pairs",
"--no_bubble", "--no_local", "--no_coverage",
"--no_correct", "--pre_correction"]
rule_acceptable_params_dict['bowtie'] = ["additional_params"]
rule_acceptable_params_dict['samtools_view'] = ["additional_params"]
rule_acceptable_params_dict['anvi_profile'] = ["--overwrite-output-destinations", "--sample-name", "--report-variability-full",
"--skip-SNV-profiling", "--profile-SCVs", "--description",
"--skip-hierarchical-clustering", "--distance", "--linkage", "--min-contig-length",
"--min-mean-coverage", "--min-coverage-for-variability", "--cluster-contigs",
"--contigs-of-interest", "--queue-size", "--write-buffer-size", "--max-contig-length"]
rule_acceptable_params_dict['annotate_contigs_database'] = []
rule_acceptable_params_dict['merge_fastas_for_co_assembly'] = []
rule_acceptable_params_dict['merge_fastqs_for_co_assembly'] = []
rule_acceptable_params_dict['anvi_merge'] = ["--sample-name", "--description", "--skip-hierarchical-clustering",
"--enforce-hierarchical-clustering", "--distance", "--linkage",
"--skip-concoct-binning", "--overwrite-output-destinations"]
rule_acceptable_params_dict['import_percent_of_reads_mapped'] = ["run"]
rule_acceptable_params_dict['krakenhll'] = ["additional_params", "run", "--db", "--gzip-compressed"]
rule_acceptable_params_dict['krakenhll_mpa_report'] = ["additional_params"]
rule_acceptable_params_dict['import_kraken_hll_taxonomy'] = ["--min-abundance"]
rule_acceptable_params_dict['remove_short_reads_based_on_references'] = ["dont_remove_just_map", \
"references_for_removal_txt", \
"delimiter-for-iu-remove-ids-from-fastq"]
self.rule_acceptable_params_dict.update(rule_acceptable_params_dict)
forbidden_params = {}
forbidden_params['krakenhll'] = ['--fastq-input', '--paired', '--output']
self.forbidden_params.update(forbidden_params)
self.dirs_dict.update({"QC_DIR": "01_QC",
"FASTA_DIR": "02_FASTA",
"CONTIGS_DIR": "03_CONTIGS",
"MAPPING_DIR": "04_MAPPING",
"PROFILE_DIR": "05_ANVIO_PROFILE",
"MERGE_DIR": "06_MERGED",
"TAXONOMY_DIR": "07_TAXONOMY"})
self.default_config.update({'samples_txt': "samples.txt",
'metaspades': {"additional_params": "--only-assembler", "threads": 7},
'megahit': {"--min-contig-len": min_contig_length_for_assembly, "--memory": 0.4, "threads": 7},
'idba_ud': {"--min_contig": min_contig_length_for_assembly, "threads": 7},
'iu_filter_quality_minoche': {"run": True, "--ignore-deflines": True},
"gzip_fastqs": {"run": True},
"bowtie": {"additional_params": "--no-unal", "threads": 3},
"samtools_view": {"additional_params": "-F 4"},
"anvi_profile": {"threads": 3, "--sample-name": "{sample}", "--overwrite-output-destinations": True},
"anvi_merge": {"--sample-name": "{group}", "--overwrite-output-destinations": True},
"import_percent_of_reads_mapped": {"run": True},
"krakenhll": {"threads": 3, "--gzip-compressed": True, "additional_params": "--preload"},
"remove_short_reads_based_on_references": {"delimiter-for-iu-remove-ids-from-fastq": " "}})
def __init__(self, args=None, run=terminal.Run(), progress=terminal.Progress()):
self.init_workflow_super_class(args, workflow_name='metagenomics')
self.target_files = [] # TODO: Once we update all other workflows then this will be initiated in WorkflowSuperClass
self.samples_information = {}
self.kraken_annotation_dict = {}
self.run_krakenuniq = None
self.run_metaspades = None
self.use_scaffold_from_metaspades = None
self.remove_short_reads_based_on_references = None
self.references_for_removal_txt = None
self.references_for_removal = {}
self.references_mode = None
self.fasta_txt_file = None
self.samples_txt_file = None
self.sample_names = None
self.group_sizes = None
self.collections_txt = None
self.collections = None
# initialize the base class
ContigsDBWorkflow.__init__(self)
self.rules.extend(['iu_gen_configs', 'iu_filter_quality_minoche', 'gen_qc_report', 'gzip_fastqs',\
'merge_fastqs_for_co_assembly', 'megahit', 'merge_fastas_for_co_assembly',\
'anvi_gen_contigs_database', 'anvi_export_gene_calls', 'centrifuge',\
'anvi_import_taxonomy', 'anvi_run_hmms', 'anvi_run_ncbi_cogs',\
'bowtie_build', 'bowtie', 'samtools_view', 'anvi_init_bam', 'idba_ud',\
'anvi_profile', 'annotate_contigs_database', 'anvi_merge', 'import_percent_of_reads_mapped',\
'krakenuniq', 'krakenuniq_mpa_report', 'import_krakenuniq_taxonomy', 'metaspades',\
'remove_short_reads_based_on_references', 'anvi_summarize', 'anvi_split'])
self.general_params.extend(['samples_txt', "references_mode", "all_against_all",\
"kraken_txt", "collections_txt"])
rule_acceptable_params_dict = {}
# defining the accesible params per rule
rule_acceptable_params_dict['iu_gen_configs'] = ["--r1-prefix", "--r2-prefix"]
rule_acceptable_params_dict['iu_filter_quality_minoche'] = ['run', '--visualize-quality-curves', '--ignore-deflines', '--limit-num-pairs', '--print-qual-scores', '--store-read-fate']
rule_acceptable_params_dict['gzip_fastqs'] = ["run"]
rule_acceptable_params_dict['anvi_summarize'] = ["additional_params", "run"]
rule_acceptable_params_dict['anvi_split'] = ["additional_params", "run"]
rule_acceptable_params_dict['metaspades'] = ["run", "additional_params", "use_scaffolds"]
rule_acceptable_params_dict['megahit'] = ["run", "--min-contig-len", "--min-count", "--k-min",
"--k-max", "--k-step", "--k-list",
"--no-mercy", "--no-bubble", "--merge-level",
"--prune-level", "--prune-depth", "--low-local-ratio",
"--max-tip-len", "--no-local", "--kmin-1pass",
"--presets", "--memory", "--mem-flag",
"--use-gpu", "--gpu-mem", "--keep-tmp-files",
"--tmp-dir", "--continue", "--verbose"]
rule_acceptable_params_dict['idba_ud'] = ["run", "--mink", "--maxk", "--step", "--inner_mink",
"--inner_step", "--prefix", "--min_count",
"--min_support", "--seed_kmer", "--min_contig",
"--similar", "--max_mismatch", "--min_pairs",
"--no_bubble", "--no_local", "--no_coverage",
"--no_correct", "--pre_correction"]
rule_acceptable_params_dict['bowtie'] = ["additional_params"]
rule_acceptable_params_dict['samtools_view'] = ["additional_params"]
rule_acceptable_params_dict['anvi_profile'] = ["--overwrite-output-destinations", "--sample-name", "--report-variability-full",
"--skip-SNV-profiling", "--profile-SCVs", "--description",
"--skip-hierarchical-clustering", "--distance", "--linkage", "--min-contig-length",
"--min-mean-coverage", "--min-coverage-for-variability", "--cluster-contigs",
"--contigs-of-interest", "--queue-size", "--write-buffer-size", "--max-contig-length", "--max-coverage-depth"]
rule_acceptable_params_dict['annotate_contigs_database'] = []
rule_acceptable_params_dict['merge_fastas_for_co_assembly'] = []
rule_acceptable_params_dict['merge_fastqs_for_co_assembly'] = []
rule_acceptable_params_dict['anvi_merge'] = ["--sample-name", "--description", "--skip-hierarchical-clustering",
"--enforce-hierarchical-clustering", "--distance", "--linkage",
"--skip-concoct-binning", "--overwrite-output-destinations"]
rule_acceptable_params_dict['import_percent_of_reads_mapped'] = ["run"]
rule_acceptable_params_dict['krakenuniq'] = ["additional_params", "run", "--db", "--gzip-compressed"]
rule_acceptable_params_dict['import_krakenuniq_taxonomy'] = ["--min-abundance"]
rule_acceptable_params_dict['remove_short_reads_based_on_references'] = ["dont_remove_just_map", \
"references_for_removal_txt", \
"delimiter-for-iu-remove-ids-from-fastq"]
self.rule_acceptable_params_dict.update(rule_acceptable_params_dict)
forbidden_params = {}
forbidden_params['krakenuniq'] = ['--fastq-input', '--paired', '--output']
self.forbidden_params.update(forbidden_params)
self.dirs_dict.update({"QC_DIR": "01_QC",
"FASTA_DIR": "02_FASTA",
"CONTIGS_DIR": "03_CONTIGS",
"MAPPING_DIR": "04_MAPPING",
"PROFILE_DIR": "05_ANVIO_PROFILE",
"MERGE_DIR": "06_MERGED",
"TAXONOMY_DIR": "07_TAXONOMY",
"SUMMARY_DIR": "08_SUMMARY",
"SPLIT_PROFILES_DIR": "09_SPLIT_PROFILES"})
self.default_config.update({'samples_txt': "samples.txt",
'metaspades': {"additional_params": "--only-assembler", "threads": 7},
'megahit': {"--min-contig-len": min_contig_length_for_assembly, "--memory": 0.4, "threads": 7},
'idba_ud': {"--min_contig": min_contig_length_for_assembly, "threads": 7},
'iu_filter_quality_minoche': {"run": True, "--ignore-deflines": True},
"gzip_fastqs": {"run": True},
"bowtie": {"additional_params": "--no-unal", "threads": 3},
"samtools_view": {"additional_params": "-F 4"},
"anvi_profile": {"threads": 3, "--sample-name": "{sample}", "--overwrite-output-destinations": True},
"anvi_merge": {"--sample-name": "{group}", "--overwrite-output-destinations": True},
"import_percent_of_reads_mapped": {"run": True},
"krakenuniq": {"threads": 3, "--gzip-compressed": True, "additional_params": ""},
"remove_short_reads_based_on_references": {"delimiter-for-iu-remove-ids-from-fastq": " "}})