Schema

The schema below is auto-generatated via the SocialGene Python Package.

# pip install socialgene
sg_schema --nodes  --markdown
sg_schema --rels  --markdown

Nodes

Label	Description	NF results subdirectory	Neo4j header file	Unique on	properties
assembly	Represents a single genome/assembly/BGC. If the input was a FASTA file or if assembly wasn't in the genbank metadata then this will represent the file the data came from.	genomic_info	assembly.header	uid	['uid', 'altitude', 'bio_material', 'bioproject', 'biosample', 'cell_line', 'cell_type', 'chromosome', 'clone', 'clone_lib', 'collected_by', 'collection_date', 'country', 'cultivar', 'culture_collection', 'db_xref', 'dev_stage', 'ecotype', 'environmental_sample', 'focus', 'germline', 'haplogroup', 'haplotype', 'host', 'identified_by', 'isolate', 'isolation_source', 'lab_host', 'lat_lon', 'macronuclear', 'map', 'mating_type', 'metagenome_source', 'mol_type', 'note', 'organelle', 'organism', 'pcr_primers', 'plasmid', 'pop_variant', 'proviral', 'rearranged', 'segment', 'serotype', 'serovar', 'sex', 'specimen_voucher', 'strain', 'sub_clone', 'submitter_seqid', 'sub_species', 'sub_strain', 'tissue_lib', 'tissue_type', 'transgenic', 'type_material', 'variety']
assembly:mibig	Represents a single Mibig entry	genomic_info	assembly.header	uid	['uid']
chebi	Represents a ChEBI term	None	None	uid	['uid', 'name']
chembl	Represents a CHEMBL term	None	None	uid	['uid']
chemical_compound:substrate	Mibig substrate (e.g. NRPS monomer)	None	None	inchi, CanonicalSmiles	['uid', 'MolWt', 'HeavyAtomMolWt', 'ExactMolWt', 'NumValenceElectrons', 'NumRadicalElectrons', 'HeavyAtomCount', 'NumAliphaticCarbocycles', 'NumAliphaticHeterocycles', 'NumAliphaticRings', 'NumAromaticCarbocycles', 'NumAromaticHeterocycles', 'NumAromaticRings', 'NumHAcceptors', 'NumHDonors', 'NumHeteroatoms', 'NumRotatableBonds', 'NumSaturatedCarbocycles', 'NumSaturatedHeterocycles', 'NumSaturatedRings', 'RingCount', 'MolLogP', 'MolMR', 'AnonymousGraph', 'ElementGraph', 'MurckoScaffold', 'ExtendedMurcko', 'MolFormula', 'AtomBondCounts', 'DegreeVector', 'Mesomer', 'HetAtomTautomer', 'HetAtomProtomer', 'RedoxPair', 'Regioisomer', 'NetCharge', 'SmallWorldIndexBR', 'SmallWorldIndexBRL', 'ArthorSubstructureOrder', 'HetAtomTautomerv2', 'inchi', 'CanonicalSmiles']
chemical_compound	Represents a chemical compound	None	None	inchi, CanonicalSmiles	['uid', 'MolWt', 'HeavyAtomMolWt', 'ExactMolWt', 'NumValenceElectrons', 'NumRadicalElectrons', 'HeavyAtomCount', 'NumAliphaticCarbocycles', 'NumAliphaticHeterocycles', 'NumAliphaticRings', 'NumAromaticCarbocycles', 'NumAromaticHeterocycles', 'NumAromaticRings', 'NumHAcceptors', 'NumHDonors', 'NumHeteroatoms', 'NumRotatableBonds', 'NumSaturatedCarbocycles', 'NumSaturatedHeterocycles', 'NumSaturatedRings', 'RingCount', 'MolLogP', 'MolMR', 'AnonymousGraph', 'ElementGraph', 'MurckoScaffold', 'ExtendedMurcko', 'MolFormula', 'AtomBondCounts', 'DegreeVector', 'Mesomer', 'HetAtomTautomer', 'HetAtomProtomer', 'RedoxPair', 'Regioisomer', 'NetCharge', 'SmallWorldIndexBR', 'SmallWorldIndexBRL', 'ArthorSubstructureOrder', 'HetAtomTautomerv2', 'inchi', 'CanonicalSmiles']
classyfire	Represents a classyfire chemical ontology term	None	None	uid	['uid', 'name', 'definition']
gnps_cluster	Represents a GNPS molecular networking cluster	None	None	cluster_index, workflow_uuid, task	['task', 'defaultgroups', 'g1', 'g2', 'g3', 'g4', 'g5', 'g6', 'gnpslinkout_cluster', 'gnpslinkout_network', 'mqscore', 'mzerrorppm', 'massdiff', 'rtmean', 'rtmean_min', 'rtstderr', 'uniquefilesources', 'uniquefilesourcescount', 'cluster_index', 'componentindex', 'number_of_spectra', 'parent_mass', 'precursor_charge', 'precursor_mass', 'sumprecursor_intensity', 'workflow_uuid']
gnps_library_spectrum	Represents a GNPS library spectrum	None	None	uid	['uid', 'compound_name', 'compound_source', 'pi', 'data_collector', 'adduct', 'precursor_mz', 'exactmass', 'charge', 'cas_number', 'pubmed_id', 'smiles', 'inchi', 'inchi_aux', 'library_class', 'ionmode', 'libraryqualitystring', 'mqscore', 'tic_query', 'rt_query', 'mzerrorppm', 'sharedpeaks', 'massdiff', 'libmz', 'specmz', 'speccharge', 'moleculeexplorerdatasets', 'moleculeexplorerfiles', 'molecular_formula', 'inchikey', 'inchikey_planar']
gnps_organism	Represents an organism (as defined by GNPS)	None	None	uid	['uid']
goterm	Represent a GO term	goterms	goterms.header	uid	['uid', 'name', 'namespace']
hmm	Represents a single non-redundant HMM model	hmm_info	sg_hmm_nodes.header	uid	['uid']
hmm_source	Represents the source of an HMM model (e.g. PFAM)	hmm_info	hmm_source.header	uid	['uid', ':LABEL', 'rel_path', 'name', 'acc', 'notes', 'description', 'date', 'hash', 'hash_used', 'model_length', 'super_category', 'category', 'subcategory', 'ga', 'tc', 'nc']
instrument	Represents an instrument	None	None	uid	['uid']
ion_source	Represents an ion source	None	None	uid	['uid']
mass_spectrum_file	Represents a GNPS molecular networking spectrum file	None	None	original_filename, workflow_uuid	['filename', 'gnps_filename', 'workflow_uuid']
mibig_activity	Represents a single Mibig bioactivity	None	None	uid	['uid']
mibig_biosynthetic_class	Represents a single Mibig biosynthetic class	None	None	uid	['uid']
mibig_compound	Represents a single Mibig compound	None	None	uid	['name', 'smiles', 'inchi']
ms2_spectrum	Represents a GNPS molecular networking spectrum	None	None	original_filename, specidx, workflow_uuid	['specidx', 'original_filename', 'parentmass', 'charge', 'rettime', 'workflow_uuid']
npatlas	Represents a single NPAtlas entry	None	None	uid	['uid', 'original_name', 'mol_formula', 'mol_weight', 'exact_mass', 'inchikey', 'smiles', 'cluster_id', 'node_id', 'synonyms', 'inchi', 'm_plus_h', 'm_plus_na', 'genus', 'species']
npclassifier_class	Represents a NPClassifier class	None	None	uid	['uid']
npclassifier_pathway	Represents a NPClassifier pathway	None	None	uid	['uid']
npclassifier_superclass	Represents a NPClassifier superclass	None	None	uid	['uid']
npmrd	Represents a single NP-MRD entry	None	None	uid	['uid']
nucleotide	Represents a single nucleotide sequence (e.g. a contig/scaffold/chromosome)	genomic_info	locus.header	uid	['uid', 'external_id', 'altitude', 'bio_material', 'bioproject', 'biosample', 'cell_line', 'cell_type', 'chromosome', 'clone', 'clone_lib', 'collected_by', 'collection_date', 'country', 'cultivar', 'culture_collection', 'db_xref', 'dev_stage', 'ecotype', 'environmental_sample', 'focus', 'germline', 'haplogroup', 'haplotype', 'host', 'identified_by', 'isolate', 'isolation_source', 'lab_host', 'lat_lon', 'macronuclear', 'map', 'mating_type', 'metagenome_source', 'mol_type', 'note', 'organelle', 'organism', 'pcr_primers', 'plasmid', 'pop_variant', 'proviral', 'rearranged', 'segment', 'serotype', 'serovar', 'sex', 'specimen_voucher', 'strain', 'sub_clone', 'submitter_seqid', 'sub_species', 'sub_strain', 'tissue_lib', 'tissue_type', 'transgenic', 'type_material', 'variety']
parameters	Parameters and environmental variables used during database creation	parameters	parameters.header	uid	['uid', 'SG_LOC_NEO4J', 'SG_LOC_HMMS', 'NEO4J_dbms_memory_pagecache_size', 'NEO4J_dbms_memory_heap_initial__size', 'NEO4J_dbms_memory_heap_max__size', 'HMMSEARCH_IEVALUE', 'HMMSEARCH_BACKGROUND', 'HMMSEARCH_BIASFILTER', 'HMMSEARCH_NULL2', 'HMMSEARCH_SEED', 'HMMSEARCH_Z', 'HMMSEARCH_DOMZ', 'HMMSEARCH_F1', 'HMMSEARCH_F2', 'HMMSEARCH_F3', 'HMMSEARCH_E', 'HMMSEARCH_DOME', 'HMMSEARCH_INCE', 'HMMSEARCH_INCDOME', 'HMMSEARCH_BITCUTOFFS', 'platform', 'architecture', 'py_executable', 'py_version', 'genome_download_command']
protein	Represents a non-redundant protein	protein_info	protein_ids.header	uid	['uid', 'crc64', 'sequence']
publication	Represents a publication	None	None	doi	['doi', 'pmid', 'authors', 'title', 'journal', 'year']
publication	Represents a publication	None	None	doi	['doi', 'pmid', 'authors', 'title', 'journal', 'year']
substructure	Represents a chemical substructure	None	None	inchi, CanonicalSmiles	['uid', 'inchi', 'CanonicalSmiles']
taxid	Represents a single taxon within NCBI taxonomy	taxdump_process	taxid.header	uid	['uid', 'name', 'rank']
tigrfam_mainrole	Represents a TIGRFAM main role	tigrfam_info	tigrfam_mainrole.header	uid	['uid']
tigrfam_role	Represents a TIGRFAM role	tigrfam_info	tigrfam_role.header	uid	['uid']
tigrfam_subrole	Represents a TIGRFAM sub role	tigrfam_info	tigrfam_subrole.header	uid	['uid']

Relationships

Label	Relationship	NF results subdirectory	Neo4j header file
ANNOTATES	(:hmm)-[:ANNOTATES]->(:protein)	parsed_domtblout	protein_to_hmm_header.header
ANALYSIS_OF	(:mass_spectrum_file)-[:ANALYSIS_OF]->(:assembly)	None	None
ALTERNATIVE_PARENTS	(:npatlas)-[:ALTERNATIVE_PARENTS]->(:classyfire)	None	None
ASSEMBLES_TO	(:nucleotide)-[:ASSEMBLES_TO]->(:assembly)	genomic_info	assembly_to_locus.header
BLASTP	(:protein)-[:BLASTP]->(:protein)	diamond_blastp	blastp.header
CLUSTERS_TO	(:ms2_spectrum)-[:CLUSTERS_TO]->(:gnps_cluster)	None	None
DIRECT_PARENT	(:npatlas)-[:DIRECT_PARENT]->(:classyfire)	None	None
ENCODES	(:nucleotide)-[:ENCODES]->(:protein)	genomic_info	locus_to_protein.header
FROM	(:gnps_library_spectrum)-[:FROM]->(:gnps_organism)	None	None
FROM	(:gnps_library_spectrum)-[:FROM]->(:instrument)	None	None
FROM	(:gnps_library_spectrum)-[:FROM]->(:ion_source)	None	None
GOTERM_RELS	(:goterm)-[:GOTERM_RELS]->(:goterm)	goterms	go_to_go.header
GO_ANN	(:hmm_source)-[:GO_ANN]->(:goterm)	tigrfam_info	tigrfam_to_go.header
HAS	(:npatlas)-[:HAS]->(:gnps_library_spectrum)	None	None
HAS	(:mass_spectrum_file)-[:HAS]->(:ms2_spectrum)	None	None
HAS	(:npatlas)-[:HAS]->(:npmrd)	None	None
HAS	(:npatlas)-[:HAS]->(:publication)	None	None
IS_A	(:gnps_library_spectrum)-[:IS_A]->(:chemical_compound)	None	None
IS_A	(:npatlas)-[:IS_A]->(:chebi)	None	None
IS_A	(:npatlas)-[:IS_A]->(:chemical_compound)	None	None
IS_A	(:npatlas)-[:IS_A]->(:npclassifier_superclass)	None	None
IS_A	(:npatlas)-[:IS_A]->(:npclassifier_pathway)	None	None
IS_A	(:npatlas)-[:IS_A]->(:npclassifier_class)	None	None
IS_A	(:gnps_library_spectrum)-[:IS_A]->(:npclassifier_pathway)	None	None
IS_TAXON	(:assembly)-[:IS_TAXON]->(:taxid)	genomic_info	assembly_to_taxid.header
IS_A	(:classyfire)-[:IS_A]->(:classyfire)	None	None
IS_A	(:gnps_library_spectrum)-[:IS_A]->(:npclassifier_superclass)	None	None
INTERMEDIATE_NODES	(:npatlas)-[:INTERMEDIATE_NODES]->(:classyfire)	None	None
IS_A	(:gnps_library_spectrum)-[:IS_A]->(:npclassifier_class)	None	None
LOWEST_CLASS	(:npatlas)-[:LOWEST_CLASS]->(:classyfire)	None	None
LIBRARY_HIT	(:gnps_cluster)-[:LIBRARY_HIT]->(:gnps_library_spectrum)	None	None
MAINROLE_ANN	(:tigrfam_role)-[:MAINROLE_ANN]->(:tigrfam_mainrole)	tigrfam_info	tigrfamrole_to_mainrole.header
MOLECULAR_NETWORK	(:gnps_cluster)-[:MOLECULAR_NETWORK]->(:gnps_cluster)	None	None
MCS_SIMILARITY	(:chemical_compound)-[:MCS_SIMILARITY]->(:chemical_compound)	None	None
MMSEQS2	(:protein)-[:MMSEQS2]->(:protein)	mmseqs2_cluster	mmseqs2.header
PRODUCES	(:taxid)-[:PRODUCES]->(:npatlas)	None	None
PROTEIN_TO_GO	(:protein)-[:PROTEIN_TO_GO]->(:goterm)	protein_info	protein_to_go.header
PRODUCES	(:assembly:mibig)-[:PRODUCES]->(:mibig_compound)	None	None
PRODUCES	(:assembly:mibig)-[:PRODUCES]->(:npatlas)	None	None
ROLE_ANN	(:hmm_source)-[:ROLE_ANN]->(:tigrfam_role)	tigrfam_info	tigrfam_to_role.header
SUBSTRUCTURE	(:chemical_compound)-[:SUBSTRUCTURE]->(:substructure)	None	None
SOURCE_DB	(:hmm)-[:SOURCE_DB]->(:hmm_source)	hmm_info	hmm_source_relationships.header
SYNONYM	(:classyfire)-[:SYNONYM]->(:chebi)	None	None
SUBROLE_ANN	(:tigrfam_role)-[:SUBROLE_ANN]->(:tigrfam_subrole)	tigrfam_info	tigrfamrole_to_subrole.header
TAXON_PARENT	(:taxid)-[:TAXON_PARENT]->(:taxid)	taxdump_process	taxid_to_taxid.header
TANIMOTO_SIMILARITY	(:chemical_compound)-[:TANIMOTO_SIMILARITY]->(:chemical_compound)	None	None