Available Databases

SmartsBio connects to 36+ major public bioinformatics databases across sequences, structures, variants, pathways, clinical data, literature, and patents. Each database is accessed through one or more tools in the API.

How it works: Databases are accessed via tools — each tool wraps one or more database APIs. Call them directly with POST /v1/tools/:id/run or let the agent automatically pick the right databases when you use the Query endpoint.

Database Reference

36 databases organized by data type. Click a database name to read the full parameter reference.

Sequence Search6 databases

Database	Tool ID	Scale	Description	Key Parameters
NCBI BLAST	ncbi_blast	Trillions of sequences	Nucleotide & protein similarity search (blastn, blastp, blastx, tblastn, tblastx) against nt, nr, refseq, swissprot.	sequence, program, database, evalue
EBI Job Dispatcher	ebi_job_dispatcher	50+ EMBL-EBI tools	EMBL-EBI Job Dispatcher: BLAST, Clustal Omega, T-Coffee, InterProScan, HMMER, and 45+ more tools.	tool, sequence, database, params
SmartsMatch	smartsmatch_protein	250M+ proteins (AI index)	Fast AI-powered protein similarity search using vector embeddings — faster and more context-aware than BLAST. Detects remote homologs and functional analogs.	sequence, top_k, threshold, search_mode, index
NCBI Nucleotide	ncbi_nucleotide	400M+ sequences	DNA/RNA sequences from GenBank, RefSeq, and EMBL. Fetch by accession or search by keyword.	accession or query, database
NCBI Protein	ncbi_protein	700M+ sequences	Protein sequences from NCBI Protein and RefSeq. Supports accession fetch and keyword search.	accession or query
NCBI SRA	ncbi_sra	30+ petabytes of reads	Sequence Read Archive: raw sequencing runs. Search by organism, study, sample, or experiment.	query, organism, platform, library_strategy

Protein & Structure6 databases

Database	Tool ID	Scale	Description	Key Parameters
RCSB PDB	pdb_toolkit	220,000+ structures	Experimentally determined 3D structures (X-ray, cryo-EM, NMR). Fetch PDB/mmCIF by ID or search by keyword.	pdb_id, format (pdb / mmcif)
AlphaFold DB	alphafold_db	214M+ predicted structures	DeepMind AlphaFold predicted structures for the entire UniProt proteome with per-residue pLDDT confidence.	uniprot_id, format
UniProt	uniprot_toolkit	250M+ entries (570K Swiss-Prot)	Protein knowledgebase: sequences, functional annotations, GO terms, pathways, and cross-references. Supports ID mapping.	accession or query, database (uniprot / swissprot), format
STRING	string_db	20B+ interactions, 59M proteins	Protein-protein interaction networks: experimental, co-expression, co-occurrence, text-mining, and genomic context.	proteins (list), species, score_threshold, network_type
InterPro	interpro_toolkit	48,000+ entries	Protein domain classification and functional prediction (Pfam, PANTHER, HAMAP, Gene3D, and 12+ member databases).	sequence or accession, databases
NCBI Structure	ncbi_structure	PDB-integrated	NCBI Structure database: structural neighbors, conserved domains, and integrated PDB access.	pdb_id or query

Genomics & Variants7 databases

Database	Tool ID	Scale	Description	Key Parameters
NCBI Gene	ncbi_gene	50M+ gene records	Gene summaries, genomic coordinates, RefSeq IDs, expression data, and orthologs across species.	gene_symbol or query, organism
Ensembl	ensembl	300+ vertebrate genomes	Genome browser and annotation for vertebrates: gene models, regulatory features, variants, and comparative genomics.	gene_id, species, features
dbSNP	ncbi_dbsnp	1B+ variants	Reference SNP details by rs ID: allele frequencies, functional annotation, HGVS notation, and population data.	rs_id
GWAS Catalog	gwas_catalog	500K+ associations	NHGRI-EBI GWAS Catalog: SNP-trait associations, effect sizes, p-values, and ancestral populations.	trait or gene, p_value_threshold
NCBI Assembly	ncbi_assembly	1M+ genome assemblies	Reference and submitted genome assemblies. Search by organism, assembly level, or accession.	organism, assembly_level, query
NCBI Taxonomy	ncbi_taxonomy	2M+ taxa	Taxonomic classification: lineage, synonyms, common names, and taxon IDs for organisms.	organism_name or taxon_id
UCSC Genome Browser	ucsc_genome_browser	100+ genomes	UCSC genome tracks: conservation, regulatory elements, ENCODE data, genome coordinates, and liftover.	chrom, start, end, genome, tracks

Pathway & Ontology4 databases

Database	Tool ID	Scale	Description	Key Parameters
KEGG	kegg_toolkit	550+ pathways (human)	KEGG pathway enrichment, gene-to-pathway mapping, metabolic networks, and SVG pathway diagrams.	genes (list), organism, p_cutoff, pathway_id
Gene Ontology	go_toolkit	44,000+ GO terms	GO term search, gene-to-term lookup, and over-representation analysis (biological process, molecular function, cellular component).	genes (list), ontology, p_cutoff, organism
Biograph Knowledge Graph	biograph	60K genes · 26K diseases · 1M+ variants	smarts.bio proprietary knowledge graph: query relationships between genes, proteins, diseases, variants, pathways, and drugs across 3 query modes (entity-lookup, search, network).	mode, entity, entity_type, relation_types, depth
EBI Search	ebi_search	170+ biological datasets	EMBL-EBI unified cross-database search across UniProt, PDB, ChEMBL, Reactome, and 165+ more in a single query.	query, domain, fields, limit

Clinical & Drug5 databases

Database	Tool ID	Scale	Description	Key Parameters
ClinicalTrials.gov	clinical_trials_toolkit	400K+ trials	Search clinical trials by condition, intervention, phase, status, sponsor, and location.	condition, intervention, phase, status, country
ChEMBL	chembl_toolkit	2.4M+ compounds	Bioactivity database: compound-target interactions, IC50/Ki values, ADMET properties, and drug candidate profiles.	compound_id or smiles, target, activity_type
OpenFDA Drug	openfda_drug_toolkit	FDA/EMA/WHO data	Drug approvals, adverse event reports (FAERS), drug labeling, recalls, and WHO international drug data.	drug_name, event_type, date_range
FDA Medical Devices	medical_devices_toolkit	500K+ devices	FDA 510k clearances, PMA approvals, device recalls, and SNOMED CT medical device codes.	device_name or k_number, device_class, recall_status
NLM Clinical Tables	clinical_tables_toolkit	25+ reference tables	NLM Clinical Tables: RxNorm drugs, ICD codes, LOINC lab tests, HPO phenotypes, and genomics reference tables.	table, query, maxList

Literature6 databases

Database	Tool ID	Scale	Description	Key Parameters
PubMed	ncbi_pubmed	37M+ citations	Boolean and MeSH-aware search of biomedical literature. Returns titles, abstracts, authors, and PMIDs.	query, maxResults, date_range
bioRxiv	biorxiv_search	200K+ preprints	Biological sciences preprints — search by keyword, author, category, or DOI.	query, category, date_range
medRxiv	medrxiv_search	50K+ preprints	Clinical and health sciences preprints — search by keyword, author, or category.	query, category, date_range
arXiv	arxiv_search	2M+ papers	Physics, mathematics, and quantitative biology preprints. Useful for computational biology and bioinformatics algorithms.	query, category (q-bio.*), max_results
Crossref	crossref_search	150M+ works	DOI resolution, citation counts, bibliographic metadata, and journal/publisher lookup for published articles.	doi or query, type, date_range
Web (Tavily)	tavily_search	Live web index	General web search for current news, tool documentation, and findings not yet indexed in academic databases.	query, maxResults

Patents2 databases

Database	Tool ID	Scale	Description	Key Parameters
Google Patents	patent_search	87M+ patents	17+ patent offices worldwide via Google Patents Public Data (BigQuery). Full-text and CPC classification code search.	query, country_code, date_range, assignee, cpc_code
USPTO PatentsView	uspto_patents_search	10M+ US patents	US patent database via PatentsView API: full text, inventor/assignee details, citation counts, and CPC codes.	query, inventor, assignee, patent_date, cpc_subgroup

Discover Databases at Runtime

from smartsbio import SmartsBio

client = SmartsBio(api_key="sk_live_...")
tools = client.tools.list()

db_categories = [
    "Sequence Search", "Protein & Structure Databases",
    "Genomics & Variant Databases", "Pathway & Ontology",
    "Clinical & Drug Databases", "Literature", "Patents",
]
for category in db_categories:
    in_cat = [t for t in tools if t.category == category]
    if in_cat:
        print(f"\n{category}:")
        for t in in_cat:
            print(f"  {t.id:35s} {t.description[:50]}")

Query Examples

# UniProt — protein annotation
uniprot = client.tools.run(
    tool_id="uniprot_toolkit",
    input={"query": "BRCA1_HUMAN", "format": "json"},
)
print(uniprot["function"], uniprot["subcellular_location"])

# Ensembl — gene coordinates
ensembl = client.tools.run(
    tool_id="ensembl",
    input={"gene_id": "ENSG00000012048", "species": "human", "features": ["variants", "regulation"]},
)

# ChEMBL — drug-target bioactivity
chembl = client.tools.run(
    tool_id="chembl_toolkit",
    input={"target": "EGFR", "activity_type": "IC50", "limit": 20},
)
for compound in chembl["compounds"][:5]:
    print(f"{compound['molecule_chembl_id']}  IC50={compound['standard_value']} nM")

# ClinicalTrials.gov — open trials
trials = client.tools.run(
    tool_id="clinical_trials_toolkit",
    input={"condition": "breast cancer", "intervention": "BRCA1", "status": "RECRUITING"},
)
for trial in trials["studies"][:5]:
    print(f"{trial['nct_id']}: {trial['brief_title']}")

← Available Tools BLAST Reference →NCBI Reference →STRING Reference →