Skip to content

K-Dense-AI/scientific-agent-skills / skills/database-lookup

database-lookup

Verified

Queries documented public database APIs with explicit endpoints, filters, pagination, and provenance. Used when a scientific, regulatory, financial, or other database-backed fact must be retrieved reproducibly from a named source rather than inferred from general knowledge.

FileKindSize
SKILL.mdskill md26.9 KB
references/addgene.mdmarkdown1.7 KB
references/alphafold.mdmarkdown2.9 KB
references/alphavantage.mdmarkdown7.9 KB
references/bea.mdmarkdown14.3 KB
references/bindingdb.mdmarkdown2.9 KB
references/biogrid.mdmarkdown3.8 KB
references/bls.mdmarkdown9.1 KB
references/brenda.mdmarkdown2.9 KB
references/cbioportal.mdmarkdown7.4 KB
references/census.mdmarkdown9.0 KB
references/chebi.mdmarkdown3.5 KB
references/chembl.mdmarkdown2.7 KB
references/clinicaltrials.mdmarkdown3.4 KB
references/clinpgx.mdmarkdown1.5 KB
references/clinvar.mdmarkdown4.1 KB
references/cod.mdmarkdown3.0 KB
references/cosmic.mdmarkdown1.3 KB
references/dailymed.mdmarkdown1.8 KB
references/database_selection_guide.mdmarkdown10.0 KB
references/datacommons.mdmarkdown7.0 KB
references/dbsnp.mdmarkdown3.5 KB
references/disgenet.mdmarkdown1.4 KB
references/drugbank.mdmarkdown1.3 KB
references/ecb.mdmarkdown5.2 KB
references/emdb.mdmarkdown1.1 KB
references/ena.mdmarkdown9.9 KB
references/encode.mdmarkdown1.8 KB
references/ensembl.mdmarkdown14.0 KB
references/epa.mdmarkdown1.9 KB
references/eurostat.mdmarkdown7.3 KB
references/fda.mdmarkdown2.1 KB
references/federal-reserve.mdmarkdown6.7 KB
references/fred.mdmarkdown9.9 KB
references/gene-ontology.mdmarkdown4.4 KB
references/geo.mdmarkdown3.8 KB
references/gnomad.mdmarkdown3.5 KB
references/gtex.mdmarkdown4.1 KB
references/gwas-catalog.mdmarkdown1.6 KB
references/hca.mdmarkdown1.4 KB
references/hpo.mdmarkdown1.2 KB
references/human-protein-atlas.mdmarkdown1.2 KB
references/interpro.mdmarkdown3.4 KB
references/jaspar.mdmarkdown1.4 KB
references/kegg.mdmarkdown2.5 KB
references/lincs-l1000.mdmarkdown2.1 KB
references/materials-project.mdmarkdown4.8 KB
references/metabolomics-workbench.mdmarkdown3.8 KB
references/monarch.mdmarkdown1.5 KB
references/mousemine.mdmarkdown1.5 KB
references/myvariant.mdmarkdown1.3 KB
references/nasa-exoplanet-archive.mdmarkdown4.3 KB
references/nasa.mdmarkdown3.0 KB
references/ncbi-gene.mdmarkdown1.7 KB
references/ncbi-protein.mdmarkdown3.2 KB
references/ncbi-taxonomy.mdmarkdown3.7 KB
references/nist.mdmarkdown3.6 KB
references/noaa.mdmarkdown6.7 KB
references/omim.mdmarkdown3.4 KB
references/opentargets.mdmarkdown7.0 KB
references/openweathermap.mdmarkdown8.2 KB
references/pdb.mdmarkdown3.2 KB
references/pride.mdmarkdown1.4 KB
references/pubchem.mdmarkdown3.4 KB
references/quickgo.mdmarkdown1.5 KB
references/reactome.mdmarkdown2.9 KB
references/regulomedb.mdmarkdown2.0 KB
references/retrieval-contract.mdmarkdown7.2 KB
references/rummageo.mdmarkdown1.3 KB
references/sdss.mdmarkdown4.4 KB
references/sec-edgar.mdmarkdown8.3 KB
references/simbad.mdmarkdown12.3 KB
references/sra.mdmarkdown4.5 KB
references/string.mdmarkdown7.7 KB
references/tcga-gdc.mdmarkdown2.0 KB
references/treasury.mdmarkdown7.2 KB
references/ucsc-genome.mdmarkdown3.3 KB
references/uniprot.mdmarkdown7.1 KB
references/usgs.mdmarkdown9.9 KB
references/uspto.mdmarkdown4.6 KB
references/who.mdmarkdown8.7 KB
references/worldbank.mdmarkdown7.0 KB
references/zinc.mdmarkdown5.7 KB

references/sra.md

View on GitHub
# SRA (Sequence Read Archive) API Reference

## Overview
Sequencing run metadata: experiments, samples, studies, and runs. Accessible via E-utilities with `db=sra`. Returns XML metadata describing sequencing experiments, platforms, library strategies, and sample attributes.

## Base URL
```
https://eutils.ncbi.nlm.nih.gov/entrez/eutils/
```

## Authentication
- **API key** (recommended): Append `&api_key=YOUR_KEY`.
- Without key: 3 req/sec. With key: 10 req/sec.
- Provide `tool` and `email` parameters.

## Key Endpoints

### 1. ESearch -- Search SRA records
```
GET esearch.fcgi?db=sra&term=QUERY&retmax=N&retmode=json
```

**Example -- search RNA-seq experiments in human:**
```
GET esearch.fcgi?db=sra&term=RNA-seq[Strategy] AND Homo sapiens[Organism]&retmax=5&retmode=json
```
Response:
```json
{
  "esearchresult": {
    "count": "584231",
    "retmax": "5",
    "idlist": ["28574913", "28574912", "28574911", ...]
  }
}
```

**Example -- search by accession:**
```
GET esearch.fcgi?db=sra&term=SRP123456[Accession] OR SRR123456[Accession]&retmode=json
```

### 2. EFetch -- Retrieve full SRA metadata (XML only)
```
GET efetch.fcgi?db=sra&id=IDS&rettype=full&retmode=xml
```

**Example -- fetch metadata for an SRA record:**
```
GET efetch.fcgi?db=sra&id=28574913&rettype=full&retmode=xml
```
Response (abbreviated XML):
```xml
<EXPERIMENT_PACKAGE_SET>
  <EXPERIMENT_PACKAGE>
    <EXPERIMENT accession="SRX12345" alias="...">
      <TITLE>RNA-seq of human liver tissue</TITLE>
      <STUDY_REF accession="SRP12345"/>
      <DESIGN>
        <LIBRARY_DESCRIPTOR>
          <LIBRARY_STRATEGY>RNA-Seq</LIBRARY_STRATEGY>
          <LIBRARY_SOURCE>TRANSCRIPTOMIC</LIBRARY_SOURCE>
          <LIBRARY_SELECTION>cDNA</LIBRARY_SELECTION>
          <LIBRARY_LAYOUT><PAIRED/></LIBRARY_LAYOUT>
        </LIBRARY_DESCRIPTOR>
      </DESIGN>
      <PLATFORM>
        <ILLUMINA><INSTRUMENT_MODEL>Illumina NovaSeq 6000</INSTRUMENT_MODEL></ILLUMINA>
      </PLATFORM>
    </EXPERIMENT>
    <SUBMISSION accession="SRA12345" center_name="GEO"/>
    <Organization><Name>Some Institute</Name></Organization>
    <STUDY accession="SRP12345">
      <DESCRIPTOR>
        <STUDY_TITLE>Transcriptomic analysis of human tissues</STUDY_TITLE>
        <STUDY_TYPE existing_study_type="Transcriptome Analysis"/>
      </DESCRIPTOR>
    </STUDY>
    <SAMPLE accession="SRS12345">
      <TITLE>Human liver RNA</TITLE>
      <SAMPLE_ATTRIBUTES>
        <SAMPLE_ATTRIBUTE><TAG>tissue</TAG><VALUE>liver</VALUE></SAMPLE_ATTRIBUTE>
        <SAMPLE_ATTRIBUTE><TAG>cell_type</TAG><VALUE>hepatocyte</VALUE></SAMPLE_ATTRIBUTE>
      </SAMPLE_ATTRIBUTES>
    </SAMPLE>
    <RUN_SET>
      <RUN accession="SRR12345" total_spots="45000000" total_bases="9000000000">
        <Statistics nreads="2">
          <Read average="150" count="45000000"/>
        </Statistics>
      </RUN>
    </RUN_SET>
  </EXPERIMENT_PACKAGE>
</EXPERIMENT_PACKAGE_SET>
```

### 3. ESummary -- Brief SRA summaries
```
GET esummary.fcgi?db=sra&id=IDS&retmode=json
```
Returns: experiment title, platform, total runs/spots/bases, create date, study/sample accessions as an XML string in the `expxml` and `runs` fields.

### 4. ELink -- Cross-link to other NCBI databases
```
GET elink.fcgi?dbfrom=sra&db=biosample&id=SRA_UID
GET elink.fcgi?dbfrom=sra&db=gds&id=SRA_UID
```

## SRA Accession Types
| Prefix | Entity |
|--------|--------|
| `SRP` / `ERP` / `DRP` | Study |
| `SRX` / `ERX` / `DRX` | Experiment |
| `SRS` / `ERS` / `DRS` | Sample |
| `SRR` / `ERR` / `DRR` | Run |
| `SRA` | Submission |

## Common Search Patterns
```
# By organism and strategy
term=Mus musculus[Organism] AND WGS[Strategy]

# By platform
term=Illumina[Platform] AND ATAC-seq[Strategy] AND human[Organism]

# By study accession
term=SRP123456[Accession]

# By BioProject
term=PRJNA123456[BioProject]

# By date range
term=("2024/01/01"[Publication Date] : "2024/12/31"[Publication Date])

# By library source
term=GENOMIC[Source] AND ChIP-Seq[Strategy] AND cancer[Text Word]

# By read count range
# Download run metadata, then filter the reported read_count field locally.
# Read length and number of reads are different quantities.

# Combined complex query
term=(RNA-Seq[Strategy] AND paired[Layout] AND Homo sapiens[Organism] AND Illumina[Platform])
```

## Rate Limits
- Without API key: 3 requests/second
- With API key: 10 requests/second
- For bulk metadata: use `usehistory=y` with `WebEnv`/`query_key`, fetch in batches
- Actual sequence data (FASTQ) is NOT available via E-utilities; use SRA Toolkit (`fastq-dump`/`fasterq-dump`) or the SRA cloud URLs
deprecation-and-migrationaddyosmani/agent-skillsManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
performance-optimizationaddyosmani/agent-skillsOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.Stars: 118kUpdated Claude CodeCodexVerifiedInstall
agent-cost-reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json.Stars: 118kUpdated Claude CodeCodexVerifiedInstall