Bio Clinical Databases Gnomad Frequencies logo

Bio Clinical Databases Gnomad Frequencies

OrganizationPopular
FreedomIntelligence
bio-clinical-databases-gnomad-frequencies

Query gnomAD for population allele frequencies to assess variant rarity. Use when filtering variants by population frequency for rare disease analysis or determining if a variant is common in the general population.

Overview

PublisherFreedomIntelligence
RepositoryOpenClaw-Medical-Skills
Skill namebio-clinical-databases-gnomad-frequencies
Stars
3K
Forks
410
Bundled files
2
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by FreedomIntelligence on GitHub. Read the source before you install it.

Installation

Install the Bio Clinical Databases Gnomad Frequencies AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills.git /tmp/OpenClaw-Medical-Skills
mkdir -p .claude/skills
cp -r /tmp/OpenClaw-Medical-Skills/skills/bio-clinical-databases-gnomad-frequencies .claude/skills/bio-clinical-databases-gnomad-frequencies
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Bio Clinical Databases Gnomad Frequencies in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Bio Clinical Databases Gnomad Frequencies on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Bio Clinical Databases Gnomad Frequencies is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Version Compatibility

Reference examples tested with: requests 2.31+, pandas 2.2+

Before using code patterns, verify installed versions match. If versions differ:

  • Python: pip show <package> then help(module.function) to check signatures

If code throws ImportError, AttributeError, or TypeError, introspect the installed package and adapt the example to match the actual API rather than retrying.

gnomAD Frequency Queries

gnomAD REST API

Goal: Retrieve exome and genome allele frequencies from gnomAD for individual variants.

Approach: Send a GraphQL query to the gnomAD API with variant ID and dataset version, then parse exome/genome frequency fields.

"Check how common this variant is in the population" → Query gnomAD for allele frequency, allele count, and homozygote count.

  • Python: GraphQL via requests.post() (requests)
  • Python: myvariant.MyVariantInfo().getvariant() (myvariant)

Query Single Variant

python
import requests

def query_gnomad(chrom, pos, ref, alt, dataset='gnomad_r4'):
    '''Query gnomAD API for variant frequency

    dataset options: gnomad_r4, gnomad_r3, gnomad_r2_1
    '''
    url = 'https://gnomad.broadinstitute.org/api'

    query = '''
    query ($variantId: String!, $dataset: DatasetId!) {
        variant(variantId: $variantId, dataset: $dataset) {
            exome {
                ac
                an
                af
                homozygote_count
            }
            genome {
                ac
                an
                af
                homozygote_count
            }
        }
    }
    '''

    variant_id = f'{chrom}-{pos}-{ref}-{alt}'
    variables = {'variantId': variant_id, 'dataset': dataset}

    response = requests.post(url, json={'query': query, 'variables': variables})
    return response.json()

Parse gnomAD Response

python
def parse_gnomad_result(result):
    '''Extract allele frequencies from gnomAD response'''
    data = result.get('data', {}).get('variant', {})
    if not data:
        return None

    exome = data.get('exome', {}) or {}
    genome = data.get('genome', {}) or {}

    return {
        'exome_af': exome.get('af'),
        'exome_ac': exome.get('ac'),
        'exome_an': exome.get('an'),
        'exome_hom': exome.get('homozygote_count'),
        'genome_af': genome.get('af'),
        'genome_ac': genome.get('ac'),
        'genome_an': genome.get('an'),
        'genome_hom': genome.get('homozygote_count')
    }

Query via myvariant.info

Goal: Retrieve gnomAD frequencies through the myvariant.info aggregation layer for simpler API access.

Approach: Query myvariant.info by HGVS notation with gnomAD fields specified, extracting exome and genome allele frequencies.

python
import myvariant

mv = myvariant.MyVariantInfo()

def get_gnomad_via_myvariant(variant_hgvs):
    '''Get gnomAD frequencies via myvariant.info'''
    result = mv.getvariant(variant_hgvs, fields=['gnomad_exome', 'gnomad_genome'])

    exome = result.get('gnomad_exome', {})
    genome = result.get('gnomad_genome', {})

    return {
        'exome_af': exome.get('af', {}).get('af'),
        'genome_af': genome.get('af', {}).get('af')
    }

Population-Specific Frequencies

Goal: Retrieve ancestry-specific allele frequencies to assess variant rarity within relevant populations.

Approach: Query the gnomAD population-stratified AF fields (AFR, AMR, ASJ, EAS, FIN, NFE, SAS) via myvariant.info.

python
def get_population_frequencies(variant_hgvs):
    '''Get gnomAD frequencies by ancestry population'''
    mv = myvariant.MyVariantInfo()
    result = mv.getvariant(variant_hgvs, fields=['gnomad_exome.af'])

    af_data = result.get('gnomad_exome', {}).get('af', {})

    populations = {
        'af': af_data.get('af'),           # Global
        'af_afr': af_data.get('af_afr'),   # African
        'af_amr': af_data.get('af_amr'),   # Admixed American
        'af_asj': af_data.get('af_asj'),   # Ashkenazi Jewish
        'af_eas': af_data.get('af_eas'),   # East Asian
        'af_fin': af_data.get('af_fin'),   # Finnish
        'af_nfe': af_data.get('af_nfe'),   # Non-Finnish European
        'af_sas': af_data.get('af_sas'),   # South Asian
    }
    return populations

Filtering Thresholds

Common frequency cutoffs for variant filtering:

ThresholdUse Case
< 0.01 (1%)Rare disease, ACMG PM2
< 0.001 (0.1%)Stringent rare disease
< 0.0001 (0.01%)Ultra-rare
AbsentNovel variant

Filter Variants by Frequency

Goal: Apply population frequency thresholds to retain only rare variants for downstream analysis.

Approach: Compare the maximum allele frequency across exome and genome datasets against a configurable threshold (default 1% per ACMG PM2).

python
def is_rare(gnomad_af, threshold=0.01):
    '''Check if variant is rare based on gnomAD AF

    threshold: Default 0.01 (1%) per ACMG PM2 supporting criterion
    Use 0.001 for more stringent filtering
    '''
    if gnomad_af is None:
        return True  # Absent from gnomAD = rare
    return gnomad_af < threshold

def filter_rare_variants(variants, threshold=0.01):
    '''Filter list of variants to keep only rare ones'''
    rare = []
    for v in variants:
        exome_af = v.get('gnomad_exome_af')
        genome_af = v.get('gnomad_genome_af')
        max_af = max(filter(None, [exome_af, genome_af]), default=None)
        if is_rare(max_af, threshold):
            rare.append(v)
    return rare

Batch Query with Local gnomAD

Goal: Perform large-scale frequency lookups using a local gnomAD Hail Table for high throughput.

Approach: Load the gnomAD sites Hail Table from Google Cloud Storage and filter by allele frequency threshold.

For large-scale analysis, use local gnomAD VCF/Hail Table:

python
# Using Hail for gnomAD v4
import hail as hl

ht = hl.read_table('gs://gcp-public-data--gnomad/release/4.0/ht/exomes/gnomad.exomes.v4.0.sites.ht')

# Filter to rare variants
rare_ht = ht.filter(ht.freq[0].AF < 0.01)

Related Skills

  • myvariant-queries - Aggregated queries including gnomAD
  • variant-prioritization - Filter by frequency thresholds
  • population-genetics/population-structure - Population stratification analysis

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Bio Clinical Databases Gnomad Frequencies AI skill do?

Query gnomAD for population allele frequencies to assess variant rarity. Use when filtering variants by population frequency for rare disease analysis or determining if a variant is common in the general population.

Why use Bio Clinical Databases Gnomad Frequencies on TypingMind?

Because you install it once and use it with any model. Bio Clinical Databases Gnomad Frequencies is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Bio Clinical Databases Gnomad Frequencies in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills/tree/main/skills/bio-clinical-databases-gnomad-frequencies. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Bio Clinical Databases Gnomad Frequencies?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Bio Clinical Databases Gnomad Frequencies?

As many as you like. As long as a model supports skills, you can use Bio Clinical Databases Gnomad Frequencies with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Bio Clinical Databases Gnomad Frequencies AI skill free?

It is published on GitHub by FreedomIntelligence. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇