Workflow for read alignment, sorting, indexing, mapping statistics, and downstream-ready alignment artifacts.
日本語の概要は準備中です。原文の説明を表示しています。
Query ClinVar for clinical variant significance. Use when user asks about variant pathogenicity, genetic variants, clinical significance, or disease-causing mutations. Triggers on "clinvar", "pathogenic", "variant significance", "clinical significance", "disease variant", "mutation pathogenicity".
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Query NCBI ClinVar for clinical significance of genetic variants.
from Bio import Entrez
import json
Entrez.email = "bioclaw@example.com"
# 1. Search ClinVar
def search_clinvar(query, max_results=10):
handle = Entrez.esearch(db="clinvar", term=query, retmax=max_results)
record = Entrez.read(handle)
handle.close()
return record
# 2. Fetch variant details
def fetch_clinvar(id_list):
ids = ",".join(str(i) for i in id_list)
handle = Entrez.efetch(db="clinvar", id=ids, rettype="vcv", retmode="xml")
result = handle.read()
handle.close()
return result
# 3. Summary for ClinVar IDs
def clinvar_summary(id_list):
ids = ",".join(str(i) for i in id_list)
handle = Entrez.esummary(db="clinvar", id=ids, retmode="json")
result = json.loads(handle.read())
handle.close()
return result
# Example: Find pathogenic BRCA1 variants
search = search_clinvar("BRCA1[gene] AND clinsig_pathogenic[prop]", max_results=5)
print(f"Total pathogenic BRCA1 variants: {search['Count']}")
if search['IdList']:
summaries = clinvar_summary(search['IdList'])
for uid in search['IdList']:
info = summaries['result'].get(str(uid), {})
title = info.get('title', 'N/A')
clinical_sig = info.get('clinical_significance', {}).get('description', 'N/A')
genes = info.get('genes', [{}])
gene = genes[0].get('symbol', 'N/A') if genes else 'N/A'
print(f"\nVariant: {title}")
print(f"Gene: {gene}")
print(f"Clinical significance: {clinical_sig}")
BRCA1[gene] AND clinsig_pathogenic[prop]rs6025[rsid]"breast cancer"[dis] AND clinsig_pathogenic[prop]17[chr] AND 43000000:44000000[chrpos37]BRCA1[gene] AND origin_germline[prop]まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Workflow for read alignment, sorting, indexing, mapping statistics, and downstream-ready alignment artifacts.
日本語の概要は準備中です。原文の説明を表示しています。
Validate protein designs using AlphaFold2 structure prediction. Use this skill when: (1) Validating designed sequences fold correctly, (2) Predicting binder-target complex structures, (3) Calculating confidence metrics (pLDDT, pTM, ipTM), (4) Self-consistency validation of designs, (5) Multi-chain complex prediction with AlphaFold-Multimer. For faster single-chain prediction, use esm. For QC thresholds, use protein-qc.
日本語の概要は準備中です。原文の説明を表示しています。
AlphaFold2 / AlphaFold-Multimer structure prediction for validation and confidence scoring. Use this skill when: (1) Validating designed sequences fold correctly, (2) Predicting binder-target complex structures, (3) Calculating confidence metrics (pLDDT, pTM, ipTM), (4) Self-consistency validation of designs, (5) Multi-chain complex prediction with AlphaFold-Multimer. For faster single-chain prediction, use esm2-sequence-scoring. For QC thresholds, use protein-design-qc.
日本語の概要は準備中です。原文の説明を表示しています。
Workflow for event-level and isoform-level splicing analysis with sashimi-ready outputs and splice QC.
日本語の概要は準備中です。原文の説明を表示しています。
ATAC-seq processing with assay QC, MACS3 peak calling, consensus peak matrices, differential accessibility, and motif or footprint follow-up.
日本語の概要は準備中です。原文の説明を表示しています。
End-to-end binder design using BindCraft hallucination. Use this skill when: (1) Designing protein binders with built-in AF2 validation, (2) Running production-quality binder campaigns, (3) Using different design protocols (fast, default, slow), (4) Need joint backbone and sequence optimization, (5) Want high experimental success rate. For backbone-only generation, use rfdiffusion. For QC thresholds, use protein-qc. For tool selection guidance, use binder-design.
日本語の概要は準備中です。原文の説明を表示しています。