life-sciences-connector

Query PubMed and scientific databases for protocols, analyze biological data with Biopython, handle HIPAA-compliant data. Use for biology research, protocol searches, sequence analysis, or scientific data handling. Cross-validates sources for high accuracy. Triggers on "PubMed", "biology", "scientific data", "sequences", "protocols", "life sciences", "HIPAA".

⭐5stars🔀1forks📁View on GitHub🕐Updated Jan 11, 2026⬇️1downloads

When & Why to Use This Skill

The Life Sciences Connector is a specialized Claude skill designed to bridge the gap between AI and biological research. It enables seamless querying of PubMed and scientific databases, automates sequence analysis using Biopython, and ensures HIPAA-compliant data handling. By providing high-accuracy cross-validation of protocols and scientific data, it significantly accelerates the research workflow for life science professionals and bioinformaticians.

Use Cases

  • Automated Literature Review: Quickly search and fetch detailed article metadata from PubMed for specific research topics like CRISPR or gene editing to stay updated with the latest publications.
  • Bioinformatics Workflows: Execute sequence analysis and alignment tasks directly by leveraging Biopython integration for parsing FASTA files and calculating alignment scores.
  • HIPAA-Compliant Data Processing: Securely handle and anonymize sensitive patient information or Protected Health Information (PHI) within research datasets to maintain regulatory compliance.
  • Protocol Discovery and Validation: Search for, retrieve, and cross-validate experimental protocols from scientific databases to ensure laboratory accuracy and reproducibility.
namelife-sciences-connector
descriptionQuery PubMed and scientific databases for protocols, analyze biological data with Biopython, handle HIPAA-compliant data. Use for biology research, protocol searches, sequence analysis, or scientific data handling. Cross-validates sources for high accuracy. Triggers on "PubMed", "biology", "scientific data", "sequences", "protocols", "life sciences", "HIPAA".

Life Sciences Connector

Purpose

Connect to scientific databases (PubMed, Benchling) for protocol queries and biological data analysis with Biopython integration.

When to Use

  • Biology research tasks
  • Protocol searches
  • Scientific data handling
  • Sequence analysis
  • Lab data integration
  • HIPAA-compliant workflows

Core Instructions

PubMed Query

from Bio import Entrez
Entrez.email = "your.email@example.com"

def search_pubmed(term, retmax=5):
    """Search PubMed for articles"""
    handle = Entrez.esearch(db="pubmed", term=term, retmax=retmax)
    record = Entrez.read(handle)
    return record['IdList']

def fetch_article(pmid):
    """Fetch article details"""
    handle = Entrez.efetch(db="pubmed", id=pmid, rettype="xml")
    return Entrez.read(handle)

# Usage
results = search_pubmed("CRISPR protocol")
for pmid in results:
    article = fetch_article(pmid)
    print(article['Title'])

Sequence Analysis

from Bio import SeqIO
from Bio.Align import PairwiseAligner

# Parse FASTA
sequences = list(SeqIO.parse("sequences.fasta", "fasta"))

# Align sequences
aligner = PairwiseAligner()
alignments = aligner.align(sequences[0].seq, sequences[1].seq)
print(f"Alignment score: {alignments[0].score}")

HIPAA Compliance

def anonymize_patient_data(data):
    """
    Anonymize patient information (HIPAA)
    """
    # Remove PHI (Protected Health Information)
    phi_fields = [
        'name', 'address', 'phone', 'email',
        'ssn', 'medical_record_number'
    ]

    anonymized = data.copy()
    for field in phi_fields:
        if field in anonymized:
            anonymized[field] = hash_or_remove(field, data[field])

    return anonymized

Guidelines

  • Accuracy: Cross-validate sources
  • Privacy: Anonymize patient data (HIPAA)
  • Citations: Always cite sources
  • Verification: Cross-check protocols

Dependencies

  • Python 3.8+
  • biopython
  • requests
  • PubMed Entrez API access

Version

v1.0.0 (2025-10-23)