life-sciences-connector

Query PubMed and analyze biological sequences with Biopython.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/doctorduke/seashells --skill life-sciences-connector
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: life-sciences-connector
Source: https://github.com/doctorduke/seashells/tree/main/.claude/skills/life-sciences-connector
Command: npx skills add https://github.com/doctorduke/seashells --skill life-sciences-connector

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires biopython, requests.

What problem does it solve?

This Skill simplifies access to vast scientific databases and provides powerful tools for biological data analysis, while ensuring critical compliance with privacy standards like HIPAA. It automates complex research tasks, saving researchers valuable time.

Core Features & Use Cases

  • PubMed Query & Fetch: Search and retrieve scientific articles from PubMed, streamlining literature reviews and protocol discovery.
  • Biological Sequence Analysis: Integrates Biopython for tasks like parsing FASTA files and aligning DNA/protein sequences.
  • HIPAA Compliance: Provides patterns for anonymizing patient data, ensuring sensitive information is handled securely and compliantly.
  • Use Case: A researcher needs to find all recent articles on "CRISPR protocol," analyze a set of gene sequences for homology, and then process patient data from a clinical trial while ensuring all personally identifiable information is anonymized according to HIPAA guidelines.

Quick Start

Example: Search PubMed for articles

from Bio import Entrez Entrez.email = "[email protected]" # Replace with your email results = Entrez.esearch(db="pubmed", term="CRISPR protocol", retmax=5) record = Entrez.read(results) print(record['IdList'])

Frequently Asked Questions about life-sciences-connector

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I search PubMed and retrieve scientific articles programmatically?▼

Search PubMed using Biopython's Entrez module to query by term and retrieve article metadata. Set your email in Entrez.email, call esearch() with your search term, and parse the returned ID list to fetch full records. This automates literature reviews and protocol discovery without manual database navigation.

Can I analyze DNA and protein sequences with Biopython?▼

Yes, Biopython provides sequence analysis tools to parse FASTA files, perform DNA and protein alignment, and compute homology. Load sequences with SeqIO, use the SeqRecord objects for analysis, and generate results for comparative genomics and research validation.

How do I handle patient data while maintaining HIPAA compliance?▼

Implement data anonymization patterns to remove personally identifiable information before processing. The Skill provides HIPAA-compliant workflows for clinical trial data, ensuring sensitive information is stripped and secure handling practices are applied throughout analysis.

What Python version and dependencies do I need to query scientific databases?▼

You need Python 3.8 or later with Biopython and requests libraries installed. These dependencies enable PubMed Entrez access and HTTP requests for database queries. Verify installation before running scripts that connect to external scientific data sources.

Can I combine PubMed protocol searches with sequence analysis in a single workflow?▼

Yes, integrate PubMed queries to find protocols with Biopython sequence analysis to validate findings against biological data. This combined approach automates research tasks by cross-validating literature against experimental sequences and lab data.

What should I know about cross-validating scientific data from multiple sources?▼

Cross-validate results across PubMed articles and sequence databases to ensure data accuracy and reliability. The Skill handles source verification and integration patterns, reducing errors when combining information from different scientific databases in research workflows.