Protocolsio Integration

pip install requests pandas
# For private protocol access or publishing:
# Register at https://www.protocols.io/developers to obtain an API token

import requests

BASE = "https://www.protocols.io/api/v4"
# For public protocols, no token needed (but add for higher rate limits)
HEADERS = {"Authorization": "Bearer YOUR_TOKEN_HERE"}  # Optional for public

# Search for CRISPR protocols
r = requests.get(f"{BASE}/protocols",
                 params={"q": "CRISPR guide RNA design", "order_field": "views",
                         "page_size": 5},
                 headers=HEADERS)
r.raise_for_status()
data = r.json()
print(f"Total CRISPR protocols: {data['pagination']['total_results']}")
for p in data["items"][:3]:
    print(f"\n  {p['title']}")
    print(f"  DOI: {p.get('doi')} | Views: {p.get('stats', {}).get('number_of_views')}")
    print(f"  Authors: {', '.join(a['name'] for a in p.get('creators', [])[:3])}")

import requests, pandas as pd

BASE = "https://www.protocols.io/api/v4"

def search_protocols(query, page_size=20, order_field="relevance", category_id=None):
    params = {"q": query, "page_size": page_size, "order_field": order_field}
    if category_id:
        params["filter[categories_ids][]"] = category_id
    r = requests.get(f"{BASE}/protocols", params=params)
    r.raise_for_status()
    return r.json()

data = search_protocols("RNA extraction tissue", page_size=10, order_field="views")
total = data["pagination"]["total_results"]
print(f"RNA extraction protocols: {total}")

rows = []
for p in data["items"][:10]:
    rows.append({
        "id": p.get("id"),
        "title": p.get("title"),
        "doi": p.get("doi"),
        "views": p.get("stats", {}).get("number_of_views", 0),
        "created": p.get("created_on"),
        "category": p.get("categories", [{}])[0].get("name", "n/a"),
    })
df = pd.DataFrame(rows).sort_values("views", ascending=False)
print(df.to_string(index=False))

# Search with category filter (get category IDs from /categories endpoint)
data_pcr = search_protocols("qPCR primer design", order_field="views")
print(f"\nqPCR protocols: {data_pcr['pagination']['total_results']}")
for p in data_pcr["items"][:3]:
    print(f"  {p['title'][:70]} (DOI: {p.get('doi', 'n/a')})")

import requests

BASE = "https://www.protocols.io/api/v4"

def get_protocol(protocol_id):
    r = requests.get(f"{BASE}/protocols/{protocol_id}")
    r.raise_for_status()
    return r.json()

# Retrieve protocol by ID (from search results or DOI lookup)
protocol_id = 45979  # Example: a public protocol
data = get_protocol(protocol_id)
protocol = data.get("payload", data)  # Handle API response structure

print(f"Title: {protocol.get('title')}")
print(f"DOI: {protocol.get('doi')}")
print(f"Authors: {', '.join(a['name'] for a in protocol.get('creators', []))}")
print(f"Steps: {len(protocol.get('steps', []))}")
print(f"Materials: {len(protocol.get('materials', []))}")
print(f"Abstract: {protocol.get('description', '')[:200]}")

# Parse protocol steps
protocol_steps = protocol.get("steps", [])
for i, step in enumerate(protocol_steps[:5], 1):
    step_desc = step.get("description", "")
    duration = step.get("duration", {})
    print(f"\nStep {i}: {step_desc[:120]}")
    if duration:
        print(f"  Duration: {duration.get('duration')} {duration.get('unit_label', '')}")

import requests, json

BASE = "https://www.protocols.io/api/v4"

def get_protocol_by_doi(doi):
    """Retrieve protocol using its DOI."""
    # URL-encode the DOI for the query
    r = requests.get(f"{BASE}/protocols",
                     params={"q": doi, "page_size": 5})
    r.raise_for_status()
    items = r.json()["items"]
    for item in items:
        if item.get("doi") == doi:
            return item
    return None

doi = "10.17504/protocols.io.bvb3n2qn"  # Example protocols.io DOI
protocol = get_protocol_by_doi(doi)
if protocol:
    print(f"Found: {protocol['title']}")
    print(f"  ID: {protocol['id']}")
    print(f"  Version: {protocol.get('version_id')}")

import requests, pandas as pd

BASE = "https://www.protocols.io/api/v4"

def get_reagents(protocol_id):
    r = requests.get(f"{BASE}/protocols/{protocol_id}")
    r.raise_for_status()
    data = r.json()
    protocol = data.get("payload", data)
    return protocol.get("materials", [])

# Get reagents list
materials = get_reagents(45979)  # Example protocol ID
print(f"Materials ({len(materials)} items):")
rows = []
for m in materials[:10]:
    rows.append({
        "name": m.get("name"),
        "quantity": m.get("quantity"),
        "unit": m.get("unit", {}).get("name", ""),
        "supplier": m.get("supplier", {}).get("name", ""),
        "catalog": m.get("sku"),
    })
df = pd.DataFrame(rows)
print(df.to_string(index=False))

import requests, pandas as pd

BASE = "https://www.protocols.io/api/v4"

r = requests.get(f"{BASE}/categories")
r.raise_for_status()
data = r.json()
categories = data.get("items", data.get("payload", []))

print(f"protocols.io categories: {len(categories)}")
df = pd.DataFrame(categories)[["id", "name"]].head(20)
print(df.to_string(index=False))

import requests

BASE = "https://www.protocols.io/api/v4"

def get_protocol_versions(protocol_id):
    r = requests.get(f"{BASE}/protocols/{protocol_id}")
    r.raise_for_status()
    protocol = r.json().get("payload", r.json())
    return {
        "title": protocol.get("title"),
        "version": protocol.get("version_id"),
        "published": protocol.get("published_on"),
        "doi": protocol.get("doi"),
        "parent_doi": protocol.get("parent_publication", {}).get("doi"),
    }

info = get_protocol_versions(45979)
for k, v in info.items():
    print(f"  {k}: {v}")

import requests, pandas as pd

BASE = "https://www.protocols.io/api/v4"

def search_and_rank(query, top_n=20):
    """Search protocols and return ranked by views + forks."""
    r = requests.get(f"{BASE}/protocols",
                     params={"q": query, "page_size": top_n, "order_field": "views"})
    r.raise_for_status()
    data = r.json()

    rows = []
    for p in data["items"]:
        stats = p.get("stats", {})
        rows.append({
            "id": p.get("id"),
            "title": p.get("title"),
            "doi": p.get("doi"),
            "views": stats.get("number_of_views", 0),
            "forks": stats.get("number_of_forks", 0),
            "steps": p.get("number_of_steps"),
            "created": p.get("created_on")[:10] if p.get("created_on") else "n/a",
            "category": p.get("categories", [{}])[0].get("name", "n/a"),
        })

    df = pd.DataFrame(rows)
    df["popularity_score"] = df["views"] * 0.7 + df["forks"] * 0.3 * 100
    return df.sort_values("popularity_score", ascending=False)

# Compare western blotting protocols
df = search_and_rank("western blot protein detection", top_n=15)
df.to_csv("western_blot_protocols.csv", index=False)
print("Top western blot protocols:")
print(df[["title", "views", "forks", "steps"]].head(8).to_string(index=False))

import requests, pandas as pd

BASE = "https://www.protocols.io/api/v4"

def extract_protocol_steps(protocol_id):
    """Extract structured step data from a protocol."""
    r = requests.get(f"{BASE}/protocols/{protocol_id}")
    r.raise_for_status()
    protocol = r.json().get("payload", r.json())

    steps = []
    for i, step in enumerate(protocol.get("steps", []), 1):
        duration = step.get("duration", {})
        steps.append({
            "step_number": i,
            "description": step.get("description", ""),
            "duration_value": duration.get("duration"),
            "duration_unit": duration.get("unit_label", ""),
            "temperature": step.get("temperature", {}).get("value"),
            "temp_unit": step.get("temperature", {}).get("unit_label", ""),
        })

    materials = [{
        "name": m.get("name"),
        "quantity": m.get("quantity"),
        "unit": m.get("unit", {}).get("name", ""),
    } for m in protocol.get("materials", [])]

    return {
        "title": protocol.get("title"),
        "doi": protocol.get("doi"),
        "steps": pd.DataFrame(steps),
        "materials": pd.DataFrame(materials),
    }

result = extract_protocol_steps(45979)
print(f"Protocol: {result['title']}")
print(f"\nSteps ({len(result['steps'])}):")
print(result["steps"][["step_number", "description", "duration_value", "duration_unit"]].head(5).to_string(index=False))
print(f"\nMaterials ({len(result['materials'])}):")
print(result["materials"].head(5).to_string(index=False))

# Export for automation
result["steps"].to_csv("protocol_steps.csv", index=False)
result["materials"].to_csv("protocol_materials.csv", index=False)