Biorxiv Database

pip install requests pandas

import requests

BASE = "https://api.biorxiv.org"

# Retrieve recent bioinformatics preprints
r = requests.get(f"{BASE}/details/biorxiv/2024-01-01/2024-01-07/0",
                 params={"category": "bioinformatics"})
r.raise_for_status()
data = r.json()
print(f"Total preprints: {int(data['messages'][0]['total'])}")  # API returns total as a string
for article in data["collection"][:3]:
    print(f"\n{article['title'][:80]}")
    print(f"  Authors : {article['authors'][:60]}")
    print(f"  DOI     : {article['doi']}")
    print(f"  Category: {article['category']}")

import requests, pandas as pd

BASE = "https://api.biorxiv.org"

def get_preprints(server, date_from, date_to, cursor=0, category=None):
    """
    server: 'biorxiv' or 'medrxiv'
    date_from, date_to: 'YYYY-MM-DD' strings
    cursor: page offset (increments of 100)
    """
    url = f"{BASE}/details/{server}/{date_from}/{date_to}/{cursor}"
    r = requests.get(url)
    r.raise_for_status()
    return r.json()

data = get_preprints("biorxiv", "2024-01-01", "2024-01-03")
total = int(data["messages"][0]["total"])  # API returns total as a string — cast for arithmetic
print(f"bioRxiv preprints Jan 1-3, 2024: {total}")

rows = []
for article in data["collection"][:10]:
    rows.append({
        "doi": article["doi"],
        "title": article["title"],
        "authors": article["authors"][:80],
        "category": article["category"],
        "date": article["date"],
        "version": article["version"],
    })
df = pd.DataFrame(rows)
print(df[["title", "category", "date"]].head())

# Paginate through all results for a date range
def get_all_preprints(server, date_from, date_to, max_results=500):
    all_articles = []
    cursor = 0
    while len(all_articles) < max_results:
        data = get_preprints(server, date_from, date_to, cursor)
        collection = data["collection"]
        if not collection:
            break
        all_articles.extend(collection)
        total = int(data["messages"][0]["total"])  # cast: API returns total as string
        cursor += 100
        if cursor >= total:
            break
    return all_articles[:max_results]

articles = get_all_preprints("biorxiv", "2024-01-01", "2024-01-07")
print(f"Retrieved {len(articles)} preprints from first week of 2024")

import requests

BASE = "https://api.biorxiv.org"

# Retrieve specific preprint by DOI
doi = "10.1101/2024.01.01.000001"  # Replace with real DOI

def get_by_doi(server, doi):
    r = requests.get(f"{BASE}/details/{server}/{doi}")
    r.raise_for_status()
    return r.json()

# Generic example using bioRxiv DOI pattern
r = requests.get(f"{BASE}/details/biorxiv/10.1101/2024.05.28.596311")
if r.ok:
    data = r.json()
    articles = data.get("collection", [])
    if articles:
        art = articles[-1]  # Latest version
        print(f"Title   : {art['title']}")
        print(f"Authors : {art['authors'][:100]}")
        print(f"Category: {art['category']}")
        print(f"Date    : {art['date']}")
        print(f"Version : {art['version']}")
        print(f"DOI     : {art['doi']}")
        print(f"Abstract (first 300): {art['abstract'][:300]}")

import requests

BASE = "https://api.biorxiv.org"

def check_published(server, doi):
    """Check if a preprint DOI has a corresponding published article."""
    r = requests.get(f"{BASE}/publisher/{server}/{doi}")
    r.raise_for_status()
    data = r.json()
    return data.get("collection", [])

# Check one known preprint
doi = "10.1101/2024.05.28.596311"
published = check_published("biorxiv", doi)
if published:
    pub = published[0]
    print(f"Published in: {pub.get('published_journal')}")
    print(f"Published DOI: {pub.get('published_doi')}")
else:
    print(f"Preprint {doi} has not been published yet (or not tracked)")

import requests, pandas as pd
from datetime import date, timedelta

BASE = "https://api.biorxiv.org"

# bioRxiv categories include: bioinformatics, genomics, neuroscience,
# immunology, cell-biology, biochemistry, microbiology, etc.

def weekly_category_digest(category, days_back=7):
    """Get preprints from last N days for a specific category."""
    today = date.today()
    date_from = (today - timedelta(days=days_back)).strftime("%Y-%m-%d")
    date_to = today.strftime("%Y-%m-%d")

    all_articles = []
    cursor = 0
    while True:
        r = requests.get(f"{BASE}/details/biorxiv/{date_from}/{date_to}/{cursor}")
        data = r.json()
        batch = [a for a in data["collection"] if category.lower() in a["category"].lower()]
        all_articles.extend(batch)
        if len(data["collection"]) < 100:
            break
        cursor += 100

    return pd.DataFrame(all_articles)[["doi", "title", "authors", "date"]] if all_articles else pd.DataFrame()

df = weekly_category_digest("genomics", days_back=3)
print(f"Recent genomics preprints: {len(df)}")
print(df[["title", "date"]].head())

import requests, pandas as pd

BASE = "https://api.biorxiv.org"

# medRxiv categories: infectious diseases, epidemiology, oncology,
# cardiology, neurology, psychiatry, public and global health, etc.

r = requests.get(f"{BASE}/details/medrxiv/2024-01-01/2024-01-07/0")
r.raise_for_status()
data = r.json()
total = int(data["messages"][0]["total"])  # cast: API returns total as string
print(f"medRxiv preprints Jan 1-7, 2024: {total}")

# Group by category
from collections import Counter
category_counts = Counter(a["category"] for a in data["collection"])
print("\nTop categories:")
for cat, count in category_counts.most_common(5):
    print(f"  {cat}: {count}")

import requests, time, pandas as pd

BASE = "https://api.biorxiv.org"

dois = [
    "10.1101/2024.05.28.596311",
    "10.1101/2023.11.28.569048",
    "10.1101/2023.03.07.531523",
]

rows = []
for doi in dois:
    r = requests.get(f"{BASE}/details/biorxiv/{doi}")
    if r.ok:
        collection = r.json().get("collection", [])
        if collection:
            art = collection[-1]  # Latest version
            rows.append({
                "doi": doi,
                "title": art.get("title"),
                "category": art.get("category"),
                "date": art.get("date"),
                "abstract": art.get("abstract", "")[:300],
            })
    time.sleep(0.2)

df = pd.DataFrame(rows)
if not df.empty:
    df.to_csv("preprint_abstracts.csv", index=False)
    print(df[["doi", "title", "category"]].to_string(index=False))
else:
    print("No valid preprints found for provided DOIs")

import requests, time, pandas as pd
from datetime import date, timedelta

BASE = "https://api.biorxiv.org"

TARGET_CATEGORIES = ["bioinformatics", "genomics", "systems biology"]
DAYS_BACK = 7

today = date.today()
date_from = (today - timedelta(days=DAYS_BACK)).strftime("%Y-%m-%d")
date_to = today.strftime("%Y-%m-%d")

print(f"Fetching bioRxiv preprints from {date_from} to {date_to}")

all_articles = []
cursor = 0
while True:
    r = requests.get(f"{BASE}/details/biorxiv/{date_from}/{date_to}/{cursor}")
    r.raise_for_status()
    data = r.json()
    batch = data["collection"]
    if not batch:
        break
    all_articles.extend(batch)
    total = int(data["messages"][0]["total"])  # cast: API returns total as string
    cursor += 100
    if cursor >= total:
        break
    time.sleep(0.1)

# Filter by target categories
filtered = [a for a in all_articles
            if any(cat in a.get("category", "").lower() for cat in TARGET_CATEGORIES)]

df = pd.DataFrame(filtered)[["doi", "title", "authors", "category", "date"]]
df = df.drop_duplicates(subset="doi")  # Remove duplicate versions

output_file = f"biorxiv_digest_{date_to}.csv"
df.to_csv(output_file, index=False)
print(f"\nSaved {len(df)} preprints across {len(TARGET_CATEGORIES)} categories → {output_file}")
print(df[["title", "category", "date"]].head(5).to_string(index=False))

import requests, time, pandas as pd

BASE = "https://api.biorxiv.org"

preprint_dois = [
    "10.1101/2024.05.28.596311",
    "10.1101/2023.11.28.569048",
]

results = []
for doi in preprint_dois:
    # Get preprint metadata
    r_meta = requests.get(f"{BASE}/details/biorxiv/{doi}")
    meta = {}
    if r_meta.ok and r_meta.json().get("collection"):
        art = r_meta.json()["collection"][-1]
        meta = {"title": art["title"], "category": art["category"],
                "preprint_date": art["date"]}

    # Check publication status
    r_pub = requests.get(f"{BASE}/publisher/biorxiv/{doi}")
    published = {}
    if r_pub.ok and r_pub.json().get("collection"):
        pub = r_pub.json()["collection"][0]
        published = {"journal": pub.get("published_journal"),
                     "pub_doi": pub.get("published_doi")}

    results.append({"preprint_doi": doi, **meta, **published})
    time.sleep(0.25)

df = pd.DataFrame(results)
print(df.to_string(index=False))
df.to_csv("preprint_publication_status.csv", index=False)