Uspto Database

pip install requests pandas matplotlib
pip install google-cloud-bigquery  # optional: for BigQuery access

import requests
import pandas as pd

# Search PatentsView API: patents assigned to "Genentech" in CPC class C12N
url = "https://api.patentsview.org/patents/query"
payload = {
    "q": {"_and": [
        {"_contains": {"assignee_organization": "Genentech"}},
        {"_contains": {"cpc_subgroup_id": "C12N"}},
    ]},
    "f": ["patent_number", "patent_title", "patent_date", "assignee_organization"],
    "o": {"per_page": 25},
}
resp = requests.post(url, json=payload)
data = resp.json()
df   = pd.DataFrame(data["patents"])
print(f"Found: {data['total_patent_count']} patents")
print(df[["patent_number", "patent_title", "patent_date"]].head())

import requests
import pandas as pd

def search_by_assignee(assignee_name: str, per_page: int = 100) -> pd.DataFrame:
    url     = "https://api.patentsview.org/patents/query"
    payload = {
        "q": {"_contains": {"assignee_organization": assignee_name}},
        "f": [
            "patent_number", "patent_title", "patent_date",
            "patent_abstract", "assignee_organization", "assignee_country",
        ],
        "o": {"per_page": per_page, "sort": [{"patent_date": "desc"}]},
    }
    resp = requests.post(url, json=payload)
    resp.raise_for_status()
    data = resp.json()
    df   = pd.DataFrame(data.get("patents", []))
    print(f"Assignee '{assignee_name}': {data.get('total_patent_count', 0)} total patents")
    return df

# Example: patents from Broad Institute
df_broad = search_by_assignee("Broad Institute")
print(df_broad[["patent_number", "patent_title", "patent_date"]].head(10))

# Paginate through all results for large portfolios
def search_assignee_all_pages(assignee_name: str, page_size: int = 100) -> pd.DataFrame:
    url  = "https://api.patentsview.org/patents/query"
    all_patents = []
    page = 1
    while True:
        payload = {
            "q": {"_contains": {"assignee_organization": assignee_name}},
            "f": ["patent_number", "patent_title", "patent_date", "cpc_subgroup_id"],
            "o": {"per_page": page_size, "page": page},
        }
        resp = requests.post(url, json=payload)
        data = resp.json()
        patents = data.get("patents", [])
        if not patents:
            break
        all_patents.extend(patents)
        total = data.get("total_patent_count", 0)
        if len(all_patents) >= total:
            break
        page += 1

    df = pd.DataFrame(all_patents)
    print(f"Retrieved {len(df)} patents for '{assignee_name}'")
    return df

import requests
import pandas as pd

# Search by CPC subgroup: C12N15 (mutation/genetic engineering)
url = "https://api.patentsview.org/patents/query"
payload = {
    "q": {"_begins": {"cpc_subgroup_id": "C12N15"}},
    "f": [
        "patent_number", "patent_title", "patent_date",
        "assignee_organization", "cpc_subgroup_id",
    ],
    "o": {"per_page": 50, "sort": [{"patent_date": "desc"}]},
}
resp = requests.post(url, json=payload)
data = resp.json()
df   = pd.DataFrame(data["patents"])
print(f"C12N15 patents: {data['total_patent_count']}")
print(df[["patent_number", "patent_title", "assignee_organization"]].head(10))

# Common life sciences CPC codes
CPC_LIFE_SCIENCES = {
    "C12N":    "Microorganisms / enzymes / compositions",
    "C12N15":  "Mutation / genetic engineering",
    "C12Q":    "Measuring / testing involving enzymes or microorganisms",
    "A61K":    "Preparations for medical use",
    "A61P":    "Therapeutic activity of chemical compounds",
    "G16B":    "Bioinformatics",
    "G16H":    "Healthcare informatics",
    "C07K":    "Peptides / proteins",
}
for code, desc in CPC_LIFE_SCIENCES.items():
    print(f"  {code:10s}: {desc}")

import requests
import pandas as pd

def keyword_search(keyword: str, per_page: int = 50) -> pd.DataFrame:
    url = "https://api.patentsview.org/patents/query"
    payload = {
        "q": {"_or": [
            {"_text_any": {"patent_title":    keyword}},
            {"_text_any": {"patent_abstract": keyword}},
        ]},
        "f": [
            "patent_number", "patent_title", "patent_date",
            "patent_abstract", "assignee_organization",
        ],
        "o": {"per_page": per_page, "sort": [{"patent_date": "desc"}]},
    }
    resp = requests.post(url, json=payload)
    resp.raise_for_status()
    data = resp.json()
    df   = pd.DataFrame(data.get("patents", []))
    print(f"Keyword '{keyword}': {data.get('total_patent_count', 0)} patents found")
    return df

# Search for CRISPR-related patents
df_crispr = keyword_search("CRISPR")
print(df_crispr[["patent_number", "patent_title", "patent_date"]].head(10))

import requests
import pandas as pd

# Search by inventor name
url = "https://api.patentsview.org/inventors/query"
payload = {
    "q": {"_and": [
        {"inventor_last_name":  "Doudna"},
        {"inventor_first_name": "Jennifer"},
    ]},
    "f": ["inventor_id", "inventor_first_name", "inventor_last_name",
          "inventor_city", "inventor_state", "inventor_country"],
    "o": {"per_page": 10},
}
resp = requests.post(url, json=payload)
data = resp.json()
print(f"Found {data.get('total_inventor_count', 0)} inventors matching 'Jennifer Doudna'")
for inv in data.get("inventors", []):
    print(f"  ID: {inv['inventor_id']}, Location: {inv.get('inventor_city')}, {inv.get('inventor_country')}")

# Get all patents for a specific inventor by inventor_id
inventor_id = "fl:j_ln:doudna-1"   # PatentsView inventor ID format

url = "https://api.patentsview.org/patents/query"
payload = {
    "q": {"inventor_id": inventor_id},
    "f": ["patent_number", "patent_title", "patent_date", "assignee_organization"],
    "o": {"per_page": 100, "sort": [{"patent_date": "desc"}]},
}
resp  = requests.post(url, json=payload)
data  = resp.json()
df    = pd.DataFrame(data.get("patents", []))
print(f"Patents for inventor {inventor_id}: {data.get('total_patent_count', 0)}")
print(df.head(5))

import requests
import pandas as pd

# Patents in gene therapy (CPC A61K48) filed 2020-2024 by a US assignee
url = "https://api.patentsview.org/patents/query"
payload = {
    "q": {"_and": [
        {"_begins":    {"cpc_subgroup_id": "A61K48"}},
        {"_gte":       {"patent_date": "2020-01-01"}},
        {"_lte":       {"patent_date": "2024-12-31"}},
        {"_eq":        {"assignee_country": "US"}},
    ]},
    "f": [
        "patent_number", "patent_title", "patent_date",
        "assignee_organization", "patent_num_claims",
    ],
    "o": {"per_page": 100, "sort": [{"patent_date": "desc"}]},
}
resp = requests.post(url, json=payload)
data = resp.json()
df   = pd.DataFrame(data.get("patents", []))
print(f"Gene therapy patents 2020-2024 (US assignee): {data.get('total_patent_count', 0)}")
print(df[["patent_number", "patent_title", "patent_date", "assignee_organization"]].head(10))

from google.cloud import bigquery

client = bigquery.Client(project="YOUR_GCP_PROJECT")

# Count CRISPR patents by year (Google Patents public data)
query = """
SELECT
    EXTRACT(YEAR FROM filing_date) AS filing_year,
    COUNT(*)                        AS patent_count,
    COUNT(DISTINCT assignee)        AS unique_assignees
FROM `patents-public-data.patents.publications`
WHERE
    (LOWER(title_localized[SAFE_OFFSET(0)].text) LIKE '%crispr%'
     OR LOWER(abstract_localized[SAFE_OFFSET(0)].text) LIKE '%crispr%')
    AND filing_date >= '2010-01-01'
    AND country_code = 'US'
GROUP BY filing_year
ORDER BY filing_year
"""
df_bq = client.query(query).to_dataframe()
print(df_bq)
print(f"Peak year: {df_bq.loc[df_bq.patent_count.idxmax(), 'filing_year']} "
      f"({df_bq.patent_count.max()} patents)")