Lead Finder

A tool that helps you find the right people to reach out to in the toxicology and pharmaceutical research world.

It searches through published scientific papers, pulls out the researchers who wrote them, finds their contact details, and ranks them based on how likely they are to be interested in your product.

---

What It Does

You give it some topics to search for (like "Drug-Induced Liver Injury" or "3D cell culture"), and it goes through four steps:

Step 1 - Find People It searches PubMed (a huge database of medical and science research papers) for papers that match your topics. It then pulls out the names of the researchers who wrote those papers, especially the lead authors.

Step 2 - Get Contact Info It takes those researchers and tries to find their email address, phone number, LinkedIn profile, and company details. It uses services like Apollo.io, Hunter.io, and Clearbit for this. You need to bring your own API keys for these services.

Step 3 - Score and Rank It gives each person a score from 0 to 100 based on things like their job title, what they research, the size of their company, and where they are located. People with a score of 80 or above are marked as High Priority.

Step 4 - Dashboard Everything shows up in a clean table where you can search, filter by score or location, and download the list as a CSV or Excel file.

---

Who This Is For

This tool is useful if you are trying to sell products or services to scientists and research teams working on:

• Drug safety testing
• 3D cell culture models
• Organ-on-chip research
• Liver toxicity studies
• Investigative toxicology

---

What You Need to Run It

• Python 3.8 or above
• API keys from one or more of these services: Apollo.io, Hunter.io, Clearbit, ContactOut (free plans work but have limits)

---

How to Set It Up

1. Clone the repo and go into the folder

git clone https://github.com/Up14/Lead-Finder.git
cd Lead-Finder

2. Install the required packages

pip install -r requirements.txt

3. Run the app

streamlit run app.py

The app will open in your browser automatically.

---

How to Use It

Once the app is open:

1. On the left sidebar, type in the topics you want to search for (example: "Drug-Induced Liver Injury, Hepatic spheroids")
2. Enter your API keys for Apollo.io or Hunter.io
3. Click Run Stage 1 to find researchers
4. Click Run Stage 2 to get their contact details
5. Click Run Stage 3 to score and rank them
6. Click Run Stage 4 to see the final dashboard
7. Download the results as a CSV or Excel file

Results are saved automatically so if you run the same search again, it loads from cache instead of hitting the APIs again.

---

How the Scoring Works

Each lead gets a score out of 100:

What is checked	Points
Job title matches roles like "Director of Toxicology" or "Preclinical Safety"	30
Recently published a paper on a relevant topic like liver injury or drug safety	40
Their company recently raised funding (Series A or B)	20
Their company already uses similar tools like organ-on-chip or 3D cell models	15
They are based in a known research hub like Boston, Bay Area, or Basel	10

Scores above 80 are High Priority. Scores between 50 and 79 are Medium Priority. Scores below 50 are Low Priority.

---

A Note on Apollo.io Free Plan

Apollo.io has a free plan but it blocks some features that this tool needs. If you see 403 errors, that is why. You can work around it by adding a Hunter.io key (for emails) or a Clearbit key (for company details). The app will still run, it just skips the parts Apollo cannot do.

---

Project Structure

Lead-Finder/
├── app.py                  Main app file
├── requirements.txt        List of packages needed
├── stages/                 The four pipeline steps
│   ├── stage1_identification.py
│   ├── stage2_enrichment.py
│   ├── stage3_ranking.py
│   └── stage4_dashboard.py
├── utils/                  Helper functions
│   ├── pubmed_api.py       Searches PubMed
│   ├── email_finder.py     Finds email addresses
│   ├── linkedin_finder.py  Finds LinkedIn profiles
│   ├── phone_finder.py     Finds phone numbers
│   ├── company_enricher.py Gets company details
│   └── scoring.py          Calculates lead scores
└── data/cache/             Saved search results (auto-generated)

---

Notes

• Start with 5 leads to enrich at a time to avoid using up your API credits too quickly.
• Cache files are stored in the data/cache/ folder. You can clear them from the sidebar inside the app.
• The PubMed search is completely free with no limits.