# FutureHouse Tutorial Series: Practical AI for Scientists 

The goal of this FutureHouse tutorial series is to help scientists use AI as a practical tool for accelerating discovery. AI is actively transforming biology, from predicting protein structures and designing new molecules to analyzing single-cell data. But many scientists still see using AI to be overly technical or limited to only computational specialists.

This course aims to close that gap by helping you become comfortable with AI: what it is, how it works at a conceptual level, and how it can support your research.

Rather than treating AI as a mysterious black box, we will approach it as a set of statistical tools built on assumptions and data. With a basic understanding, you can evaluate AI methods, question the outputs, and apply them thoughtfully in scientific work.

# Target Audience

This course is designed for scientists from non-computational backgrounds and focuses on practical use. We will cover core AI concepts, learn to use large language models for scientific discovery, and understand how AI agents can help automate scientific workflows through interactive, biology-focused examples.

# What You Will Gain

By the end of this series, you should:

- Feel familiar with the basic ideas behind modern AI and machine learning (ML)
- Be able to read AI-heavy scientific publications without feeling lost
- Identify clear opportunities to integrate AI into your own workflow
- Implement AI tools and agents on your own

# Prerequisites

- A curious mindset

# How to Use the Tutorials

The tutorials can be launched using the rocket (🚀) button  at the top of the page. 

<details>
<summary> 👇 Expand to see more details  </summary>

### Option 1 — Google Colab (**recommended**)
Opens the notebook in Google Colab with the fastest and most reliable experience.

Before running the tutorial, add your API keys using **either**:

- a `.env` file, or
- **Colab Secrets** (`🔑 Secrets` tab in the left sidebar)

Example `.env`:
```bash
OPENAI_API_KEY=your_key_here
ANTHROPIC_API_KEY=your_key_here
```

### Option 2 — MyBinder
Launches a temporary cloud Jupyter environment directly in your browser.

⚠️ Binder environments can take a few minutes to build and start.

After the notebook loads, create a `.env` file in the notebook directory containing your API keys:

```bash
OPENAI_API_KEY=your_key_here
ANTHROPIC_API_KEY=your_key_here
```

### Notes
- You only need API keys for the providers used in a given notebook.
- Never commit or publicly share your API keys.
- If a cell fails due to missing credentials, verify that your keys were loaded correctly before rerunning the cell.
</details>


# Submit Your Work

This tutorial series was created to help grow the scientific community’s engagement with AI and agentic workflows. If you enjoyed the series and built an agent, workflow, or related project, we’d love to see what you created.

Project submissions are completely optional, but we welcome examples of experiments, tools, workflows, or extensions inspired by the tutorials.

You can submit your work using this [Google Form](https://docs.google.com/forms/d/e/1FAIpQLSdgBk-ATooOA1teiqcqztAmBIQ_9jkEl4Ts5CDImV7KBdqA2Q/viewform?usp=dialog)

# Provide Feedback

We’d love to hear from you! Whether you run into issues, have ideas for improving the tutorials, or want to suggest new topics, feel free to reach out. 

Email us at: [tutorials@futurehouse.org](tutorials@futurehouse.org)

When reporting an issue, it’s helpful to include:

- The tutorial chapter number and/or title
- Whether you used Google Colab or Binder
- The full error message or screenshot (if available)

We’re actively improving these tutorials and appreciate your feedback and contributions.