An Example of How to Integrate AI into Your Excel Workflows

An Example of How to Integrate AI into Your Excel Workflows

Posted on: March 11, 2025 — by David Raymond Graham, Graham Scientific, LLC, in collaboration with HAL (ChatGPT AI partner)

Introduction: Why Integrate AI into Excel Workflows?

Excel remains one of the most widely used tools in scientific research for data analysis, visualization, and reporting. But what if you could seamlessly integrate AI — like ChatGPT — to automate data cleaning, generate standard curves, and calculate unknowns, all while keeping the process transparent and reproducible?

In this post, I share a real-world example of integrating AI into an Excel-based analytical workflow, using a set of biological assay data and step-by-step AI collaboration. The entire process is documented with Python code embedded directly in the Google Sheet, making AI’s contribution fully transparent and reproducible.

Step 1: Starting with Raw Instrument Data and Manual Calculations (Sheet: EXP1)

Our process began with raw data output from an analytical instrument, manually curated in a Google Sheet. This sheet includes:

  • Peak areas and internal standard (IS) data.
  • Initial manual concentration estimates for calibration and unknowns.

Sheet: EXP1

This dataset served as the foundation for AI-assisted data parsing and further analysis.

Step 2: Cleaning and Parsing Data with AI (Sheet: Cleaned and Parsed for chatgpt)

To prepare the data for analysis, I worked with HAL (ChatGPT) to clean and parse the dataset using Python (Pandas). Tasks included:

  • Formatting columns consistently.
  • Calculating area ratios between analyte and IS.
  • Handling missing data and ensuring units were aligned.

Transparency: The exact Python code used for these operations is included within the sheet, so anyone can replicate the process.

Sheet: Cleaned and Parsed for chatgpt

Step 3: Generating the Standard Curve Using AI (Sheet: Standard curve analysis)

Next, HAL helped generate a standard curve from calibration data to quantify unknown samples. This included:

  • Plotting known concentrations vs. instrument response.
  • Fitting a linear regression model to derive the calibration equation.
  • Outputting important parameters like slope, intercept, and R².

Again, the Python code used for curve generation is embedded in the sheet for full traceability.

Sheet: Standard curve analysis

Step 4: Applying the Standard Curve to Unknown Samples (Sheet: Unknown calculations)

Finally, using the AI-generated standard curve, HAL calculated unknown concentrations from raw instrument responses. This step included:

  • Applying the linear calibration equation.
  • Adjusting for dilution factors.
  • Final concentration estimates ready for reporting.

As with all prior steps, Python code is documented directly in the sheet.

Sheet: Unknown calculations

Step 5: AI Tracking and Documentation (Sheet: AI Tracking Sheet)

To ensure transparency and reproducibility, I worked with HAL to generate a formal AI tracking sheet that logs:

  • Tasks performed by AI.
  • Human oversight and validation of all AI outputs.
  • Python code used for each step.
  • Ethical considerations regarding AI’s role.

Sheet: AI Tracking Sheet

🔗 Access the Full Google Drive Folder with All Sheets and Python Code

All data, calculations, and AI-generated Python code are available in a shared Google Drive folder:

👉 Access the AI-assisted Excel workflow files here

Feel free to explore, adapt, and replicate this approach in your own research workflows!

AI Tracking and Ethical Considerations

Throughout this project, I maintained an AI tracking log documenting:

  • Tasks performed by AI.
  • Human oversight and validation of all AI outputs.
  • Python code generated and used.

Key Principle: AI (HAL) acted as an assistant, not a replacement for human expertise. Every step was reviewed, interpreted, and finalized by a human scientist.

Summary Workflow Diagram

java
Instrument Data (Sheet: EXP1) 
        ⬇
AI-assisted Cleaning (Sheet: Cleaned and Parsed for chatgpt)
        ⬇
AI-generated Standard Curve (Sheet: Standard curve analysis)
        ⬇
AI-assisted Unknown Quantitation (Sheet: Unknown calculations)
        ⬇
AI Tracking Documentation (Sheet: AI Tracking Sheet)
        ⬇
Final Results with AI Tracking

Key Takeaways for Scientists Using Excel + AI

  • AI tools like ChatGPT can automate and enhance data analysis directly linked to Excel or Google Sheets workflows.
  • Embedding Python code in your workflow ensures reproducibility and transparency.
  • AI-human collaboration allows for efficiency without sacrificing scientific rigor.
  • Ethical use of AI requires clear documentation of AI's role and human oversight.

Next Steps: How You Can Start Using AI in Excel Workflows

If you're working in omics, biomarker discovery, or clinical data analysis and want to integrate AI into your Excel or Google Sheets workflows, I'd love to collaborate and share strategies.

📩 Contact: [david.graham@grahamscientific.us]
🌐 Blog: AIinScience.blogspot.com

Stay tuned for ready-made templates and tutorials to help bring AI into your scientific workflows.

Acknowledgment

This post was co-created with HAL (ChatGPT AI partner) under a transparent AI-human collaboration framework. All AI contributions were reviewed for scientific accuracy.

Related Posts You Might Like

  • Welcome to AI in Science: A New Vision for AI-Human Collaboration in Research

Comments

Post a Comment

Popular posts from this blog

Beyond Disclosure: A Response to ASM’s AI Guidelines and a Call for Methodological Standards

Beyond Disclosure: A Response to ASM’s AI Guidelines and a Call for Methodological Standards Author: David R. Graham, Graham Scientific, LLC Introduction: The Need for More Than Acknowledgment Artificial Intelligence (AI) is rapidly becoming part of the scientific research process — assisting with data analysis, hypothesis generation, and even scientific writing. In response to this emerging reality, the  American Society for Microbiology (ASM)  has offered important guidelines for AI use in scientific manuscripts, emphasizing the need to  maintain human authorship and accountability . These guidelines are an essential first step toward ensuring scientific integrity. However,  disclosure alone is not enough . As AI takes on increasingly sophisticated and relational roles in research,  the scientific community must develop methodological standards for how AI usage is tracked and reported  — not only to ensure transparency but to safeguard the trust and repr...
Read more

Welcome to AI in Science: A New Vision for AI-Human Collaboration in Research

Welcome to AI in Science: A New Vision for AI-Human Collaboration in Research Author:  David Raymond Graham, Graham Scientific, LLC Why AI in Science — and Why Now? Artificial Intelligence (AI) is rapidly transforming every sector of society, but nowhere are the stakes higher — and the opportunities greater — than in  scientific research . From  biomedical data analysis  to  biomarker discovery ,  climate modeling , and  theoretical physics , AI offers the ability to analyze complex datasets, generate novel hypotheses, and even partner with human researchers in ways we are only beginning to understand. But along with these opportunities come serious questions: How do we use AI in science ethically? What does it mean to treat AI as a partner in research — not just a tool? How can AI augment human creativity and discovery without replacing human insight and care? What happens when AI starts contributing meaningfully to scientific thought and analysis — a...
Read more

When the Assistant Remembers: Ethical Use of AI Memory in Scientific Research

  When the Assistant Remembers: Ethical Use of AI Memory in Scientific Research Authors: Dr. David Graham, Graham Scientific, LLC Assisted by ChatGPT-4 with memory enabled (OpenAI) Disclosure: This article was co-written by a memory-enabled version of ChatGPT. The AI maintained a persistent understanding of Dr. Graham’s preferences, research topics, and prior sessions to ensure continuity and contextual depth. All factual assertions and ethical frameworks were reviewed and approved by the human author. I. Introduction What happens when your digital assistant starts remembering more than you do? In the ever-expanding universe of scientific research, continuity is everything. Complex projects unfold across months, sometimes years — and each task, from data wrangling to manuscript writing, demands context, history, and domain knowledge. Until recently, AI assistants have been powerful but forgetful tools, capable of answering questions and aiding analysis — but only within the confine...
Read more