A match made in tech heaven

Biotech and AI: the possibilities are endless

Artificial Intelligence (AI) is a powerful tool.

  • Information is curated by ChatGPT which is ruling the AI space for chatbot services and information.

  • Business Intelligence companies are solving big data problems in a fraction of the time that we’ve seen historically.

  • Algorithms are being perfected for consumer engagement on social media platforms. With this, comes the power to influence the beliefs, values and ideologies of an entire generation.

Beyond being able to improve individuals’ and companies’ capabilities, AI has unlocked the potential to help rectify some of the world’s most time-sensitive issues like climate change, food security and wildlife conservation. If your immediate thought is ‘climate change isn’t real’; this blog isn’t for you. I’m a research scientist and I believe in data.

A massive challenge we face in the world is food security. It’s a looming topic, and quite seriously poses population-wide health risks. In the biotech space, food security is being addressed through many approaches including cellular agriculture, molecular farming, precision fermentation and microbial-based solutions.

Taking biology’s innate nature of replication and flexibility, we are engineering new technologies that allow us to create food without the reliance on legacy food systems like factory farming. In tackling a challenge as large as feeding the world’s population, there’s a lot of data being generated. AI and biotech are already being integrated in many ways, however here I aim to point out a few areas where AI can accelerate Cellular Agriculture that I believe need more investment and development.


  1. Microscopy assistance

    In my experience as a research scientist I can’t tell you how long I looked down a microscope lens wondering what I’m looking at. All of my colleagues will agree, it’s a genuine pain point and time waste. Over time, I trained my eye to identify different types of cells, microbial contaminations and any abnormalities in my cells. Still, I rely heavily on my own perception and am prone to human error.

    There is a transformative potential for Deep Learning to be integrated into live microscopes and microscope images, labelling them with their most confident predictions. At times, scientists need to manually go through thousands of images, classify and categorise them for data collection. If enough investment is made into the marriage of AI + biotech in classification models, quicker & more accurate labelling will soon become high-demand enough that some platforms can operate open-source.

  2. Consumable predictions

    Regardless of which cell system you are working with (mammalian, microbial, plant), you will be burning through consumables including growth media/broth, single-use equipment and reusable equipment. Stock level forecasting powered through complex time series models can be utilised to ensure stock levels never run below specified thresholds. This could be such an easy win, since companies and research groups already have the data records of their ordering patterns.

  3. Monitoring cellular performance

    Cell culture relies on the reproducibility of biological processes. However, anyone who has worked with cells will tell you that sometimes things don’t go as planned for no apparent reason. Sometimes it feels like the position of the moon is having adverse effects on our cells. However, the reality isn’t so superstitious.

    There’s usually a preventable root cause but with so many variables to investigate, it becomes an evaluation of value and effort. Integrating equipment churn rate predictions and troubleshooting metric analysis into your cell culture platform will empower you to identify which variable may be at cause of any unexpected results.

    In the RnD stage, AI can process DSD, DoE and Single cell cloning data to select for the best cell lines, media ingredients and biomaterials.

    When production facilities reach bioreactor scale, AI can be used to digest mountains of data to identify the most effective ways to culture, maintain and harvest cells.

These are just a few examples of big data challenges that every cellular agriculture company is currently facing, they’re a reality of working with biological systems. The list is truly endless when you take into consideration the scope across the entire biotechnology industry.


At RMSBC, we’re incorporating AI and Machine Learning into our services so that our clients have access to the best tools in the industry. The faster and more accurately we progress towards developing sustainable food systems, the less lives will suffer. So run, don’t walk. Let’s see to it that AI and biotech collide and change the world together!


If you’re as excited about this as we are, reach out and let’s discuss your biggest ideas and how we can turn them into solutions for your business.

Enquire following this link to start a conversation.


Thank you for reading!

Subscribe to receive blog updates straight to your inbox. No spam, just weekly content.

Previous
Previous

3 tips to set your company up for success in 2023

Next
Next

The bleeding edge of cultivated meat