The headlines led with a 22,000-litre tank and a 99% cost drop. Here is a bioreactor engineer’s read on what Parima and Vow actually proved, why the media breakthrough matters more than the vessel, and the quiet shift that turned cultivated meat into a fermentation problem.
I rebuilt two published CHO cell-culture papers — a hybrid ODE + machine-learning growth model, and a genome-scale metabolic reduction pipeline — as an interactive digital twin that runs in the browser. Here’s how it works, what’s under the hood, and an honest take on what it’s good for. No hosted version yet; the code is on GitHub and a live instance is coming soon.
If you’ve ever read a paper on lysine production with Corynebacterium glutamicum and thought “right, but what do I actually do on Monday morning when I’m standing in front of the bioreactor” — this post is for you. I’m going to walk through the entire process of setting up and running a 5L bench-scale fed-batch… Read More: Running a 5-Litre Lysine Fermentation From Scratch. Everything Nobody Tells… »
The Features That Matter After training the developability model on 100+ therapeutic antibodies, I looked at the feature importance rankings. The model had learned to weight certain properties more heavily than others when making predictions. Some of these were obvious. Some were surprising. All of them tell us something about what actually makes antibodies difficult… Read More: What Makes an Antibody Hard to Manufacture? Data-Driven Insights »