NEW TECH FOODS

Singapore-based Umami Bioworks has expanded its Alkemyst AI platform with a new computational feed biology capability designed to predict how fish cells metabolise nutrients and lipids before physical feed trials begin.

The update allows aquaculture feed performance to be modelled at the cellular level, addressing one of the sector’s most persistent challenges: uncertainty around feed formulation, particularly as traditional fish oil supplies tighten and algal oils become a more important omega-3 source.

Feed represents the largest cost in aquaculture and is a major driver of price volatility. Yet most formulations are still developed through trial-and-error, involving long testing cycles, high capital requirements and limited insight into why certain feeds perform better than others.

Key biological processes such as lipid metabolism, nutrient uptake and stress response are typically only observed after trials are completed.

Umami’s new 'Virtual Marine Cell' capability aims to change this by simulating how different fish species process proteins, lipids and algal oils under varying conditions. Using the Alkemyst platform, feed developers can assess performance, optimal inclusion rates and metabolic trade-offs in silico before moving to animal trials.

According to Umami Bioworks, the system can model how marine cells metabolise algal lipids, helping producers avoid over-formulation of expensive ingredients, reduce waste and target fatty acid profiles linked to growth, resilience and product quality.

Dozens of formulations can be screened digitally within hours, allowing physical trials to focus only on the most promising candidates.

“By computing feed biology at the cellular level, we understand how fish respond to nutrition before committing time, capital, and animals. That changes how decisions are made,” said Shivansh Singhal, machine learning scientist at Umami Bioworks.

Umami Bioworks said it is already working with global aquaculture producers and feed companies to deploy the technology across multiple species and production systems.

With feed accounting for as much as 70% of production costs in species such as salmon, tuna and yellowtail, the company positions the new capability as a step toward improving the economics and predictability of aquaculture feed development.