Scientific risk assessment specialist SciPinion has launched an AI-led solution that aims to give food-tech start-ups a faster path to market for their ingredients in the US, ahead of proposed changes to the Generally Recognized as Safe (GRAS) approval process.

The platform features a set of tools that pair AI-assisted software with a menu of professional services to measure and document how closely a candidate food ingredient matches a substance that is already approved through the US Food and Drug Administration (FDA)’s GRAS process.

GRAS status enables an ingredient to launch without full pre-market approval. A proposed FDA rule would change the process from voluntary to mandatory – food-tech start-ups, such as those developing alternative protein ingredients, would no longer be able to self-affirm GRAS status, with only narrow exemptions applying to ingredients shown to be the same as one the FDA has already reviewed with no questions.

SciBridge has been developed to fast-track the process for food businesses. According to SciPinion, its tool can turn months of manual comparison work into a documented similarity report within minutes.

SciPinion said that potentially tens of thousands of ‘substitutional’ ingredients, cases where multiple manufacturers rely on the same single precedent notice, are currently uncounted in any public data.

“The FDA has acknowledged its own strain here, and the agency's proposed rule specifically asks for comment on ways to make it easier for notifiers to draw on data from already-submitted GRAS notices, which is exactly what SciBridge is built to do,” said Vanessa Feher Castagna, director of food safety and claims at SciPinion.

“The FDA has never defined how to show similarity, which is understandable, because two food substances are never identical the way two generic drugs are. What companies need, and what FDA is asking for, is a standard, documented method, applied the same way every time.”

The platform includes three tools, built from the FDA’s GRAS Notice inventory: Browse, a synced and structured index of FDA’s GRAS Notice database with a compare tool; Screen, a rapid similarity check that ranks a new substance against precedent notices; and Bridge, a field-by-field substantial similarity evaluation against up to three comparators, with a downloadable report and full audit trail.

The AI-assisted process also includes human expert review, the company emphasised, adding that the program was built with data security as a core requirement to ensure the safety of confidential ingredient data submitted for review.

The tools were shaped with nearly a year of quality control and prompt refinement before launch, with direct feedback and evaluation from the FDA also incorporated into this process, SciPinion confirmed – though it said this does not represent the FDA’s endorsement or use of the software.

The platform is designed for both ingredient and finished-product manufacturers and distributors, and can also be used by regulatory consultants, law firms and trade associations.

Aletta Schnitzler, chief scientific officer at animal-free lactoferrin start-up TurtleTree, said: “At the time when we achieved GRAS for our recombinant bovine lactoferrin, there was no template for proving substantial similarity to an existing ingredient”.

“Our teams never lacked data. The entire GRAS record is public. What the industry lacked was a structured way to navigate the key information in the regulatory data. SciBridge is the only tool I've seen that uses the FDA record as the template itself.”

Dennis Keefe, former director of office of food additive safety at the FDA, commented: “FDA’s food ingredient programmes, including the GRAS review staff, are severely resource constrained, and the proposed rule, if finalised, will only exacerbate the current review bottlenecks”.

He added: “A streamlined, systematic, structured data review process is a clear value add for industry to help organise their data in such a way to make it easier for bridging evaluations and enhancing FDA to further its public health protection mission.”