Apoha exits stealth with $36M to model matter behavior

Science can identify a molecule and map its structure with remarkable precision. But what it has never been able to do, affordably and at a meaningful scale, is predict how that molecule behaves once it encounters the unpredictable conditions of the real world. That blind spot is where promising drugs fail in clinical trials, where food products fall short of their intended flavor profiles, and where artificial intelligence increasingly hits a wall.

Apoha, a London-based company born from 15 years of research in interfacial physics, claims to have built the missing measurement tool. On June 3, the company emerged from stealth with $36 million in funding, unveiled at the Frontier Technologies Stage during SXSW London.

The investment round is led by Singular, with participation from Tim Draper’s Draper Associates and continued support from seed investors Redalpine, Seedcamp, Wilbe, and Nucleus, alongside grant funding from Innovate UK.

Apoha calls its data layer Liquid State Intelligence, a new category it positions alongside sequence and structure. Just as genomics digitized the language of biology and structural biology digitized design, Apoha aims to digitize behavior: how matter actually reacts under stress. The company says the funding will be used to establish this as a foundational data class for biologics, food, materials, and physical-world AI.

The science traces back to 2008, when founder and CEO Shamit Shrivastava began tackling a problem left open by the Nobel-winning Hodgkin-Huxley model of nerve signaling: the physics of the boundary where matter meets liquid.

In 2014, he published evidence of two-dimensional solitary sound waves at a lipid interface, work the company says was later named among Scientific American’s discoveries that could change everything. In 2021, he co-founded Apoha with Anshika Srivastava, its chief operating officer and a former executive director at Goldman Sachs.

Apoha now holds more than 60 patents spanning hardware, software, data, and AI models.

Its first product is VIBE, an empirical readout of how a sample behaves under controlled stress. The platform takes a minuscule amount of material, small enough to sit on a pinhead, suspends it in liquid, applies a series of perturbations, and records the wave patterns the molecule emits in response.

Those patterns resolve into more than 1,000 measured descriptors of behavior in a single reading, where conventional assays capture one property at a time. Within minutes, Apoha says, a VIBE readout can flag whether an experimental drug will fail before it even reaches a trial.

The platform is already in commercial use, with the strongest evidence found in a preprint. In joint research with Boehringer Ingelheim, a multi-year commercial partner, Apoha identified high-risk antibody candidates with greater than 90% precision using as little as 8 micrograms of material.

A second version of the benchmarking work reports that the platform outperforms 12 industry-standard developability tests across 236 clinical antibodies, surfacing information that conventional measures miss rather than simply duplicating them.

Other customers highlight the platform’s range. Apoha is working with German biotech Ethris to predict how lipid nanoparticles carrying mRNA behave in animals, and with plant-based food company THIS on a protein replacement destined for supermarket shelves. It also lists Somru BioSciences and several Fortune 500 companies across pharma, food, and materials.

The broader bet is that physical-world AI will eventually need this kind of data. Models have learned to see and read, and a new generation of physical AI systems is being built to act on matter. But none of them can yet sense how a drug dissolves or how a flavor holds, because that data has never been collected at scale.

“It cannot be scraped from the internet, synthesised, or retrofitted from existing assays,” Shrivastava said. “It has to be measured.” Whether enough buyers agree to turn this into a true data class is the question the next funding round will have to answer.