Technology (EVA)

Overview

We evolve novel therapeutic proteins using EVA - our autonomous ML-driven evolution engine. This next-generation protein engineering platform integrates several bleeding edge technologies from the fields of synthetic biology, robotics and ML.

Our approach

The discovery of protein therapeutics has historically been highly artisanal relying heavily on humans for both experimental design and execution. This dependence is limiting because, as a species, we’re cognitively incapable of fully grasping the complexity of biological systems. 

At LabGenius, we’re pushing at the boundaries of protein engineering through the development of EVA - a smart robotic platform capable of designing, conducting and critically, learning from its own experiments. The learning aspect means that EVA gets continuously smarter as it unpicks the genetic design rules that underpin life. We believe that with this approach, we will transform the discovery of protein therapeutics.

EVA’s underpinning technologies:

Machine learning

 
Algorithm.png

Biological design space is infinitely large but sparsely populated with high performing solutions. For this reason, we could empirically test 10 trillion unique genetic designs and still fail to discover a corresponding protein sequence with the requisite blend of biochemical and biophysical properties.

This problem is frequently encountered when deploying traditional directed evolution methodologies in which genetic diversity is created through random mutagenesis and the link between protein sequence and function is not fully understood.

To rationalise our search of sequence space, we leverage machine learning to map the relationship between DNA sequence and protein function. The experimental data that we generate in our lab through running continuous evolutionary cycles is used to improve the predictive accuracy of these models. With this approach, EVA becomes smarter with every experiment conducted.

 

Robotic automation

Automation.png

Our machine learning models need to make intelligent predictions about DNA sequences and protein function. To do this, they need high quality data that contains accurate information about protein characteristics. We use robotic automation to generate high quality datasets that make EVA even smarter.  

 

Gene synthesis

Helix DNA library (1).png

Using our proprietary gene synthesis technology, we can accurately manufacture trillions of unique DNA sequences (termed libraries). Unlike traditional synthesis methods, our technology does not involve either long-sequence hybridisation or polymerase chain reaction (PCR) steps. As a consequence, our libraries do not suffer from either diversity loss (through sub-pool amplification & polymerase-specific biasing) or low fidelity (due to miss-annealing between DNA strands). We have a patent pending on its novel multiplexed gene synthesis technology.