To reshape

Protein therapeutics discovery with
next-generation AI

Helixon is developing technology platforms that transform the discovery of protein therapeutics.

We aim to design

Novel antibodies

to target antigen epitopes precisely. By integrating deep learning, structural biology and high-throughput techniques, our platform enables more efficient discovery, and with a higher successful rate, compared to traditional methods.
Our integrated platform conjoins

Deep learning and
high-throughput biology

designing antibody sequences at massive scale, predicting their properties, validating via experiments, and self-improving iteratively.

We balance the tradeoff between exploration and exploitation and search the sequence landscape, aiming for more precise epitope targeting and better developability after each iterative design cycle.

Deep learning models of antibody-antigen interaction landscape

Deep learning models of antibody-antigen interaction landscape

We train deep learning models to predict binding between antibodies and antigens. With ever-growing structural a=nd functional data, our models become more precise and detailed.

Design and synthesis of antibody library

Design and synthesis of antibody library

Given an antigen, we efficiently search the antibody sequence space to identify molecules that target an epitope with significant therapeutic implications. A library of up to millions of antibodies are then synthesized for testing.

High-throughput profiling of antibody properties

High-throughput profiling of antibody properties

Using a variety of technologies, we obtain functional and biophysical measurements of individual antibodies in our library in a high-throughput manner.

Iterations towards optimized antibodies

Iterations towards optimized antibodies

By repeating the previous steps, we learn from the successes and failures of earlier experiments, train better models, design a new library of candidates, and further improve antibodies with desired properties.


Deep learning optimized human antibody against SARS-Cov-2 variants

Helixon introduced a useful computational antibody optimization tool2, and has applied it on optimizing neutral antibodies against multiple severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) variants.

Protein structure can be predicted from its primary sequence with high accuracy

Helixon has been always looking for new perspectives to build the next generation of protein structure AI model.


to out-evolve nature

We are building a team of passionate scientists and engineers to drive scientific advances and technology innovations for bringing better therapies and improving human health.