A Platform For Real Impact In Immunology Medicines

We are opening a new landscape of novel biologics by applying machine learning specifically to immunology, guided by our team of experts in biologics discovery and development.

From Linear To Parallel Drug Development

To Parallelize is to optimize multiple relevant desired parameters simultaneously to rapidly modulate key drug-like attributes of protein therapeutics.

Traditional protein identification and optimization involves inefficient, independent sequential optimization and protracted combination steps.

Seismic’s IMPACT platform enables parallelized multi-property optimization by integrating Machine Learning with Structural Biology, Protein Engineering, and Translational Immunology for the accelerated generation of novel biologics.

Enabling The Unexpected

The IMPACT platform opens new protein sequence space, allows the simultaneous optimization of multiple drug-like properties, including immunogenicity, and shortens the time and limits the number of design/test cycles.

New Sequence Space
The IMPACT platform allows us to find previously unexplored sequences and to design proteins with optimal drug-like properties.

Design Test Cycle
The IMPACT platform enables parallelization, thereby removing many cycles of iteration and mutation combinations and shortening the time of each cycle to rapidly identify top candidates faster.

The IMPACT Platform in Action

Our pipeline programs leverage our IMPACT platform, which is integrated into our experienced biotherapeutics, structural biology, machine learning, and immunology teams to discover and develop novel enzyme and antibody drug candidates for autoimmune diseases.

Our Pipeline

The following explains how we’ve applied our IMPACT platform and machine learning to make improved drug molecules.

Immunoglobulin (Ig)-Sculpting Enzyme
See How We Made A Better Drug Molecule

We leveraged the IMPACT platform to screen thousands of naturally occurring enzymes that modify pathogenic antibodies, and rapidly re-engineer them into novel enzymes with ideal drug-like characteristics using multi-parameter optimization. Using this approach, we have discovered and developed invisibilized, developable, and functional novel Ig proteases.


How we optimized IG-Sculpting Enzyme

  • Elucidate pairwise and higher order residue dependencies to optimize drug-like properties (i.e. thermostability)
  • Remove chemical liabilities
  • Remove B-cell and T-cell epitopes to create proteins with increased invisibility
  • Retain or augment enzymatic activity (i.e. cleavage function)
Dual-Cell Bidirectional (Dcb) Antibody
See How We Made A Better Drug Molecule

Seismic’s DcB antibody approach targets dysregulated cell-mediated immunity by optimally engaging both T cells and antigen presenting cells, such as B cells, to restore immune homeostasis. Activating the normal inhibitory pathways of the immune system may control multiple diseases, such as multiple sclerosis, lupus and rheumatoid arthritis. DcB antibodies simultaneously engage multiple inhibitory pathways in more than one immune cell type thereby targeting and regulating both sides of the immune cell synapse.

Our proven team of integrated protein engineers and immunologists work collectively with our cutting-edge ML team to optimize the drug-like properties of antibodies discovered through traditional discovery campaigns. Our IMPACT platform is critical to advancing the design of our FcγRIIb selective Fc domains by predicting mutations that tune for the desired binding properties at the Fc/FcgRIIb interface, informing optimal mutations to be tested experimentally for enhanced checkpoint agonism, ensuring invisibilization of these biologics to reduce the risk of immunogenicity in the clinic, and predicting antibody epitopes to support epitope binning and epitope/function relationship analysis.


How we optimized our DCB Antibody +

  • Map protein-protein interfaces using machine learning thereby enabling design of FcγRIIb selective Fc domains
  • Map protein-protein interfaces using ML thereby enabling design of FcgRIIb selective Fc domains
  • Predict epitopes recognized by our proprietary antibodies to enable in silico epitope binning and epitope/function relationship elucidation
  • Enable de novo paratope generation in silico for antibody generation/discovery
  • Optimize developability of antibodies
  • Map and remove immunogenic T-cell epitopes to create novel inhibitory receptor agonist antibodies with increased invisibility

The IMPACT Platform and Capabilities

Our platform integrates Machine Learning along with Structural Biology, Protein Engineering, and Translational Immunology. At the center of our ability to harness the power of Machine Learning is our team’s deep expertise in biologics discovery and development, and our commitment to integrating different disciplines. Together, our platform and our people bring the capabilities to drive innovation for immunology drug discovery.

About Us


This links to an external website.