EpiVax Adds AI Models to ISPRI Immunogenicity Platform

Sep 2, 2026
EpiVax released AI enhancements for ISPRI, including JanusMatrix 2.1, a JAX immunogenicity score, and ADA 2.2 for antibody immunogenicity risk assessment.

EpiVax has released AI enhancements to ISPRI, its in silico platform for assessing immunogenicity risk in biotherapeutics, the company announced in a press release.

The update includes JanusMatrix 2.1, which applies AI to improve immune tolerance prediction by weighting human epitope cross conservation with expression and prevalence data. ISPRI already combines EpiMatrix and JanusMatrix to evaluate T cell epitope content and human cross conservation in therapeutic sequences.

EpiVax also added the JAX score, which incorporates JanusMatrix tolerance potential into EpiMatrix scores. The company said the score is designed to align more closely with clinical immunogenicity outcomes.

The release also includes ADA 2.2, an updated model for antibody immunogenicity risk. ADA 2.2 combines measures based on epitopes with biophysical attributes and mode of action criteria, and was trained using clinical monoclonal antibody data.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Life AI Weekly or Daily AI Brief.

Also, consider following us on social media:

Healthcare & Life Sciences AI AI Brief AI Brief (X)
Free newsletter

Life AI Weekly

Weekly coverage of AI applications in healthcare, drug development, biotechnology research, and genomics breakthroughs.

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.