Mechanistic immune intelligence
Making immune complexity predictable and actionable
ImmuNovus combines mechanistic models of the immune system with AI-assisted simulation to explore what may happen, explain why, and identify what to examine next.
Prediction grounded in mechanism
Our models represent immune pathways and interactions as executable biology. AI helps teams configure questions, run simulations, and interrogate results. The mechanistic layer keeps assumptions visible and makes predictions explainable.
Designed to connect mechanisms across scales as the model and evidence base expand.
One view of the immune system. Three ways to put it to work.
Pharma and biotech
Decide what to pursue, test, and advance
Explore targets, compounds, indications, biomarkers, and responder hypotheses before the next costly stage.
Explore pharma →Clinicians
Recognize changing immune states earlier
Bring longitudinal data into an explainable view designed to support clinical interpretation and follow-up.
Explore clinical →Individuals
Understand what may be changing
Turn personal immune data into clearer questions and more informed conversations with care teams.
Explore individual →How it works
01
Ask a question
Start with the question, comparison, or decision point you need to understand.
02
Configure context
Represent relevant biology, intervention assumptions, measurements, and population context.
03
Simulate mechanisms
Mechanistic models represent the immune response as executable biology. AI-assisted tools help explore scenarios while the logic stays inspectable.
04
Inspect rationale
See which mechanisms and assumptions drive each result, including uncertainty and alternative explanations.
05
Choose the next step
Translate the result into the next experiment, measurement, or question.
The science behind mechanistic immune intelligence
Peer-reviewed research by ImmuNovus founder Tomáš Helikar and colleagues at the University of Nebraska–Lincoln and collaborating institutions demonstrates how mechanistic models can connect immune responses, identify therapeutic targets, and explain behavior across biological scales.
Modeling the connected immune system
A mechanistic model spanning 11 disease contexts connects immune cells and secreted signals to simulate responses to infection, autoimmunity, and lung transplantation. The study evaluated its predictions in 38 validation experiments against published observations.
- 11
- disease contexts
- 1,450
- regulatory interactions
- 38
- validation experiments
Moore et al. · Frontiers in Immunology · 2026
A comprehensive mechanistic multicellular model of the human immune system spanning 11 diseases
Read the studyIdentifying therapeutic targets
Disease-specific metabolic models identified 68 candidate drug targets across three autoimmune diseases. In vitro experiments combined with published evidence supported CD4+ T-cell suppression for half of the identified targets.
- 68
- candidate targets
- 3
- autoimmune diseases
Puniya et al. · npj Systems Biology and Applications · 2021
Integrative computational approach identifies drug targets in CD4+ T-cell-mediated immune disorders
Read the studyConnecting molecular mechanisms to immune behavior
A CD4+ T-cell model integrated signaling, metabolism, cell populations, and cytokine dynamics using four modeling approaches. It reproduced published experimental behaviors and predicted emergent immune responses arising across scales.
- 4
- modeling approaches
- 3
- spatial scales
Wertheim et al. · PLOS Computational Biology · 2021
A multi-approach and multi-scale platform to model CD4+ T cells responding to infections
Read the study