Immunetrics models support novel targets. We use all publicly available data first to constrain the model, enabling the best and most-informed prediction of effects of modulating a novel target. We can then also incorporate data from our collaborators to fine tune model prediction accuracy.


We train our models to multiple drug targets, therapeutic compounds, clinical trials, doses, and routes of administration, imparting a high level of confidence in our predictions.

  • We work closely with our clients to ensure that our model is updated to reflect the current understanding of the biology
  • We can test how hypotheses compare to our predictions via relevant biological research and rigorous data analysis
  • Our predictions can improve the understanding of a drug by revealing new signaling effects of the novel therapy
  • We can run virtual clinical trials across a range of inclusion criteria, doses/schedules, and routes of administration, as well as clinical outputs, thereby predicting the success of target modulation under various conditions
    • If significant clinical efficacy fails in simulation, we provide advice on alternate study design
    • We can also filter our large virtual population to select subgroups that represent alternate trial enrollment criteria and phenotype-specific characteristics. These populations can then be used to investigate alternate trial designs
  • Informed clinical trial predictions can be achieved using limited data, including: patient-level baseline data alone, placebo trajectory data alone, phase 2 data alone (to predict phase 3 results), or via inclusion of only published in vitro and preclinical data


Trial Power Analysis

Immunetrics can predict the probability of achieving efficacy endpoints, for any point in time, over any range of population sizes.

This service is invaluable in trial design, as it indicates the minimum number of patients necessary to achieve a given probability of success. We can identify the success criteria and the number of enrolled patients that satisfy any definition of acceptable risk.

Unlike traditional statistical power analysis, Immunetrics does not assume that prior observed results are true:

  • Individual patients are simulated in detail over all relevant trial scenarios
  • The biology of the model dictates future predictions, not the prior observations
  • This enables the model to highlight any Type I (false positive) errors in earlier trials


Trial Design Optimization

An optimal trial design can minimize trial costs and maximize the chance of success.

The Immunetrics modeling team can provide early recommendations for trial design by:

  • Identifying optimal inclusion/exclusion criteria
  • Determining optimal trial size using our power analysis approach instead of the traditional statistical approach
  • Providing risk stratification
  • Comparing outcomes from different doses, dosing schedules, and routes of administration
  • Simulating the effects of dose ranging on clinical outcome measures


Non-Inferiority/Bioequivalence Analysis

Defining and running a non-inferiority trial can be challenging. Given a proposed outcome measure, Immunetrics can provide probability of achieving a significant result for any point in time, over any range of population sizes and success margins.

This includes:

  • Testing a novel compound against a control drug, at any population size, with any margin, to optimize clinical trial design and achieve the optimal probability of success
  • Determining the best non-inferiority margin for your trial in advance of protocol submission


Dose Equivalence & Optimization

Immunetrics modeling approaches allow testing of a wider range of drug doses in silico than logistically or economically feasible in an actual trial setting.

For example:

  • We can help optimize dose-ranging studies.
  • We can reduce the cost of clinical trials by determining the point at which doses diverge and are not equivalent, and likewise, identifying dosing strategies that are equivalent.
  • Our previous dose equivalence modeling successes helped convince the FDA that testing a higher dose was unnecessary, which saved our client millions of dollars.