How to Use

1. Navigate to Immune Changes
   
   • In the left-hand sidebar, click Immune Changes.
2. Select Your Parameters
   
   • Endpoint – Choose the grouping to compare (e.g., study timepoint, age group, sex, treatment line, treatment response, subject name).
   • Show Cells As % Of – Choose the reference population (e.g., T cells, B cells, non-granulocytes, NK cells).
   • Cell Type(s) – Pick the specific populations you want to include in your analysis.
3. Run Pocket Immunologist
   
   • Click the AI Pocket Immunologist buttton in the upper right corner of the panel:

Tips for Refining Your Analysis

• Filter – Use the filter button on the right to focus on specific data (e.g., timepoint, sample, age, sex, treatment line/response, subject).

• Group By – Group your data by study timepoint, age group, sex, treatment line, treatment response, or subject name.

* Important Note - If the AI Pocket Immunologist button is greyed out, it means there are no p-values available for your current selection. The AI requires p-values to identify the most relevant changes and guide you toward the next steps.

Sample of AI Pocket Immunologist: 

Summary of Your Drug's Effects
Clinical response is strongly associated with the expansion of highly differentiated CD4+ T effector memory cells, alongside a concurrent rise in regulatory T cells.

1. Response Linked to CD4+ Effector T Cell Expansion
   
   • Finding: Responders show a highly significant increase in CD4+ T Effector Memory RA+ (TEMRA) cells (log2 fold-change = 2.24, p=0.0004) and CD4+ T Effector Memory (TEM) cells (log2 fold-change = 1.53, p=0.0043).
   • Interpretation: This is a strong signal that your drug's efficacy is driven by promoting a powerful, terminally-differentiated CD4+ T cell response. These cells are critical for orchestrating the overall immune attack.
2. Concurrent Rise in Suppressive T Cells
   
   • Finding: Regulatory T cells (Tregs) are also significantly increased in Responders (log2 fold-change = 1.27, p=0.0159).
   • Interpretation: This suggests a potential negative feedback mechanism is also activated. While this may control immune-related toxicity, a high Treg to effector ratio could eventually limit the durability of the response.

Emerging Story & Next Step:
The data reveals a potent but counter-regulated CD4+ T cell response driving clinical benefit, with a notable absence of a CD8+ T cell signature. The key question is the balance between these opposing forces. We recommend you directly visualize the ratio of effector to regulatory T cells.

What could you do next with these AI insights?

‍Create a chart that compares the proportion of effector T cells (immune-activating) to regulatory T cells (immune-suppressing). This ratio helps you assess whether the immune response is dominated by activation or suppression, and how that balance shifts over time or between groups.

‍