- Applications
- Target & MoA
- Target Prioritization & MoA Pilot Study
Prioritize interventions in patient context.
A Crohn’s disease computational pilot explores how SynCausal™ compares target hypotheses, tests modulation strength, and guides mechanistic follow-up using patient single-cell data from CD4+ T cells and CD8+ T cells.
Model capabilities
SynCausal™
Target & MoA discovery
- Cell-type resolution
- Perturbation strength
- Mechanistic hypotheses
- Molecular endpoint specificity
- Per-patient resolution
10
paired patient contexts
7
target candidates
2
virtual suppression levels
3
views: pooled + two T-cell types
Crohn’s disease · CD4+ T cells · CD8+ T cells
One pilot. Two decision lenses.
The target prioritization and patient stratification pages present the same pilot study, viewed through two complementary R&D decisions.
SynCausal™ can be applied across different diseases, indications, and cell types using suitable patient data; this pilot illustrates one biological context.
Illustrative, anonymized case study. Target identities, source cohort, and patient identities remain masked. Outputs are molecular-response hypotheses—not clinical-response labels.
- WHAT THE PILOT SHOWS
- 01 · Evidence for target prioritization
Compare the intervention. Interpret the response.
SynCausal™ evaluates target hypotheses through three complementary readouts. Together, they help identify which interventions and conditions warrant experimental follow-up.
Direction
Does the predicted molecular change point toward or away from the patient-matched reference?
Magnitude
How much molecular change is predicted? A larger shift needs to be interpreted with its direction.
Data support
Is there enough evidence in the patient and cellular context to interpret the prediction?
Pilot example · Modulation sensitivity
Two candidates respond differently to deeper suppression.
50% → 90%
virtual down-regulation
Candidate F
Movement increases
Directional alignment
Increases
Movement magnitude
Increases
Both measures increase in CD4+ T cells and CD8+ T cells. Candidate F has the largest movement gain in the common comparison panel.
Question for follow-up
Does deeper target suppression reproduce the predicted molecular shift?
Candidate G
Movement decreases
Directional alignment
Decreases
Movement magnitude
Decreases
Both measures decrease in CD4+ T cells and CD8+ T cells, revealing a different dependence on target-suppression strength.
Question for follow-up
Does the inverse-depth pattern persist when modulation strength is tested?
Depth comparison: five candidates across six support-qualified patient contexts and two lineages. Arrows show changes in the comparison summaries; individual patient responses can differ.
Prioritization implication
A target hypothesis includes the intervention strength and biological context. Direction, magnitude, and support must be considered together when choosing what to test next.
- 02 · Patient context
The same intervention panel. Different directional responses.
Patient context changes how a molecular shift should be interpreted. Within this panel, predicted direction is often similar across candidates in a given context, yet differs across contexts.
Patient-level directional profiles
One cellular lineage
6
Positive directional profiles
Predicted shifts tend to align with the matched reference direction.
2
Near-neutral or mixed profiles
Directional alignment is limited or varies across the intervention panel.
2
Negative directional profiles
Predicted shifts tend to oppose the matched reference direction.
Ten context profiles summarized across all fourteen candidate × depth predictions per context. These are molecular direction profiles, rather than clinical-response categories.
Reading the pattern
A large molecular shift needs a direction.
A candidate may generate an aligned shift in one context and an opposing shift in another.
Near-neutral alignment can also coexist with molecular movement in a different direction.
Question for follow-up
Which patient-derived states should be included when testing the target hypothesis?
- 03 · Molecular response fingerprint
Guide the next mechanism experiment.
Comparing responses across patients, cellular lineages, and modulation depths helps focus mechanism-of-action studies on the conditions and readouts that deserve follow-up.
Reading the pattern
Shared patient ordering
Patient ordering is highly similar across CD4+ T cells and CD8+ T cells.
Cross-lineage rank correlation
≈ 0.9
Movement magnitude
A cellular-context dimension
Response magnitude differs between CD4+ T cells and CD8+ T cells.
Cross-lineage rank correlation
≈ 0.1
Depth comparison: five candidates across six support-qualified patient contexts and two lineages. Arrows show changes in the comparison summaries; individual patient responses can differ.
Reading the pattern
Shared patient ordering
01
Select the context
Choose patient states and lineages with contrasting modeled responses.
02
Examine the molecular program
Use pathway-specific readouts to investigate which predicted changes explain the contrast.
03
Test the hypothesis
Measure the response after target modulation in the selected experimental contexts.
Example follow-up workflow. This pilot characterizes response dependencies to guide investigation of the underlying molecular mechanism.
- Study design & interpretation
Explore the scientific detail
How the pilot was run
Paired disease-involved and matched reference single-cell profiles from ten patients with Crohn’s disease were used to evaluate seven preselected candidate interventions at 50% and 90% virtual down-regulation.
Predicted molecular responses were examined in pooled cells, CD4+ T cells, and CD8+ T cells. These are three overlapping analysis views.
Model output and study readout
SynCausal™ predicts expression profiles across approximately 20,000 protein-coding genes. This pilot evaluated the output using a shared disease-related readout of approximately 1,000 genes selected through pooled-cell analysis. This broad gene pool may limit the directional score’s ability to distinguish specific signaling differences between targets.
Pathway-specific submodules can be examined in follow-up to distinguish more detailed target and lineage responses.
Readout
Definition and interpretation
Direction
Cosine alignment between the predicted molecular shift and the disease-to-reference direction. +1 is aligned; −1 is opposing. Zero indicates an orthogonal shift and does not establish an absence of molecular change.
Magnitude
Weighted root-mean-square norm of the predicted molecular shift. It describes the size of the movement and must be interpreted alongside direction and support.
Support
Low cell coverage and unstable estimates limit interpretation. Estimates failing the study’s quality criteria are excluded from the corresponding comparisons.
Comparison populations
Depth sensitivity: six support-qualified contexts, five candidates, two lineages. Changes compare 90% with 50% virtual suppression.
Cross-lineage correlation: seven support-qualified contexts on a common four-candidate panel. Other contexts are excluded from that comparison.
What the evidence supports
The ten-context pilot illustrates relative comparison within qualified patient and cellular contexts. Cross-context absolute effect sizes are not yet calibrated.
Virtual suppression levels describe model interventions; they are not drug doses. The study does not establish a universal target rank or a validated clinical response.
Interpreting the response fingerprint
In this panel, patient context accounts for most directional variation; magnitude reflects both patient and candidate effects. Shared pathway membership and the broad gene readout may compress differences between candidates. A larger cohort, pathway-specific analysis, and experimental follow-up would help assess robustness and investigate the underlying mechanism.
- Partner decision package
From predicted response to experimental priorities.
A focused program connects candidate comparisons to the biological context and evidence needed for follow-up.
01
Target shortlist
Candidate hypotheses interpreted through direction, magnitude, and data support.
02
Context map
Patient and cellular contexts with aligned, opposing, or uncertain responses.
03
Response fingerprint
Context and modulation dependencies that help focus MoA studies.
04
Validation priorities
Candidate-specific readouts and experimental comparisons to test next.
Your biology · your decision
Bring the target question your team needs to resolve.
Define the intervention panel and relevant patient contexts, then connect the resulting hypotheses to a focused validation plan.