The current FORTE dashboard includes 25 agents (15 Core + 10 Innovation). While comprehensive for standard clinical trial analysis, critical gaps exist for uncovering hidden insights specific to BRAF-targeted therapy in CNS and solid tumors.
Uncovering hidden patterns in how responses evolve over time
Identifies patients whose ctDNA clearance kinetics predict acquired resistance 3-6 months before radiographic progression, enabling combination therapy escalation.
Patients with >50% ctDNA reduction at Week 2 have 89% probability of confirmed response at Week 8 - enabling early efficacy signals for regulatory discussions.
Identifies the "super-responder" phenotype: patients with complete molecular response by Week 8 + specific genomic profile have 70% probability of response >24 months.
Specialized analysis for blood-brain barrier penetration and CNS tumor dynamics
Identifies imaging patterns that distinguish pseudoprogression from true progression with 85% accuracy at Week 8, reducing unnecessary treatment discontinuations by 40%.
Correlates CNS response with estimated intracranial drug exposure, identifying patients who may benefit from dose escalation or P-gp inhibitor combinations.
Identifies early LMD warning signs in patients with CNS parenchymal response, enabling prophylactic strategies to prevent this devastating complication.
Specialized analysis for targeted therapy mechanisms and safety
Plixorafenib is designed as a "paradox breaker" - this agent validates that design by monitoring for the absence of paradoxical activation signals that plague older BRAF inhibitors.
Identifies the "molecular window" for MEK inhibitor addition - the optimal timing to add combination therapy before clinical resistance manifests.
FORTE Sub-Protocol D specifically targets BRAF fusions - this agent identifies which fusion partners predict enhanced or diminished response.
Deep profiling of outliers - both exceptional responders and near-misses
Identifies the "cure signature" - the combination of baseline tumor/host factors that predict which patients may achieve functional cure with BRAF inhibition alone.
Patients with SD and 20-25% tumor reduction may have responded with MEK inhibitor combination or higher dose - identifies these "almost responders" for rescue strategies.
Identifies co-mutations (e.g., PTEN loss, NF1 mutations) that predict primary resistance, enabling better patient selection and reducing futile treatment.
Tracking how tumors adapt and evolve during treatment
Identifies the emergence of resistant subclones (e.g., NRAS Q61 mutations) at variant allele frequencies as low as 0.1%, enabling preemptive combination therapy.
BRAF inhibition can reprogram the TME, increasing T-cell infiltration - identifies which patients may benefit from BRAF + IO combinations based on TME changes.
Identifies "sanctuary sites" where response is discordant - e.g., systemic response but CNS progression, enabling targeted local therapy strategies.
Leveraging the unique FORTE basket trial design for cross-learning
Discovers that CNS tumors (Sub-Protocol A) and ameloblastoma (Sub-Protocol C) share a unique response pattern not seen in other solid tumors - leading to new mechanistic hypotheses.
Identifies the "universal BRAF V600 response signature" that predicts response regardless of tumor type - supporting tissue-agnostic FDA approval pathway.
Even with only 3 ameloblastoma patients in Sub-Protocol C, integrates external case reports and mechanistic data to build a compelling regulatory narrative.
Integrating digital biomarkers and real-world patient data
Detects subtle improvements in gait, balance, and activity levels in CNS tumor patients that precede radiographic response by 4-6 weeks.
Identifies that cognitive function improvement (critical for CNS tumor patients) correlates more strongly with long-term outcomes than tumor shrinkage alone.
Proposed expansion from 25 to 45 agents, adding 20 specialized agents designed to uncover hidden insights that standard clinical trial analysis misses.
How novel agents connect to uncover insights no single agent could find alone
| Discovery Pathway | Primary Agents | Supporting Agents | Hidden Insight Type |
|---|---|---|---|
| Early Resistance Warning | 26, 27, 33 | 38, 18 | Predict resistance 3-6 months early |
| Super-Responder Identification | 35, 28 | 39, 27 | Identify "cure signature" patients |
| CNS-Specific Optimization | 29, 30, 31 | 44, 45 | Pseudoprogression discrimination |
| Cross-Cohort Learning | 41, 42, 43 | 34, 16 | Tissue-agnostic approval support |
| Safety Differentiation | 32, 10 | 33, 18 | Validate paradox-breaker design |
| Salvage Opportunity | 36, 37 | 38, 33 | Rescue near-miss responders |