Drug Repurposing & Indication Expansion
Map compound alignment across functional disease states to prioritize new indications, rescue failed assets, and identify therapeutic gaps
The Challenge
Failed Trials with Uncharacterized Alignment
Substantial investment in Phase II/III trials that fail overall — but a subset of patients show dramatic responses. The drug works, but the wrong patients were enrolled.
Unknown Mechanism = Unknown Indications
Your drug has activity in preclinical screens, but the true mechanism of action is unclear. Which diseases would benefit? Which molecular contexts show the strongest mechanistic alignment?
Resistance Mechanisms Undiscovered
Trials fail due to acquired resistance, but you don't know which pathways compensate. Finding combination partners requires expensive screening campaigns.
No Systematic Framework for Indication Mapping
Traditional repurposing lacks a structured way to assess which indications a drug could expand into, where therapeutic gaps exist, and how a compound's mechanism aligns with the biology of each disease state. Decisions rely on clinical intuition rather than systematic evidence.
"Our compound failed in an unselected population, but a subset of patients showed strong compound–biology alignment. A systematic framework for mapping that alignment would have saved the program."
The Helomnix Solution
Helomnix approaches drug repurposing as a state-aware, mechanism-driven prioritization problem. By integrating pathway-level activity patterns with therapeutic response signatures and mapping them onto functional disease states within the Digital Twin Map, the platform constructs a Drug Opportunity Landscape that highlights where existing compounds are mechanistically aligned with disease biology. Functional states showing limited alignment with current therapies are explicitly identified, guiding both indication expansion strategies and the exploration of new therapeutic targets.
Pathway-level activity is scored across curated biological programs and linked to therapeutic sensitivity patterns. This enables the platform to move beyond individual gene-level associations and capture the broader functional context in which a drug operates — connecting compound mechanisms to the disease biology of specific functional disease states within the Digital Twin Map.
Cross-cancer repositioning extends this analysis beyond a single indication. Response and resistance signatures derived from other cancer contexts are applied to identify mechanistically aligned compounds across indications, enabling systematic indication expansion grounded in shared biological mechanisms rather than empirical screening.
Unique Differentiator
The Drug Opportunity Landscape provides a structured, state-aware framework for compound prioritization. Rather than testing drugs against individual cell lines or patient cohorts, Helomnix maps compound–state alignment across the full functional spectrum of disease, identifying both high-alignment opportunities and sparse therapeutic regions where new targets are needed.
How It Works
Drug Signature Generation
Provide gene expression or pathway activity data from drug-treated cells. We generate a ranked molecular signature capturing the compound's functional impact across biological programs.
Drug Opportunity Landscape Construction
Your compound's signature is integrated with pathway-level activity patterns and perturbational reference signatures to construct a Drug Opportunity Landscape — mapping alignment between therapeutic compounds and functional disease states across the Digital Twin Map.
State-Aware Subgroup Mapping & Gap Identification
Map your drug's mechanism onto functional disease states to characterize compound–disease alignment across functional disease states. Functional states with limited mechanistic alignment to existing therapies are explicitly flagged, representing opportunities for new target exploration or underserved populations.
Cross-Cancer Repositioning & Combination Discovery
Response and resistance signatures derived from other cancer contexts are applied to identify mechanistically aligned compounds across indications. Resistance pathway analysis reveals combination therapy candidates and informs rational multi-agent strategies.
Real-World Application
A pharma partner had a Phase II trial in DLBCL with limited overall mechanistic alignment across the unselected population. They wanted to rescue the asset by characterizing the aligned functional disease state and exploring additional indications.
Before
Post-hoc analysis: Spent over a year profiling trial samples, comparing molecular profiles across outcome groups. Found enrichment for a molecular subtype, but too late to salvage trial. No systematic assessment of other indications.
After
Helomnix Drug Opportunity Landscape: Mapped the compound's signature onto functional disease states across the Digital Twin Map. Identified a specific molecular subgroup with strong pathway-level alignment. Sparse therapeutic alignment analysis revealed additional functional states underserved by existing therapies, highlighting opportunities for new target exploration.
Outcome
Supported design of a biomarker-informed study focused on the aligned functional disease state. The characterized subgroup showed substantially stronger compound–biology alignment than the unselected population. Pathway analysis also identified cross-cancer repositioning opportunities and functional states with sparse therapeutic alignment, informing the partner's broader indication expansion strategy.
Value to Your Organization
Systematic Prioritization
Move from empirical screening to mechanism-informed indication exploration. The Drug Opportunity Landscape provides structured evidence for which indications offer the strongest mechanistic rationale.
Indication Landscape
Structured assessment of where compounds align with disease biology across functional states, enabling systematic indication expansion grounded in pathway-level evidence.
Early De-Risking
Pathway-level evidence supporting repurposing hypotheses before clinical investment. Characterize mechanistic alignment patterns and therapeutic gaps early, reducing the risk of unselected trial failures.
Our Methodology
Data Inputs
- Gene expression data from drug-treated cells (vs. control)
- Drug concentration and timepoint
- Cell line or patient samples used
- Known mechanism of action (if available)
- Failed trial data (optional: samples with clinical outcome annotations)
AI/ML Techniques
- Pathway-level activity scoring across curated biological programs
- Drug Opportunity Landscape construction (compound–state alignment mapping)
- Perturbational reference signature analysis for mechanistic similarity
- Digital Twin Map projection for functional disease state characterization
- Sparse therapeutic alignment identification across functional disease states
- Cross-cancer repositioning via response and resistance signatures
- Multi-cohort validation across independent datasets
Deliverables
- Drug Opportunity Landscape: compound–state alignment map across functional disease states
- Sparse alignment analysis highlighting functional states with limited therapeutic coverage
- Cross-cancer repositioning report with signature-level evidence for indication expansion
- Biomarker signatures for mechanistically aligned functional disease states
- Digital Twin Map showing compound–state alignment patterns and underserved functional states
- Resistance mechanism analysis and combination therapy candidates
- Evidence supporting study design considerations, indication expansion priorities, or new target exploration
Discuss a Translational Application
We welcome discussions about how this approach can support your translational research.