A patient's biological sample goes in. A manufactured, personalized treatment comes out.
Any patient. Any condition. Any modality.
One continuous loop. The patient's own biology defines the target, our engine designs the therapy, and manufacturing delivers it back.
Sequencing, expression, and variant data from a single patient sample define the therapeutic target with individual precision.
Our models generate, score, and refine candidate therapies against that target across every available modality.
The selected candidate moves into synthesis and manufacturing as a physical, patient-specific therapeutic.
Outcome data trains only our models. The intelligence compounds with every patient.
Four capabilities that compose into a single system. Each one works alone. Together they cover the full path from target to therapy.
Read a patient's genome to determine which existing drugs will work, which will fail, and which will cause harm — before the first dose.
PharmacogenomicsGenerate entirely new molecules against targets that have no drug — small molecules, peptides, and biologics designed de novo.
Drug DesignCorrect the defect at its source. Guide design, delivery, and off-target prediction for therapies that rewrite the underlying sequence.
Gene TherapyDirect biological systems rather than merely inhibiting them — instructing immune cells and cellular machinery toward a chosen outcome.
Biological CommandEvery program is at target-to-hit: candidates designed and computationally scored, and validation-ready as academic medical center collaborations are finalized. Behind them sits a designed candidate library spanning every modality we operate in.
| Program | Indication | Progress | Status |
|---|---|---|---|
| MAP2K1 | MEK1 — solid tumors | Target-to-hit | |
| KRAS G12D | Pancreatic, colorectal | Target-to-hit | |
| RAC1 | Metastatic progression | Target-to-hit | |
| CTNNB1 · IDH1 | Multi-target oncology | Target-to-hit | |
| Additional oncology targets | Broad solid & liquid tumors | Target-to-hit | |
| Immune Activation Platform | Immuno-oncology | In design | |
| Antimicrobial Programs | Resistant infection | In design | |
| Gene Therapy Programs | Monogenic disease | Planned |
Every candidate in the pipeline was designed de novo by our engine and is a LillixBio asset. Candidates are validation-ready, with academic medical center collaborations being finalized.
Competitors can rebuild any single layer. Rebuilding all three, and the compounding between them, is the actual barrier.
Patient outcome data flows back into our models and nowhere else. Every treated patient makes the next design better — an advantage that cannot be bought, only accumulated.
Models spanning target identification, generative design, structure prediction, and safety — the ones we train sitting alongside open tools we license and run. The advantage is the composition and the shared constraints.
Design only matters if the molecule can be made. Our engine is coupled to manufacturability from the first candidate, not retrofitted after the fact.
The platform is disease-agnostic by construction. Oncology is the proving ground; the same system extends domain by domain.
For partnership, investment, and scientific collaboration inquiries.