Lumina Bio — In-silico drug design and validation for hard targets

Why we exist

When a target fights back, we re-route.

Drug discovery is slow and expensive, and it stalls most often on the targets that matter most — the hard ones, the ones called undruggable. Many teams have a good target but no clear path to a molecule.

We route around that bottleneck with computational design and multi-layer validation. When one approach is blocked, we find another path — inhibition gives way to degradation, one chemistry to another — where conventional discovery stops.

We do not screen millions by brute force. We aim, carefully, at a small number of well-understood candidates. Precision is the strategy.

The platform

One pipeline, from a target to a validated candidate.

Our proprietary platform runs a single, sequential pipeline: generate novel molecules, filter them through independent computational gates, and accumulate what we learn. Each stage is built to remove the false positives the previous stage could not see.

01 — Generate

Create

Novel molecules designed directly in the target's binding site — not screened from known libraries.

02 — Cross-validate

Confirm

Independent, orthogonal methods at every stage, so one signal never decides.

03 — Accumulate

Compound

Every result — including negative ones — feeds the platform and sharpens the next design.

01Generative design Create novel candidate molecules for the target.

02AI binding prediction Rapidly triage promising binders from the rest.

03Structure-based docking Predict how a molecule sits in the binding site.

04Molecular dynamics Test whether the binding holds over time.

05Free-energy methods Quantify binding strength on a physical basis.

06ADMET & drug-likeness Evaluate absorption, metabolism, safety, and more.

07Synthesizability Confirm a real, viable route to make it.

08Novelty screening Check it is distinct enough to protect.

→ Validated candidate A molecule that has passed every independent gate.

Validation discipline

We trust no single signal.

A good docking score is not binding. Binding is not potency. Each layer must be independently confirmed — and this discipline is what separates a real candidate from a computational artifact.

Principle 01

Distrust single metrics

No one score decides. Binding prediction, dynamic stability, and free energy each say something different — and any of them can reverse the verdict.

Principle 02

Independent cross-validation

We confirm with methods built on different principles. Synthesizability is checked several ways; free energy is computed by two mathematical routes at once.

Principle 03

Prediction meets measurement

We compare predictions against real measurements and correct the next prediction with the gap. The platform grows more accurate the more it is used.

The real asset is not any single molecule. A candidate list ages; the ability to design better molecules — and the discipline to validate them — does not. Every project deepens the platform.

What the gates actually do

Three million molecules in. Nineteen out.

A recent multi-target campaign in neurodegeneration, stage by stage.

Structure-based generation 3,000,000

Passed novelty filter 424,387

Passed property & CNS suitability 34,847

Docked against all three targets 34,755

Strong binding at every target 1,645

Completed AI binding prediction 1,644

Top tier, carried forward to extended dynamics 19

Every stage is an independent gate, and each one uses a different principle from the last. The overall pass rate is 0.0006%. We treat that number as a measure of rigour, not a weakness — a pipeline that passes most of what enters it is not filtering anything.

We have found errors in our own pipeline, withdrawn the conclusions that rested on them, and recomputed. A validation system working does not mean errors are absent. It means errors are found.

Targeted protein degradation

It is a geometry problem, not a binding problem.

Inhibitors block a protein's function. Degraders remove the protein. That difference bypasses the feedback activation which limits inhibitors, and it is less vulnerable to resistance driven by target overexpression — and because degraders act catalytically, activity does not require sustained high occupancy.

The trade-off is difficulty. An inhibitor needs to bind one site. A degrader must hold the target and an E3 ligase at the same time, and the resulting ternary complex has to adopt a geometry that actually permits ubiquitin transfer. Lumina Bio has concentrated on treating that geometry problem computationally.

PROTAC — current focus Molecular glue — extension Antibody-based — out of scope

Ternary complex predictionDeep-learning co-folding of the bound complex.

Stability under dynamicsExtended simulation of the predicted structure.

Benchmarked against published structuresMeasured against active-state complexes in the literature.

Exhaustive lysine scanUbiquitination sites mapped, not assumed.

Independent cross-checkConfirmed by a method built on other principles.

An honest boundary

We report these as geometric feasibility assessments, not verification. Computation evaluates whether a productive arrangement is possible; actual degradation efficiency is established experimentally, and we do not describe one as the other.

Membrane context

Some targets do not work in solution.

Most degrader work models the ternary complex in water. Many of the proteins that matter never see that state — small GTPases held to the inner leaflet by a lipid anchor, receptors, transporters. They sit on a membrane in a defined orientation, and that orientation decides where an E3 ligase can and cannot reach. We build those systems, run them, and hand back a result you can check.

Deliverable 01

Ternary dynamics in a bilayer

The whole system — target, degrader, E3 ligase and its adaptors — in an explicit lipid bilayer of the composition the biology calls for. We report whether the interactions that define the complex survive the run, residue by residue, with occupancy measured across the trajectory rather than read off one frame.

Deliverable 02

Is the geometry even reachable

An E3 ligase arriving at an anchored target has to fit somewhere, and part of the space around that target is taken up by the bilayer. We measure how much of a trajectory admits a given ternary geometry and report it as a reorientation cost in kcal/mol, so it can be weighed against the other terms in your model.

This is the part solution-phase prediction cannot see.

Deliverable 03

System build, with the checks shown

If you run your own simulations, we will build and verify the system. Setup errors in membrane and multi-protein systems are usually silent: the run completes, the numbers look reasonable, and the answer is wrong. Our protocol is twenty-two checks covering atom and charge bookkeeping, degrees of freedom, bilayer integrity, protein placement and orientation, and the chemistry of the bound ligand — which routinely passes every count-based check while being structurally incorrect.

The report is the deliverable, not an appendix to it.

What we have checked

A published ternary complex, reproduced. From crystallographic coordinates, 100 ns of unrestrained dynamics kept every interaction the structure paper identifies. The defining salt bridge held in every frame, at a mean distance matching the crystallographic value.
Ligand parameters without hand correction, across 298–1,486 Da and including degraders with more than twenty rotatable bonds. No missing parameters, no substituted analogies.
Bilayer properties against experiment. Thickness within 0.2% of the scattering value, and the deuterium order parameter profile reproduced along both acyl chains, including the dip at the site of unsaturation.
Orientation behaviour against the literature, including its dependence on anionic lipid. Published studies reached those states with microseconds of sampling; ours arrived within hundreds of nanoseconds across independent replicates.

What we do not claim

We do not predict degradation. No DC50, no Dmax, no ranking of compounds by potency. Nothing we produce has been tested against a degradation assay.
We do not quantify cooperativity. The membrane term we measure is one contribution among several, and we do not currently model the others.
Our validation is against published structures and published measurements, not against experiments we commissioned.
Sampling is finite. Where a system has several accessible states, hundreds of nanoseconds may find them without establishing how often each occurs. We say which of the two we have done.

Services

Where our partners come in.

We develop our own pipeline — and we put the platform to work for other teams. Partners enter at different points; we meet them there.

Entry 01

Strong chemistry, no in-silico

You have an excellent medicinal chemistry team but no computational design capability. We design candidates for your target; you synthesize.

Entry 02

You ran it. Can you trust it?

The simulation finished and the answer looks clean, but nobody can tell whether the system underneath it was built correctly. Setup errors in this work are usually silent. That is the part we check.

Entry 03

Biology, meet computation

We connect target biology and molecular simulation in one integrated pipeline.

In-silico DesignNovel candidates designed for your target.

Multi-stage ValidationYour molecules, put through the full gauntlet.

Synthesis CoordinationSynthetic routes and external CRO synthesis, coordinated.

Hard-Target StrategyWorkaround design for targets that resist.

Milestone PartnershipMilestone-based, with joint-IP options.

Advisory RetainerOngoing in-silico support, month to month.

Membrane-Context SimulationTernary complexes in an explicit bilayer, with the build verified.

Your data

Nothing has to leave your side

We run our own on-premise GPU infrastructure, so your project is never bottlenecked by rented compute and research data does not transit external cloud services. Structures and compounds can be processed entirely on premises; we do not require upload to a hosted service.

Your IP

You get the system, not only the answer

Coordinates, topologies, trajectories, analysis scripts and the verification report — enough to repeat the calculation yourself or hand it to another group. Rights to what a commissioned campaign discovers belong to you; the platform and its methodology remain ours. We set this out in contract, work under NDA, and never repurpose your target for anyone else.

No risk to start

Start with a free pilot.

New to us? We take your target and deliver an initial in-silico design pass at no cost. If you like it, we scope a paid engagement. Your structures stay yours — always under NDA.

Request a pilot

Pipeline

What the platform has produced.

These are in-silico validated assets — evidence that the platform carries a candidate all the way through. They are not clinical-stage programs; wet-lab validation lies ahead.

Program	Disease area	Stage
Program A	Neurodegeneration	In-silico validation complete — preparing patent filing
Program B	Neurodegeneration (multi-target)	In-silico validation ongoing
Program C	Oncology	In-silico validation ongoing

Stages: Design → Multi-stage validation → Free-energy → Synthesis → Binding assay → in-vivo PoC → Partnering

Shown as evidence of capability, not as approved or clinical-stage medicines. Targets, structures and figures are deliberately withheld until patent filings are in place — we will expand this table as they are.

Company

Built from the ground up, for precision.

We believe the next generation of medicines can be designed — computationally, rigorously, and for the targets the world has given up on. We build that capability, and prove it one validated molecule at a time.

Lumina Bio develops and operates the Andromeda platform in house. No single score decides an outcome here, and nothing advances on computation alone — that discipline, rather than any one molecule, is what we take to be the asset.

CompanyLumina Bio Co., Ltd.

CEOChoi, Jae Yong

LocationRoom 409, 204 Munhwa-ro, Naju-si, Jeollanam-do, Republic of Korea

Business registration223-88-03724

FocusIn-silico small-molecule drug discovery