AI-DRIVEN ANTIBODY & NANOBODY DISCOVERY & ENGINEERING
Generative design backed by Alloy's integrated build-and-screen engine
New AI-first antibody services for optimization and de novo design
10,000+
up to 360°
ATX REFORGE & ATX CAST
Choose the right starting point
Learn how to get started, review results from real campaigns, understand what you receive, and explore the commitments behind every engagement.
HOW TO GET STARTED
Start with a molecule, or start with a target
Both programs connect computational design with Alloy’s build-and-screen capabilities. The difference is where the work begins.
Define the right starting point
Whether you’re starting with a molecule or a target, the ATX Design Assessment helps define your priorities, evaluate the opportunity, and identify the right path into ATX-Reforge or ATX-Cast. Costs can be credited towards ATX-Reforge or ATX-Cast. Assessment fees can be credited toward a subsequent program.
Start with an antibody
Bring us a clinical asset, a shelved program, or a lead that needs rebalancing. Together, we define your program goals. Alloy redesigns the antibody, builds and screens the variants, and ranks the resulting candidates against that profile.
Optimize against the full target product profile
Rebalance affinity, potency, specificity, half-life, immunogenicity, and developability against the profile you define, rather than blindly trading one away for another.
Select with confidence
Come away with a ranked portfolio and the data behind every candidate in it.
Build a differentiated and future-proof portfolio
Give your IP counsel a portfolio of candidates that are materially distinct at the sequence level from the parent you already own, each with measured properties and a documented design rationale.
Start with a target
Bring us a target, an epitope, and a functional objective. Alloy designs a focused set of antibody or nanobody candidates, then builds and experimentally screens them.
Target a defined epitope and function
Point the design at the target and epitope you define, with the functional objective written into the design brief before anything is built.
Generate new starting matter
Generate starting matter orthogonal to what immunization returns, for targets where conventional approaches keep producing the same handful of clones.
Move selected hits into optimization
Selected hits feed directly into an ATX-Reforge program, carrying the campaign data forward into optimization.
CAMPAIGN RESULTS
Measured results from completed campaigns
Results from optimization programs and de novo design campaigns
Optimization campaigns
In two design–build–test rounds, completed in approximately six weeks, candidates reached picomolar affinity, improved functional potency, and cross-species binding beyond the clinical comparator
Most leads reach picomolar affinity with zero developability flags within six weeks.
199/200
Variants bound the target
We expressed and characterized all 200 variants. 199 bound the target, 147 measured below 10 nM, including five in the picomolar range.
<100 pM
Affinity in two rounds
In this campaign, approximately six weeks of design, build, and testing produced sub-100 pM affinity and functional potency that exceeded the clinical comparator.
Human + cyno
Cross-reactivity not achieved by comparator
Designed candidates retained binding across both species through two optimization rounds. The clinical comparator showed no cross-reactivity.
De novo design performance
Results from de novo design campaigns on targets for which only a predicted structure was available.
46/46
De novo designs expressed
All 46 designed molecules expressed, allowing the screen to evaluate binding performance rather than construct failure.
>10%
Top recombinant hit rate
On average, more than one in ten VHH designs produced a recombinant hit against therapeutically relevant targets.
14 nM
Best first-pass binder
A fully de novo VHH reached 14 nM affinity in the first design round against a target with no experimental structure available.
CAMPAIGN DELIVERABLES
What you receive
A decision-ready package built for scientists, program teams, and leadership showing a clear record of what changed from the starting molecule, supported by experimental data.
A denoising trajectory from a diffusion run. Successive steps, from noise to a folded single-domain backbone. Alloy has developed best-in-class algorithms for sampling candidate sequences from modern protein design models built on top of our proprietary data.
A ranked candidate portfolio
Candidates ranked against your target product profile, with performance and sequence diversity shown separately to make the trade-offs visible.
The underlying experimental data
Every measurement behind the final designs: selection and enrichment data, expression, affinity, and developability readouts on the characterized set. Your team receives the relevant measurements, not only a summary.
A one-page story per candidate
What changed from the parent molecule, which properties improved, where trade-offs were observed, and how far the sequence moved.
A sequence-space analysis
Design neighborhoods, edit-distance distributions, liabilities, and measured properties presented together for scientific and intellectual-property review.
Comparative context
When enough comparable campaign data exists, we show the relevant distribution. When it does not, we state that limitation.
A recommended next step
The final report recommends whether to optimize, advance, test further, or stop. When additional work is appropriate, we include the proposed scope and cost.
OUR COMMITMENTS
Guiding Principles & Guarantees
The campaign scope, quality criteria, data package, and ownership terms are documented before work begins.
A defined, quality-controlled process
A defined, quality-controlled workflow with a clear path forward written into the contract. What the biology does is measured and shared with you as we find it.
Clear ownership and data terms
When you option a candidate, the molecule and its data belong to you under the terms of the agreement. Partner molecules and data are not used to train Alloy models or shared with another partner.
Evidence for scientific and IP decisions
You receive a diverse set of candidates, measured properties, and the associated design record. Your scientific and legal teams can use that evidence to evaluate development and filing options. Patentability and freedom-to-operate determinations remain with your counsel.
getting started
Find the right path forward
Within five business days, Alloy will assess the design opportunity, identify the main constraints, and recommend a path forward.
Bring us a molecule or a target, and the properties or function you need.
We evaluate the available information, identify the main constraints, and recommend an appropriate program path.
If you move forward, we turn the assessment into a design campaign and generate the experimentally tested molecules and data for your next program decision.