Overview
| Name | Mosaic |
|---|---|
| Full name | The repository uses the tool name only; no expanded name |
| Ambiguous names (not auto-linked) | Mosaic |
| Family | Not a family entry. A single open-source library with no family members |
| Organization | Escalante Bio |
| Organization type | AI-native biotech |
| Country | United States |
| Model class | Design (multi-objective differentiable optimisation library) |
| Domain | Proteins (also: Molecule generation) |
| First release | † unverified · code release Basis: Repository creation and first commit (no earlier public announcement or paper found this round) Note: Policy forbids repository creation as a first release, so this date must display as unverified; the only tagged version is v0.1.0 (2026-10-06) source |
| Other milestones | |
| Latest update | · code release Basis: Repository commits: structure-model contract and sampler options Adds a structure-model contract and exponential/geometric sampler options; recent commits added two structure backends and an enzyme-design backend and removed an older one; v0.1.0 tagged 2026-10-06 source The most recent sourced event, not a claim that nothing changed since. |
| Status | Active · Tagged release and ongoing commits within 12 months |
| Openness | Code: Open · MIT Weights: Unclear The library has no weights of its own and depends on third-party scorer weights under their own terms |
| Benchmarks reported | 1 counted (board 1) |
| Wet-lab validation | 2 recorded campaigns |
| Unverified fields | † first_release, release_milestones.first_public_evidence, wetlab_validation[1].date, background.products_partnerships, open_status.weights |
| As of | 2026-11-16 |
What it does
Not a single model but a library that combines co-folding predictors and other scoring terms into one differentiable multi-objective loss, then optimises sequences by gradient to design binders, with swappable scorers that track newer models. Like BindCraft it backpropagates through scorers, but its backends are interchangeable; it differs from the trained generative route of BoltzGen, and typical backends come from models such as Boltz-2.
Benchmarks reported
Every row is one pairing from the survey's relation file; a score belongs to the benchmark page's ranking, where it is shown with metric, eval set, source type and date. 1 of 1 pairings are counted.
| Benchmark | Relation | Eval set / protocol | Source type | Note and evidence |
|---|---|---|---|---|
| 28 Adaptyv competitions / BenchBB | Official leaderboard or results | — | Board | Entrant in the 2025 de novo track with results on the organiser site; hit rates are self-reported · evidence |
Other evaluations (outside the 44)
- Own two-target minibinder test (Wet-lab validation) Self-reported: Three design arms across two targets, reporting the best arm's per-target hit rate
- Scorer interchangeability demonstration (Case study) Self-reported: The repository demonstrates plugging different structure and enzyme-design backends into the same optimisation loop
Developers report: assembling off-the-shelf scorers into a differentiable objective already yields minibinders that bind at a high rate, with top-ranked designs in a public competition's de novo track.
Independent evidence: The organiser's results page records design-level outcomes for that competition and can be checked against the entry, but it gives no per-tool hit rate and so is not an independent evaluation of the library.
Training data
Group in Figure 7: Public data + wet lab for validation only.
| Class | Value | Detail |
|---|---|---|
| a. Public databases | No | No training of its own; relies on the weights of the models it calls source |
| b. Private or licensed data | No | |
| c. Own wet-lab data used for training | No | |
| d. Wet lab used only for validation | Yes | Designs assayed by a protein measurement service provider, for validation only source |
Wet-lab validation
Every rate carries its numerator and denominator. Claims that could not be verified are shown as unverified, without numbers; different paper versions are separate entries.
Denominator basis: Ten designs, one target, self-reported
The "1st-4th" framing means four of its designs ranked top-four de novo by affinity, not participant placings; the organiser's participant ranking differs. Keep the n=10 single-target caveat
Executor: Executed by the organiser and its measurement provider; hit counts self-reported
Denominator basis: Ten designs per method per target, three methods across two targets, 60 sent in total
Both rates are the best method arm per target and must be stated as selected across three arms
Executor: Executed by a protein measurement service provider
Background
- Organization: A small protein-design company focused on computational minibinder design and open-source tooling; its jobs page calls it a well-funded startup, while founding year, funding and headcount are not publicly disclosed and so are not stated.
- Funding: Not disclosed
- Products and partnerships: The product is the open library itself, alongside open work porting an open binder-generation model to another framework (per a developer social post, second-hand); no pharma partnerships are disclosed.
- Related models: BindCraft, Boltz-2, BoltzGen
Reading notes
- The 9/10 figure rests on ten designs against one target, so the confidence interval is wide.
- Distinguish the ranking: four of its designs placed top-four, which is not a participant placing.
- The 8/10 and 7/10 figures are best-of-three arms and must not be read as one method's hit rate.
- It is a library, not a model, so performance tracks the chosen scorers; its first-release date is inadmissible under policy and displays as unverified.
Caveats
- The first-release basis is repository creation or first commit, which policy disallows; it must show as unverified.
- Hit rates and placings come from the developer blog, and the competition ranks by affinity.
- The library has no training or weights of its own, so performance cannot be attributed to it alone.
- The self-test blog page carries no sourced date.
Sources
- Code repository (repository)
- Releases API (repository)
- Developer competition blog post (company blog)
- Developer minibinder blog post (company blog)
- Competition results page (leaderboard)
Corrections
3 corrections
| Field | Was | Now | Basis | Found |
|---|---|---|---|---|
| wetlab_validation | Took first to fourth place in de novo (participant placings) | Its four designs rank top four by affinity; the organizer's participant ranking is different | source | 2026-11-16 |
| wetlab_validation | Hit rates of 8/10 and 7/10 on two targets | Same numbers, but it must be noted that they come from the best of three design arms | source | 2026-11-16 |
| first_release | 2025 (no basis) | 2025-01-12, based on repository creation / first commit, which the policy does not accept; shown as unverified | source | 2026-11-16 |
Part of the AI for Bio benchmarks survey · all 112 models · open in the explorer. Record as of 2026-11-16.