AI for Bio · Model

Dyno Psi-1 / Psi-Phi

Open-weight binder design model of about 200M parameters with a companion filter and agent suite

ProteinsAI-native biotechUnited StatesActive中文

Overview

NameDyno Psi-1 / Psi-Phi · aliases: Dyno Psi, DynoPsi, Psi-1, Psi-Phi
Full nameNo separate expanded name
Ambiguous names (not auto-linked)None
FamilyCovers the Psi generator series and the companion filter/agent suite Psi-Phi; the wet-lab arm used the earlier Psi-0.5, which is separate from Psi-1
  • Psi-1 ·
  • Psi-Phi ·
  • Psi-1.5 Cicada ·
OrganizationDyno Therapeutics
Organization typeAI-native biotech
CountryUnited States
Model classBinder backbone generation
DomainProteins
First release · code release
Basis: GitHub v1.0.0 with the whitepaper and press release on the same day (conference launch)
Note: Repository creation dates are not used as first release; the press-release date was not independently re-checked source
Other milestones
  • Code release: · GitHub v1.0.0 source
  • Weights release: · Weights released with v1.0.0 source
Latest update · new version
Basis: GitHub release 2.0.0
Version 2.0.0: default weights switched to Psi-1.5 Cicada, with breaking API changes source
The most recent sourced event, not a claim that nothing changed since.
StatusActive · New version and new weights within 12 months
OpennessCode: Open · Apache-2.0
Weights: Open · Apache-2.0
Weights and code Apache-2.0; the synthetic training dataset CC BY 4.0
Benchmarks reported0 counted · none of the 44
Wet-lab validation1 recorded campaign
Unverified fieldsNone
As of2026-11-16

What it does

An open-weight binder design model: a flow-matching backbone generator of about 200M parameters followed by a sequence-design tool, with Psi-Phi as the companion filter and agent suite.

Benchmarks reported

None of the 44 benchmarks. This model is on the zero-pairing list.

How it evaluates itself: In silico binder filter, 5 targets; IL-7RA yeast-display comparison; Press-release comparison

Other evaluations (outside the 44)

  • Five-target in-silico filter pass rate (Own task set) Self-reported: Psi-1 computational filtering: 16,900 designs per model across 13 length bins; best on only 2 of 5 targets, i.e. parity not a win; this is not a wet-lab result
  • Press-release comparison (Comparison against baselines only) Self-reported: The company states an advantage over several open methods without per-target numbers

Developers report: Developers report that this ~200M open-weight model, with test-time scaling against high-throughput experiments, gives a higher IL-7RA wet-lab success rate than the comparator

Independent evidence: No independent evidence found. No independent head-to-head found

Training data

Group in Figure 7: Public data + wet lab for validation only.

ClassValueDetail
a. Public databasesYesExperimental and predicted structure databases plus ~4M synthetic domain-interface dimers (32,253 high-confidence ones used for fine-tuning)
b. Private or licensed dataNo
c. Own wet-lab data used for trainingNot disclosedThe extent of experimental feedback into training is not disclosed
d. Wet lab used only for validationYesYeast display and SPR used for validation only

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.

IL-7RA yeast-display comparison (Psi-0.5)
Targets — · Designs tested 100 · Hits — · Success — · Best affinity —

Denominator basis: Initial sampling budget matched (~12k), not design counts: the comparator's full pipeline yielded 125 designs from that budget while these designs were subsampled from the same budget; success was measured on the top 100 designs ranked by ipSAE, with no per-target numbers, so no rate is printed
The wet-lab arm is the earlier Psi-0.5, not Psi-1; developer-run, not an independent replication

Self-reported · No sourced date · verified · source

Background

  • Organization: Dyno Therapeutics is an AI-driven AAV capsid design company founded in Massachusetts in 2018
  • Funding: Announced a $100M Series A in 2021-05 led by a16z
  • Products and partnerships: Capsid deals with large pharma companies (one licence exercised in 2026-04); the whitepaper was written by the company's AI lab with engineering support from a GPU company
  • Related models: La-Proteina, BoltzGen, RFdiffusion2 / RFdiffusion3

Reading notes

  1. The five-target result is Psi-1 computational filtering, not a five-target wet-lab campaign
  2. The wet-lab comparison matches sampling budget rather than design counts, and used Psi-0.5
  3. Success was measured only on the top 100 ranked designs, with no per-target numbers

Caveats

  1. No results reported on any of the 44 benchmarks
  2. The press release's advantage claim has no per-target data behind it

Sources

  1. GitHub repository dynotx/dynopsi (repository)
  2. GitHub repository dynotx/dynopsi (repository)
  3. Hugging Face page api/models (repository)
  4. Official page dynopsi.dynotx.com (company blog)
  5. Hugging Face page dynotx/dynopsi (repository)

Corrections

2 corrections
FieldWasNowBasisFound
wetlab_validationComparison at equal design countsInitial sampling budget matched (~12k); the wet-lab arm is Psi-0.5source2026-11-16
other_evaluationsFive-target wet-lab pass ratePsi-1 computational filtering, best on only 2 of 5 targetssource2026-11-16

Part of the AI for Bio benchmarks survey · all 112 models · open in the explorer. Record as of 2026-11-16.