EH18 Designerinternal · no API · weights not distributed
- parameters
- 85.2 Meh18-85M-A_oud.pt
- gate
- 67.7%unselected fresh draws
- floor
- 62.6%paste-together, real leader and real core
- ceiling
- 82.7%real held out precursors
- NeuRiPP
- 74.2%floor 71.4%
- bar set in advance
- 65.2%to claim it beats paste-together
- tested in a lab
- 0of 978 candidates
| Written precursor against the enzyme requirements | Full gate | NeuRiPP only |
| Random, matched for composition | 20.2% | 22.4% |
| Paste-together, leader i with core j — the floor | 62.6% | 71.4% |
| EH18 Designer, unselected fresh draws | 67.7% | 74.2% |
| Real held-out precursors — the ceiling | 82.7% | 94.7% |
The floor is paste-together, not random: it has a real leader and
a real core, and only the pairing is broken. That is the honest thing to beat.
On NeuRiPP the model is above it and that figure does not depend on length. On
the full gate it is undecided: the bar set in advance is
65.2% and the two length regimes differ, design median 72 residues
against 63. An earlier version of this page compared against the random floor
and so showed the model four times above it.
| Novelty, alignment against all 3,008 training precursors, on all 600 designs | Identity |
| median | 43.0% |
| highest | 55.4% |
| above the 80% line | 0 |
| Size | Gate, five fresh draws |
| 85 M parameters | 55.2% |
| 393 M, best step | 54.5% |
| 393 M, last step | 50.0% |
These three figures come from an older instrument: five fresh draws each, not the 990 held-out pairs used above. They are comparable to each other and not to the 67.7% at the top of this section. The reading is that 393 M is not better than 85 M, 0.7 points apart, which is a draw.
| Cyanobactin cores | Meet the requirements |
| EH18 Designer | 0.25% |
| Random from the same twelve residues — floor | 0.45% |
| Candidates | Count |
| written by EH18 Designer | 750 |
| enumerated or found without a model | 5,955 |
| total | 6,705 |
| tested in a lab | 0 |
All measurements for EH18 Designer →