EnzymeCoT - Stage III joint checkpoint

Joint adapters for reaction-conditioned, three-round de novo enzyme design: Qwen3-4B as the understanding model and RFdiffusion3 as the generator, trained together.

What this file is

s3_best.pt - a 553 MB PyTorch state_dict (755 tensors, 138.9 M parameters). Adapters only: no optimizer state, no base model weights.

Training 4000 steps, run to completion
Validation L_gen 0.386 -> 0.3497 (the lowest value over the whole run)
Trained parts Qwen LoRA + structure/ligand projections + injection (2.29 M) + RFdiffusion3 LoRA (2.89 M, MLP)
Date 2026-09-11

Important caveat about the reported numbers

Evaluation figures reported for this line of work - catalytic-site RMSD 0.94 A, LigandMPNN-8 self-consistency 5/8 and 8/8 designable, pLDDT 77.9 / 94.5 - were produced with the step-2500 checkpoint (val 0.3526).

This file is step-4000 (val 0.3497). They are not the same checkpoint, and the step-4000 weights have not been re-evaluated end to end. Please do not attribute those numbers to this file without re-running the evaluation yourself.

Requirements

This is an adapter checkpoint, not a standalone model. You need:

  • Qwen3-4B base weights
  • RFdiffusion3

Task definition

Given a reaction (SMILES), the ligand's chemistry and 3D coordinates, and a target protein length, the model designs an enzyme in three rounds:

  1. R1 - an unindexed catalytic-residue set (identity + catalytic/support role) together with local geometry relative to the ligand. Object IDs carry no sequence position.
  2. R2 - a full backbone, then an assignment of the round-1 objects onto positions in that generated backbone.
  3. R3 - the remaining sequence and side chains, inheriting the committed core identities.

Data

Trained on the EnzymeCoT corpus (19,888 train / 1,123 validation records, lengths 100-997) with a reaction- and homology-disjoint split. Ligand binding conformations are taken from reference complexes, which are Boltz predictions rather than experimental structures.

Limitations

  • No experimental validation. No catalytic activity has been measured.
  • The metrics above are computational self-consistency and RMSD-to-reference; neither establishes catalysis.
  • Autonomous three-round design quality remains weak; treat this checkpoint as a research artifact, not a working enzyme designer.
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support