> ## Documentation Index
> Fetch the complete documentation index at: https://proto.evodesign.org/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Cycling Optimizer
> Alternates a conditioning step with a generation step each cycle to drive feedback loops such as Protein Hunter (structure prediction -> inverse folding), keeping proposals that pass the filter constraints.
This optimizer is open source. Any third-party models, product names, or trademarks referenced are the property of their respective owners, and Proto is not affiliated with them.
Cycling optimizer for iterative sequence refinement.
A generalized optimizer that cycles between a user-defined conditioning function
and a generator:
1. Call conditioning function with current sequences (from result\_sequences)
2. Pass conditioning output to generator's sample() method (into proposal\_sequences)
3. Accept passing proposals into result\_sequences (failed stay unchanged)
4. Repeat for num\_steps
This enables flexible optimization patterns such as:
* Protein Hunter: Structure prediction -> inverse folding cycles
* Evo2 with feedback: Constraint-guided prompt modification -> generation cycles
- Constraints are optional; if provided, must be filter constraints
(have `threshold` set) - only passing proposals update result\_sequences
## How It Works
Cycling alternates a conditioning function with a generator, looping between two views of the design (for `protein-hunter`, sequence and structure) and keeping only proposals that pass every filter.
Cycling alternates a conditioning function with a generator. Each cycle conditions on the current sequences, generates proposals from that conditioning, and keeps only proposals that pass every filter:
```
for cycle in 1..num_steps:
data = conditioning_fn(result_sequences)
proposals = generator.sample(data)
result_i ← proposal_i ⇔ proposal_i passes all filters (else keep prior)
```
Cycling takes **filter-only** constraints (each needs a `threshold`; a scoring constraint raises an error). The built-in `protein-hunter` pipeline sets `conditioning_fn` to structure prediction (Boltz-2 / Chai-1 / AlphaFold3) feeding inverse folding: predict a structure, then redesign the sequence for it.
## API Reference
Configuration for CyclingOptimizer.
This optimizer cycles between a conditioning function and a generator.
On each cycle, the conditioning function receives the current proposal sequences,
produces conditioning data, which is then passed to the generator's sample() method.
The conditioning function can be provided either:
1. Directly via the `conditioning_fn` parameter (programmatic use)
2. Via the `pipeline` field using a predefined pipeline (API/JSON use)
* Pipeline-specific constraints:
* `protein-hunter` requires an inverse\_folding generator
* Constraints are optional but if provided must be filter constraints
(must have `threshold` set)
Number of conditioning-then-generation cycles to run.
Candidate design trajectories for this optimizer. Overrides program-level count.
Predefined conditioning pipeline. 'protein-hunter' uses structure prediction -> inverse folding.
Configuration for protein-hunter pipeline. Only used when pipeline='protein-hunter'.
Random seed for reproducible optimization, generator, and constraint tool streams.
Save history and log progress every N steps. Step 0 and final step always saved.
Save granular per-proposal results (accept/reject) in history snapshots.
Emit per-step debug information about proposals, scores, and acceptance through the logger.
evo-design/proto-language/proto\_language/optimizer/cycling\_optimizer.py
