Huge thanks to Colin, Minkyu, and Aymen for all the help, and @alisiafadini.bsky.social, @moalquraishi.bsky.social for the guidance!!

ConforNets: Latents-Based Conformational Control in OpenFold3 Models from the AlphaFold (AF) family reliably predict one dominant conformation for most well-ordered proteins but struggle to capture biologically relevant alternate states. Several efforts have foc...

arXiv: arxiv.org/abs/2604.18559
Code: github.com/aqlaboratory...

All training, inference, and benchmarking data/code is open-sourced!
🧵 8/8

These results suggest that AF3 models may learn (uncalibrated) implicit conformational landscapes, and that the right interface can unlock new capabilities without retraining. We're excited to explore interpretability, transferability, and applications of ConforNets.

🧵 7/8

We train “conformational prompts” on 3 therapeutically important protein families and show strong induction of desired states:

- GPCR active: 24% → 79%
- Kinase DFG-out: 6% → 23%
- Transporter outward-facing: 16% → 57%

Built-in templates cause no observable shift.

🧵6/8

Yet, the above benchmarks only ask whether an alternate state is observed among hundreds of samples. Can we prompt the model to consistently predict states that are rarely sampled? A "conformation prompt”?

🧵 5/8

On multi-state benchmarks such as membrane transporters, ConforNets double recovery of alternate states from 24.3% → 51.1% over the OF3p baseline, at the cost of 3 GPU-minutes for a 400-residue protein.

🧵4/8

2. Learn a desired state from one protein that can then be induced in many other proteins

🧵3/8

Our key idea is to operate globally across Pairformer channels, instead of residues, to broadly sculpt conformational preferences. This makes it possible to:

1. Maximize unsupervised objectives like conformational diversity by coordinately training multiple ConforNets

🧵2/8

We introduce ConforNets, a mechanism for conformational control in AlphaFold3 models

- SoTA at producing diverse conformations on every multistate benchmark (N=104)
- Novel capability: transfer state from one protein to another

Outperforms BioEmu, ConforMix and AFsample3

🧵1/8

These results suggest that AF3 models may learn (uncalibrated) implicit conformational landscapes, and that the right interface can unlock new capabilities without retraining. We're excited to explore interpretability, transferability, and applications of ConforNets.

🧵 7/8