Very cool work! Do you think this approach could also work for protein folding models like Alphafold, RFDiffusion, Protenix, DISCO, etc? So far the only thing I’ve found in the literature is FoldSAE (https://arxiv.org/pdf/2511.22519), and they find only very basic features like the neuron for alpha helices vs beta sheets
Thanks! One of the main reasons I work specifically with single-cell FMs is because I believe they learn much richer biology, because you model systems-level with them. There is only so much you can learn from structure models, and, unlike with single cell models, I think most of the value of the structure models is in their outputs.
That said, one can definitely apply similar methods to them. I would be happy to do that myself, but currently it’s not a priority for me for the reasons described.
Very cool work! Do you think this approach could also work for protein folding models like Alphafold, RFDiffusion, Protenix, DISCO, etc? So far the only thing I’ve found in the literature is FoldSAE (https://arxiv.org/pdf/2511.22519), and they find only very basic features like the neuron for alpha helices vs beta sheets
Thanks! One of the main reasons I work specifically with single-cell FMs is because I believe they learn much richer biology, because you model systems-level with them. There is only so much you can learn from structure models, and, unlike with single cell models, I think most of the value of the structure models is in their outputs.
That said, one can definitely apply similar methods to them. I would be happy to do that myself, but currently it’s not a priority for me for the reasons described.