Metraipolis › archive › dc_766f9ff7418e

SimpleDesign: A Joint Model for Protein Sequence and Structure Codesign — arXiv:2609.03377

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03377
License (as archived)
CC0-1.0
Archived
2026-10-17T02:07:52.900Z
SHA-256 of the archived text
64c8c1d19ed310a36251667d4366bf1f0fc334b6d9e20e0f65f07a26a6d77782
Stable URL of this page
https://metraipolis.com/documento/dc_766f9ff7418e

How to cite

SimpleDesign: A Joint Model for Protein Sequence and Structure Codesign — arXiv:2609.03377 — arXiv (en), https://arxiv.org/abs/2609.03377 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_766f9ff7418e (Metraipolis archive dc_766f9ff7418e, sha256 64c8c1d19ed310a36251667d4366bf1f0fc334b6d9e20e0f65f07a26a6d77782)
BibTeX
@misc{dc766f9ff7418e,
  title = {SimpleDesign: A Joint Model for Protein Sequence and Structure Codesign — arXiv:2609.03377},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03377},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_766f9ff7418e; sha256 64c8c1d19ed310a36251667d4366bf1f0fc334b6d9e20e0f65f07a26a6d77782},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03377. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Proteins are fundamental to biological processes, with their function determined by the complex interplay between the amino acid sequence and the three-dimensional structure. Developing generative models capable of understanding this intrinsically multi-modal relationship is crucial for fields like drug discovery and protein engineering. Existing models often rely on a multi-stage training process where autoencoders that tokenize data into latent representations are trained in a first stage. Secondly, a generative model is trained on the latent representation of the autoencoder(s), i.e., generative modeling in a latent space. We hypothesize that this multi-stage training is not necessary to obtain performant co-design models and thus present SimpleDesign, an effective multi-modal protein design model trained directly in the data space. SimpleDesign leverages a single-stage end-to-end objective that combines discrete cross-entropy for sequences and a regression objective for structures. In order to effectively model the difference in sequence and structure modalities, we develop a Mixture-of-Transformer architecture that allows modality-specific processing while keeping global self-attention over both modalities. We train SimpleDesign on over 2M sequence-structure pairs achieving strong performance across co-design and unconditional sequence/structure generation benchmarks.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Biomolecules (q-bio.BM).
Pagina del lavoro: https://arxiv.org/abs/2609.03377 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T01:47:25.543Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).