Abstract Accurately modeling and designing protein complex structures is a central problem in computational structural biology, with broad implications for understanding cellular function and developing therapeutics. This thesis investigates two fundamental aspects of this problem using deep learning: domain-specific architectures that capture the hierarchical nature of protein structures, and search algorithms that efficiently navigate the vast sequence spaces of protein complexes to identify interacting homologs for improving complex structure prediction and to design protein sequences.
Explore similar work Sep 3, 2026 · Jiarui Lu, Yuyang Wang, Yizhe Zhang +4 Protein Design Sequence Modeling
Aug 11, 2026 · Jiabao Wei, Zilong Geng, Yuze Wang +5 Protein Molecular Dynamics
May 15, 2026 · Chen Wei, Fanding Xu, Minghao Sun +5 Protein Design Protein
Sep 3, 2026 · cs.LG J/K move · Enter open · S save
Jiarui Lu, Yuyang Wang, Yizhe Zhang, Jiatao Gu +3
Mila, Université de Montréal, Apple · Apple
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.