Triangle Multiplication Is All You Need For Biomolecular Structure Representations
This work addresses the high runtime and memory costs for researchers and practitioners in computational biology, enabling more efficient virtual screening and protein design, though it is incremental as it builds on existing AlphaFold frameworks.
The paper tackles the computational bottleneck of AlphaFold3-style models in large-scale biomolecular applications by introducing Pairmixer, which eliminates triangle attention and achieves up to 4x faster inference and 34% lower training cost while matching state-of-the-art performance on folding and docking benchmarks.
AlphaFold has transformed protein structure prediction, but emerging applications such as virtual ligand screening, proteome-wide folding, and de novo binder design demand predictions at a massive scale, where runtime and memory costs become prohibitive. A major bottleneck lies in the Pairformer backbone of AlphaFold3-style models, which relies on computationally expensive triangular primitives-especially triangle attention-for pairwise reasoning. We introduce Pairmixer, a streamlined alternative that eliminates triangle attention while preserving higher-order geometric reasoning capabilities that are critical for structure prediction. Pairmixer substantially improves computational efficiency, matching state-of-the-art structure predictors across folding and docking benchmarks, delivering up to 4x faster inference on long sequences while reducing training cost by 34%. Its efficiency alleviates the computational burden of downstream applications such as modeling large protein complexes, high-throughput ligand and binder screening, and hallucination-based design. Within BoltzDesign, for example, Pairmixer delivers over 2x faster sampling and scales to sequences ~30% longer than the memory limits of Pairformer.