From the source
Lead story
Ask your AI
Top stories
Models & availability
Latest
SimpleDesign: A Joint Model for Protein Sequence and Structure Codesign
Single-stage model jointly designs protein sequences and structures without autoencoders
Apple researchers present SimpleDesign, a multi-modal protein design model that jointly generates protein sequences and structures using a single-stage end-to-end training objective, trained on over 2 million sequence-structure pairs.
The model achieves competitive performance on co-design and unconditional generation benchmarks.
From the source
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. We train SimpleDesign on over 2M sequence-structure pairs achieving competitive performance across co-design and unconditional sequence/structure generation benchmarks.
machinelearning.apple.com
