Unsupervised cross-domain translation via deep learning and adversarial attention neural networks and application to music-inspired protein designs.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 36960446.
- Also identified by DOI 10.1016/j.patter.2023.100692 and PMC identifier 10028431.
- Licence recorded as CC BY-NC-ND.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
Taking inspiration from nature about how to design materials has been a fruitful approach, used by humans for millennia. In this paper we report a method that allows us to discover how patterns in disparate domains can be reversibly related using a computationally rigorous approach, the AttentionCrossTranslation model. The algorithm discovers cycle- and self-consistent relationships and offers a bidirectional translation of information across disparate knowledge domains. The approach is validated with a set of known translation problems, and then used to discover a mapping between musical data-based on the corpus of note sequences in J.S. Bach's Goldberg Variations created in 1741-and protein sequence data-information sampled more recently. Using protein folding algorithms, 3D structures of the predicted protein sequences are generated, and their stability is validated using explicit solvent molecular dynamics. Musical scores generated from protein sequences are sonified and rendered into audible sound.