PT  - JOURNAL ARTICLE
AU  - Hannes Stärk
AU  - Christian Dallago
AU  - Michael Heinzinger
AU  - Burkhard Rost
TI  - Light Attention Predicts Protein Location from the Language of Life
AID  - 10.1101/2021.04.25.441334
DP  - 2021 Jan 01
TA  - bioRxiv
PG  - 2021.04.25.441334
4099  - http://biorxiv.org/content/early/2021/04/26/2021.04.25.441334.short
4100  - http://biorxiv.org/content/early/2021/04/26/2021.04.25.441334.full
AB  - Although knowing where a protein functions in a cell is important to characterize biological processes, this information remains unavailable for most known proteins. Machine learning narrows the gap through predictions from expertly chosen input features leveraging evolutionary information that is resource expensive to generate. We showcase using embeddings from protein language models for competitive localization predictions not relying on evolutionary information. Our lightweight deep neural network architecture uses a softmax weighted aggregation mechanism with linear complexity in sequence length referred to as light attention (LA). The method significantly outperformed the state-of-the-art for ten localization classes by about eight percentage points (Q10). The novel models are available as a web-service and as a stand-alone application at embed.protein.properties.Competing Interest StatementThe authors have declared no competing interest.