English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recently, there has been great interest in learning how to best representproteins, specifically with fixed-length embeddings. Deep learning has become apopular tool for protein representation learning as a model's hidden layersproduce potentially useful vector embeddings. TAPE introduced a number ofbenchmark tasks and showed that semi-supervised learning, via pretraininglanguage models on a large protein corpus, improved performance on downstreamtasks. Two of the tasks (fluorescence prediction and stability prediction)involve learning fitness landscapes. In this paper, we show that CNN modelstrained solely using supervised learning both compete with and sometimesoutperform the best models from TAPE that leverage expensive pretraining onlarge protein datasets. These CNN models are sufficiently simple and small thatthey can be trained using a Google Colab notebook. We also find for thefluorescence task that linear regression outperforms our models and the TAPEmodels. The benchmarking tasks proposed by TAPE are excellent measures of amodel's ability to predict protein function and should be used going forward.However, we believe it is important to add baselines from simple models to putthe performance of the semi-supervised models that have been reported so farinto perspective.

Is Transfer Learning Necessary for Protein Landscape Prediction?