Year: 2024
Type: article
Abstract: Protein language models have been tested and proved to be reliable when used on curated datasets but have not yet been applied to full proteomes. Accordingly, we tested how two different machine learning-based methods performed when decoding functional information from the proteomes of selected model organisms. We found that protein language models are more precise and informative than deep learning methods for all the species tested and across the three gene ontologies studied, and that they better recover functional information from transcriptomic experiments. The results obtained indicate that these language models are likely to be suitable for large-scale annotation and downstream analyses, and we recommend a guide for their use.
Source: NAR Genomics and Bioinformatics
Language: English
Subfield: Molecular Biology
Domain: Life Sciences
Open Access status: gold
Estimated APC paid: $2,904
Awards: G1175115578, G121809054, G1553193024, G1817161782, G1855990336, G2064873908, G2262748287, G2309174360, G2355262757, G2660406951, G2682119551, G279363373, G288263039, G3005324705, G300979063, G34346518, G3480869486, G3610420607, G3690828678, G425668148, G430777504, G4421639114, Reconstructing water to land transitions in arthropod evolution combining atoms, genes and fossils, G4558491918, G5080475149, G5421974903, G5852091828, Land animal evolution: genomic landmarks on the path to terrestrial life, G6669376639, G69051668, G7084143925, G7425137858, G7936468371, G8445991159, G8684520763, G897484643, G99296377
OpenAlex ID: W4400242398