Modeling aspects of the language of life through transfer-learning protein sequences
BMC Bioinformatics2019Vol. 20(1), pp. 723–723
Citations Over TimeTop 1% of 2019 papers
Michael Heinzinger, Ahmed Elnaggar, Yu Wang, Christian Dallago, Dmitrii Nechaev, Florian Matthes, Burkhard Rost
Abstract
Transfer-learning succeeded to extract information from unlabeled sequence databases relevant for various protein prediction tasks. SeqVec modeled the language of life, namely the principles underlying protein sequences better than any features suggested by textbooks and prediction methods. The exception is evolutionary information, however, that information is not available on the level of a single sequence.
Related Papers
- → A high-stringency blueprint of the human proteome(2020)215 cited
- → The human eye proteome project(2013)9 cited
- → Indian proteomics efforts and human proteome project(2015)5 cited
- → Human Proteome Project and Current Bioinformatics Status in Disease Diagnosis and Treatment(2018)1 cited
- → HICL table can manipulate all proteins in human complete proteome(2016)