%0 Journal Article %T End-to-End Differentiable Learning of Protein Structure %J - %D 2019 %R https://doi.org/10.1016/j.cels.2019.03.006 %X £¿ Neural network predicts protein structure from sequence without using co-evolution £¿ Model replaces structure prediction pipelines with one mathematical function £¿ Achieves state-of-the-art performance on novel protein folds £¿ Learns a low-dimensional representation of protein sequence spac %U https://www.cell.com/cell-systems/fulltext/S2405-4712(19)30076-6