Protein sequence-to-structure learning: Is this the end(-to-end revolution)?
Not on the map. Why?
Abstract (arXiv)
The potential of deep learning has been recognized in the protein structure prediction community for some time, and became indisputable after CASP13. In CASP14, deep learning has boosted the field to unanticipated levels reaching near-experimental accuracy. This success comes from advances transferred from other machine learning areas, as well as methods specifically designed to deal with protein sequences and structures, and their abstractions. Novel emerging approaches include (i) geometric learning, i.e. learning on representations such as graphs, 3D Voronoi tessellations, and point clouds; (ii) pre-trained protein language models leveraging attention; (iii) equivariant architectures preserving the symmetry of 3D space; (iv) use of large meta-genome databases; (v) combinations of protein representations; (vi) and finally truly end-to-end architectures, i.e. differentiable models starting from a sequence and returning a 3D structure. Here, we provide an overview and our opinion of the novel deep learning approaches developed in the last two years and widely used in CASP14.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 30 of its 192 references that are in the map. First posted on arXiv 16 May 2021.
Builds on
30 of 192 references.
References · 30
- 2017Attention Is All You Needcited by 60,361
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017Graph Attention Networkscited by 8,923
- 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
- 2017Neural Message Passing for Quantum Chemistrycited by 3,487
- 2018Deep contextualized word representationscited by 2,290
- 2020Rethinking Attention with Performerscited by 1,601
- 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,167
- 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,133
- 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 746
- 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 607
18 more
- 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 571
- 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
- 20183D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Datacited by 354
- 2020Learning from Protein Structure with Geometric Vector Perceptronscited by 313
- 2016Steerable CNNscited by 305
- 2019Cormorant: Covariant Molecular Neural Networkscited by 263
- 2019Evaluating Protein Transfer Learning with TAPEcited by 231
- 2020ProGen: Language Modeling for Protein Generationcited by 128
- 2016A Convolutional Encoder Model for Neural Machine Translationcited by 54
- 2018N-body Networks: a Covariant Hierarchical Neural Network Architecture for Learning Atomic Potentialscited by 42
- 2019ProteinNet: a standardized data set for machine learning of protein structurecited by 39
- 2016Accurate De Novo Prediction of Protein Contact Map by Ultra-Deep Learning Modelcited by 31
- 2020Protein model quality assessment using rotation-equivariant, hierarchical neural networkscited by 8
- 2017Dilated Convolutions for Modeling Long-Distance Genomic Dependenciescited by 7
- 2020Spherical convolutions on molecular graphs for protein model quality assessmentcited by 5
- 2019Accurate Protein Structure Prediction by Embeddings and Deep Learning Representationscited by 4
- 2013Protein Contact Prediction by Integrating Joint Evolutionary Coupling Analysis and Supervised Learningcited by 2
- 2020Hierarchical, rotation-equivariant neural networks to select structural models of protein complexescited by 1
Built on by
Citing papers per year: 2021: 2; 2022: 0; 2023: 0; 2024: 0; 2025: 0; 2026: 1.
3 papers.