Using deep learning to annotate the protein universe

By Maxwell L. Bileschi, David Belanger, D. Bryant, T. Sanderson, Brandon Carter, David Sculley, Alex Bateman, Mark A. DePristo, Lucy J. Colwell. 2019

304 citations recorded by the source corpus.

Subfields: Molecular Biology, Spectroscopy

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

In Spectroscopy

Citations in the corpus

Evolutionary context-integrated deep sequence modeling for protein engineering (2020, methodology): “More recently, a trend is emerging that pre-trains a language model (LM) on large protein sequence datasets to learn protein sequence representation [26–30] .”
SaProt: Protein Language Modeling with Structure-aware Vocabulary (2024, background): “…applications, including clinical disease variant prediction (Frazer et al., 2021), fitness landscape prediction (Dallago et al., 2021; He et al., 2024), protein-protein interaction (Nooren & Thornton, 2003), as well as diverse protein function predictions (Bileschi et al., 2022; Yu et al., 2023).”
Artificial intelligence and illusions of understanding in scientific research (2024, unknown): “In biology, predictive AI tools are already being used for the automated annotation of protein function 50,51 and cell types 52 .”
InterPro in 2022 (2022, unknown): “A Google Research team is working on the development of ProtENN, a deep-learning method predicting functional annotations for unaligned amino acid sequences using Pfam families as a training set (31).”
Exploring evolution-based & -free protein language models as protein function predictors (2022, methodology): “In this paper, we focus on functional annotation prediction (classiﬁcation task) [45, 5] and ﬁtness prediction (including both regression [8, 25] and zero-shot prediction [16, 24] tasks), as shown in Figure 2.”
MGnify: the microbiome sequence data analysis resource in 2023 (2022, background): “, (24)), which uses convolutional neural networks to annotate each protein residue in the database with a Pfam family (or clan) label that is then converted into domain calls.”
The language of proteins: NLP, machine learning & protein sequences (2021, methodology): “There have been works using contextualized embedding models (e.g. ELMO) on proteins for supervised-learning tasks (such as GO annotation, subcellular localization or structure prediction), as well as clustering sequences based on the learned representations [15,29,54,34].”
Efficient evolution of human antibodies from general protein language models (2023, unknown): “Our techniques can also be used in conjunction with supervised approaches 9,28,33,34,51–54 , and supervising a model over multiple experimental rounds might ultimately lead to higher fitness.”
InterPro: the protein sequence classification resource in 2025 (2024, unknown): “ProtENN2, trained on Pfam data, uses convolutional neural networks to annotate protein sequences with Pfam family labels ( 55 ).”
Expanding functional protein sequence spaces using generative adversarial networks (2021, methodology): “Although HMMs are powerful and a de facto golden standard for protein functional annotation 39,40 , when used for sequence generation, the first-order HMM did not recapitulate the sequence conservation present in the training data, as the positional entropy error (m.s.e.) of HMM-generated sequences…”