Cited by 1,131Protein Structure and DynamicsMachine Learning in BioinformaticsRNA and protein synthesis mechanisms

The DOI matches its Crossref record; 80 of the 80 references it cites were found in a registry or an index.

Unified rational protein engineering with sequence-based deep representation learning

Open access

Alley, Ethan C., Khimulya, Grigory, Biswas, Surojit, AlQuraishi, Mohammed, Church, George M.·2019·Nature Methods

DOI 10.1038/s41592-019-0598-1PMC PMC7067682

Published version of a preprint

Open this paper in CoChat — free account Open PDF

Abstract

Rational protein engineering requires a holistic understanding of protein function. Here, we apply deep learning to unlabeled amino-acid sequences to distill the fundamental features of a protein into a statistical representation that is semantically rich and structurally, evolutionarily and biophysically grounded. We show that the simplest models built on top of this unified representation (UniRep) are broadly applicable and generalize to unseen regions of sequence space. Our data-driven approach predicts the stability of natural and de novo designed proteins, and the quantitative function of molecularly diverse mutants, competitively with the state-of-the-art methods. UniRep further enables two orders of magnitude efficiency improvement in a protein engineering task. UniRep is a versatile summary of fundamental protein features that can be applied across protein engineering informatics.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

Integrity signals

Registry

Crossref · 10.1038/s41592-019-0598-1

Cites

80 of 80 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016 · cited 1×
“We used basic agglomerative clustering (implemented in Python with sklearn 73 ) with the average linkage metric and Euclidean distance for all vector representations, and a precomputed Levenshtein distance matrix using the Python Levenshtein package for the sequence-only control.”
Method
The Protein Data Bank
Berman, H. M. (2000) · Nucleic Acids Research · doi:10.1093/nar/28.1.235 · Cited by 40,196 · cited 4×
“We computed the full sequence of hidden states at every position of 3,720 single-domain proteins from the SCOP database 60 (for which we had secondary structure annotation for each of the positions obtained from the PDB 80 ).”
MethodInfluential
Untitled work
(2008) · Journal of Machine Learning Research · Cited by 33,051
Dictionary of protein secondary structure: Pattern recognition of hydrogen‐bonded and geometrical features
Kabsch, W., & Sander, C. (1983) · Biopolymers · doi:10.1002/bip.360221211 · Cited by 15,320
On the Properties of Neural Machine Translation: Encoder–Decoder Approaches
Cho, K., van Merriënboer, B., Bahdanau, D., & Bengio, Y. (2014) · SSST@EMNLP · doi:10.3115/v1/w14-4012 · Cited by 7,251
Learning to Forget: Continual Prediction with LSTM
Gers, F. A., Schmidhuber, J., & Cummins, F. (2000) · Neural Computation · doi:10.1162/089976600300015015 · Cited by 6,122
NWChem: A comprehensive and scalable open-source solution for large scale molecular simulations
Valiev, M., Bylaska, E. J., Govind, N., Kowalski, K., Straatsma, T. P., van Dam, H. J. J., Wang, D., Nieplocha, J., Aprà, E., Windus, T. L., et al. (2010) · Computer Physics Communications · doi:10.1016/j.cpc.2010.04.018 · Cited by 5,849
In-Datacenter Performance Analysis of a Tensor Processing Unit
Jouppi, N. P., Young, C., Patil, N., Patterson, D., Agrawal, G., Bajwa, R., Bates, S., Bhatia, S., Boden, N., Borchers, A., et al. (2017) · Proceedings of the 44th Annual International Symposium on Computer Architecture · doi:10.1145/3079856.3080246 · Cited by 4,537
An Overview of Multi-Task Learning in Deep Neural NetworksPreprint
Ruder, S. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1706.05098 · Cited by 3,827
Molecular dynamics simulations of biomolecules
Karplus, M., & McCammon, J. (2002) · Nature Structural Biology · doi:10.1038/nsb0902-646 · Cited by 3,401

Show all 80 references

Research works printed but not linked: 8

Brookes, D. H., Park, H. & Listgarten, J. Conditioning by adaptive sampling for robust design. Proc. Machine Learn. Res. 97, 773–782 (2019).
Hernández-Lobato, J. M., Requeima, J., Pyzer-Knapp, E. O. & Aspuru-Guzik, A. Parallel and distributed thompson sampling for large-scale accelerated exploration of chemical space. Preprint at arXiv https://arxiv.org/abs/1706.01825 (2017). · arXiv
Snoek, J., Larochelle, H. & Adams, R. P. in Advances in Neural Information Processing Systems Vol. 25 (eds. Pereira, F. et al.) 2951–2959 (Curran Associates, Inc., 2012).
Griffiths, R.-R. & Hernández-Lobato, J. M. Constrained Bayesian optimization for automaticchemical design. Preprint at arXiv https://arxiv.org/abs/1709.05501 (2017). · arXiv
Yang, K. K., Chen, Y., Lee, A. & Yue, Y. Batched stochastic Bayesian optimization via combinatorial constraints design. Preprint at arXiv https://arxiv.org/abs/1904.08102 (2019). · arXiv
González, J., Longworth, J., James, D. C. & Lawrence, N. D. Bayesian optimization for synthetic gene design. Preprint at arXiv https://arxiv.org/abs/1505.01627 (2015). · arXiv
Jouppi, N. P. et al. In-datacenter performance analysis of a tensorprocessing unit. In Proc. 44th Annual International Symposium of Computer Architecture Vol. 45, 1–12 (ACM, 2017).
Salimans, T. & Kingma, D. P. Weight normalization: a simple reparameterization to accelerate training of deep neural networks. Preprint at arXiv https://arxiv.org/abs/1602.07868 (2016). · arXiv

Sorted by citations

Items 901–1,000 of 1,003

A computational walk to the hidden peaks of protein performance
Billerbeck, S. (2021) · Synthetic Biology · doi:10.1093/synbio/ysab011 · Cited by 1
“Instead of learning the fitness landscape of an individual protein from experimental data, they first built a deep learning algorithm that extracts the fundamental features of all functional proteins from the >20 million available unlabeled amino-acid sequences in the UniREF database (7).”
Background
Application of Protein Language Models to low-N Engineering of metalloproteinase inhibitors
Buxton, E. K., Patel, R., Toumaian, M. R., & Raeeszadeh‐Sarmazdeh, M. (2021) · International Conference on Computational Science and Computational Intelligence (CSCI) · doi:10.1109/csci54926.2021.00048 · Cited by 1
“[1] pre-trained an autoregressive bidirectional LSTM language model,called Unirep, on 24M protein sequences from Uniref50 .”
BackgroundMethod
ResCNNT-fold: Combining residual convolutional neural network and Transformer for protein fold recognition from language model embeddings
Qin, X., Liu, M., & Liu, G. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107571 · Cited by 2
ProSE-Pero: Peroxisomal Protein Localization Identification Model Based on Self-Supervised Multi-Task Language Pre-Training Model
Sui, J., Chen, J., Chen, Y., Iwamori, N., & Sun, J. (2023) · Frontiers in Bioscience-Landmark · doi:10.31083/j.fbl2812322 · Cited by 1
“In this study, three feature extraction methods, namely SeqVec [18] based on the ELMO model, TAPE [19] based on the BERT model, and ProSE [20] based on a pre-trained multi-task language model, were employed to extract features from peroxisomal protein sequences.”
Method
DeepPPThermo: A Deep Learning Framework for Predicting Protein Thermostability Combining Protein-Level and Amino Acid-Level Features
Xiang, X., Gao, J., & Ding, Y. (2023) · Journal of Computational Biology · doi:10.1089/cmb.2023.0097 · Cited by 1
“Alley et al. (2019) proposed a protein sequence coding method based on deep learning.”
NCSP-PLM: An ensemble learning framework for predicting non-classical secreted proteins based on protein language models and deep learning
Liu, T., Song, C., & Wang, C. (2023) · Mathematical Biosciences & Engineering · doi:10.3934/mbe.2024063 · Cited by 1
“(4) The UniRep model contains a layer of multiplicative LSTM with 1900 hidden units, which was trained on the UniRef50 database [20].”
Method
Deep learning-powered enzyme efficiency boosting with evolutionary information
Woodard, J. C., & Huang, X. (2024) · 中国科学通报：英文版 · doi:10.1016/j.scib.2024.03.034 · Cited by 1
Antibody Complementarity-Determining Region Sequence Design Using AlphaFold2 and Binding Affinity Prediction Model
Ueki, T., & Ohue, M. (2023) · Congress in Computer Science, Computer Engineering, and Applied Computing (CSCE) · doi:10.1109/csce60160.2023.00350 · Cited by 1
“Therefore, they are unsuitable for designing mutations in sequences with high variabilities, such as CDR or sequences without experimental data [5]–[7].”
Background
Concluding remarks: Faraday Discussion on data-driven discovery in the chemical sciences
Cooper, A. I. (2024) · Faraday Discussions · doi:10.1039/d4fd00174e · Cited by 1
Fitness translocation: improving variant effect prediction with biologically-grounded data augmentation
Mialland, A., Fukunaga, S., Katsuki, R., Dong, Y., Yamaguchi, H., & Saitō, Y. (2026) · Bioinformatics · doi:10.1093/bioinformatics/btag415 · Cited by 1
“S8 , S12, available as supplementary data at Bioinformatics online) and had the second biggest improvement.”
GPT2-ICC: A data-driven approach for accurate ion channel identification using pre-trained large language models
Zhou, Z., Yu, Y., Yang, C., Cao, L., Zhang, S., Li, J., Zhang, Y., Han, H., Shi, G., Zhang, Q., et al. (2025) · Journal of Pharmaceutical Analysis · doi:10.1016/j.jpha.2025.101302 · Cited by 1
Boost Protein Language Model with Injected Structure Information Through Parameter Efficient Fine-tuning
Zhang, Z., Zhou, Y., Zheng, J. X., Feng, C.-M., Cui, S. R., Wang, S., & Li, Z. (2025) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2025.110607 · Cited by 2
Speaking to nature: a deep learning representational model of proteins ushers in protein linguistics
Bojar, D. (2019) · Synthetic Biology · doi:10.1093/synbio/ysz013 · Cited by 1
Adaptive Residue-wise Profile Fusion for Low Homologous Protein Secondary Structure Prediction Using External Knowledge
Wang, Q., Wei, J., Wang, B., Li, Z., Wang, S., & Cui, S. R. (2021) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/490 · Cited by 1
A Review of Protein Structure Prediction using Deep Learning
Susanty, M., Rajab, T. L. E., & Hertadi, R. (2021) · BIO Web of Conferences · doi:10.1051/bioconf/20214104003 · Cited by 1
SeBPPI: A Sequence-Based Protein–Protein Binding Predictor
Wang, B., Mao, J. W., Wei, M., Qi, Y., & Zhang, J. Z. H. (2022) · Journal of Computational Biophysics and Chemistry · doi:10.1142/s2737416522500314 · Cited by 1
Struktur‐ und Daten‐basiertes Protein Engineering von Transaminasen zur Verbesserung von Aktivität und Stereoselektivität
Ao, Y., Pei, S., Xiang, C., Menke, M. J., Shen, L. F., Sun, C., Dörr, M., Born, S., Höhne, M., & Bornscheuer, U. T. (2023) · Angewandte Chemie · doi:10.1002/ange.202301660 · Cited by 1
Rational Design of the β‐Bulge Gate in a Green Fluorescent Protein Accelerates the Kinetics of Sulfate Sensing**
Ong, W. S. Y., Ji, K., Pathiranage, V., Maydew, C., Baek, K., Villones, R. L. E., Meloni, G., Walker, A. R., & Dodani, S. C. (2023) · Angewandte Chemie · doi:10.1002/ange.202302304 · Cited by 1
A Hierarchical Approach to Scaling Batch Active Search Over Structured DataPreprint
Myers, V., & Greenside, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.10263 · Cited by 1
DeepPSC (protein structure camera): computer vision-based protein backbone structure reconstruction from alpha carbon trace as a case studyPreprint
Zhang, X., Luo, J., Cai, Y., Zhu, W., Yang, X., Cai, H., & Lin, Z. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.08.12.247312 · Cited by 1
SidechainNet: An All-Atom Protein Structure Dataset for Machine LearningPreprint
King, J. E., & Koes, D. R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.08162 · Cited by 1
“In addition to the dominance of the AlphaFold deep learning method in the 2018 Critical Assessment of protein Structure Prediction (CASP) competition [1, 2, 3], many novel deep learning-based methods have been developed for protein representation [4, 5], property prediction [6, 7], and structure prediction [8, 9, 10,…”
Method
Deep learning model for the prediction and classification of protein toxins across all domains of lifePreprint
Caceres‐Delpiano, J., Ibañez, R., Correa, S., Dunne, M. P., Retamal, P. A., & Álvarez, L. (2021) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2021.06.29.450401 · Cited by 1
In silico protein science: from sequence to network
Marrero, M. C. (2021) · doi:10.18174/547092 · Cited by 1
Energetic basis of excited-state enzyme design and functionPreprint
Lin, C., Romei, M. G., Mathews, I. I., & Boxer, S. G. (2021) · doi:10.33774/chemrxiv-2021-9l2vn-v2 · Cited by 1
Drug design and repurposing with a sequence-to-drug paradigmPreprint
Chen, L., Fan, Z., Chang, J., Yang, R., Guo, H., Zhang, Y., Yang, T., Zhou, C., Chen, Z., Zheng, C., et al. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.03.26.485909 · Cited by 1
Energetic basis of excited-state enzyme design and functionPreprint
Lin, C., Romei, M. G., Mathews, I. I., & Boxer, S. G. (2021) · doi:10.33774/chemrxiv-2021-9l2vn · Cited by 1
OrganelX Web Server for Sub-Peroxisomal and Sub-Mitochondrial protein localisationPreprint
Anteghini, M., Haja, A., dos Santos, V. A. P. M., Schomaker, L., & Saccenti, E. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.06.21.497045 · Cited by 1
“The three classification algorithms start representing the sequence as a concatenation of two deep learning-based sequence embeddings, namely UniRep and Seqvec [9, 10].”
BackgroundMethod
Protein Redesign and Engineering Using Machine Learning
Basit, Z., Akram, H., Iqbal, M. M., Muhammad, G., Aslam, M., Gul, I., Jamil, M., & Tahir, M. H. (2022) · Wiley eBooks · doi:10.1002/9781394167258.ch9 · Cited by 1
Domain loss enabled evolution of novel functions in a gene superfamilyPreprint
Koludarov, I., Senoner, T., Jackson, T., Dashevsky, D., Heinzinger, M., Aird, S. D., & Rost, B. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.12.15.520616 · Cited by 1
A robust deep learning platform to predict CD8+ T-cell epitopesPreprint
Lee, C. H.-J., Huh, J., Buckley, P. R., Jang, M., Pinho, M. P., Fernandes, R. A., Antanaviciute, A., Simmons, A., & Koohy, H. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.12.29.522182 · Cited by 1
Gene Mutagenesis Methods in Directed Evolution and Rational Enzyme Design
Reetz, M. T., Sun, Z., & Qu, G. (2023) · Enzyme Engineering · doi:10.1002/9783527836895.ch3 · Cited by 1
Co-evolution integrated deep learning framework for variants generation and fitness predictionPreprint
Tan, X. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.01.28.526023 · Cited by 1
Unraveling codon usage of Escherichia coli using machine learningPreprint
Huang, B., Hu, Y., Chen, X., & Lin, S. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.02.07.527422 · Cited by 1
“The problem is how to describe the codon usage, or which model shall be used. protein engineering, and protein structure prediction (Zhong et al., 2021, Alley et al., 2019, Jumper et al., 2021, Baek et al., 2021).”
Background
Protein language model-based end-to-end type II polyketide prediction without sequence alignmentPreprint
Huang, J., Gao, Q., Tang, Y., Wu, Y., Zhang, H., & Qin, Z. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.04.18.537339 · Cited by 1
“However, the above and other (7-9) methods frequently rely 50 on multiple sequence alignments, which are time-consuming and do not effectively 51 represent protein structural information (10, 11).”
Background
P-PPI: accurate prediction of peroxisomal protein-protein interactions (P-PPI) using deep learning-based protein sequence embeddingsPreprint
Anteghini, M., dos Santos, V. A. P. M., & Saccenti, E. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.06.30.547177 · Cited by 1
“In this work, we aim to benchmark and compare the most commonly used DL-based embeddings [14, 15, 13] for predicting PPIs solely based on protein sequence information, relying on high quality training data (that includes experimentally validated negative protein-protein interactions).”
BackgroundMethod
Opinion piece/Book chapter: Artificial Intelligence learns protein predictionPreprint
Heinzinger, M., & Rost, B. (2023) · OSF Preprints (OSF Preprints) · doi:10.31219/osf.io/n7wfp · Cited by 1
SENSE-PPI reconstructs protein-protein interactions of various complexities, within, across, and between species, with sequence-based evolutionary scale modeling and deep learningPreprint
Volzhenin, K., Bittner, L., & Carbone, A. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.09.19.558413 · Cited by 1
“PLMs have demonstrated tremendous potential for a broad range of protein-related problems, such as predicting 3D shapes, interactions, mutational outcomes, and subcellular localizations [42, 1, 15, 40].”
Background
Artificial Intelligence and Machine Learning in Bioinformatics
O’Brien, M. J., Sng, L. M. F., Ramarao-Milne, P., Didi, K., & Bauer, D. C. (2024) · Elsevier eBooks · doi:10.1016/b978-0-323-95502-7.00108-1 · Cited by 1
Protein Language Models in Directed EvolutionPreprint
Maguire, R. G., Bloznelyte, K., Adepoju, F., Armean-Jones, M., Dewan, S., Fozzard, S., Goddard, S. E., Gupta, A. K., Ibrahimi, E., Jones, F. P., et al. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.08.20.608752 · Cited by 1
“…of reference sequences (Suzek et al., 2015) to predict next or masked amino acids, learning the distribution of amino acids in context: UniRep (Alley et al., 2019) is a single-sequence recurrent neural network; ESM1b (Rives et al., 2021) is a single-sequence transformer encoder; and MSA…”
Background
Protein Structure Prediction Using Convolutional Neural Networks Augmented with Cellular Automata
Sree, P. K., Chakrabarti, P., Margala, M., & Devi, N. S. U. (2024) · Computational Intelligence · doi:10.1002/9781394214259.ch7 · Cited by 1
Recombinant DNA Technology in the Improvement of Microbial Enzyme Production
Udhayakumar, M., Jeyasundar, P. G. S. A., Das, M. P. A., Azeem, M., Mani, V. M., & Ayswaria, R. (2024) · doi:10.1002/9783527844340.ch37 · Cited by 1
AlignAb: Pareto-Optimal Energy Alignment for Designing Nature-Like AntibodiesPreprint
Wen, Y., Xu, C., Hu, J. Y.-C., & Liu, H. (2025) · Qeios · doi:10.32388/ovbkgz · Cited by 1
Protein Language Model Identifies Disordered, Conserved Motifs Driving Phase SeparationPreprint
Zhang, Y., Zheng, J., & Zhang, B. (2025) · eLife · doi:10.7554/elife.105309.1 · Cited by 1
SSAlign: fast and sensitive protein structure search at scale
Wang, L., Zhang, X., Wang, Y., & Xue, Z. (2026) · Bioinformatics · doi:10.1101/2025.07.03.662911 · Cited by 1
Modality-chain reasoning enables multimodal protein modelling and designPreprint
Liu, C., Chao, L., Ji, S., Wang, H., Zhou, G., Zheng, J. X., Hong, D., Guo, Y., Jiang, T., Gao, Z., et al. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.07.21.665832 · Cited by 2
“Sequence-based models, including the ESM family 7,8 , have learned representations that support diverse tasks such as structure prediction, mutation-effect estimation and function annotation 7–9 .”
Protein Language Model Identifies Disordered, Conserved Motifs Implicated in Phase SeparationPreprint
Zhang, Y., Zheng, J., & Zhang, B. (2025) · eLife · doi:10.7554/elife.105309.2 · Cited by 1
Pretrained protein language models choose between sequence novelty and structural completenessPreprint
Subramanian, A. M., Martinez, Z. A., & Thomson, M. W. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.10.01.679905 · Cited by 1
“Treating proteins as amino-acid ”texts,” PLMs internalize knowledge about sequence determinants within natural proteins, and implicitly learn features of structure and function including α -helical vs β -strand content, residue-wise contact maps, and binding/active sites [6–8].”
Decoding the physicochemical basis of taxonomy preferences in protein design modelsPreprint
Dillon, L. B., Maiwald, A., & Crook, O. M. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.10.21.683350 · Cited by 1
“To design new proteins, researchers modified existing structures through rational design and directed evolution, or relied on computationally expensive physics-based energy functions [7–12].”
How Much Does Protein Structure Really Help? A Case Study in Mutation-Induced Stability PredictionPreprint
Moldwin, A., & Shehu, A. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2025.12.22.694225 · Cited by 1
“[4 –7] Yet the prevailing architectural paradigm for protein prediction tasks where knowledge suggest three-dimensional (3D) protein structure is important combines PLM embed-42 dings with explicit 3D structure and auxiliary biochemical features, reflecting a widespread intu-43 ition: PLMs lack…”
Fast, accurate construction of multiple sequence alignments from protein language embeddingsPreprint
Hoang, M., Armour-Garb, I., & Singh, M. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.01.02.697423 · Cited by 1
“For each model, ARIES SP scores on BAliBASE are computed when representing amino acids using concatenations of the last ℓ PLM layer embeddings, with ℓ ∈ [1 , 3 , 6 , 9 , 12].”
High Diversity Gene Libraries Facilitate Machine Learning Guided Exploration of Fluorescent Protein Sequence SpacePreprint
Benabbas, A., Kearns, P., Billo, A., Chisholm, L. O., & Plesa, C. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.03.01.706892 · Cited by 1
Generative AI designs functional thiolation domains for reprogramming non-ribosomal peptide synthetasesPreprint
Bülbül, E. F., Bang, S., George, K., Bianchi, G., Raj, P., Chung, S., Pauline, V., Hochstrasser, R., Minas, H. A., Elgaher, W. A. M., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.03.03.709401 · Cited by 2
ProteomeLM: A proteome-scale language model enables accurate and rapid prediction of protein–protein interactions and gene essentiality across taxa
(2026) · doi:10.1073/pnas.2524201123 · Cited by 2
“Trained on large ensembles of protein sequences, they learn sequence representations that encode structural and functional signals (1–12), and have advanced the prediction of protein structure (9, 10), subcellular localization (13), and mutational effects (14, 15).”
Fixed-Length Protein Embeddings using Contextual LensesPreprint
Shanehsazzadeh, A., Belanger, D., & Dohan, D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.15065
“However, they did not ﬁnd that performance on the language modeling task correlates strongly with downstream performance, which is a key motivating result from NLP. RNN protein language models were developed by Alley et al. [1] and by Bepler et al. [3].”
Accurate computational evolution of proteins and its dependence on deep learningPreprint
Narayanan, P. S., & Runthala, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.01951
“For extracting the underlying functionally crucial features of a protein, Ethan’s group has deployed deep learning methodology in their methodologies for explaining the structural, biophysical and evolutionary relationships within the protein sequences [45].”
BackgroundMethodInfluential
Computational approaches to discover novel enzymes for fragrance and flavour
Durairaj, J. (2021) · doi:10.18174/551031
Peer Review #1 of "Navigating the amino acid sequence space between functional proteins using a deep learning framework (v0.1)"
(2021) · PeerJ Computer Science · doi:10.7287/peerj-cs.684v0.1/reviews/1
Protein matchmaking through representation learning
Heinzinger, M., Dallago, C., & Rost, B. (2021) · Cell Systems · doi:10.1016/j.cels.2021.09.007
A multitask transfer learning framework for the prediction of virus-human protein-protein interactions
Dong, T. N., Brogden, G., Gerold, G., & Khosla, M. (2021) · Institutional Repository of Leibniz Universität Hannover (Leibniz Universität Hannover) · doi:10.15488/12212
Peer Review #2 of "Navigating the amino acid sequence space between functional proteins using a deep learning framework (v0.1)"
(2021) · PeerJ Computer Science · doi:10.7287/peerj-cs.684v0.1/reviews/2
Faculty Opinions recommendation of Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences.
Koehl, P. (2021) · Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature · doi:10.3410/f.739876259.793585293
Rational evolution of a recombinant DNA polymerase for efficient incorporation of unnatural nucleotides by dual-site boostingPreprint
Cao, R., Zhai, L., Xie, Q., Wang, Z., Zheng, Y., Zhang, W., Büll, A., Xu, X., Dong, Y., Xu, C., et al. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.02.27.482192
How to Best Represent Proteins in Machine Learning-based Prediction of Drug/Compound-Target InteractionsPreprint
Ataş, H., & Doğan, T. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.05.01.490207
Faculty Opinions recommendation of Highly accurate protein structure prediction with AlphaFold.
Arulanandam, A. J. (2021) · Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature · doi:10.3410/f.740477161.793587548
Faculty Opinions recommendation of Highly accurate protein structure prediction with AlphaFold.
Chakraborty, S. (2021) · Faculty Opinions – Post-Publication Peer Review of the Biomedical Literature · doi:10.3410/f.740477161.793587538
Rational evolution of a recombinant DNA polymerase for efficient incorporation of unnatural nucleotides by dual-site boostingPreprint
Lyu, W., Cao, R., Zhai, L., Xie, Q., Wang, Z., Zheng, Y., Zhang, W., Buell, A. K., Xu, X., Dong, Y., et al. (2022) · Research Square · doi:10.21203/rs.3.rs-1570035/v1
Accelerating Inhibitor Discovery for Multiple SARS-CoV-2 Targets with a Single, Sequence-Guided Deep Generative FrameworkPreprint
Chenthamarakshan, V., Hoffman, S. C., Owen, C. D., Lukacik, P., Strain-Damerell, C. M., Fearon, D., Malla, T. R., Tumber, A., Schofield, C., Duyvesteyn, H. M. E., et al. (2022) · Research Square · doi:10.21203/rs.3.rs-1648691/v1
Predicting Drug-Target Interactions Binding Affinity by Using Dual Updating Multi-task Learning
Shi, C., Lin, S., Chen, J., Wang, M., & Gao, Q. (2022) · Communications in computer and information science · doi:10.1007/978-981-19-4549-6_6
CysPresso: A classification model utilizing deep learning protein representations to predict recombinant expression of cysteine-dense peptides
Ouellet, S., Ferguson, L., Lau, A. Z., & Lim, T. K. Y. (2022) · doi:10.1101/2022.09.17.508377
Peer Review #2 of "Using genetic programming to predict and optimize protein function (v0.1)"
(2022) · PeerJ Physical Chemistry · doi:10.7287/peerj-pchem.24v0.1/reviews/2
Peer Review #1 of "Using genetic programming to predict and optimize protein function (v0.1)"
(2022) · PeerJ Physical Chemistry · doi:10.7287/peerj-pchem.24v0.1/reviews/1
META ANALISIS PENELITIAN TEKNIK INFORMATIKA
Supriyadi, E., Hermawanto, A. R., Siahaan, J., & Gusdevi, H. (2022) · Naratif Jurnal Nasional Riset Aplikasi dan Teknik Informatika · doi:10.53580/naratif.v4i2.166
Computational Approaches for Peroxisomal Protein Localization
Anteghini, M., & dos Santos, V. A. P. M. (2023) · Methods in molecular biology · doi:10.1007/978-1-0716-3048-8_29
Protein Engineering for Thermostability through Deep EvolutionPreprint
Chu, H., Tian, Z., Hu, L., Zhang, H., Chang, H., Bai, J., Liu, D., Cheng, J., & Jiang, H. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.05.04.539497
CELL-E: zero-shot sequence-to-image synthesis for protein localization predictionPreprint
Khwaja, E., Song, Y. S., & Huang, B. (2023) · Research Square · doi:10.21203/rs.3.rs-2963881/v1
“UniRep is an LSTM model that predicts the next amino acid in a variable length sequence [41], while BERT uses bidirectional masked language modeling to predict the identity of masked tokens throughout the sequence [42].”
Method
TAPE-Pero: Using Deep Representation Learning Model to Identify and Localize Peroxisomal Proteins
Sui, J., Chen, Y., Cao, Y., & Zhao, Y. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-4749-2_48
A Stacking Machine Learning Method for IL-10-Induced Peptide Sequence Recognition Based on Unified Deep Representation Learning
Li, J., Jiang, J., Pei, H., & Lv, Z. (2023) · Applied Sciences · doi:10.3390/app13169346
Domain-PFP: Protein Function Prediction Using Function-Aware Domain Embedding RepresentationsPreprint
Ibtehaz, N., Kagaya, Y., & Kihara, D. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.08.23.554486
T Cell Receptor Protein Sequences and Sparse Coding: A Novel Approach to Cancer Classification
Tayebi, Z., Ali, S., Chourasia, P., Murad, T., & Patterson, M. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-8141-0_17
Computer-guided substrate scope exploration of engineered peptide-modifying biocatalystsPreprint
Siirola, E., Debon, A., Eggimann, F. K., & Šnajdrová, R. (2023) · Research Square · doi:10.21203/rs.3.rs-3639162/v1
MehNet: a vigesimal-based model by amino acid melting points generates unique ID numbers for protein sequences
Erten, M. (2024) · Journal of Biomolecular Structure and Dynamics · doi:10.1080/07391102.2024.2302937
“Similarly, it was used an LSTM-based architecture to learn an embedding of whole protein sequences into a fixed-length vector (Alley et al., 2019).”
SE(3) Equivalent Graph Attention Network as an Energy-Based Model for Protein Side Chain Conformation
Liu, D., Chen, S., Zheng, S., Zhang, S., & Yang, Y. (2023) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm58861.2023.10385826
Genotype sampling for deep-learning assisted experimental mapping of fitness landscapesPreprint
Wagner, A. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.01.18.576262
Deep Learning-Driven Protein Design
You, A., & Xu, X. (2024) · Advances in Computer Signals and Systems · doi:10.23977/acss.2024.080120
Additional file 1 of Protein language models can capture protein quaternary state
Avraham, O., Tsaban, T., Ben-Aharon, Z., Tsaban, L., & Schueler‐Furman, O. (2023) · Figshare · doi:10.6084/m9.figshare.24564069
Directed Evolution
Leconte, A. M., & Colee, C. M. (2024) · ACS in focus · doi:10.1021/acsinfocus.7e8004
Latent-based Directed Evolution accelerated by Gradient Ascent for Protein Sequence DesignPreprint
Ngo, N. K., Tran, T. V. T., Nguyen, V. T. D., & Hy, T. S. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.04.13.589381
Discovering nuclear localization signal universe through a novel deep language learning network with attention as the neuronsPreprint
Shen, H., Li, Y., & Pan, X. (2024) · Research Square · doi:10.21203/rs.3.rs-4204156/v1
Artificial intelligence-based parametrization of Michaelis–Menten maximal velocity: Toward in silico New Approach Methodologies (NAMs)Preprint
Karakoltzidis, A., Karakitsios, S., & Sarigiannis, D. A. (2024) · Research Square · doi:10.21203/rs.3.rs-4276245/v1
Ocean to Tree: Leveraging Single-Molecule RNA-Seq to Repair Genome Gene Models and Improve Phylogenomic Analysis of Gene and Species Evolution
Hsiao, J., Deng, L. C., Moroz, L. L., Chalasani, S. H., & Edsinger, E. (2024) · Methods in molecular biology · doi:10.1007/978-1-0716-3642-8_19
A Protein Structure Enhanced Pre-training Model for Allosteric Site Detection
Lv, Q., Zhang, X., Jiang, X., Chen, M., Cao, Y., & He, W.-X. (2023) · ICAICE · doi:10.1145/3652628.3652822
Protein Design
Ramya, L., Ragunathan, P. T., & Yennamalli, R. M. (2024) · Elsevier eBooks · doi:10.1016/b978-0-323-95502-7.00103-2
Preventing escape and malfunction of recoded cells due to tRNA base changesPreprint
Chiappino-Pepe, A., Radford, F., Budnik, B., Taş, H., Augustin, T. L., Burgess, H. M., Moret, M., Dharani, A. M., Zheng, Q., Fan, W., et al. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.07.18.604179
“Machine learning models trained with millions of protein sequences (protein language models) learn the contextual importance of an amino acid in a sequence 31 .”
BackgroundSelf-citation
Boosting Protein Language Models with Negative Sample Mining
Xu, Y., Zhao, X., Song, X., Wang, B., & Yu, T. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-70381-2_13
Intelligent prediction and biological validation of the high reassortment potential of avian H5N1 and human H3N2 influenza virusesPreprint
Li, J., Wei, J., Li, Y., Zhang, S., Jiang, S., Chen, Y., Li, Y., Feng, Y., Kang, X., Liu, W., et al. (2024) · Research Square · doi:10.21203/rs.3.rs-4989707/v1 · Cited by 1
VIEPred: Predicting Viral Immune Evasion with Multimodal Representation Learning
Liang, B., Wang, N., Huang, H., Hou, Y., & Qiang, X. (2024) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2868/1/012029 · Cited by 1
TCellR2Vec: efficient feature selection for TCR sequences for cancer classification
Tayebi, Z., Ali, S., & Patterson, M. (2024) · PeerJ Computer Science · doi:10.7717/peerj-cs.2239
Current Advancements: Application of Artificial Intelligence in Drug Discovery and Development
Buragohain, P., Prasad, S., Kimneiniang, N., Das, H., Rajak, P., & Pathak, H. (2024) · Drug Delivery Letters · doi:10.2174/0122103031313111241203042224
Transformer models for protein-guided drug compound generation: A comparison of amino acid sequences, pre-trained protein embeddings, SMILES, and SELFIES
Fossl, D. (2024) · doi:10.24124/2024/59584
GP-nano: a geometric graph network for nanobody polyreactivity prediction
Zhou, X., Yuan, Q., Zheng, S., Wang, Y., & Yang, Y. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10822038
“Lim’s method primarily combines language descriptors (UniRep [14], TAPE [48]) with biochemical patterns (F46, 46 bio-chemical patterns) and employs traditional machine learning techniques for classification (GBM, XGB).”

Authors: Alley, E. C., Khimulya, G., Biswas, S., AlQuraishi, M., & Church, G. M.
Affiliations: Harvard University (US)
Corresponding author: Church, George M.
ORCID: Alley, Ethan C.
Biswas, Surojit
AlQuraishi, Mohammed
Church, George M.
Venue: Nature Methods
Publisher: Springer Science and Business Media LLC
Published: 2019-10-21
Volume: 16
Issue: 12
Pages: 1315-1322
ISSN: 1548-7091 (ISSN-L)
1548-7105
DOI: 10.1038/s41592-019-0598-1
PMC: PMC7067682
OpenAlex: W2980789587
Cited by: 1,131
References: 80
Citations by year: 2026: 130 · 2025: 170 · 2024: 201 · 2023: 197 · 2022: 188 · 2021: 159 · 2020: 69 · 2019: 17
FWCI: 35.71
Type: journal article
Language: en
Open access: green
doi.org
Licence: cc-by-nc-nd
www.springer.com/tdm (tdm)
www.springer.com/tdm (vor)
Locations: Nature Methods (publishedVersion)
bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
Research Square (acceptedVersion, cc-by)
PubMed (publishedVersion)
Europe PMC (PubMed Central) (acceptedVersion)
PubMed Central (acceptedVersion)
OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) (submittedVersion)
Funders: Amazon Web Services Cloud Credits for Research
Center for Effective Altruism
U.S. Department of Health & Human Services | National Institutes of Health (T32HG002295, U54-CA225088)
National Science Foundation GRFP Fellowship
U.S. Department of Health & Human Services | NIH | National Institute of General Medical Sciences (P50GM107618)
Topics: Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Structure and Dynamics
Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › RNA and protein synthesis mechanisms
Keywords: rational protein design, protein stability prediction, de novo protein design, protein mutants, recurrent neural networks, protein function prediction
MeSH terms: Deep Learning, Amino Acid Sequence, Mutation, Protein Engineering, Protein Stability

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Unified rational protein engineering with sequence-based deep representation learning

Abstract

Overview

Integrity signals

Verification

Claims the paper makes

Claims other papers make about this one

Self-check

Citations

Cites

Cited by

Related

Metadata

Record

About these checks