CoChat
Sign Up
PreprintCited by 35Monoclonal and Polyclonal Antibodies Researchvaccines and immunoinformatics approachesMachine Learning in Bioinformatics

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

Meta Learning Improves Robustness and Performance in Machine Learning-Guided Protein Engineering

Open access
Minot, Mason, Reddy, Sai T.·2023·Cell Systems
DOI 10.1101/2023.01.30.526201

Preprint — published as 10.1016/j.cels.2023.12.003 · Paper page

Open this paper in CoChat — free accountOpen PDF

Abstract

Machine learning-guided protein engineering continues to rapidly progress, however, collecting large, well-labeled data sets remains time and resource intensive. Directed evolution and protein engineering studies often require extensive experimental processes to eliminate noise and fully label high-throughput protein sequence-function data. Meta learning methods established in other fields (e.g. computer vision and natural language processing) have proven effective in learning from noisy data, given the availability of a small data set with trusted labels and thus could be applied for protein engineering. Here, we generate yeast display antibody mutagenesis libraries and screen them for target antigen binding followed by deep sequencing. Meta learning approaches are able to learn under high synthetic and experimental noise as well as in under labeled data settings, typically outperforming baselines significantly and often requiring a fraction of the training data. Thus, we demonstrate meta learning may expedite and improve machine learning-guided protein engineering. Availability and implementation: The code used in this study is publicly available at https://github.com/LSSI-ETH/meta-learning-for-protein-engineering . Graphical Abstract:

Overview

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1101/2023.01.30.526201

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Verification

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.

A few free checks a day · papers already verified open instantly · results are public

Self-check

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

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

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 48

  1. 10.1126/science.abj8754 · DOI · Paper page
  2. 2020, Learning from positive and unlabeled data: a survey, Mach. Learn, 109, 719, 10.1007/s10994-020-05877-5 · DOI · Paper page
  3. 10.1093/protein/gzq002 · DOI
  4. 10.1038/s41592-021-01100-y · DOI · Paper page
  5. 10.1038/nbt0697-553 · DOI
  6. 2021, Deep diversification of an AAV capsid protein by machine learning, Nat. Biotechnol, 39, 691, 10.1038/s41587-020-00793-4 · DOI
  7. 10.1073/pnas.89.10.4285 · DOI
  8. 10.1038/nprot.2006.94 · DOI
  9. 10.1186/s12864-019-6413-7 · DOI · Paper page
  10. 10.1038/nature01392 · DOI
  11. 10.1038/352624a0 · DOI
  12. Dallago,C. et al. (2021) FLIP: Benchmark tasks in fitness landscape inference for proteins. Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks, 1. · DOI
  13. 10.1126/science.add2187 · DOI · Paper page
  14. Elkan,C. and Noto,K. (2008) Learning classifiers from only positive and unlabeled data. In, Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining, KDD ‘08. Association for Computing Machinery, New York, NY, USA, pp. 213–220. · DOI
  15. 2015, ANT: Software for Generating and Evaluating Degenerate Codons for Natural and Expanded Genetic Codes, ACS Synth. Biol, 4, 935, 10.1021/acssynbio.5b00018 · DOI
  16. 10.1038/nmeth.3027 · DOI · Paper page
  17. 10.1177/1087057103260590 · DOI
  18. 10.1016/j.compchemeng.2019.106533 · DOI
  19. 10.1021/ci000397q · DOI
  20. 2020, Leveraging Uncertainty in Machine Learning Accelerates Biological Discovery and Design, Cell Syst, 11, 461, 10.1016/j.cels.2020.09.007 · DOI · Paper page
  21. Jiang,L. et al. (2020) Beyond Synthetic Noise: Deep Learning on Controlled Noisy Labels. In, Proceedings of the 37th International Conference on Machine Learning. PMLR, pp. 4804–4815.
  22. 10.1074/jbc.M115.662783 · DOI
  23. LeCun,Y. and Bengio,Y. (1998) Convolutional networks for images, speech, and time series. In, The handbook of brain theory and neural networks. MIT Press, Cambridge, MA, USA, pp. 255–258.
  24. Li,M. and Zhang,W. (2021) PHIAF: prediction of phage-host interactions with GAN-based data augmentation and sequence-based feature fusion. Brief. Bioinform. · DOI
  25. 10.1016/j.ccr.2004.09.027 · DOI
  26. 2020, A Generative Neural Network for Maximizing Fitness and Diversity of Synthetic DNA and Protein Sequences, Cell Syst, 11, 49, 10.1016/j.cels.2020.05.007 · DOI · Paper page
  27. 10.1038/s41586-022-04599-z · DOI
  28. 2022, Co-optimization of therapeutic antibody affinity and specificity using machine learning models that generalize to novel mutational space, Nat. Commun, 13, 3788, 10.1038/s41467-022-31457-3 · DOI
  29. 2021, Optimization of therapeutic antibodies by predicting antigen specificity from antibody sequence via deep learning, Nat. Biomed. Eng, 5, 600, 10.1038/s41551-021-00699-9 · DOI · Paper page
  30. Minot,M. and Reddy,S.T. (2022) Nucelotide augmentation for machine learning-guided protein engineering. Bioinforma. Adv., vbac094. · DOI
  31. 10.1016/j.csbj.2021.03.022 · DOI
  32. Paszke,A. et al. (2019) PyTorch: An Imperative Style, High-Performance Deep Learning Library. In, Advances in Neural Information Processing Systems. Curran Associates, Inc.
  33. Rao,R.M. et al. (2021) MSA Transformer. In, Proceedings of the 38th International Conference on Machine Learning. PMLR, pp. 8844–8856. · DOI · Paper page
  34. Ren,M. et al. (2018) Learning to Reweight Examples for Robust Deep Learning. In, Proceedings of the 35th International Conference on Machine Learning. PMLR, pp. 4334–4343.
  35. Rives,A. et al. (2021) Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proc. Natl. Acad. Sci., 118. · DOI · Paper page
  36. 2022, Computational counterselection identifies nonspecific therapeutic biologic candidates, Cell Rep. Methods, 2, 100254, 10.1016/j.crmeth.2022.100254 · DOI
  37. 2021, Protein design and variant prediction using autoregressive generative models, Nat. Commun, 12, 2403, 10.1038/s41467-021-22732-w · DOI · Paper page
  38. Shu,J. et al. (2019) Meta-weight-net: learning an explicit mapping for sample weighting. In, Proceedings of the 33rd International Conference on Neural Information Processing Systems. Curran Associates Inc., Red Hook, NY, USA, pp. 1919–1930.
  39. 2021, Inferring Protein Sequence-Function Relationships with Large-Scale Positive-Unlabeled Learning, Cell Syst, 12, 92, 10.1016/j.cels.2020.10.007 · DOI
  40. Taft,J.M. et al. (2022) Deep mutational learning predicts ACE2 binding and antibody escape to combinatorial mutations in the SARS-CoV-2 receptor-binding domain. Cell. · DOI
  41. Vaswani,A. et al. (2017) Attention is All you Need. In, Advances in Neural Information Processing Systems. Curran Associates, Inc.
  42. 10.1038/nprot.2017.126 · DOI
  43. 10.1093/bioinformatics/btx469 · DOI
  44. 10.1126/science.add1964 · DOI · Paper page
  45. 2021, Informed training set design enables efficient machine learning-assisted directed protein evolution, Cell Syst, 12, 1026, 10.1016/j.cels.2021.07.008 · DOI
  46. 2020, Signal Peptides Generated by Attention-Based Neural Networks, ACS Synth. Biol, 9, 2154, 10.1021/acssynbio.0c00219 · DOI
  47. 10.1038/s41592-019-0496-6 · DOI
  48. 2021, Meta Label Correction for Noisy Label Learning, Proc. AAAI Conf. Artif. Intell, 35, 11053

Metadata

Authors
Minot, M., & Reddy, S. T.
Affiliations
ETH Zurich (CH)
Corresponding author
Reddy, Sai T.
ORCID
Venue
Cell Systems
Publisher
openRxiv
Published
2023-01-30
Volume
15
Issue
1
Pages
4-18.e4
ISSN
2405-4712 (ISSN-L)
DOI
10.1101/2023.01.30.526201
OpenAlex
W4390674232
Cited by
35
References
1
Citations by year
2026: 6 · 2025: 22 · 2024: 6 · 2023: 1
FWCI
8.66
Type
journal article
Language
en
Open access
Locations
  • Cell Systems (publishedVersion)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
Funders
  • National Science Foundation
  • Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung (197941, 310030)
  • Eidgenössische Technische Hochschule Zürich
Topics
  • Life Sciences › Immunology and Microbiology › Immunology › Monoclonal and Polyclonal Antibodies Research
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › vaccines and immunoinformatics approaches
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
Keywords
meta-learning, antibody engineering, noisy training data, protein engineering, yeast surface display, positive-unlabeled learning, out-of-distribution robustness, bi-level optimization, deep sequencing
MeSH terms
Machine Learning, Amino Acid Sequence, Antibodies, Engineering, Mutagenesis

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