CoChat
Sign Up
PreprintCited by 18Machine Learning in BioinformaticsProtein Structure and DynamicsEnzyme Structure and Function

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

LambdaPP: Fast and accessible protein-specific phenotype predictions

Open access
Olenyi, Tobias, Marquet, Céline, Heinzinger, Michael, Kröger, Benjamin, Nikolova, Tiha, Bernhofer, Michael, Sändig, Philip, Schütze, Konstantin, Littmann, Maria, Mirdita, Milot, Steinegger, Martin, Dallago, Christian, Rost, Burkhard·2022·Protein Science
DOI 10.1101/2022.08.04.502750PMC PMC9793974

Preprint — published as 10.1002/pro.4524

Open this paper in CoChat — free accountOpen PDF

Abstract

The availability of accurate and fast Artificial Intelligence (AI) solutions predicting aspects of proteins are revolutionizing experimental and computational molecular biology. The webserver LambdaPP aspires to supersede PredictProtein, the first internet server making AI protein predictions available in 1992. Given a protein sequence as input, LambdaPP provides easily accessible visualizations of protein 3D structure, along with predictions at the protein level (GeneOntology, subcellular location), and the residue level (binding to metal ions, small molecules, and nucleotides; conservation; intrinsic disorder; secondary structure; alpha-helical and beta-barrel transmembrane segments; signal-peptides; variant effect) in seconds. The structure prediction provided by LambdaPP - leveraging ColabFold and computed in minutes - is based on MMseqs2 multiple sequence alignments. All other feature prediction methods are based on the pLM ProtT5 . Queried by a protein sequence, LambdaPP computes protein and residue predictions almost instantly for various phenotypes, including 3D structure and aspects of protein function. Accessibility Statement: LambdaPP is freely available for everyone to use under embed.predictprotein.org , the interactive results for the case study can be found under https://embed.predictprotein.org/o/Q9NZC2 . The frontend of LambdaPP can be found on GitHub ( github.com/sacdallago/embed.predictprotein.org ), and can be freely used and distributed under the academic free use license (AFL-2). For high-throughput applications, all methods can be executed locally via the bio-embeddings ( bioembeddings.com ) python package, or docker image at ghcr.io/bioembeddings/bio_embeddings , which also includes the backend of LambdaPP. Impact Statement: We introduce LambdaPP, a webserver integrating fast and accurate sequence-only protein feature predictions based on embeddings from protein Language Models (pLMs) available in seconds along with high-quality protein structure predictions. The intuitive interface invites experts and novices to benefit from the latest machine learning tools. LambdaPP’s unique combination of predicted features may help in formulating hypotheses for experiments and as input to bioinformatics pipelines.

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 · 10.1101/2022.08.04.502750

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: 76

  1. 2018, Assessment of hard target modeling in CASP12 reveals an emerging role of alignment-based contact prediction methods, Proteins, 86, 97
  2. Alexander-Brett JM , Kober DL (2015) Triggering receptor expressed on myeloid cells 2. · DOI
  3. 2019, Unified rational protein engineering with sequence-based deep representation learning, Nat Methods, 16, 1315, 10.1038/s41592-019-0598-1 · DOI · Paper page
  4. 10.1093/bioinformatics/btx431 · DOI
  5. 2022, Deep learning and protein structure modeling, Nat Methods, 19, 13, 10.1038/s41592-021-01360-8 · DOI
  6. 2020, ConSurf-DB: An accessible repository for the evolutionary conservation patterns of the majority of PDB proteins, Protein Science, 29, 258, 10.1002/pro.3779 · DOI
  7. 2013, Representation Learning: A Review and New Perspectives, IEEE TPAMI, 35, 1798, 10.1109/TPAMI.2013.50 · DOI · Paper page
  8. Bepler T , Berger B. Learning protein sequence embeddings using information from structure. (2019). arXiv.
  9. 2021, Learning the protein language: Evolution, structure, and function, Cell Systems, 12, 654, 10.1016/j.cels.2021.05.017 · DOI · Paper page
  10. 10.1093/bioinformatics/bth070 · DOI
  11. 2021, PredictProtein - Predicting Protein Structure and Function for 29 Years, NAR, 49, W535, 10.1093/nar/gkab354 · DOI
  12. Bernhofer M , Rost B. TMbed – Transmembrane proteins predicted through Language Model embeddings. (2022). bioRxiv. · DOI
  13. 2022, Using deep learning to annotate the protein universe, Nat Biotechnol, 40, 932, 10.1038/s41587-021-01179-w · DOI · Paper page
  14. Bordin N , Sillitoe I , Nallapareddy V , Rauer C , Lam SD , Waman VP , Sen N , Heinzinger M , Littmann M , Kim S et al. (2022) AlphaFold2 reveals commonalities and novelties in protein structure space for 21 model organisms. bioRxiv. · DOI · Paper page
  15. 10.1038/s41592-021-01101-x · DOI · Paper page
  16. 2021, Peptides derived from gp43, the most antigenic protein from Paracoccidioides brasiliensis, form amyloid fibrils in vitro: implications for vaccine development, Sci Rep, 11, 23440, 10.1038/s41598-021-02898-5 · DOI · Paper page
  17. Chowdhary KR . Natural Language Processing. In: Chowdhary KR , Ed. (2020) Fundamentals of Artificial Intelligence. Springer India, New Delhi, pp. 603–649. · DOI
  18. Cid FP , Rilling JI , Graether SP , Bravo LA , Mora MdLL , Jorquera MA (2016) Properties and biotechnological applications of ice-binding proteins in bacteria. FEMS Microbiology Letters 363. · DOI
  19. 2020, Visualizing Human Protein-Protein Interactions and Subcellular Localizations on Cell Images Through CellMap, Current Protocols Bioinf, 69, e97, 10.1002/cpbi.97 · DOI
  20. 2021, Learned Embeddings from Deep Learning to Visualize and Predict Protein Sets, Current Protocols, 1, e113, 10.1002/cpz1.113 · DOI
  21. 2020, ODiNPred: comprehensive prediction of protein order and disorder, Sci Rep, 10, 14780, 10.1038/s41598-020-71716-1 · DOI
  22. 10.1093/bioinformatics/btaa537 · DOI
  23. Elnaggar A , Heinzinger M , Dallago C , Rehawi G , Wang Y , Jones L , Gibbs T , Feher T , Angerer C , Steinegger M et al. (2021) ProtTrans: Towards Cracking the Language of Lifes Code Through Self-Supervised Deep Learning and High Performance Computing. IEEE Transactions on Pattern Analysis and Machine Intelligence:1–1. · DOI · Paper page
  24. 10.1186/s12859-019-3220-8 · DOI · Paper page
  25. 2022, Contrastive learning on protein embeddings enlightens midnight zone, NAR Gen Bioinf, 4, lqac043
  26. 10.1073/pnas.89.22.10915 · DOI · Paper page
  27. 2022, Evolutionary velocity with protein language models predicts evolutionary dynamics of diverse proteins, Cell Systems, 13, 274, 10.1016/j.cels.2022.01.003 · DOI
  28. Høie MH , Kiehl EN , Petersen B , Nielsen M , Winther O , Nielsen H , Hallgren J , Marcatili P (2022) NetSurfP-3.0: accurate and fast prediction of protein structural features by protein language models and deep learning. NAR:gkac439. · DOI
  29. Ilzhoefer D , Heinzinger M , Rost B. SETH predicts nuances of residue disorder from protein embeddings. (2022). bioRxiv. · DOI
  30. 10.7554/eLife.20391 · DOI · Paper page
  31. 2021, Conformational changes in Lassa virus L protein associated with promoter binding and RNA synthesis activity, Nat Commun, 12, 7018, 10.1038/s41467-021-27305-5 · DOI · Paper page
  32. 2021, Critical assessment of methods of protein structure prediction (CASP)—Round XIV, Proteins, 89, 1607, 10.1002/prot.26237 · DOI · Paper page
  33. 2019, GEMME: A Simple and Fast Global Epistatic Model Predicting Mutational Effects, Molecular Biology and Evolution, 36, 2604, 10.1093/molbev/msz179 · DOI
  34. Lin Z , Akin H , Rao R , Hie B , Zhu Z , Lu W , Santos Costa Ad , Fazel-Zarandi M , Sercu T , Candido S et al. (2022) Language models of protein sequences at the scale of evolution enable accurate structure prediction. bioRxiv:2022.2007.2020.500902.
  35. Lin Z , Akin H , Rao R , Hie BL , Zhu Z , Lu W , dos Santos Costa A , Fazel-Zarandi M , Sercu T , Candido S et al. (2022) Language models of protein sequences at the scale of evolution enable accurate structure prediction. bioRxiv.
  36. 2021, Clustering FunFams using sequence embeddings improves EC purity, Bioinformatics, 37, 3449, 10.1093/bioinformatics/btab371 · DOI
  37. 2021, Embeddings from deep learning transfer GO annotations beyond homology, Sci Rep, 11, 1160, 10.1038/s41598-020-80786-0 · DOI
  38. 2021, Protein embeddings and deep learning predict binding residues for various ligand classes, Sci Rep, 11, 23916, 10.1038/s41598-021-03431-4 · DOI
  39. Madani A , McCann B , Naik N , Keskar NS , Anand N , Eguchi RR , Huang P-S , Socher R. ProGen: Language Modeling for Protein Generation. (2020). bioRxiv. · DOI
  40. 2021, Humanization of antibodies using a machine learning approach on large-scale repertoire data, Bioinformatics
  41. Marquet C , Heinzinger M , Olenyi T , Dallago C , Erckert K , Bernhofer M , Nechaev D , Rost B (2021) Embeddings from protein language models predict conservation and variant effects. Hum Genet. · DOI · Paper page
  42. 2022, Method of the Year: protein structure prediction, Nat Methods, 19, 5, 10.1038/s41592-021-01359-1 · DOI
  43. Meier J , Rao R , Verkuil R , Liu J , Sercu T , Rives A. Language models enable zero-shot prediction of the effects of mutations on protein function. (2021). Curran Associates, Inc., pp. 29287–29303. · DOI · Paper page
  44. 2022, ColabFold: making protein folding accessible to all, Nat Methods, 19, 679, 10.1038/s41592-022-01488-1 · DOI · Paper page
  45. 10.1093/bioinformatics/bty1057 · DOI · Paper page
  46. 1965, Cramming more components onto integrated circuits, Electronics, 38, 114
  47. 2020, Quantitative Protein Disorder Assessment Using NMR Chemical Shifts, Methods Mol Biol, 2141, 303, 10.1007/978-1-0716-0524-0_15 · DOI
  48. 2021, The language of proteins: NLP, machine learning & protein sequences, Computational and Structural Biotechnology Journal, 19, 1750, 10.1016/j.csbj.2021.03.022 · DOI
  49. 10.1073/pnas.1508380112 · DOI
  50. Piovesan D , Monzon AM , Tosatto SCE (2022) Intrinsic Protein Disorder, Conditional Folding and AlphaFold2. bioRxiv:2022.2003.2003.482768. · DOI
  51. Redl I , Fisicaro C , Dutton O , Hoffmann F , Henderson L , Owens BMJ , Heberling M , Paci E , Tamiola K (2022) ADOPT: intrinsic protein disorder prediction through deep bidirectional transformers. bioRxiv:2022.2005.2025.493416. · DOI
  52. 2018, Deep generative models of genetic variation capture the effects of mutations, Nat Methods, 15, 816, 10.1038/s41592-018-0138-4 · DOI · Paper page
  53. 10.1073/pnas.2016239118 · DOI · Paper page
  54. 1992, Jury returns on structure prediction, Nature, 360, 540, 10.1038/360540b0 · DOI
  55. 10.1006/jmbi.1993.1413 · DOI
  56. 10.1146/annurev.bb.25.060196.000553 · DOI
  57. 10.1093/bioinformatics/10.1.53 · DOI
  58. 10.1002/prot.25585 · DOI
  59. 10.1093/nar/gkab314 · DOI · Paper page
  60. 2021, CATH: increased structural coverage of functional space, NAR, 49, D266, 10.1093/nar/gkaa1079 · DOI · Paper page
  61. 2022, Reaching alignment-profile-based accuracy in predicting protein secondary and tertiary structural properties without alignment, Sci Rep, 12, 7607, 10.1038/s41598-022-11684-w · DOI
  62. 2021, Light attention predicts protein location from the language of life, Bioinformatics Advances, 1, vbab035, 10.1093/bioadv/vbab035 · DOI · Paper page
  63. 10.1038/s41592-019-0437-4 · DOI · Paper page
  64. 2018, Clustering huge protein sequence sets in linear time, Nat Commun, 9, 2542, 10.1038/s41467-018-04964-5 · DOI · Paper page
  65. 10.1074/jbc.RA118.002352 · DOI · Paper page
  66. 10.1093/nar/gkaa1100 · DOI · Paper page
  67. 2017, The End of Moore’s Law: A New Beginning for Information Technology, Computing in Science & Engineering, 19, 41, 10.1109/MCSE.2017.29 · DOI
  68. 10.1093/NAR/GKAB1061 · DOI · Paper page
  69. Weissenow K , Heinzinger M , Rost B (2022) Protein language model embeddings for fast, accurate, alignment-free protein structure prediction. Structure:2021.2007.2031.454572. · DOI · Paper page
  70. 10.3390/ijms23094591 · DOI · Paper page
  71. Wu R , Ding F , Wang R , Shen R , Zhang X , Luo S , Su C , Wu Z , Xie Q , Berger B et al. (2022) High-resolution de novo structure prediction from primary sequence. bioRxiv:2022.2007.2021.500999. · DOI · Paper page
  72. 10.1093/nar/gku366 · DOI
  73. 10.1093/nar/gks966 · DOI
  74. 2021, Structure of the human RNA polymerase I elongation complex, Cell Discovery, 7, 97, 10.1038/s41421-021-00335-5 · DOI
  75. 2020, Mutation effect estimation on protein– protein interactions using deep contextualized representation learning, NAR Gen Bioinf, 2, lqaa015
  76. 10.1186/s13059-019-1835-8 · DOI · Paper page

Metadata

Authors
Olenyi, T., Marquet, C., Heinzinger, M., Kröger, B., Nikolova, T., Bernhofer, M., Sändig, P., Schütze, K., Littmann, M., Mirdita, M., Steinegger, M., Dallago, C., & Rost, B.
Affiliations
  • Technical University of Munich (DE)
  • Seoul National University (KR)
Corresponding author
Olenyi, Tobias
ORCID
Venue
Protein Science
Publisher
openRxiv
Published
2022-08-05
Volume
32
Issue
1
Pages
e4524-e4524
ISSN
0961-8368 (ISSN-L)
DOI
10.1101/2022.08.04.502750
PMC
PMC9793974
OpenAlex
W4310498446
Cited by
18
References
1
Citations by year
2026: 2 · 2025: 3 · 2024: 8 · 2023: 2 · 2022: 3
FWCI
1.30
Type
journal article
Language
en
Open access
Licence
cc-by-nc
Locations
  • Protein Science (publishedVersion, cc-by-nc)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc)
  • PubMed Central (publishedVersion, cc-by-nc)
  • PubMed (publishedVersion)
  • Seoul National University Open Repository (Seoul National University) (submittedVersion)
Funders
  • Alexander von Humboldt-Stiftung
  • DeepMind
  • National Research Foundation (2021-R1C1-C102065)
  • Deutsche Forschungsgemeinschaft (DFG-GZ: RO1320/4-1, RO1320/4‐1)
  • Bundesministerium für Bildung und Forschung (01IS17049, 031L0168)
  • Seoul National University
  • National Research Foundation of Korea (2021-R1C1-C102065, 2021-M3A9-I4021220, 2020M3‐A9G7‐103933, 2019R1-A6A1-A10073437)
  • Technische Universität München (01IS17049)
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Structure and Dynamics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Structural Biology › Enzyme Structure and Function
Keywords
protein structure prediction, ColabFold, ProtT5, subcellular localization, metal ion binding, small molecule binding, nucleotide binding, intrinsic disorder, secondary structure prediction, transmembrane helices, signal peptide, variant effect prediction, protein conservation, web server
MeSH terms
Amino Acid Sequence, Artificial Intelligence, Proteins, Software, Sequence Alignment, Protein Structure, Secondary

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