CoChat
Sign Up
Cited by 50Genomics and Phylogenetic StudiesBioinformatics and Genomic NetworksFractal and DNA sequence analysis

SonicParanoid2: fast, accurate, and comprehensive orthology inference with machine learning and language models

Open access
Salvatore Cosentino, Sira Sriswasdi, Wataru Iwasaki·2024·Genome biology
DOI 10.1186/s13059-024-03298-4PMC PMC11270883

Published version of a preprint

Open this paper in CoChat — free account

Abstract

Accurate inference of orthologous genes constitutes a prerequisite for comparative and evolutionary genomics. SonicParanoid is one of the fastest tools for orthology inference; however, its scalability and accuracy have been hampered by time-consuming all-versus-all alignments and the existence of proteins with complex domain architectures. Here, we present a substantial update of SonicParanoid, where a gradient boosting predictor halves the execution time and a language model doubles the recall. Application to empirical large-scale and standardized benchmark datasets shows that SonicParanoid2 is much faster than comparable methods and also the most accurate. SonicParanoid2 is available at https://gitlab.com/salvo981/sonicparanoid2 and https://zenodo.org/doi/10.5281/zenodo.11371108 .

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

OpenAlex · 10.1186/s13059-024-03298-4

Cites

4 of 4 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.

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

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.

Cites

Flagged first, then by citations

Research works printed but not linked: 49

  1. [1]Koonin EV. Orthologs, paralogs, and evolutionary genomics. Annu Rev Genet. 2005;39:309–38. 16285863 10.1146/annurev.genet.39.073003.114725 · DOI · Paper page
  2. [2]Li L, Stoeckert CJ, Roos DS. OrthoMCL: identification of ortholog groups for eukaryotic genomes. Genome Res. 2003;13:2178–89. 12952885 10.1101/gr.1224503 PMC403725 · DOI · Paper page
  3. [3]Lechner M, Findeiß S, Steiner L, Marz M, Stadler PF, Prohaska SJ. Proteinortho: detection of (Co-)orthologs in large-scale analysis. BMC Bioinformatics. 2011;12:1–9. 21526987 10.1186/1471-2105-12-124 PMC3114741 · DOI
  4. [4]Sonnhammer ELL, Östlund G. InParanoid 8: orthology analysis between 273 proteomes, mostly eukaryotic. Nucleic Acids Res. 2015;43:D234-9. 25429972 10.1093/nar/gku1203 PMC4383983 · DOI
  5. [5]Nevers Y, Kress A, Defosset A, Ripp R, Linard B, Thompson JD, et al. OrthoInspector 3.0: open portal for comparative genomics. Nucleic Acids Res. 2019;47:D411–8. PMC6323921 30380106
  6. [6]Altenhoff AM, Train C-M, Gilbert KJ, Mediratta I, Mendes de Farias T, Moi D, OMA orthology in, et al. website overhaul, conserved isoforms, ancestral gene order and more. Nucleic Acids Res. 2021;2021(49):D373–9. 10.1093/nar/gkaa1007 PMC7779010 33174605 · DOI
  7. [7]Vilella AJ, Severin J, Ureta-Vidal A, Heng L, Durbin R, Birney E. EnsemblCompara GeneTrees: complete, duplication-aware phylogenetic trees in vertebrates. Genome Res. 2009;19:327–35. 19029536 10.1101/gr.073585.107 PMC2652215 · DOI · Paper page
  8. [8]Mi H, Ebert D, Muruganujan A, Mills C, Albou L-P, Mushayamaha T, et al. PANTHER version 16: a revised family classification, tree-based classification tool, enhancer regions and extensive API. Nucleic Acids Res. 2021;49:D394–403. 33290554 10.1093/nar/gkaa1106 PMC7778891 · DOI
  9. [9]Fuentes D, Molina M, Chorostecki U, Capella-Gutiérrez S, Marcet-Houben M, Gabaldón T. PhylomeDB V5: an expanding repository for genome-wide catalogues of annotated gene phylogenies. Nucleic Acids Res. 2022;50:D1062–8. 34718760 10.1093/nar/gkab966 PMC8728271 · DOI
  10. [11]Chorostecki U, Molina M, Pryszcz LP, Gabaldón T. MetaPhOrs 2.0: integrative, phylogeny-based inference of orthology and paralogy across the tree of life. Nucleic Acids Res. 2020;48:W553–7. PMC7319458 32343307
  11. [12]Kristensen DM, Wolf YI, Mushegian AR, Koonin EV. Computational methods for Gene Orthology inference. Brief Bioinform. 2011;12:379–91. 21690100 10.1093/bib/bbr030 PMC3178053 · DOI
  12. [13]Altenhoff AM, Boeckmann B, Capella-Gutierrez S, Dalquen DA, DeLuca T, Forslund K, et al. Standardized benchmarking in the quest for orthologs. Nat Methods. 2016;13:425–30. 27043882 10.1038/nmeth.3830 PMC4827703 · DOI · Paper page
  13. [14]Sayers EW, Cavanaugh M, Clark K, Pruitt KD, Sherry ST, Yankie L, et al. GenBank 2023 update. Nucleic Acids Res. 2023;51:D141–4. 36350640 10.1093/nar/gkac1012 PMC9825519 · DOI
  14. [15]Steinegger M, Söding J. MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets. Nat Biotechnol. 2017;35:1026–8. 29035372 10.1038/nbt.3988 · DOI · Paper page
  15. [16]Buchfink B, Reuter K, Drost H-G. Sensitive protein alignments at tree-of-life scale using DIAMOND. Nat Methods. 2021;18:366–8. 33828273 10.1038/s41592-021-01101-x PMC8026399 · DOI · Paper page
  16. [17]Camacho C, Coulouris G, Avagyan V, Ma N, Papadopoulos J, Bealer K, et al. BLAST+: architecture and applications. BMC Bioinformatics. 2009;10:421. 20003500 10.1186/1471-2105-10-421 PMC2803857 · DOI · Paper page
  17. [18]Dalquen DA, Dessimoz C. Bidirectional best hits miss many orthologs in duplication-rich clades such as plants and animals. Genome Biol Evol. 2013;5:1800–6. 24013106 10.1093/gbe/evt132 PMC3814191 · DOI · Paper page
  18. [19]Wang M, Caetano-Anollés G. The evolutionary mechanics of domain organization in proteomes and the rise of modularity in the protein world. Structure. 2009;17:66–78. 19141283 10.1016/j.str.2008.11.008 · DOI
  19. [20]Persson E, Kaduk M, Forslund SK, Sonnhammer ELL. Domainoid: domain-oriented orthology inference. BMC Bioinformatics. 2019;20:523. 31660857 10.1186/s12859-019-3137-2 PMC6816169 · DOI
  20. [21]Huang L-C, Taujale R, Gravel N, Venkat A, Yeung W, Byrne DP, et al. KinOrtho: a method for mapping human kinase orthologs across the tree of life and illuminating understudied kinases. BMC Bioinformatics. 2021;22:446. 34537014 10.1186/s12859-021-04358-3 PMC8449880 · DOI
  21. [22]Persson E, Sonnhammer ELL. InParanoiDB 9: ortholog groups for protein domains and full-length proteins. J Mol Biol. 2023;435: 168001. 36764355 10.1016/j.jmb.2023.168001 · DOI
  22. [23]Unsal S, Atas H, Albayrak M, Turhan K, Acar AC, Doğan T. Learning functional properties of proteins with language models. Nat Mach Intell. 2022;4:227–45. 10.1038/s42256-022-00457-9 · DOI
  23. [24]Liu J, Li J, Wang H, Yan J. Application of deep learning in genomics. Sci China Life Sci. 2020;63:1860–78. 33051704 10.1007/s11427-020-1804-5 · DOI
  24. [25]Nissen JN, Johansen J, Allesøe RL, Sønderby CK, Armenteros JJA, Grønbech CH, et al. Improved metagenome binning and assembly using deep variational autoencoders. Nat Biotechnol. 2021;39:555–60. 33398153 10.1038/s41587-020-00777-4 · DOI
  25. [26]Pan S, Zhu C, Zhao X-M, Coelho LP. A deep Siamese neural network improves metagenome-assembled genomes in microbiome datasets across different environments. Nat Commun. 2022;13:2326. 35484115 10.1038/s41467-022-29843-y PMC9051138 · DOI
  26. [29]Sutphin GL, Mahoney JM, Sheppard K, Walton DO, Korstanje R. WORMHOLE: novel least diverged ortholog prediction through machine learning. PLOS Comput Biol. 2016;12: e1005182. 27812085 10.1371/journal.pcbi.1005182 PMC5094675 · DOI
  27. [30]Derelle R, Philippe H, Colbourne JK. Broccoli: combining phylogenetic and network analyses for orthology assignment. Mol Biol Evol. 2020;37:3389–96. 32602888 10.1093/molbev/msaa159 · DOI
  28. [31]Cosentino S, Iwasaki W. SonicParanoid: fast, accurate and easy orthology inference. Bioinformatics. 2019;35:149–51. 30032301 10.1093/bioinformatics/bty631 PMC6298048 · DOI · Paper page
  29. [32]Kuznetsov D, Tegenfeldt F, Manni M, Seppey M, Berkeley M, Kriventseva EV, et al. OrthoDB v11: annotation of orthologs in the widest sampling of organismal diversity. Nucleic Acids Res. 2023;51:D445–51. 36350662 10.1093/nar/gkac998 PMC9825584 · DOI
  30. [33]Freund Y, Schapire RE. A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci. 1997;55:119–39. 10.1006/jcss.1997.1504 · DOI · Paper page
  31. [34]Le Q, Mikolov T. Distributed representations of sentences and documents. Proc 31st Int Conf Mach Learn [Internet]. PMLR; 2014 [cited 2022 Oct 12]. p. 1188–96. Available from: https://proceedings.mlr.press/v32/le14.html
  32. [35]Enright AJ, Van Dongen S, Ouzounis CA. An efficient algorithm for large-scale detection of protein families. Nucleic Acids Res. 2002;30:1575–84. 11917018 10.1093/nar/30.7.1575 PMC101833 · DOI
  33. [36]Linard B, Ebersberger I, McGlynn SE, Glover N, Mochizuki T, Patricio M, et al. Ten years of collaborative progress in the quest for orthologs. Mol Biol Evol. 2021;38:3033–45. 33822172 10.1093/molbev/msab098 PMC8321534 · DOI · Paper page
  34. [37]Nevers Y, Jones TEM, Jyothi D, Yates B, Ferret M, Portell-Silva L, et al. The quest for orthologs orthology benchmark service in 2022. Nucleic Acids Res. 2022;50:W623–32. 35552456 10.1093/nar/gkac330 PMC9252809 · DOI · Paper page
  35. [38]Klemm P, Stadler PF, Lechner M. Proteinortho6: pseudo-reciprocal best alignment heuristic for graph-based detection of (co-)orthologs. Front Bioinforma [Internet]. 2023 [cited 2024 Jan 4];3. Available from: https://www.frontiersin.org/articles/10.3389/fbinf.2023.1322477 PMC10751348 38152702 · DOI
  36. [39]Emms DM, Kelly S. Benchmarking orthogroup inference accuracy: revisiting orthobench. Genome Biol Evol. 2020;12:2258–66. 33022036 10.1093/gbe/evaa211 PMC7738749 · DOI · Paper page
  37. [40]Deutekom ES, Snel B, van Dam TJP. Benchmarking orthology methods using phylogenetic patterns defined at the base of Eukaryotes. Brief Bioinform. 2021;22:bbaa206. PMC8138875 32935832
  38. [41]Mistry J, Chuguransky S, Williams L, Qureshi M, Salazar GA, Sonnhammer ELL, et al. Pfam: the protein families database in 2021. Nucleic Acids Res. 2021;49:D412–9. 33125078 10.1093/nar/gkaa913 PMC7779014 · DOI · Paper page
  39. [42]Dosch J, Bergmann H, Tran V, Ebersberger I. FAS: assessing the similarity between proteins using multi-layered feature architectures. Bioinformatics. 2023;39:btad226. PMC10185405 37084276
  40. [44]Asgari E, Mofrad MRK. Continuous distributed representation of biological sequences for deep proteomics and genomics. PLOS ONE. 2015;10: e0141287. 26555596 10.1371/journal.pone.0141287 PMC4640716 · DOI
  41. [46]Nayfach S, Roux S, Seshadri R, Udwary D, Varghese N, Schulz F, et al. A genomic catalog of Earth’s microbiomes. Nat Biotechnol. 2021;39:499–509. 33169036 10.1038/s41587-020-0718-6 PMC8041624 · DOI
  42. [47]Bowers RM, Kyrpides NC, Stepanauskas R, Harmon-Smith M, Doud D, Reddy TBK, et al. Minimum information about a single amplified genome (MISAG) and a metagenome-assembled genome (MIMAG) of bacteria and archaea. Nat Biotechnol. 2017;35:725–31. 28787424 10.1038/nbt.3893 PMC6436528 · DOI · Paper page
  43. [48]Altenhoff AM, Garrayo-Ventas J, Cosentino S, Emms D, Glover NM, Hernández-Plaza A, et al. The Quest for Orthologs benchmark service and consensus calls in 2020. Nucleic Acids Res. 2020;48:W538–45. 32374845 10.1093/nar/gkaa308 PMC7319555 · DOI
  44. [49]Behnel S, Bradshaw R, Citro C, Dalcin L, Seljebotn DS, Smith K. Cython: the best of both worlds. Comput Sci Eng. 2011;13:31–9. 10.1109/MCSE.2010.118 · DOI
  45. [50]Radim Rehurek PS. Software framework for topic modelling with large corpora. Proc LREC 2010 Workshop New Chall NLP Framew. 2010. p. 46–50.
  46. [52]Mikolov T, Chen K, Corrado G, Dean J. Efficient estimation of word representations in vector space [Internet]. arXiv; 2013 [cited 2022 Oct 31]. Available from: http://arxiv.org/abs/1301.3781 · arXiv
  47. [53]Melidis DP, Nejdl W. Capturing protein domain structure and function using self-supervision on domain architectures. Algorithms. 2021;14:28. 10.3390/a14010028 · DOI
  48. [54]Cosentino S, Sriswasdi S, Iwasaki W. SonicParanoid2: fast, accurate, and comprehensive orthology inference with machine learning and language models. Zenodo. 2024. https://zenodo.org/doi/10.5281/zenodo.11371108 PMC11270883 39054525 · DOI
  49. [55]Cosentino S, Sriswasdi S, Iwasaki W. SonicParanoid2: fast, accurate, and comprehensive orthology inference with machine learning and language models. Zenodo. 2024. https://zenodo.org/doi/10.5281/zenodo.11361984 PMC11270883 39054525 · DOI

Cited by

Sorted by citations

Authors
Cosentino, S., Sriswasdi, S., & Iwasaki, W.
Affiliations
  • The University of Tokyo (JP)
  • Chulalongkorn University (TH)
  • Institute for Quantitative Biosciences, The University of Tokyo (JP)
Corresponding author
Wataru Iwasaki
ORCID
Venue
Genome biology
Publisher
Springer Science and Business Media LLC
Published
2024-07-25
Volume
25
Issue
1
Pages
195-195
ISSN
  • 1465-6906 (ISSN-L)
  • 1474-760X
DOI
10.1186/s13059-024-03298-4
PMC
PMC11270883
OpenAlex
W4400987661
Cited by
50
References
4
Citations by year
2026: 19 · 2025: 23 · 2024: 7 · 2023: 1
FWCI
6.67
Type
journal article
Language
en
Open access
Licence
Locations
  • Genome biology (publishedVersion, cc-by)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
Funders
  • JSPS KAKENHI (16H06279, 19H05688, 22H04925)
  • JST CREST (JPMJCR19S2)
  • MEXT (JPMXD1521474594)
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Phylogenetic Studies
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Bioinformatics and Genomic Networks
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Fractal and DNA sequence analysis
Keywords
orthology inference, ortholog prediction, gradient boosting, language models, protein domain architecture, comparative genomics, evolutionary genomics, benchmark dataset
MeSH terms
Machine Learning, Humans, Software, Sequence Alignment, Genomics

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