CoChat
Sign Up
Cited by 1Genomics and Rare DiseasesProtein Structure and DynamicsMachine Learning in Bioinformatics

The DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.

ASCARIS: Positional feature annotation and protein structure-based representation of single amino acid variations

Open access
Cankara, Fatma, Doğan, Tunca·2023·Computational and Structural Biotechnology Journal
DOI 10.1016/j.csbj.2023.09.017PMC PMC10562615

Published version of a preprint

Open this paper in CoChat — free accountOpen PDF

Abstract

Background: Genomic variations may cause deleterious effects on protein functionality and perturb biological processes. Elucidating the effects of variations is critical for developing novel treatment strategies for diseases of genetic origin. Computational approaches have been aiding the work in this field by modeling and analyzing the mutational landscape. However, new approaches are required, especially for accurate representation and data-centric analysis of sequence variations. Method: In this study, we propose ASCARIS (Annotation and StruCture-bAsed RepresentatIon of Single amino acid variations), a method for the featurization (i.e., quantitative representation) of single amino acid variations (SAVs), which could be used for a variety of purposes, such as predicting their functional effects or building multi-omics-based integrative models. ASCARIS utilizes the direct and spatial correspondence between the location of the SAV on the sequence/structure and 30 different types of positional feature annotations (e.g., active/lipidation/glycosylation sites; calcium/metal/DNA binding, inter/transmembrane regions, etc.), along with structural features and physicochemical properties. The main novelty of this method lies in constructing reusable numerical representations of SAVs via functional annotations. Results: We statistically analyzed the relationship between these features and the consequences of variations and found that each carries information in this regard. To investigate potential applications of ASCARIS, we trained variant effect prediction models that utilize our SAV representations as input. We carried out an ablation study and a comparison against the state-of-the-art methods and observed that ASCARIS has a competing and complementary performance against widely-used predictors. ASCARIS can be used alone or in combination with other approaches to represent SAVs from a functional perspective. ASCARIS is available as a programmatic tool at https://github.com/HUBioDataLab/ASCARIS and as a web-service at https://huggingface.co/spaces/HUBioDataLab/ASCARIS.

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 · 10.1016/j.csbj.2023.09.017

Cites

5 of 5 references verified0 citation errors · 0 not checkable

Statistics

Figures

Graphical abstract
Graphical abstract CC BY-NC-ND · PubMed Central
Fig. 1 The overall workflow of the proposed variant featurization/representation method, ASCARIS, together with its application to the problem of variant effect prediction.
Fig. 1 The overall workflow of the proposed variant featurization/representation method, ASCARIS, together with its application to the problem of variant effect prediction.CC BY-NC-ND · PubMed Central
Fig. 2 Dataset construction and featurization steps: (a) the sources of structural information and statistics about the data from each source, (b) the representation of different types of features on SAV representations, (c) mapping of positional sequence annotations and the SAV onto the 3-D protein structure, and part of the SAV feature vector that corresponds to these annotations.
Fig. 2 Dataset construction and featurization steps: (a) the sources of structural information and statistics about the data from each source, (b) the representation of different types of features on SAV representations, (c) mapping of positional sequence annotations and the SAV onto the 3-D protein structure, and part of the SAV feature vector that corresponds to these annotations.CC BY-NC-ND · PubMed Central
Fig. 3 . (a) Distribution of neutral and deleterious SAV data points according to their domain region correspondence. Mutations found within the domains tend to be more deleterious (61.3%) compared to the ones outside (30.6%), (b) distribution of neutral and deleterious SAV data points according to their location on the structure of the protein. Mutations found within the core and interface regions tend to be more deleterious (71.7% and 69.4%, respectively) compared to the ones on the surface (48.6%).
Fig. 3 . (a) Distribution of neutral and deleterious SAV data points according to their domain region correspondence. Mutations found within the domains tend to be more deleterious (61.3%) compared to the ones outside (30.6%), (b) distribution of neutral and deleterious SAV data points according to their location on the structure of the protein. Mutations found within the core and interface regions tend to be more deleterious (71.7% and 69.4%, respectively) compared to the ones on the surface (48.6%).CC BY-NC-ND · PubMed Central
Fig. 4 . (a) The coverage of each annotation category on the proteins in our SAV dataset (e.g., nearly 23% of proteins in our dataset have at least one active site annotation in UniProtKB), (b) the rates of deleterious vs neutral variations for each annotation category, which are calculated considering the SAV data points in our dataset that coincide with a positional annotation on the same residue, (c) Mean spatial distances between annotated residues and mutated residues in the structure, calculated independently for each annotation category, considering the cases in which the SAV and annotated residue do not coincide on the same residue. In the case of the existence of multiple annotations on a protein, only the annotation that is located spatially closest to the mutation of interest is taken into account. Dashed lines indicate overall averages calculated by taking the mean of all distances. For the calculation of Euclidean distances between residues, the coordinates of C⍺ of the respective amino acids are extracted from PDB models.
Fig. 4 . (a) The coverage of each annotation category on the proteins in our SAV dataset (e.g., nearly 23% of proteins in our dataset have at least one active site annotation in UniProtKB), (b) the rates of deleterious vs neutral variations for each annotation category, which are calculated considering the SAV data points in our dataset that coincide with a positional annotation on the same residue, (c) Mean spatial distances between annotated residues and mutated residues in the structure, calculated independently for each annotation category, considering the cases in which the SAV and annotated residue do not coincide on the same residue. In the case of the existence of multiple annotations on a protein, only the annotation that is located spatially closest to the mutation of interest is taken into account. Dashed lines indicate overall averages calculated by taking the mean of all distances. For the calculation of Euclidean distances between residues, the coordinates of C⍺ of the respective amino acids are extracted from PDB models.CC BY-NC-ND · PubMed Central
Fig. 5 Performance results (AUROC) of ASCARIS and 46 different VEPs from the literature, on the deep mutational scanning data. AUROC scores indicate the success of methods in distinguishing deleterious (pathogenic) SAVs from the neutral (benign) ones on the; (a) BRCA1, (b) CALM1, and (c) P53 genes. The number of test SAVs for each class are shown in plot titles. ASCARIS scores are shown in blue colored bars (DMS: deep mutational scanning, Supervised: machine learning -ML- models that learns from labeled samples, Unsupervised: ML models that learns from evolutionary conservation and multiple sequence alignments, Empirical: different from ML models, these are VEPs that rely on empirical calculations, Metapredictor: mostly supervised ML models that utilize the results of other VEPs as its input).
Fig. 5 Performance results (AUROC) of ASCARIS and 46 different VEPs from the literature, on the deep mutational scanning data. AUROC scores indicate the success of methods in distinguishing deleterious (pathogenic) SAVs from the neutral (benign) ones on the; (a) BRCA1, (b) CALM1, and (c) P53 genes. The number of test SAVs for each class are shown in plot titles. ASCARIS scores are shown in blue colored bars (DMS: deep mutational scanning, Supervised: machine learning -ML- models that learns from labeled samples, Unsupervised: ML models that learns from evolutionary conservation and multiple sequence alignments, Empirical: different from ML models, these are VEPs that rely on empirical calculations, Metapredictor: mostly supervised ML models that utilize the results of other VEPs as its input).CC BY-NC-ND · PubMed Central

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

Research works printed but not linked: 82

  1. Hindorff L.A., Sethupathy P., Junkins H.A., Ramos E.M., Mehta J.P., Collins F.S. and Manolio T.A.: Potential etiologic and functional implications of genome-wide association loci for human diseases and traits. Proc Natl Acad Sci USA 2009; 106: 9362. · DOI · Paper page
  2. Fariselli P., Martelli P.L., Savojardo C. and Casadio R.: INPS: predicting the impact of non-synonymous variations on protein stability from sequence. Bioinformatics 2015; 31: 2816. · DOI
  3. Datta A., Mazumder M.H., Chowdhury A.S. and Hasan M.A.: Functional and structural consequences of damaging single nucleotide polymorphisms in human prostate cancer predisposition gene RNASEL. Biomed Res Int 2015; 2015: 271458. · DOI
  4. 10.1038/nature13835 · DOI · Paper page
  5. 10.1038/10297 · DOI
  6. 10.1038/nrg.2015.17 · DOI
  7. 10.1016/j.cell.2014.01.051 · DOI
  8. 10.1038/s41437-018-0104-z · DOI
  9. 10.1038/s42256-022-00457-9 · DOI
  10. 10.1002/humu.21047 · DOI
  11. 10.1038/nmeth0410-248 · DOI · Paper page
  12. Adzhubei I., Jordan D.M. and Sunyaev S.R.: Predicting functional effect of human missense mutations using PolyPhen-2. Curr Protoc Hum Genet, Chapter 2013; 7. Unit7.20.
  13. Bromberg Y. and Rost B.: SNAP: predict effect of non-synonymous polymorphisms on function. Nucleic Acids Res 2007; 35: 3823. · DOI
  14. Bromberg Y., Yachdav G. and Rost B.: SNAP predicts effect of mutations on protein function. Bioinformatics 2008; 24: 2397. · DOI
  15. 10.1158/0008-5472.CAN-09-1133 · DOI
  16. Chennen K., Weber T., Lornage X., Kress A., Böhm J., Thompson J., Laporte J. and Poch O.: MISTIC: A prediction tool to reveal disease-relevant deleterious missense variants. PLoS One 2020; 15: e0236962. · DOI
  17. 10.1093/bioinformatics/btv195 · DOI
  18. Clifford R.J., Edmonson M.N., Nguyen C. and Buetow K.H.: Large-scale analysis of non-synonymous coding region single nucleotide polymorphisms. Bioinformatics 2004; 20: 1006. · DOI
  19. Kaminker J.S., Zhang Y., Watanabe C. and Zhang Z.: CanPredict: a computational tool for predicting cancer-associated missense mutations. Nucleic Acids Res 2007; 35: W595. · DOI
  20. 10.1093/nar/gkg509 · DOI
  21. Pandurangan A.P. and Blundell T.L.: Prediction of impacts of mutations on protein structure and interactions: SDM, a statistical approach, and mCSM, using machine learning. Protein Sci 2020; 29: 247. · DOI
  22. 10.1093/bioinformatics/btt691 · DOI · Paper page
  23. 10.1093/bioinformatics/btw361 · DOI
  24. 10.1093/nar/gky1016 · DOI · Paper page
  25. 10.1038/nmeth.2890 · DOI · Paper page
  26. 10.1002/humu.20896 · DOI
  27. Topham C.M., Srinivasan N. and Blundell T.L.: Prediction of the stability of protein mutants based on structural environment-dependent amino acid substitution and propensity tables. Protein Eng 1997; 10: 7. · DOI
  28. 10.1093/nar/gkr363 · DOI
  29. Yang Y., Chen B., Tan G., Vihinen M. and Shen B.: Structure-based prediction of the effects of a missense variant on protein stability. Amino Acids 2013; 44: 847. · DOI
  30. 10.1016/j.jmb.2005.12.025 · DOI
  31. 10.1002/mgg3.214 · DOI
  32. Tan K.P., Kanitkar T.R., Kwoh C.K. and Madhusudhan M.S.: Packpred: predicting the functional effect of missense mutations. Front Mol Biosci 2021; 8: 646288. · DOI
  33. 10.1371/journal.pcbi.1007775 · DOI
  34. 10.1016/j.jmb.2019.04.009 · DOI
  35. Marquet C., Heinzinger M., Olenyi T., Dallago C., Erckert K., Bernhofer M., Nechaev D. and Rost B.: Embeddings from protein language models predict conservation and variant effects. Hum Genet 2022; 141: 1629. · DOI
  36. Meier J., Rao R., Verkuil R., Liu J., Sercu T. and Rives A.: Language models enable zero-shot prediction of the effects of mutations on protein function. bioRxiv 2021; . 2021.2007.2009.450648.
  37. Brandes N., Goldman G., Wang C.H., Ye C.J. and Ntranos V.: Genome-wide prediction of disease variants with a deep protein language model. bioRxiv 2022; 2022. 2008.2025.505311..
  38. 10.1093/nar/gky1049 · DOI · Paper page
  39. Kulmanov M. and Hoehndorf R.: DeepGOPlus: improved protein function prediction from sequence. Bioinformatics 2020; 36: 422. · DOI
  40. Rifaioglu A.S., Dogan T., Sarac O.S., Ersahin T., Saidi R., Atalay M.V., Martin M.J. and Cetin-Atalay R.: Large-scale automated function prediction of protein sequences and an experimental case study validation on PTEN transcript variants. Proteins 2018; 86: 135. · DOI
  41. Dogan T.: HPO2GO: prediction of human phenotype ontology term associations for proteins using cross ontology annotation co-occurrences. PeerJ 2018; 6: e5298. · DOI
  42. 10.1186/1471-2164-14-S3-S6 · DOI
  43. 10.1093/nar/gkx1153 · DOI · Paper page
  44. Kawabata T., Ota M. and Nishikawa K.: The Protein Mutant Database. Nucleic Acids Res 1999; 27: 355. · DOI
  45. Mudunuri U., Che A., Yi M. and Stephens R.M.: bioDBnet: the biological database network. Bioinformatics 2009; 25: 555. · DOI
  46. 10.1093/nar/28.1.235 · DOI · Paper page
  47. 10.1093/nar/gky427 · DOI
  48. 10.1093/nar/gkt1144 · DOI
  49. 10.1093/nar/gky1100 · DOI · Paper page
  50. Aboderin A.A.: An empirical hydrophobicity scale for α-amino-acids and some of its applications. Int J Biochem 1971; 2: 537. · DOI
  51. Goldsack D.E. and Chalifoux R.C.: Contribution of the free energy of mixing of hydrophobic side chains to the stability of the tertiary structure of proteins. J Theor Biol 1973; 39: 645. · DOI
  52. 10.1126/science.185.4154.862 · DOI
  53. Capriotti E., Ozturk K. and Carter H.: Integrating molecular networks with genetic variant interpretation for precision medicine. Wiley Interdiscip Rev Syst Biol Med 2019; 11: e1443. · DOI
  54. Engin H.B., Hofree M. and Carter H.: Identifying mutation specific cancer pathways using a structurally resolved protein interaction network. Pac Symp Biocomput 2015; : 84.
  55. 10.1073/pnas.0403255101 · DOI
  56. 10.1371/journal.pone.0066273 · DOI
  57. 10.12688/f1000research.7931.1 · DOI
  58. Momen-Roknabadi A., Sadeghi M., Pezeshk H. and Marashi S.-A.: Impact of residue accessible surface area on the prediction of protein secondary structures. BMC Bioinforma 2008; 9: 357. · DOI
  59. 10.1038/nmeth.4540 · DOI
  60. Breiman L.: Mach Learn 2001; 45: 261. · DOI
  61. Dasgupta A., Sun Y.V., König I.R., Bailey-Wilson J.E. and Malley J.D.: Brief review of regression-based and machine learning methods in genetic epidemiology: the Genetic Analysis Workshop 17 experience. Genet Epidemiol 2011; 35: S5. · DOI
  62. 10.1006/jcss.1997.1504 · DOI · Paper page
  63. Friedman J., Hastie T. and Tibshirani R.: Additive logistic regression: a statistical view of boosting (With discussion and a rejoinder by the authors). Ann Stat 2000; 28. · DOI · Paper page
  64. N. Cristianini J. Shawe-Taylor An Introduction to Support Vector Machines and Other Kernel-based Learning Methods 2000. · DOI · Paper page
  65. Hastie T., Friedman J. and Tibshirani R.: The Elements of Statistical Learning. : Springer Series in Statistics, 2001. · DOI · Paper page
  66. Doğan T., MacDougall A., Saidi R., Poggioli D., Bateman A., O'Donovan C. and Martin M.J.: UniProt-DAAC: domain architecture alignment and classification, a new method for automatic functional annotation in UniProtKB. Bioinformatics 2016; 32: 2264. · DOI
  67. 10.1002/humu.23738 · DOI
  68. 10.1002/bies.201600062 · DOI
  69. 10.1016/j.molp.2016.06.004 · DOI
  70. Cox M.A.A. and Cox T.F.: Multidimensional Scaling. Handb Data Vis 2008; : 315.
  71. van der M. and Geoffrey Hinton L.: Visualizing Data using t-SNE. J Mach Learn Res 2008; 9: 2579.
  72. 10.1101/gr.3804205 · DOI
  73. Doğan T., Akhan Güzelcan E., Baumann M., Koyas A., Atas H., Baxendale I.R., Martin M. and Cetin-Atalay R.: Protein domain-based prediction of drug/compound–target interactions and experimental validation on LIM kinases. PLOS Comput Biol 2021; 17: e1009171. · DOI
  74. Consortium G.P., Auton A., Brooks L., Durbin R., Garrison E. and Kang H.: A global reference for human genetic variation. Nature 2015; 526: 68. · DOI · Paper page
  75. Heberle H., Meirelles G.V., da Silva F.R., Telles G.P. and Minghim R.: InteractiVenn: a web-based tool for the analysis of sets through Venn diagrams. BMC Bioinforma 2015; 16: 169. · DOI
  76. 10.1002/humu.22768 · DOI · Paper page
  77. Livesey B.J. and Marsh J.A.: Using deep mutational scanning to benchmark variant effect predictors and identify disease mutations. Mol Syst Biol 2020; 16: e9380. · DOI
  78. Karczewski K. and Francioli L.: The genome aggregation database (gnomAD). MacArthur Lab 2017; : 1.
  79. 10.1002/ppul.22567 · DOI
  80. Bhattacharyya S. and Tobacman J.K.: Arylsulfatase B regulates colonic epithelial cell migration by effects on MMP9 expression and RhoA activation. Clin Exp Metastas-- 2009; 26: 535. · DOI
  81. Karageorgos L., Brooks D.A., Pollard A., Melville E.L., Hein L.K., Clements P.R., Ketteridge D., Swiedler S.J., Beck M., Giugliani R., Harmatz P., Wraith J.E., Guffon N., Leao Teles E., Sa Miranda M.C. and Hopwood J.J.: Mutational analysis of 105 mucopolysaccharidosis type VI patients. Hum Mutat 2007; 28: 897. · DOI
  82. 10.1093/nar/gkab543 · DOI

Metadata

Authors
Cankara, F., & Doğan, T.
Affiliations
  • Koç University (TR)
  • Hacettepe University (TR)
Corresponding author
Doğan, Tunca
ORCID
Venue
Computational and Structural Biotechnology Journal
Publisher
American Association for the Advancement of Science (AAAS)
Published
2023-01
Volume
21
Pages
4743-4758
ISSN
2001-0370 (ISSN-L)
DOI
10.1016/j.csbj.2023.09.017
PMC
PMC10562615
OpenAlex
W4386813159
Cited by
1
References
5
Citations by year
2026: 1
FWCI
0.17
Type
journal article
Language
en
Open access
Licence
Locations
  • Computational and Structural Biotechnology Journal (publishedVersion, cc-by-nc-nd)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
  • Digital Collections portal (Koç University) (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
Koç Üniversitesi
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Genetics › Genomics and Rare Diseases
  • 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
Keywords
variant effect prediction, protein structure, functional annotation, protein binding sites, physicochemical properties, multi-omics integration, Ascaris

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