Statistical classifiers for diagnosing disease from immune repertoires: a case study using multiple sclerosis
Open accessAbstract
BACKGROUND: Deep sequencing of lymphocyte receptor repertoires has made it possible to comprehensively profile the clonal composition of lymphocyte populations. This opens the door for novel approaches to diagnose and prognosticate diseases with a driving immune component by identifying repertoire sequence patterns associated with clinical phenotypes. Indeed, recent studies support the feasibility of this, demonstrating an association between repertoire-level summary statistics (e.g., diversity) and patient outcomes for several diseases. In our own prior work, we have shown that six codons in VH4-containing genes in B cells from the cerebrospinal fluid of patients with relapsing remitting multiple sclerosis (RRMS) have higher replacement mutation frequencies than observed in healthy controls or patients with other neurological diseases. However, prior methods to date have been limited to focusing on repertoire-level summary statistics, ignoring the vast amounts of information in the millions of individual immune receptors comprising a repertoire. We have developed a novel method that addresses this limitation by using innovative approaches for accommodating the extraordinary sequence diversity of immune receptors and widely used machine learning approaches. We applied our method to RRMS, an autoimmune disease that is notoriously difficult to diagnose. RESULTS: We use the biochemical features encoded by the complementarity determining region 3 of each B cell receptor heavy chain in every patient repertoire as input to a detector function, which is fit to give the correct diagnosis for each patient using maximum likelihood optimization methods. The resulting statistical classifier assigns patients to one of two diagnosis categories, RRMS or other neurological disease, with 87% accuracy by leave-one-out cross-validation on training data (N = 23) and 72% accuracy on unused data from a separate study (N = 102). CONCLUSIONS: Our method is the first to apply statistical learning to immune repertoires to aid disease diagnosis, learning repertoire-level labels from the set of individual immune repertoire sequences. This method produced a repertoire-based statistical classifier for diagnosing RRMS that provides a high degree of diagnostic capability, rivaling the accuracy of diagnosis by a clinical expert. Additionally, this method points to a diagnostic biochemical motif in the antibodies of RRMS patients, which may offer insight into the disease process.
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
Cites
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?
Statistical classifiers can identify immune profiles of patients with chronic lymphocytic leukemia, multiple sclerosis or influenza from NGS data alone.
“It was demonstrated that statistical classifiers can identify immune profiles of patients with chronic lymphocytic leukemia [220], multiple sclerosis [221] or influenza [222] from NGS data alone.”
From Computational approaches to therapeutic antibody design: established methods and emerging trends (2020) · cites this paper as [221]
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
Diagnostic criteria for multiple sclerosis: 2010 revisions to the McDonald criteria
Polman, C. H., Reingold, S. C., Banwell, B., Clanet, M., Cohen, J. A., Filippi, M., Fujihara, K., Havrdova, E., Hutchinson, M., Kappos, L., et al. (2011) · Annals of Neurology · doi:10.1002/ana.22366 · Cited by 9,802 · see citing works
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G. S., Davis, A., Dean, J., Devin, M., et al. (2016) · arXiv · doi:10.48550/arxiv.1603.04467 · Cited by 9,408 · see citing works
New Multiple Sclerosis Phenotypic Classification
LUBLIN, F. D. (2014) · European Neurology · doi:10.1159/000367614 · Cited by 4,277 · see citing works
IgBLAST: an immunoglobulin variable domain sequence analysis tool
Ye, J., Ma, N., Madden, T., & Ostell, J. M. (2013) · Nucleic Acids Research · doi:10.1093/nar/gkt382 · Cited by 1,161 · see citing works
Heiden, J. A. V., Yaari, G., Uduman, M., Stern, J. N. H., O’Connor, K. C., Hafler, D. A., Vigneault, F., & Kleinstein, S. H. (2014) · Bioinformatics · doi:10.1093/bioinformatics/btu138 · Cited by 469 · see citing works
Solving the protein sequence metric problem
Atchley, W. R., Zhao, J., Fernandes, A. D., & Drüke, T. (2005) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0408677102 · Cited by 452 · see citing works
Revised diagnostic criteria of multiple sclerosis
Milo, R., & Miller, A. (2014) · Autoimmunity Reviews · doi:10.1016/j.autrev.2014.01.012 · Cited by 323 · see citing works
Iglesia, M. D., Vincent, B. G., Parker, J. S., Hoadley, K. A., Carey, L., Perou, C. M., & Serody, J. S. (2014) · Clinical Cancer Research · doi:10.1158/1078-0432.ccr-13-3368 · Cited by 276 · see citing works
Postow, M. A., Manuel, M., Wong, P., Yuan, J., Dong, Z., Liu, C., Perez, S., Tanneau, I., Noel, M., Courtier, A., et al. (2015) · Journal for ImmunoTherapy of Cancer · doi:10.1186/s40425-015-0070-4 · Cited by 232 · see citing works
Practical guidelines for B-cell receptor repertoire sequencing analysis
Yaari, G., & Kleinstein, S. H. (2015) · Genome Medicine · doi:10.1186/s13073-015-0243-2 · Cited by 224 · see citing works
Sequencing the functional antibody repertoire—diagnostic and therapeutic discovery
Robinson, W. H. (2014) · Nature Reviews Rheumatology · doi:10.1038/nrrheum.2014.220 · Cited by 171 · see citing works
Frohman, E. M., Havrdová, E., LUBLIN, F. D., Barkhof, F., Achiron, A., Sharief, M. K., Stüve, O., Racke, M. K., Steinman, L., Weiner, H. L., et al. (2006) · Archives of Neurology · doi:10.1001/archneur.63.4.614 · Cited by 82 · see citing works
Jia, Q., Zhou, J., Chen, G., Shi, Y., Yu, H., Guan, P. F., Lin, R., Jiang, N. J., Yu, P.-W., Li, Q.-J., et al. (2015) · OncoImmunology · doi:10.1080/2162402x.2014.1001230 · Cited by 73 · see citing works
VH4 Gene Segments Dominate the Intrathecal Humoral Immune Response in Multiple Sclerosis
Owens, G. P., Winges, K. M., Ritchie, A. M., Edwards, S. J., Burgoon, M. P., Lehnhoff, L., Nielsen, K., Corboy, J. R., Gilden, D. H., & Bennett, J. L. (2007) · The Journal of Immunology · doi:10.4049/jimmunol.179.9.6343 · Cited by 72 · see citing works
Cameron, E. M., Spencer, S. M., Lazarini, J., Harp, C. T., Ward, E. S., Burgoon, M. P., Owens, G. P., Racke, M. K., Bennett, J. L., Frohman, E. M., et al. (2009) · Journal of Neuroimmunology · doi:10.1016/j.jneuroim.2009.05.014 · Cited by 52 · see citing works
Self-citationQuail, M. A., Smith, M., Jackson, D. K., Leonard, S. R., Skelly, T., Swerdlow, H., Gu, Y., & Ellis, P. (2014) · BMC Genomics · doi:10.1186/1471-2164-15-110 · Cited by 49 · see citing works
Kim, S. S., Richman, D. P., Johnson, W. O., Hald, J. K., & Agius, M. A. (2013) · Multiple Sclerosis Journal · doi:10.1177/1352458513491329 · Cited by 43 · see citing works
A new method to prevent carry-over contaminations in two-step PCR NGS library preparations
Seitz, V., Schaper, S., Dröge, A., Lenze, D., Hummel, M., & Hennig, S. (2015) · Nucleic Acids Research · doi:10.1093/nar/gkv694 · Cited by 42 · see citing works
CSF IgG heavy-chain bias in patients at the time of a clinically isolated syndrome
Bennett, J. L., Haubold, K., Ritchie, A. M., et al. (2008) · Journal of Neuroimmunology · doi:10.1016/j.jneuroim.2008.04.031 · Cited by 37 · see citing works
Luo, W., Ma, L., Wen, Q. P., et al. (2008) · Clinical & Experimental Immunology · doi:10.1111/j.1365-2249.2008.03770.x · Cited by 29 · see citing works
Marrero, I., Hamm, D. E., & Davies, J. D. (2013) · PLoS ONE · doi:10.1371/journal.pone.0076546 · Cited by 26 · see citing works
MSPrecise: A molecular diagnostic test for multiple sclerosis using next generation sequencing
Rounds, W. H., Salinas, E. A., Wilks, T., et al. (2015) · Gene · doi:10.1016/j.gene.2015.07.011 · Cited by 19 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 1
- [11]Kingma D Ba J Adam: A method for stochastic optimization arXiv preprint arXiv 2014 1412 6980
Cited by
Sorted by citations
Computational approaches to therapeutic antibody design: established methods and emerging trends
Norman, R. A., Ambrosetti, F., Bonvin, A. M. J. J., Colwell, L. J., Kelm, S., Kumar, S., & Krawczyk, K. (2020) · Briefings in Bioinformatics · doi:10.1093/bib/bbz095 · Cited by 219 · see citing works
“It was demonstrated that statistical classifiers can identify immune profiles of patients with chronic lymphocytic leukemia [220], multiple sclerosis [221] or influenza [222] from NGS data alone.”
BackgroundMiho, E., Yermanos, A., Weber, C. R., Berger, C. T., Reddy, S. T., & Greiff, V. (2018) · Frontiers in Immunology · doi:10.3389/fimmu.2018.00224 · Cited by 189 · see citing works
Brown, A. J., Snapkov, I., Akbar, R., Pavlović, M., Miho, E., Sandve, G. K., & Greiff, V. (2019) · Molecular Systems Design & Engineering · doi:10.1039/c9me00071b · Cited by 59 · see citing works
Repertoire-based diagnostics using statistical biophysics
Arora, R., Kaplinsky, J., Li, A., & Arnaout, R. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/519108 · Cited by 10 · see citing works
- Authors
- Ostmeyer, J., Christley, S., Rounds, W. H., Toby, I., Greenberg, B. M., Monson, N. L., & Cowell, L. G.
- Affiliations
- The University of Texas Southwestern Medical Center (US)
- Corresponding author
- Cowell, Lindsay G.
- ORCID
- Venue
- BMC Bioinformatics
- Published
- 2017-09-07
- Volume
- 18
- Issue
- 1
- Pages
- 401-401
- ISSN
- 1471-2105 (ISSN-L)
- PMC
- PMC5588725
- OpenAlex
- W2751843937
- Cited by
- 63
- References
- 22
- Citations by year
- 2026: 2 · 2025: 3 · 2024: 2 · 2023: 4 · 2022: 12 · 2021: 14 · 2020: 6 · 2019: 11 · 2018: 7 · 2017: 2
- FWCI
- 5.58
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- BMC Bioinformatics (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- eScholarship (California Digital Library) (submittedVersion)
- eScholarship (California Digital Library) (submittedVersion, cc-by)
- Funders
- National Institute of Allergy and Infectious Diseases (AI097403)
- Cancer Prevention and Research Institute of Texas (RP160157)
- Topics
- Health Sciences › Medicine › Pathology and Forensic Medicine › Multiple Sclerosis Research Studies
- Life Sciences › Immunology and Microbiology › Immunology › T-cell and B-cell Immunology
- Physical Sciences › Engineering › Biomedical Engineering › Artificial Immune Systems Applications
- Keywords
- relapsing-remitting multiple sclerosis, immune repertoire, B cell receptor, CDR3, disease diagnosis, statistical classifiers, maximum likelihood estimation, sequence classification, cerebrospinal fluid, neurological disorders, replacement mutations
- MeSH terms
- Amino Acid Sequence, B-Lymphocytes, Humans, Nervous System Diseases, ROC Curve, Models, Statistical, Area Under Curve, Multiple Sclerosis, Relapsing-Remitting, Complementarity Determining Regions, High-Throughput Nucleotide Sequencing
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
