Deep generative selection models of T and B cell receptor repertoires with soNNia

Isacchini, Giulio; Walczak, Aleksandra M.; Mora, Thierry; Nourmohammad, Armita

doi:10.1073/pnas.2023141118

Cited by 57 publications

(90 citation statements)

References 67 publications

(82 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning is increasingly used for AIRR classification both on the sequence (Akbar et al 2021;Friedensohn et al 2020;Isacchini et al 2021;Greiff et al 2017b) and repertoire-level (Shemesh et al 2021;Emerson et al 2017;Sidhom et al 2021;Pavlović et al 2021). Future studies will need to investigate whether differences in RGM also impact repertoire classification (Greiff et al 2020).…”

Section: Discussionmentioning

confidence: 99%

Individualized VDJ recombination predisposes the available Ig sequence space

Slabodkin

Chernigovskaya

Mikocziova

et al. 2021

Preprint

View full text Add to dashboard Cite

The process of recombination between variable (V), diversity (D), and joining (J) immunoglobulin (Ig) gene segments determines an individual's naive Ig repertoire, and consequently (auto)antigen recognition. VDJ recombination follows probabilistic rules that can be modeled statistically. So far, it remains unknown whether VDJ recombination rules differ between individuals. If these rules differed, identical (auto)antigen-specific Ig sequences would be generated with individual-specific probabilities, signifying that the available Ig sequence space is individual-specific. We devised a sensitivity-tested distance measure that enables inter-individual comparison of VDJ recombination models. We discovered, accounting for several sources of noise as well as allelic variation in Ig sequencing data, that not only unrelated individuals but also human monozygotic twins and even inbred mice possess statistically distinguishable immunoglobulin recombination models. This suggests that, in addition to genetic, there is also non-genetic modulation of VDJ recombination. We demonstrate that population-wide individualized VDJ recombination can result in orders of magnitude of difference in the probability to generate (auto)antigen-specific Ig sequences. Our findings have implications for immune receptor-based individualized medicine approaches relevant to vaccination, infection, and autoimmunity.

show abstract

Section: Discussionmentioning

confidence: 99%

Individualized VDJ recombination predisposes the available Ig sequence space

Slabodkin

Chernigovskaya

Mikocziova

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…These two levels of selection make sequence features of functional lineage progenitors distinct from the pool of unproductive BCRs that reflects biases of the generation process prior to any selection. In addition, differential selection on receptor features can be used to quantify a distance between repertoires of different cohorts that reflect their functional differences in responses to immune challenges (Isacchini et al, 2021).…”

Section: Differential Selection On B-cell Repertoires In Response To Sars-cov-2 Longer Hcdr3mentioning

confidence: 99%

“…We characterized the probability to observe a clonal lineage ancestor in the periphery as post (σ) ∼ gen (σ) ]^: features`^( a) , which deviates from the inferred generation probability of the receptor gen (σ) by selection factors 5 ( ) (Isacchini et al, 2020a(Isacchini et al, , 2020b(Isacchini et al, , 2021Sethna et al, 2020). These selection factors 5 ( ) depend on sequence features, including IGHVgene and IGHJ-gene usages, HCDR3 length, and amino acid preferences at different positions in the HCDR3 (Methods) (Elhanati et al, 2014;Isacchini et al, 2020aIsacchini et al, , 2020bIsacchini et al, , 2021Marcou et al, 2018;Sethna et al, 2020). Importantly, the inferred selection models are robust to the differences in the sample size of the repertoires, as long as enough data is available to train the models (Methods and Fig.…”

Section: Differential Selection On B-cell Repertoires In Response To Sars-cov-2 Longer Hcdr3mentioning

confidence: 99%

See 1 more Smart Citation

Dynamics of B-cell repertoires and emergence of cross-reactive responses in COVID-19 patients with different disease severity

Montague

Otwinowski

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

COVID-19 patients show varying severity of the disease ranging from asymptomatic to requiring intensive care. Although a number of monoclonal antibodies against SARS-CoV-2 have been identified, we still lack an understanding of the overall landscape of B-cell receptor (BCR) repertoires in COVID-19 patients. Here, we used high-throughput sequencing of BCR repertoires collected over multiple time points during an infection to characterize statistical and dynamical signatures of the B-cell response to SARS-CoV-2 in 19 patients with different disease severities. Based on principled statistical approaches, we determined differential sequence features of BCRs associated with different disease severity. We identified 34 significantly expanded rare clonal lineages shared among patients as candidates for a specific response to SARS-CoV-2. Moreover, we identified natural emergence of a BCR with cross-reactivity to SARS-CoV and SARS-CoV-2 in a number of patients. Overall, our results provide important insights for development of rational therapies and vaccines against COVID-19.

show abstract

“…For bioinformatics applications, several software tools (e.g., IMGT/HighV-QUEST (11), IgBLAST (12), MiXCR (13), etc.) have been developed to extract quantitative repertoire information from NGS data, and modeling of the dynamics of T cell repertoire generation and selection is also being actively studied (14,15,16,17). For example, a mathematical model of recombination successfully classifies public and private TCRs (18).…”

Section: Introductionmentioning

confidence: 99%

MotifBoost: k-mer based data-efficient immune repertoire classification method

Katayama

Kobayashi

2021

Preprint

View full text Add to dashboard Cite

The repertoire of T cell receptors encodes various types of immunological information. Machine learning is indispensable for decoding such information from repertoire datasets measured by next-generation sequencing. In particular, the classiﬁcation of repertoires is the most basic task, which is relevant for a variety of scientiﬁc and clinical problems. Supported by the recent appearance of large datasets, efﬁcient but data-expensive methods have been proposed. However, it is unclear whether they can work efficiently when the available sample size is severely restricted as in practical situations. In this study, we demonstrate that the their performances are impaired catastrophically below critical sample sizes. To overcome this, we propose MotifBoost, which exploits the information of short motifs of TCRs. MotifBoost can perform the classiﬁcation as efﬁciently as a deep learning method on large datasets while providing more stable and reliable results on small datasets. We also clarify that the robustness of MotifBoost can be attributed to the efﬁciency of motifs as representation features of repertoires. Finally, by comparing predictions of these methods, we show that the whole sequence identity and sequence motifs encode partially different information and that a combination of such complementary information is necessary for further development of repertoire analysis.

show abstract

Deep generative selection models of T and B cell receptor repertoires with soNNia

Cited by 57 publications

References 67 publications

Individualized VDJ recombination predisposes the available Ig sequence space

Individualized VDJ recombination predisposes the available Ig sequence space

Dynamics of B-cell repertoires and emergence of cross-reactive responses in COVID-19 patients with different disease severity

MotifBoost: k-mer based data-efficient immune repertoire classification method

Contact Info

Product

Resources

About