Cargando…
Immune2vec: Embedding B/T Cell Receptor Sequences in ℝ(N) Using Natural Language Processing
The adaptive branch of the immune system learns pathogenic patterns and remembers them for future encounters. It does so through dynamic and diverse repertoires of T- and B- cell receptors (TCR and BCRs, respectively). These huge immune repertoires in each individual present investigators with the c...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8340020/ https://www.ncbi.nlm.nih.gov/pubmed/34367141 http://dx.doi.org/10.3389/fimmu.2021.680687 |
_version_ | 1783733718800662528 |
---|---|
author | Ostrovsky-Berman, Miri Frankel, Boaz Polak, Pazit Yaari, Gur |
author_facet | Ostrovsky-Berman, Miri Frankel, Boaz Polak, Pazit Yaari, Gur |
author_sort | Ostrovsky-Berman, Miri |
collection | PubMed |
description | The adaptive branch of the immune system learns pathogenic patterns and remembers them for future encounters. It does so through dynamic and diverse repertoires of T- and B- cell receptors (TCR and BCRs, respectively). These huge immune repertoires in each individual present investigators with the challenge of extracting meaningful biological information from multi-dimensional data. The ability to embed these DNA and amino acid textual sequences in a vector-space is an important step towards developing effective analysis methods. Here we present Immune2vec, an adaptation of a natural language processing (NLP)-based embedding technique for BCR repertoire sequencing data. We validate Immune2vec on amino acid 3-gram sequences, continuing to longer BCR sequences, and finally to entire repertoires. Our work demonstrates Immune2vec to be a reliable low-dimensional representation that preserves relevant information of immune sequencing data, such as n-gram properties and IGHV gene family classification. Applying Immune2vec along with machine learning approaches to patient data exemplifies how distinct clinical conditions can be effectively stratified, indicating that the embedding space can be used for feature extraction and exploratory data analysis. |
format | Online Article Text |
id | pubmed-8340020 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-83400202021-08-06 Immune2vec: Embedding B/T Cell Receptor Sequences in ℝ(N) Using Natural Language Processing Ostrovsky-Berman, Miri Frankel, Boaz Polak, Pazit Yaari, Gur Front Immunol Immunology The adaptive branch of the immune system learns pathogenic patterns and remembers them for future encounters. It does so through dynamic and diverse repertoires of T- and B- cell receptors (TCR and BCRs, respectively). These huge immune repertoires in each individual present investigators with the challenge of extracting meaningful biological information from multi-dimensional data. The ability to embed these DNA and amino acid textual sequences in a vector-space is an important step towards developing effective analysis methods. Here we present Immune2vec, an adaptation of a natural language processing (NLP)-based embedding technique for BCR repertoire sequencing data. We validate Immune2vec on amino acid 3-gram sequences, continuing to longer BCR sequences, and finally to entire repertoires. Our work demonstrates Immune2vec to be a reliable low-dimensional representation that preserves relevant information of immune sequencing data, such as n-gram properties and IGHV gene family classification. Applying Immune2vec along with machine learning approaches to patient data exemplifies how distinct clinical conditions can be effectively stratified, indicating that the embedding space can be used for feature extraction and exploratory data analysis. Frontiers Media S.A. 2021-07-22 /pmc/articles/PMC8340020/ /pubmed/34367141 http://dx.doi.org/10.3389/fimmu.2021.680687 Text en Copyright © 2021 Ostrovsky-Berman, Frankel, Polak and Yaari https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Immunology Ostrovsky-Berman, Miri Frankel, Boaz Polak, Pazit Yaari, Gur Immune2vec: Embedding B/T Cell Receptor Sequences in ℝ(N) Using Natural Language Processing |
title | Immune2vec: Embedding B/T Cell Receptor Sequences in ℝ(N) Using Natural Language Processing |
title_full | Immune2vec: Embedding B/T Cell Receptor Sequences in ℝ(N) Using Natural Language Processing |
title_fullStr | Immune2vec: Embedding B/T Cell Receptor Sequences in ℝ(N) Using Natural Language Processing |
title_full_unstemmed | Immune2vec: Embedding B/T Cell Receptor Sequences in ℝ(N) Using Natural Language Processing |
title_short | Immune2vec: Embedding B/T Cell Receptor Sequences in ℝ(N) Using Natural Language Processing |
title_sort | immune2vec: embedding b/t cell receptor sequences in ℝ(n) using natural language processing |
topic | Immunology |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8340020/ https://www.ncbi.nlm.nih.gov/pubmed/34367141 http://dx.doi.org/10.3389/fimmu.2021.680687 |
work_keys_str_mv | AT ostrovskybermanmiri immune2vecembeddingbtcellreceptorsequencesinrnusingnaturallanguageprocessing AT frankelboaz immune2vecembeddingbtcellreceptorsequencesinrnusingnaturallanguageprocessing AT polakpazit immune2vecembeddingbtcellreceptorsequencesinrnusingnaturallanguageprocessing AT yaarigur immune2vecembeddingbtcellreceptorsequencesinrnusingnaturallanguageprocessing |