The immuneML ecosystem for machine learning analysis of adaptive immune receptor repertoires

Milena Pavlović; Lonneke Scheffer; Keshav Motwani; Chakravarthi Kanduri; Radmila Kompova; Nikolay Vazov; Knut Waagan; Fabian L.M. Bernal; Alexandre Almeida Costa; Brian Corrie; Rahmad Akbar; Ghadi S. Al Hajj; Gabriel Balaban; Todd M. Brusko; Maria Chernigovskaya; Scott Christley; Lindsay G. Cowell; Robert Frank; Ivar Grytten; Sveinung Gundersen; Ingrid Hobæk Haff; Eivind Hovig; Ping Han Hsieh; Günter Klambauer; Marieke L. Kuijjer; Christin Lund-Andersen; Antonio Martini; Thomas Minotto; Johan Pensar; Knut Rand; Enrico Riccardi; Philippe A. Robert; Artur Rocha; Andrei Slabodkin; Igor Snapkov; Ludvig M. Sollid; Dmytro Titov; Cédric R. Weber; Michael Widrich; Gur Yaari; Victor Greiff; Geir Kjetil Sandve

doi:10.1038/s42256-021-00413-z

The immuneML ecosystem for machine learning analysis of adaptive immune receptor repertoires

Milena Pavlović, Lonneke Scheffer, Keshav Motwani, Chakravarthi Kanduri, Radmila Kompova, Nikolay Vazov, Knut Waagan, Fabian L.M. Bernal, Alexandre Almeida Costa, Brian Corrie, Rahmad Akbar, Ghadi S. Al Hajj, Gabriel Balaban, Todd M. Brusko, Maria Chernigovskaya, Scott Christley, Lindsay G. Cowell, Robert Frank, Ivar Grytten, Sveinung GundersenIngrid Hobæk Haff, Eivind Hovig, Ping Han Hsieh, Günter Klambauer, Marieke L. Kuijjer, Christin Lund-Andersen, Antonio Martini, Thomas Minotto, Johan Pensar, Knut Rand, Enrico Riccardi, Philippe A. Robert, Artur Rocha, Andrei Slabodkin, Igor Snapkov, Ludvig M. Sollid, Dmytro Titov, Cédric R. Weber, Michael Widrich, Gur Yaari, Victor Greiff, Geir Kjetil Sandve

Bar-Ilan University - The Alexander Kofkin Faculty of Engineering

Research output: Contribution to journal › Article › peer-review

43 Scopus citations

Abstract

Adaptive immune receptor repertoires (AIRR) are key targets for biomedical research as they record past and ongoing adaptive immune responses. The capacity of machine learning (ML) to identify complex discriminative sequence patterns renders it an ideal approach for AIRR-based diagnostic and therapeutic discovery. So far, widespread adoption of AIRR ML has been inhibited by a lack of reproducibility, transparency and interoperability. immuneML (immuneml.uio.no) addresses these concerns by implementing each step of the AIRR ML process in an extensible, open-source software ecosystem that is based on fully specified and shareable workflows. To facilitate widespread user adoption, immuneML is available as a command-line tool and through an intuitive Galaxy web interface, and extensive documentation of workflows is provided. We demonstrate the broad applicability of immuneML by (1) reproducing a large-scale study on immune state prediction, (2) developing, integrating and applying a novel deep learning method for antigen specificity prediction and (3) showcasing streamlined interpretability-focused benchmarking of AIRR ML.

Original language	English
Pages (from-to)	936-944
Number of pages	9
Journal	Nature Machine Intelligence
Volume	3
Issue number	11
DOIs	https://doi.org/10.1038/s42256-021-00413-z
State	Published - Nov 2021

Bibliographical note

Publisher Copyright:
© 2021, The Author(s), under exclusive licence to Springer Nature Limited.

Funding

We acknowledge generous support by The Leona M. and Harry B. Helmsley Charitable Trust (grant number 2019PG-T1D011, to V.G. and T.M.B.), the UiO World-Leading Research Community (to V.G. and L.M.S.), the UiO:LifeScience Convergence Environment Immunolingo (to V.G. and G.K.S.), EU Horizon 2020 iReceptorplus (grant number 825821, to V.G. and L.M.S.), a Research Council of Norway FRIPRO project (grant number 300740, to V.G.), a Research Council of Norway IKTPLUSS project (grant number 311341, to V.G. and G.K.S.), the National Institutes of Health (grant numbers P01 AI042288 and HIRN UG3 DK122638 to T.M.B.) and Stiftelsen Kristian Gerhard Jebsen (K.G. Jebsen Coeliac Disease Research Centre, to L.M.S. and G.K.S.). We acknowledge support from ELIXIR Norway in recognizing immuneML as a national node service.

Funders	Funder number
EU Horizon 2020 iReceptorplus	825821
K.G. Jebsen Coeliac Disease Research Centre
LifeScience Convergence Environment Immunolingo
National Institutes of Health	P01 AI042288, HIRN UG3 DK122638
Leona M. and Harry B. Helmsley Charitable Trust	2019PG-T1D011
Stiftelsen Kristian Gerhard Jebsen
Norges Forskningsråd	300740, 311341

Access to Document

10.1038/s42256-021-00413-z

Cite this

Pavlović, M., Scheffer, L., Motwani, K., Kanduri, C., Kompova, R., Vazov, N., Waagan, K., Bernal, F. L. M., Costa, A. A., Corrie, B., Akbar, R., Al Hajj, G. S., Balaban, G., Brusko, T. M., Chernigovskaya, M., Christley, S., Cowell, L. G., Frank, R., Grytten, I., ... Sandve, G. K. (2021). The immuneML ecosystem for machine learning analysis of adaptive immune receptor repertoires. Nature Machine Intelligence, 3(11), 936-944. https://doi.org/10.1038/s42256-021-00413-z

@article{131127967d354ee8a591b66d1cf7bd19,

title = "The immuneML ecosystem for machine learning analysis of adaptive immune receptor repertoires",

abstract = "Adaptive immune receptor repertoires (AIRR) are key targets for biomedical research as they record past and ongoing adaptive immune responses. The capacity of machine learning (ML) to identify complex discriminative sequence patterns renders it an ideal approach for AIRR-based diagnostic and therapeutic discovery. So far, widespread adoption of AIRR ML has been inhibited by a lack of reproducibility, transparency and interoperability. immuneML (immuneml.uio.no) addresses these concerns by implementing each step of the AIRR ML process in an extensible, open-source software ecosystem that is based on fully specified and shareable workflows. To facilitate widespread user adoption, immuneML is available as a command-line tool and through an intuitive Galaxy web interface, and extensive documentation of workflows is provided. We demonstrate the broad applicability of immuneML by (1) reproducing a large-scale study on immune state prediction, (2) developing, integrating and applying a novel deep learning method for antigen specificity prediction and (3) showcasing streamlined interpretability-focused benchmarking of AIRR ML.",

author = "Milena Pavlovi{\'c} and Lonneke Scheffer and Keshav Motwani and Chakravarthi Kanduri and Radmila Kompova and Nikolay Vazov and Knut Waagan and Bernal, {Fabian L.M.} and Costa, {Alexandre Almeida} and Brian Corrie and Rahmad Akbar and {Al Hajj}, {Ghadi S.} and Gabriel Balaban and Brusko, {Todd M.} and Maria Chernigovskaya and Scott Christley and Cowell, {Lindsay G.} and Robert Frank and Ivar Grytten and Sveinung Gundersen and Haff, {Ingrid Hob{\ae}k} and Eivind Hovig and Hsieh, {Ping Han} and G{\"u}nter Klambauer and Kuijjer, {Marieke L.} and Christin Lund-Andersen and Antonio Martini and Thomas Minotto and Johan Pensar and Knut Rand and Enrico Riccardi and Robert, {Philippe A.} and Artur Rocha and Andrei Slabodkin and Igor Snapkov and Sollid, {Ludvig M.} and Dmytro Titov and Weber, {C{\'e}dric R.} and Michael Widrich and Gur Yaari and Victor Greiff and Sandve, {Geir Kjetil}",

note = "Publisher Copyright: {\textcopyright} 2021, The Author(s), under exclusive licence to Springer Nature Limited.",

year = "2021",

month = nov,

doi = "10.1038/s42256-021-00413-z",

language = "אנגלית",

volume = "3",

pages = "936--944",

journal = "Nature Machine Intelligence",

issn = "2522-5839",

publisher = "Springer International Publishing",

number = "11",

}

Pavlović, M, Scheffer, L, Motwani, K, Kanduri, C, Kompova, R, Vazov, N, Waagan, K, Bernal, FLM, Costa, AA, Corrie, B, Akbar, R, Al Hajj, GS, Balaban, G, Brusko, TM, Chernigovskaya, M, Christley, S, Cowell, LG, Frank, R, Grytten, I, Gundersen, S, Haff, IH, Hovig, E, Hsieh, PH, Klambauer, G, Kuijjer, ML, Lund-Andersen, C, Martini, A, Minotto, T, Pensar, J, Rand, K, Riccardi, E, Robert, PA, Rocha, A, Slabodkin, A, Snapkov, I, Sollid, LM, Titov, D, Weber, CR, Widrich, M, Yaari, G, Greiff, V & Sandve, GK 2021, 'The immuneML ecosystem for machine learning analysis of adaptive immune receptor repertoires', Nature Machine Intelligence, vol. 3, no. 11, pp. 936-944. https://doi.org/10.1038/s42256-021-00413-z

TY - JOUR

T1 - The immuneML ecosystem for machine learning analysis of adaptive immune receptor repertoires

AU - Pavlović, Milena

AU - Scheffer, Lonneke

AU - Motwani, Keshav

AU - Kanduri, Chakravarthi

AU - Kompova, Radmila

AU - Vazov, Nikolay

AU - Waagan, Knut

AU - Bernal, Fabian L.M.

AU - Costa, Alexandre Almeida

AU - Corrie, Brian

AU - Akbar, Rahmad

AU - Al Hajj, Ghadi S.

AU - Balaban, Gabriel

AU - Brusko, Todd M.

AU - Chernigovskaya, Maria

AU - Christley, Scott

AU - Cowell, Lindsay G.

AU - Frank, Robert

AU - Grytten, Ivar

AU - Gundersen, Sveinung

AU - Haff, Ingrid Hobæk

AU - Hovig, Eivind

AU - Hsieh, Ping Han

AU - Klambauer, Günter

AU - Kuijjer, Marieke L.

AU - Lund-Andersen, Christin

AU - Martini, Antonio

AU - Minotto, Thomas

AU - Pensar, Johan

AU - Rand, Knut

AU - Riccardi, Enrico

AU - Robert, Philippe A.

AU - Rocha, Artur

AU - Slabodkin, Andrei

AU - Snapkov, Igor

AU - Sollid, Ludvig M.

AU - Titov, Dmytro

AU - Weber, Cédric R.

AU - Widrich, Michael

AU - Yaari, Gur

AU - Greiff, Victor

AU - Sandve, Geir Kjetil

PY - 2021/11

Y1 - 2021/11

N2 - Adaptive immune receptor repertoires (AIRR) are key targets for biomedical research as they record past and ongoing adaptive immune responses. The capacity of machine learning (ML) to identify complex discriminative sequence patterns renders it an ideal approach for AIRR-based diagnostic and therapeutic discovery. So far, widespread adoption of AIRR ML has been inhibited by a lack of reproducibility, transparency and interoperability. immuneML (immuneml.uio.no) addresses these concerns by implementing each step of the AIRR ML process in an extensible, open-source software ecosystem that is based on fully specified and shareable workflows. To facilitate widespread user adoption, immuneML is available as a command-line tool and through an intuitive Galaxy web interface, and extensive documentation of workflows is provided. We demonstrate the broad applicability of immuneML by (1) reproducing a large-scale study on immune state prediction, (2) developing, integrating and applying a novel deep learning method for antigen specificity prediction and (3) showcasing streamlined interpretability-focused benchmarking of AIRR ML.

AB - Adaptive immune receptor repertoires (AIRR) are key targets for biomedical research as they record past and ongoing adaptive immune responses. The capacity of machine learning (ML) to identify complex discriminative sequence patterns renders it an ideal approach for AIRR-based diagnostic and therapeutic discovery. So far, widespread adoption of AIRR ML has been inhibited by a lack of reproducibility, transparency and interoperability. immuneML (immuneml.uio.no) addresses these concerns by implementing each step of the AIRR ML process in an extensible, open-source software ecosystem that is based on fully specified and shareable workflows. To facilitate widespread user adoption, immuneML is available as a command-line tool and through an intuitive Galaxy web interface, and extensive documentation of workflows is provided. We demonstrate the broad applicability of immuneML by (1) reproducing a large-scale study on immune state prediction, (2) developing, integrating and applying a novel deep learning method for antigen specificity prediction and (3) showcasing streamlined interpretability-focused benchmarking of AIRR ML.

UR - http://www.scopus.com/inward/record.url?scp=85119092036&partnerID=8YFLogxK

U2 - 10.1038/s42256-021-00413-z

DO - 10.1038/s42256-021-00413-z

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

C2 - 37396030

AN - SCOPUS:85119092036

SN - 2522-5839

VL - 3

SP - 936

EP - 944

JO - Nature Machine Intelligence

JF - Nature Machine Intelligence

IS - 11

ER -

The immuneML ecosystem for machine learning analysis of adaptive immune receptor repertoires

Abstract

Bibliographical note

Funding

Access to Document

Other files and links

Fingerprint

Cite this