The AIRR Community is pleased to announce the addition of a new Type 1 Diabetes (T1D) focused repository in the AIRR Data Commons. This is a collaboration between the iReceptor team (Simon Fraser University), The Sugar Science group, the Aaron Michels Lab (University of Colorado), and the Todd Brusko Lab (University of Florida) among others. This repository contains the first fully HLA/MHC genotyped study that adheres to the the AIRR v1.4 MHC genotype standard, with over 62 million annotated sequences from 359 repertoires from the Mitchell et al. longitudinal study of TCR repertoires (TRB locus) in children who progressed to T1D. This new T1D AIRR-seq data is searchable through the iReceptor Gateway and there is of course more T1D data to come from this collaboration. We encourage the community to share this valuable type of data!
A new episode of #OnAIRR – the podcast of the AIRR Community is now available. Prof Ralf Küppers, @UniklinikEssen, Germany discusses AIRR-Seq in understanding B cell lymphomas. Building upon Ralf’s background in B cell differentiation in health and pathogenesis of human B cell lymphomas, we discuss how micro-dissection and Sanger sequencing is still the method of choice when analysing Hodgkin lymphoma and the V-gene usage and mutations in CLL as prognostic indicators before talking about tracking pathogenic clones when surveying for relapse during clinical follow up.
Subscribe and listen in your favourite app or check out all of the On AIRR episodes here: http://onairr.airr-community.org
Interested in studies of the adaptive immune receptor repertoire (AIRR)? Catch up on the latest in this new episode of On AIRR – An AIRR-C Podcast Series. Dr. Ulrik Stervbo and Dr. Zhaoqing Ding sit down with Vadim Nazarov the Co-Founder & CEO of the startup ImmunoMind to discuss the use of AI for repertoire insights.
Check out On AIRR Podcast #9 The ImmunoMind or wielding an AI for repertoire insights with Vadim Nazarov.
Machine learning for the analysis of adaptive immune receptors and repertoires
Adaptive immune receptor repertoires (AIRRs) capture past and present immune responses and therefore represent a powerful resource for developing diagnostics and therapeutics. Machine learning (ML) has the ability to discover complex sequence patterns and help further these diagnostic and therapeutic aims. However, to exploit these opportunities, it is necessary to overcome the intrinsic challenges of AIRR data: unknown rules determining antigen binding, high diversity and specificity of receptors with low overlap between AIRRs, and low signal-to-noise ratio. Further, different ML approaches need to be validated and compared before they could be deployed in practice. In this webinar, we will focus on standardized and reproducible ML workflows, benchmarking, and comparison of AIRR ML approaches. We will argue for the use of simulation for validation and benchmarking of ML methods before moving to experimental datasets.
Maria Chernigovskaya is a PhD candidate supervised by Prof. Victor Greiff and Prof. Geir Kjetil Sandve at the University of Oslo, Norway. Maria is working on a methodology for simulating synthetic adaptive immune receptor repertoire (AIRR) datasets to guide the development and benchmarking of AIRR-based machine learning.
Milena Pavlović is a postdoctoral researcher in the Sandve lab at the University of Oslo working on machine learning, causal inference, and their application to biomedical domains. During her PhD, Milena developed the immuneML platform (https://immuneml.uio.no) for the analysis of adaptive immune receptors and repertoires (AIRR), focusing on model robustness and reproducibility, and examined how the knowledge of the data generating process and the causal inference framework could improve AIRR machine learning diagnostics.
The AIRR Community is pleased to announce the release of v1.4 of the AIRR Standards, including v1.2 of the AIRR Data Commons API (ADC API) to query AIRR compliant data repositories. This release enables additional compatibility with single-cell and emerging technologies, supports extended data/metadata capture, and improves data standardization and integration. Major changes include updated quantification fields and conversion of several fields to ontology references to provide consistency across studies.
Several exciting experimental releases are included in this update: new Germline and Genotype schemas for documenting VDJ germline reference sequences and subject VDJ and MHC genotypes, extensions to the Cell schema for storing single-cell gene expression and receptor reactivity, and data aggregation schemas to facilitate more complex and reproducible analyses.
The ADC API specification included in this release contains new capabilities for querying AIRR v1.4 Schema objects including Clone, Cell, CellExpression, and Receptor objects.
Check out these key links: