Mechanistic diversity in MHC class I antigen recognition.

Throughout its evolution, the human immune system has developed a plethora of strategies to diversify the antigenic peptide sequences that can be targeted by the CD8+ T cell response against pathogens and aberrations of self. Here we provide a general overview of the mechanisms that lead to the diversity of antigens presented by MHC class I complexes and their recognition by CD8+ T cells, together with a more detailed analysis of recent progress in two important areas that are highly controversial: the prevalence and immunological relevance of unconventional antigen peptides; and cross-recognition of antigenic peptides by the T cell receptors of CD8+ T cells.

Bronchiectasis in the Kimberley region of Western Australia.

OBJECTIVE: To review the work-up and inpatient management of non-cystic fibrosis bronchiectasis exacerbations against best practice guidelines in the Kimberley, a remote region of Western Australia, with the ultimate goal of improving treatment in the region.^ DESIGN: Retrospective cohort study and audit of remote adult bronchiectasis hospital admissions between 2011 and 2016. SETTING: Remote hospital inpatients. PARTICIPANTS: Thirty-two patients and 110 hospital admissions were included. Patients were ≥15 years old, had computed tomography confirmed bronchiectasis and at least one hospital admission for acute respiratory illness prior to January 2011. MAIN OUTCOMES MEASURED: The 5-year mortality and compliance to a Lung Foundation position statement on non-cystic fibrosis bronchiectasis which suggests investigating for an underlying cause at diagnosis and during exacerbations prolonged antibiotics (10-14 days) and prolonged hospital admissions (≥7 days) are required. RESULTS: The overall 5-year mortality was 21.8%, with the median age at death of 37 years (interquartile range, 27-63). The median duration of hospital admission was shorter than the recommended 3 days (interquartile range, 2-5) with 11 of 100 (11%) patients admitted for ≥7 days. The median duration of antibiotics was also shorter than the recommended 7 days (interquartile range, 4-10), with 31 of the 98 (32%) patients prescribed ≥10 days and 6 of the 98 (6%) prescribed ≥14 days of therapy. CONCLUSION: We found under-treatment and under-investigation of non-cystic fibrosis bronchiectasis in the Kimberley region. Five-year mortality was high, consistent with other rural Australian Indigenous cohorts.§ Following this audit, a strategy to improve awareness, as well as update and promote regional guidelines has been developed.

Building Representation Learning Models for Antibody Comprehension.

Antibodies are versatile proteins with both the capacity to bind a broad range of targets and a proven track record as some of the most successful therapeutics. However, the development of novel antibody therapeutics is a lengthy and costly process. It is challenging to predict the functional and biophysical properties of antibodies from their amino acid sequence alone, requiring numerous experiments for full characterization. Machine learning, specifically deep representation learning, has emerged as a family of methods that can complement wet lab approaches and accelerate the overall discovery and engineering process. Here, we review advances in antibody sequence representation learning, and how this has improved antibody structure prediction and facilitated antibody optimization. We discuss challenges in the development and implementation of such models, such as the lack of publicly available, well-curated antibody function data and highlight opportunities for improvement. These and future advances in machine learning for antibody sequences have the potential to increase the success rate in developing new therapeutics, resulting in broader access to transformative medicines and improved patient outcomes.

Deciphering the language of antibodies using self-supervised learning.

An individual's B cell receptor (BCR) repertoire encodes information about past immune responses and potential for future disease protection. Deciphering the information stored in BCR sequence datasets will transform our understanding of disease and enable discovery of novel diagnostics and antibody therapeutics. A key challenge of BCR sequence analysis is the prediction of BCR properties from their amino acid sequence alone. Here, we present an antibody-specific language model, Antibody-specific Bidirectional Encoder Representation from Transformers (AntiBERTa), which provides a contextualized representation of BCR sequences. Following pre-training, we show that AntiBERTa embeddings capture biologically relevant information, generalizable to a range of applications. As a case study, we fine-tune AntiBERTa to predict paratope positions from an antibody sequence, outperforming public tools across multiple metrics. To our knowledge, AntiBERTa is the deepest protein-family-specific language model, providing a rich representation of BCRs. AntiBERTa embeddings are primed for multiple downstream tasks and can improve our understanding of the language of antibodies.