BIITE: A Tool to Determine HLA Class II Epitopes from T Cell ELISpot Data

Boelen, Lies; O'Neill, Patrick; Quigley, Kathryn; Reynolds, Catherine J.; Maillère, Bernard; Robinson, John H.; Lertmemongkolchai, Ganjana; Altmann, Daniel M.; Boyton, Rosemary J.; Asquith, Becca

doi:10.1371/journal.pcbi.1004796

Cited by 4 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…6c-e). This limitation is consistent with the fact that presentation of antigens is essential but not sufficient for induction of robust T cell responses 51,55,58 (Supplementary Note 2). Therefore, by combining deep learning 59 and large-scale T cell response data, we envision that a future method will provide refined predictions for the immunogenicity of HLA ligands, whether autoantigens relevant for autoimmunity, alloantigens relevant to transplantation or as vaccine candidates relevant for diverse applications.…”

Section: Discussionsupporting

confidence: 75%

Predicting HLA class II antigen presentation through integrated deep learning

et al. 2019

View full text Add to dashboard Cite

Accurate prediction of antigen presentation by human leukocyte antigen (HLA) class II molecules would be valuable for vaccine development and cancer immunotherapies. Current computational methods trained on in vitro binding data are limited by insufficient training data and algorithmic constraints. Here we describe MARIA (major histocompatibility complex analysis with recurrent integrated architecture; https://maria.stanford.edu/), a multimodal recurrent neural network for predicting the likelihood of antigen presentation from a gene of interest in the context of specific HLA class II alleles. In addition to in vitro binding measurements, MARIA is trained on peptide HLA ligand sequences identified by mass spectrometry, expression levels of antigen genes and protease cleavage signatures. Because it leverages these diverse training data and our improved machine learning framework, MARIA (area under the curve = 0.89-0.92) outperformed existing methods in validation datasets. Across independent cancer neoantigen studies, peptides with high MARIA scores are more likely to elicit strong CD4 + T cell responses. MARIA allows identification of immunogenic epitopes in diverse cancers and autoimmune disease.

show abstract

Section: Discussionsupporting

confidence: 75%

Predicting HLA class II antigen presentation through integrated deep learning

et al. 2019

View full text Add to dashboard Cite

show abstract

“…While the case for host-dependent selection pressure is a difficult one to make for Bp, it is noteworthy that p6, a T cell epitope highlighted in the present study, as in our earlier work, was found to have been deleted from a pathogenic, clinical isolate from Cambodia 14 . Although the Bp immunome is clearly large and complex, the definition of highly immunodominant, common, peptide-HLA complexes offers the potential for developments in future immune monitoring of immune status 12 – 14 , 22 , 23 . A new tool developed from analysis of Bp pMHC and Pseudomonas aerguniosa 24 pMHC complexes in responder datasets is BIITE, a means of elucidating likely pMHC combinations out of bulk PBMC responses in HLA-heterozygous individuals who will be expressing multiple HLA class II heterodimers to present peptide 23 .…”

Section: Discussionmentioning

confidence: 99%

“…Although the Bp immunome is clearly large and complex, the definition of highly immunodominant, common, peptide-HLA complexes offers the potential for developments in future immune monitoring of immune status 12 – 14 , 22 , 23 . A new tool developed from analysis of Bp pMHC and Pseudomonas aerguniosa 24 pMHC complexes in responder datasets is BIITE, a means of elucidating likely pMHC combinations out of bulk PBMC responses in HLA-heterozygous individuals who will be expressing multiple HLA class II heterodimers to present peptide 23 . AhpC, and specifically, the p6 epitope from this antigen, stand out as a part of the Bp immunome that is highly visible to the T cell repertoire.…”

Section: Discussionmentioning

confidence: 99%

Infection with Burkholderia pseudomallei – immune correlates of survival in acute melioidosis

Dunachie

Jenjaroen

Reynolds

et al. 2017

Sci Rep

Self Cite

View full text Add to dashboard Cite

Melioidosis, caused by Burkholderia pseudomallei, is a potentially lethal infection with no licensed vaccine. There is little understanding of why some exposed individuals have no symptoms, while others rapidly progress to sepsis and death, or why diabetes confers increased susceptibility. We prospectively recruited a cohort of 183 acute melioidosis patients and 21 control subjects from Northeast Thailand and studied immune parameters in the context of survival status and the presence or absence of diabetes. HLA-B*46 (one of the commonest HLA class I alleles in SE Asia) and HLA-C*01 were associated with an increased risk of death (odds ratio 2.8 and 3.1 respectively). Transcriptomic analysis during acute infection in diabetics indicated the importance of interplay between immune pathways including those involved in antigen presentation, chemotaxis, innate and adaptive immunity and their regulation. Survival was associated with enhanced T cell immunity to nine of fifteen immunodominant antigens analysed including AhpC (BPSL2096), BopE (BPSS1525), PilO (BPSS1599), ATP binding protein (BPSS1385) and an uncharacterised protein (BPSL2520). T cell immunity to GroEL (BPSL2697) was specifically impaired in diabetic individuals. This characterization of immunity associated with survival during acute infection offers insights into correlates of protection and a foundation for design of an effective multivalent vaccine.

show abstract

“…In this section, we use the master equation (19) for the evolution of the probability density p t (σ), to derive dynamical equations for the macroscopic parameters m(σ) = (m 1 (σ), . .…”

Section: Appendix Kramers-moyal Expansion Of the Master Equationmentioning

confidence: 99%

“…However, they normally ignore microscopic details and stochasticity, due to noise in the biological environment or fluctuations in cellular densities, and generally require the estimation of a large number of unknown parameters. Agent-based simulations [12][13][14][15] and machine learning approaches [16][17][18][19] have been successful in incorporating statistical noise and microscopic information (e.g. cellular interactions, antibodies sequences etc), however, they usually require more significant computational efforts.…”

Section: Introductionmentioning

confidence: 99%

The role of the T-helper/T-suppressor ratio in the adaptive immune response: a dynamical model

Annibale¹,

Dziobek-Garrett²,

Tari³

2018

J. Phys. A: Math. Theor.

View full text Add to dashboard Cite

Recent experimental studies have suggested the ratio between T-helper and T-suppressor lymphocytes as an index of immunosuppression in HIV, cancer, immunosenescence and inflammatory and auto-immune diseases. However, a quantitative understanding of the impact of this ratio on the immune response has lagged behind data and its validity as a tool for prognostic monitoring or therapeutic target remains an open question. In this work, we use statistical physics and dynamical systems approaches to analyze the time-dependent response to an antigen, of a simplified model of the adaptive immune system, which comprises B, T-helper and T-suppressor lymphocytes. The model is remarkably robust against changes in the noise level and kinetic parameters, but it is very sensitive to changes in the ratio between T-helper and T-suppressor lymphocytes, exhibiting, in particular, a transition from a responsive to an immuno-suppressed phase, as the ratio is lowered below a critical value, which is in line with experiments. This result supports the validity of the T-helper/T-suppressor ratio as an index of immunosuppression and may provide a useful theoretical benchmark to interpret and compare experiments.

show abstract

BIITE: A Tool to Determine HLA Class II Epitopes from T Cell ELISpot Data

Cited by 4 publications

References 21 publications

Predicting HLA class II antigen presentation through integrated deep learning

Predicting HLA class II antigen presentation through integrated deep learning

Infection with Burkholderia pseudomallei – immune correlates of survival in acute melioidosis

The role of the T-helper/T-suppressor ratio in the adaptive immune response: a dynamical model

Contact Info

Product

Resources

About