![]() ![]() ![]() We demonstrate the utility of deep learning to provide an improved ‘featurization’ of the TCR across multiple human and murine datasets, including improved classification of antigen-specific TCRs and extraction of antigen-specific TCRs from noisy single-cell RNA-Seq and T-cell culture-based assays. We present DeepTCR, a suite of unsupervised and supervised deep learning methods able to model highly complex TCR sequencing data by learning a joint representation of a TCR by its CDR3 sequences and V/D/J gene usage. T-cell receptor (TCR) sequencing assesses the diversity of the adaptive immune system and allows for modeling its sequence determinants of antigenicity. The ability to learn complex patterns in data has tremendous implications in immunogenomics. The control group consisted of ACs and normal CD4-positive samples.Deep learning algorithms have been utilized to achieve enhanced performance in pattern-recognition tasks. a–d p-values were calculated by the Wilcoxon-Mann-Whitney (WMW ) test using R. d Gini–Simpson index values for different subtypes of ATL (acute, lymphoma, chronic and smoldering) and control samples were compared. c Gin–Simpson index values for aggressive ATL, indolent ATL and control samples were compared. c, d Estimation of diversity was carried out with the Gini-Simpson index. b The number of clonotypes was compared among different ATL subtypes and the control samples. The differences between the aggressive and indolent types as compared with the control group were also significant. a The number of clonotypes in aggressive ATL was significantly different from that in indolent ATL. a, b The number of clonotypes was compared among the different groups of samples. Genome informatics High-throughput screening.Īnalysis of the number and diversity of clonotypes present in individuals with different clinical subtypes of ATL. Thus, determining monoclonal architecture and clonal diversity by RNA sequencing might be useful for prognostic purposes and for personalizing ATL diagnosis and assessment of treatments. CDR3 sequence length distribution, amino acid conservation and gene usage variability for ATL patients resembled those of peripheral blood cells from ACs and healthy donors. ACs, CD4 -positive samples and smoldering patients showed significantly higher TCR diversity compared with chronic, acute and lymphoma subtypes. Expression of TCRα and TCRβ genes in the dominant clone differed among the samples. ![]() Based on these TCR profiles, CD4-positive cells and ACs showed polyclonal patterns, whereas ATL patients showed oligo- or monoclonal patterns (with 446 average clonotypes across samples). We analyzed 62 sets of high-throughput RNA sequencing data from 59 samples of HTLV-1-infected individuals-asymptomatic carriers (ACs), smoldering, chronic, acute and lymphoma ATL subtypes-and three uninfected controls to evaluate TCR distribution. Here we examined the diversity of TCR clonality and its association with pathogenesis and prognosis in adult T-cell leukemia/lymphoma (ATL), a malignancy caused by infection with human T-cell leukemia virus type-1 (HTLV-1). The TCR repertoire can be altered in the context of infections, malignancies or immunological disorders. High-throughput sequencing technologies now allow examination of antigen receptor repertoires at single-nucleotide and, more recently, single-cell resolution. The diversity of T-cell receptor (TCR) repertoires, as generated by somatic DNA rearrangements, is central to immune system function. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |