PiTE: TCR-epitope Binding Affinity Prediction Pipeline using Transformer-based Sequence Encoder.

Accurate prediction of TCR binding affinity to a target antigen is important for development of immunotherapy strategies. Recent computational methods were built on various deep neural networks and used the evolutionary-based distance matrix BLOSUM to embed amino acids of TCR and epitope sequences to numeric values. A pre-trained language model of amino acids is an alternative embedding method where each amino acid in a peptide is embedded as a continuous numeric vector. Little attention has yet been given to summarize the amino-acid-wise embedding vectors to sequence-wise representations. In this paper, we propose PiTE, a two-step pipeline for the TCR-epitope binding affinity prediction. First, we use an amino acids embedding model pre-trained on a large number of unlabeled TCR sequences and obtain a real-valued representation from a string representation of amino acid sequences. Second, we train a binding affinity prediction model that consists of two sequence encoders and a stack of linear layers predicting the affinity score of a given TCR and epitope pair. In particular, we explore various types of neural network architectures for the sequence encoders in the two-step binding affinity prediction pipeline. We show that our Transformer-like sequence encoder achieves a state-of-the-art performance and significantly outperforms the others, perhaps due to the model's ability to capture contextual information between amino acids in each sequence. Our work highlights that an advanced sequence encoder on top of pre-trained representation significantly improves performance of the TCR-epitope binding affinity prediction.

ATM-TCR: TCR-Epitope Binding Affinity Prediction Using a Multi-Head Self-Attention Model.

TCR-epitope pair binding is the key component for T cell regulation. The ability to predict whether a given pair binds is fundamental to understanding the underlying biology of the binding mechanism as well as developing T-cell mediated immunotherapy approaches. The advent of large-scale public databases containing TCR-epitope binding pairs enabled the recent development of computational prediction methods for TCR-epitope binding. However, the number of epitopes reported along with binding TCRs is far too small, resulting in poor out-of-sample performance for unseen epitopes. In order to address this issue, we present our model ATM-TCR which uses a multi-head self-attention mechanism to capture biological contextual information and improve generalization performance. Additionally, we present a novel application of the attention map from our model to improve out-of-sample performance by demonstrating on recent SARS-CoV-2 data.

A mixture model to detect edges in sparse co-expression graphs with an application for comparing breast cancer subtypes.

We develop a method to recover a gene network's structure from co-expression data, measured in terms of normalized Pearson's correlation coefficients between gene pairs. We treat these co-expression measurements as weights in the complete graph in which nodes correspond to genes. To decide which edges exist in the gene network, we fit a three-component mixture model such that the observed weights of 'null edges' follow a normal distribution with mean 0, and the non-null edges follow a mixture of two lognormal distributions, one for positively- and one for negatively-correlated pairs. We show that this so-called L2 N mixture model outperforms other methods in terms of power to detect edges, and it allows to control the false discovery rate. Importantly, our method makes no assumptions about the true network structure. We demonstrate our method, which is implemented in an R package called edgefinder, using a large dataset consisting of expression values of 12,750 genes obtained from 1,616 women. We infer the gene network structure by cancer subtype, and find insightful subtype characteristics. For example, we find thirteen pathways which are enriched in each of the cancer groups but not in the Normal group, with two of the pathways associated with autoimmune diseases and two other with graft rejection. We also find specific characteristics of different breast cancer subtypes. For example, the Luminal A network includes a single, highly connected cluster of genes, which is enriched in the human diseases category, and in the Her2 subtype network we find a distinct, and highly interconnected cluster which is uniquely enriched in drug metabolism pathways.

Multiview Cluster Analysis Identifies Variable Corticosteroid Response Phenotypes in Severe Asthma.

Rationale: Corticosteroids (CSs) are the most effective asthma therapy, but responses are heterogeneous and systemic CSs lead to long-term side effects. Therefore, an improved understanding of the contributing factors in CS responses could enhance precision management. Although several factors have been associated with CS responsiveness, no integrated/cluster approach has yet been undertaken to identify differential CS responses. Objectives: To identify asthma subphenotypes with differential responses to CS treatment using an unsupervised multiview learning approach. Methods: Multiple-kernel k-means clustering was applied to 100 clinical, physiological, inflammatory, and demographic variables from 346 adult participants with asthma in the Severe Asthma Research Program with paired (before and 2-3 weeks after triamcinolone administration) sputum data. Machine-learning techniques were used to select the top baseline variables that predicted cluster assignment for a new patient. Measurements and Main Results: Multiple-kernel clustering revealed four clusters of individuals with asthma and different CS responses. Clusters 1 and 2 consisted of young, modestly CS-responsive individuals with allergic asthma and relatively normal lung function, separated by contrasting sputum neutrophil and macrophage percentages after CS treatment. The subjects in cluster 3 had late-onset asthma and low lung function, high baseline eosinophilia, and the greatest CS responsiveness. Cluster 4 consisted primarily of young, obese females with severe airflow limitation, little eosinophilic inflammation, and the least CS responsiveness. The top 12 baseline variables were identified, and the clusters were validated using an independent Severe Asthma Research Program test set. Conclusions: Our machine learning-based approaches provide new insights into the mechanisms of CS responsiveness in asthma, with the potential to improve disease treatment.

Phosphoproteomic Analysis of the Amygdala Response to Adolescent Glucocorticoid Exposure Reveals G-Protein Coupled Receptor Kinase 2 as a Target for Reducing Motivation for Alcohol.

Early life stress is associated with risk for developing alcohol use disorders (AUDs) in adulthood. Though the neurobiological mechanisms underlying this vulnerability are not well understood, evidence suggests that aberrant glucocorticoid and noradrenergic system functioning play a role. The present study investigated the long-term consequences of chronic exposure to elevated glucocorticoids during adolescence on the risk of increased alcohol-motivated behavior, and on amygdalar function in adulthood. A discovery-based analysis of the amygdalar phosphoproteome using mass spectrometry was employed, to identify changes in function. Adolescent corticosterone (CORT) exposure increased alcohol, but not sucrose, self-administration, and enhanced stress-induced reinstatement with yohimbine in adulthood. Phosphoproteomic analysis indicated that the amygdala phosphoproteome was significantly altered by adolescent CORT exposure, generating a list of potential novel mechanisms involved in the risk of alcohol drinking. In particular, increased phosphorylation at serines 296⁻299 on the α2A adrenergic receptor (α2AAR), mediated by the G-protein coupled receptor kinase 2 (GRK2), was evident after adolescent CORT exposure. We found that intra-amygdala infusion of a peptidergic GRK2 inhibitor reduced alcohol seeking, as measured by progressive ratio and stress reinstatement tests, and induced by the α2AAR antagonist yohimbine. These results suggest that GRK2 represents a novel target for treating stress-induced motivation for alcohol which may counteract alterations in brain function induced by adolescent stress exposure.

Ethnic variability in the allelic distribution of pharmacogenes between Korean and other populations.

OBJECTIVE: We examined the differences in allele frequencies for pharmacogenes among the Korean (KOR), Chinese (CHB), Japanese (JPT), Caucasian (CEU), and Nigerian (YRI) populations. METHODS: Fifty-seven pharmacogenes were selected from the imputed Korean Association REsource and HapMap databases. Minor allele frequencies were analyzed using the sample size-modified single nucleotide polymorphism-specific fixation index (FST) and the χ-test with Bonferroni's correction. Geneset analysis was also carried out to identify pharmacogenes that have significantly different allele frequencies among the various populations tested. RESULTS: The KOR population was the most divergent group from the YRI population (FST: 0.079) but very similar to the CHB and JPT populations (FST: 0.003). VKORC1 showed a large population divergence in the KOR-YRI (0.439) comparison. CYP3A4 was also highly divergent in the KOR-YRI (FST: 0.361) comparison. The calcium signaling pathway gene set was divergent in all pairwise population comparisons. CONCLUSION: In terms of the 57 pharmacogenes studied, there were no significant differences among the KOR, CHB, and JPT populations. However, the YRI and CEU populations were significantly differentiated from the three Eastern Asian groups. Future pharmacogenomics studies can utilize the polymorphisms identified in this study, as these variants may have important implications for the selection of highly informative single nucleotide polymorphisms for future clinical trials.