TCR-Seq Identifies Distinct Repertoires of Distant-Metastatic and Nondistant-Metastatic Thyroid Tumors

DeepLION2: deep multi-instance contrastive learning framework enhancing the prediction of cancer-associated T cell receptors by attention strategy on motifs

Introduction

T cell receptor (TCR) repertoires provide valuable insights into complex human diseases, including cancers. Recent advancements in immune sequencing technology have significantly improved our understanding of TCR repertoire. Some computational methods have been devised to identify cancer-associated TCRs and enable cancer detection using TCR sequencing data. However, the existing methods are often limited by their inadequate consideration of the correlations among TCRs within a repertoire, hindering the identification of crucial TCRs. Additionally, the sparsity of cancer-associated TCR distribution presents a challenge in accurate prediction.

Methods

To address these issues, we presented DeepLION2, an innovative deep multi-instance contrastive learning framework specifically designed to enhance cancer-associated TCR prediction. DeepLION2 leveraged content-based sparse self-attention, focusing on the top k related TCRs for each TCR, to effectively model inter-TCR correlations. Furthermore, it adopted a contrastive learning strategy for bootstrapping parameter updates of the attention matrix, preventing the model from fixating on non-cancer-associated TCRs.

Results

Extensive experimentation on diverse patient cohorts, encompassing over ten cancer types, demonstrated that DeepLION2 significantly outperformed current state-of-the-art methods in terms of accuracy, sensitivity, specificity, Matthews correlation coefficient, and area under the curve (AUC). Notably, DeepLION2 achieved impressive AUC values of 0.933, 0.880, and 0.763 on thyroid, lung, and gastrointestinal cancer cohorts, respectively. Furthermore, it effectively identified cancer-associated TCRs along with their key motifs, highlighting the amino acids that play a crucial role in TCR-peptide binding.

Conclusion

These compelling results underscore DeepLION2's potential for enhancing cancer detection and facilitating personalized cancer immunotherapy. DeepLION2 is publicly available on GitHub, at https://github.com/Bioinformatics7181/DeepLION2, for academic use only.

DeepLION: Deep Multi-Instance Learning Improves the Prediction of Cancer-Associated T Cell Receptors for Accurate Cancer Detection

Recent studies highlight the potential of T cell receptor (TCR) repertoires in accurately detecting cancers via noninvasive sampling. Unfortunately, due to the complicated associations among cancer antigens and the possible induced T cell responses, currently, the practical strategy for identifying cancer-associated TCRs is the computational prediction based on TCR repertoire data. Several state-of-the-art methods were proposed in recent year or two; however, the prediction algorithms were still weakened by two major issues. To facilitate the computational processes, the algorithms prefer to decompose the original TCR sequences into length-fixed amino acid fragments, while the first dilemma comes as the lengths of cancer-associated motifs are suggested to be various. Moreover, the correlations among TCRs in the same repertoire should be further considered, which are often ignored by the existing methods. We here developed a deep multi-instance learning method, named DeepLION, to improve the prediction of cancer-associated TCRs by considering these issues. First, DeepLION introduced a deep learning framework with alternative convolution filters and 1-max pooling operations to handle the amino acid fragments with different lengths. Then, the multi-instance learning framework modeled the TCR correlations and assigned adjusted weights for each TCR sequence during the predicting process. To validate the performance of DeepLION, we conducted a series of experiments on several cohorts of patients from nine cancer types. Compared to the existing methods, DeepLION achieved, on most of the cohorts, higher prediction accuracies, sensitivities, specificities, and areas under the curve (AUCs), where the AUC reached notably 0.97 and 0.90 for thyroid and lung cancer cohorts, respectively. Thus, DeepLION may further support the detection of cancers from TCR repertoire data. DeepLION is publicly available on GitHub, at https://github.com/Bioinformatics7181/DeepLION, for academic usage only.

Identification and validation of potential novel biomarkers to predict distant metastasis in differentiated thyroid cancer

Background

Distant metastasis (DM) is not common in differentiated thyroid cancer (DTC). However, it is associated with a significantly poor prognosis. Early detection of high-risk DTC patients is difficult, and the molecular mechanism is still unclear. Therefore, the present study aims to establish a novel predictive model based on clinicopathological parameters and DM-related gene signatures to provide guidelines for clinicians in decision making.

Methods

Weighted gene co-expression network analysis (WGCNA) was performed to discover co-expressed gene modules and hub genes associated with DM. Univariate and multivariate analyses were carried out to identify independent clinicopathological risk factors based on The Cancer Genome Atlas (TCGA) database. An integrated nomogram prediction model was established. Finally, real hub genes were validated using the GSE60542 database and various thyroid cell lines.

Results

The midnightblue module was most significantly positively correlated with DM (R=0.56, P=9e-06) by as per WGCNA. DLX5 (AUC: 0.769), COX6B2 (AUC: 0.764), and LYPD1 (AUC: 0.760) were determined to be the real hub genes that play a crucial role in predicting DM. Meanwhile, univariate and multivariate analyses demonstrated that T-stage (OR, 15.03; 95% CI, 1.75-319.40; and P=0.024), histologic subtype (OR, 0.17; 95% CI, 0.03-0.92; and P=0.042) were the independent predictors of DM. Subsequently, a nomogram model was constructed based on gene signatures and independent clinical risk factors exhibited good performance. Additionally, the mRNA expressions of real hub genes in the GSE60542 dataset were consistent with TCGA.

Conclusions

The present study has provided a reliable model to predict DM in patients with DTC. This model is likely to serve as an individual risk assessment tool in therapeutic decision-making.