Biology subjects

Shen, L.-C.

Publications and source records attributed to Shen, L.-C..

3 recordsLinked to original sources

bioRxiv2025

Self-iterative multiple instance learning enables the prediction of CD4+ T cell immunogenic epitopes

Accurately predicting the antigen presentation to CD4+ T cells and subsequent induction of immune response is fundamentally important for vaccine development, autoimmune disease treatments, and cancer neoepitope identification. In immunopeptidomics, single-allelic data are highly specific but limited in allele scope, while multi-allelic data contain broader coverage at the cost of weakly labeling. Existing computational approaches either overlook the massive multi-allelic data or introduce label ambiguity due to inadequate modeling strategies. Here, we introduce ImmuScope, a weakly supervised deep-learning framework integrating precise MHC-II antigen presentation, CD4+ T cell epitopes, and immunogenicity predictions. ImmuScope leverages self-iterative multiple-instance learning with positive-anchor triplet loss to explore peptide-MHC-II (pMHC-II) binding from weakly labeled multi-allelic data and single-allelic data, comprising over 600,000 ligands across 142 alleles. Moreover, ImmuScope can also interpret the MHC-II binding specificity and motif deconvolution of immunopeptidomics data. We successfully applied ImmuScope to discover melanoma neoantigens, revealing variations in pMHC-II binding and immunogenicity upon epitope mutations. We further employed ImmuScope to assess the effects of SARS-CoV-2 epitope mutations on immune escape, with its predictions aligned well with experimentally determined immune escape dynamics. Overall, ImmuScope provides a comprehensive solution for CD4+ T cell antigen recognition and immunogenicity assessment, with broad potential for advancing vaccine design and personalized immunotherapy.

bioinformatics↗

bioRxiv2024

scRCA: a Siamese network-based pipeline for the annotation of cell types using imperfect single-cell RNA-seq reference data

A critical step in the analysis of single-cell transcriptomic (scRNA-seq) data is the accurate identification and annotation of cell types. Such annotation is usually conducted by comparative analysis with known (reference) data sets - which assumes an accurate representation of cell types within the reference sample. However, this assumption is often incorrect, because factors, such as human errors in the laboratory or in silico, and methodological limitations, can ultimately lead to annotation errors in a reference dataset. As current pipelines for single-cell transcriptomic analysis do not adequately consider this challenge, there is a major demand for a computational pipeline that achieves high-quality cell type annotation using imperfect reference datasets that contain inherent errors (often referred to as "noise"). Here, we built a Siamese network-based pipeline, termed scRCA, that achieves an accurate annotation of cell types employing imperfect reference data. For researchers to decide whether to trust the scRCA annotations, an interpreter was developed to explore the factors on which the scRCA model makes its predictions. We also implemented 3 noise-robust losses-based cell type methods to improve the accuracy using imperfect dataset. Benchmarking experiments showed that scRCA outperforms the proposed noise-robust loss-based methods and methods commonly in use for cell type annotation using imperfect reference data. Importantly, we demonstrate that scRCA can overcome batch effects induced by distinctive single cell RNA-seq techniques. We anticipate that scRCA (https://github.com/LMC0705/scRCA) will serve as a practical tool for the annotation of cell types, employing a reference dataset-based approach.

bioinformatics↗

bioRxiv2023

ConBoTNet: supervised contrastive learning enhances MHC-II peptide binding affinity prediction

Accurate prediction of major histocompatibility complex (MHC)-peptide binding affinity can improve our understanding of cellular immune responses and guide personalized immunotherapies. Nevertheless, the existing deep learning-based approaches for predicting MHC-II peptide interactions fall short of satisfactory performance and offer restricted model interpretability. In this study, we propose a novel deep neural network, termed ConBoTNet, to address the above issues by introducing the designed supervised contrastive learning and bottleneck transformer extractors. Specifically, the supervised contrastive learning pre-training enhances the models representative and generalizable capabilities on MHC-II peptides by pulling positive pairs closer and pushing negative pairs further in the feature space, while the bottleneck transformer module focuses on MHC-II peptide interactions to precisely identify binding cores and anchor positions in an unsupervised manner. Extensive experiments on benchmark datasets under 5-fold cross-validation, leave-one-molecule-out validation, independent testing, and binding core prediction settings highlighted the superiority of our proposed ConBoTNet over current state-of-the-art methods. Data distribution analysis in the latent feature space demonstrated that supervised contrastive learning can aggregate MHC-II-peptide samples with similar affinity labels and learn common features of similar affinity. Additionally, we interpreted the trained neural network by associating the attention weights with peptides and innovatively find both well-established and potential peptide motifs. This work not only introduces an innovative tool for accurately predicting MHC-II peptide affinity, but also provides new insights into a new paradigm for modeling essential biological interactions, advancing data-driven discovery in biomedicine.

bioinformatics↗