Biology subjects

Filippidis, P.

Publications and source records attributed to Filippidis, P..

3 recordsLinked to original sources

bioRxiv2026

Robust semi-supervised scRNA-seq integration from virtual adversarial learning

Single-cell RNA sequencing integration methods that rely solely on transcriptomic data often struggle to preserve fine-grained distinctions between closely related cell subtypes. As a result, cell populations that are separable in the raw data may become over-mixed after integration, reducing biological resolution and interpretability. Incorporating marker gene information can potentially address these issues; however, the variability and complexity of available marker sets limit their effective application. To address this, we introduce scCRAFT+, a semi-supervised integration model that innovatively incorporates marker gene information through Virtual Adversarial Training (VAT). By jointly optimizing marker-derived supervision and transcriptome-wide representations, VAT enforces local prediction smoothness among transcriptionally similar cells, improving robustness to noisy marker annotations while enhancing both integration quality and cell type auto-annotation. This targeted approach significantly enhances annotation accuracy and robustness, particularly when faced with incomplete or incorrect marker gene sets. Benchmarking shows that scCRAFT+ achieves consistently stronger performance than current unsupervised and supervised integration approaches, resulting in improved integration quality and biologically meaningful sub-cell type auto-annotations.

bioinformatics↗

bioRxiv2025

Single cell immunophenotyping identifies CD8+ GZMK+ IFNG+ T cells as a key immune population in cutaneous Lyme disease

The skin lesion erythema migrans (EM) is the first clinical sign of Lyme disease, an infection due to the tick-transmitted bacterium Borrelia burgdorferi (Bb). Previously, we used scRNA-Seq to characterize the cutaneous immune response in the EM lesion, focusing on B cells. Here, with an expanded sample size, we profiled T cell responses in EM lesions compared to autologous uninvolved skin. In addition to CD4+ T cell subsets known to be abundant in the EM, we identified clonal expansion of CD8+ GZMK+ IFNG+ T cells that exhibited significant differential expression of interferon-regulated genes. This subset included IFNG+ cells with low cytotoxic gene expression, which may promote inflammation. While FOXP3+ regulatory T cells were also increased in EM, they exhibited little IL10 expression. In contrast, a CD4+ FOXP3- tissue-resident T cell subset contained the largest population of cells with IL10 expression. Fibroblasts, endothelial cells, and pericytes were the principal cells that significantly differentially expressed key T cell-recruiting chemokines. These studies represent the first comprehensive interrogation of the cutaneous T cell response to Bb infection using single cell transcriptomics with adaptive immune receptor sequencing, providing insight into the skin barrier defense and orchestration of the immune response to this vector-borne pathogen.

immunology↗

bioRxiv2024

Partially characterized topology guides reliable anchor-free scRNA integration

Single-cell RNA sequencing (scRNA-seq) is an important technique for obtaining biological insights at cellular resolution, with scRNA-seq batch integration a key step before downstream statistical analysis. Despite the plethora of methods proposed, achieving reliable batch correction while preserving the heterogeneity of biological signals that define cell type continues to pose a challenge, with existing methods performance varying significantly across different scenarios and datasets. To address this, we propose scCRAFT, an autoencoder model designed to segregate cell-type-related biological signals from batch effects for reliable multi-batch scRNA-seq integration. scCRAFT comprises three key loss components: a reconstruction loss that targets observation reconstruction, a multi-domain adaptation loss aimed at eliminating batch effects, and an innovative dual-resolution triplet loss for preserving topology within each batch, which is introduced as an effective mechanism to counteract the over-correction effect of domain adaptation loss amid heterogeneous cell distributions across batches. We show that scCRAFT effectively manages unbalanced batches, rare cell types, and batch-specific cell phenotypes in simulations, and surpasses state-of-the-art methods in a diverse set of real datasets.

bioinformatics↗