Search

Abstract Formalin-fixed paraffin-embedded (FFPE) samples are valuable but underutilized in single-cell omics research due to their low RNA quality. In this study, leveraging a recent advance in single-cell genomic technology, we introduce snPATHO-seq, a versatile method to derive high-quality single-nucleus transcriptomic data from FFPE samples. We benchmarked the performance of the snPATHO-seq workflow against existing 10x 3’ and Flex assays designed for frozen or fresh samples and highlighted the consistency in snRNA-seq data produced by all workflows. The snPATHO-seq workflow also demonstrated high robustness when tested across a wide range of healthy and diseased FFPE tissue samples. When combined with FFPE spatial transcriptomic technologies such as FFPE Visium, the snPATHO-seq provides a multi-modal sampling approach for FFPE samples, allowing more comprehensive transcriptomic characterization.

Abstract Tumour-Infiltrating Lymphocytes (TILs) are pivotal in the immune response against cancer cells. Existing deep learning methods for TIL analysis in whole-slide images (WSIs) demand extensive patch-level annotations, often requiring labour-intensive specialist input. To address this, we propose a framework named annotation-efficient segmentation and attention-based classifier (ANSAC). ANSAC requires only slide-level labels to classify WSIs as having high vs. low TIL scores, with the binary classes divided by an expert-defined threshold. ANSAC automatically segments tumour and stroma regions relevant to TIL assessment, eliminating extensive manual annotations. Furthermore, it uses an attention model to generate a map that highlights the most pertinent regions for classification. Evaluating ANSAC on four breast cancer datasets, we demonstrate substantial improvements over three baseline methods in identifying TIL-relevant regions, with up to 8% classification improvement on a held-out test dataset. Additionally, we propose a pre-processing modification to a well-known method, enhancing its performance up to 6%.