Mantle cell lymphoma (MCL) is a rare lymphoid malignancy with a poor prognosis characterised by frequent relapse and short durations of treatment response. Most patients present with aggressive disease, but there exist indolent subtypes without the need for immediate intervention. The very heterogeneous behaviour of MCL is genetically characterised by the translocation t(11;14)(q13;q32), leading to Cyclin D1 overexpression with distinct clinical and biological characteristics and outcomes. There is still an unfulfilled need for precise MCL prognostication in real-time. Machine learning and deep learning neural networks are rapidly advancing technologies with promising results in numerous fields of application. This study develops and compares the performance of deep learning (DL) algorithms and radiomics-based machine learning (ML) models to predict MCL relapse on baseline CT scans. Five classification algorithms were used, including three deep learning models (3D SEResNet50, 3D DenseNet, and an optimised 3D CNN) and two machine learning models based on K-nearest Neighbor (KNN) and Random Forest (RF). The best performing method, our optimised 3D CNN, predicted MCL relapse with a 70% accuracy, better than the 3D SEResNet50 (62%) and the 3D DenseNet (59%). The second-best performing method was the KNN-based machine learning model (64%) after principal component analysis for improved accuracy. Our optimised CNN developed by ourselves correctly predicted MCL relapse in 70% of the patients on baseline CT imaging. Once prospectively tested in clinical trials with a larger sample size, our proposed 3D deep learning model could facilitate clinical management by precision imaging in MCL.

The products of the genes of the major histocompatibility complex (MHC) are known to be drivers of pathogen resistance and sexual selection enhancing offspring genetic diversity. The MHC further influences individual odour types and social communication. However, little is known about the receptors and their volatile ligands that are involved in this type of chemical communication. Here, we have investigated chemosensory receptor genes that ultimately enable females to assess male genes through odour cues. As a model, we used an invasive population of North American raccoons ( Procyon lotor ) in Germany. We investigated the effect of two groups of chemosensory receptor genes—trace amine-associated receptors (TAARs) and olfactory receptors (ORs)—on MHC-dependent mate choice. Females with more alleles of the TAAR or OR loci were more likely to choose a male with a diverse MHC. We additionally found that MHC class I genes have a stronger effect on mate choice than the recently reported effect for MHC class II genes, probably because of their immunological relevance for viral resistance. Our study is among the first to show a genetic link between behaviour and chemosensory receptor genes. These results contribute to understanding the link between genetics, olfaction and associated life-history decisions.

Cell-free human cytomegalovirus (HCMV) can be inhibited by a soluble form of the cellular HCMV-receptor PDGFRα, resembling neutralization by antibodies. The cell-associated growth of recent HCMV isolates, however, is resistant against antibodies. We investigated whether PDGFRα-derivatives can inhibit this transmission mode. A protein containing the extracellular PDGFRα-domain and 40-mer peptides derived therefrom were tested regarding the inhibition of the cell-associated HCMV strain Merlin-pAL1502, hits were validated with recent isolates, and the most effective peptide was modified to increase its potency. The modified peptide was further analyzed regarding its mode of action on the virion level. While full-length PDGFRα failed to inhibit HCMV isolates, three peptides significantly reduced virus growth. A 30-mer version of the lead peptide (GD30) proved even more effective against the cell-free virus, and this effect was HCMV-specific and depended on the viral glycoprotein O. In cell-associated spread, GD30 reduced both the number of transferred particles and their penetration. This effect was reversible after peptide removal, which allowed the synchronized analysis of particle transfer, showing that two virions per hour were transferred to neighboring cells and one virion was sufficient for infection. In conclusion, PDGFRα-derived peptides are novel inhibitors of the cell-associated spread of HCMV and facilitate the investigation of this transmission mode.