Augustin, J. | bioRxiv Science

bioRxiv2024

Self-supervised learning to predict intrahepatic cholangiocarcinoma transcriptomic classes on routine histology

ObjectiveThe transcriptomic classification of intrahepatic cholangiocarcinomas (iCCA) has been recently refined from two to five classes, associated with pathological features, targetable genetic alterations and survival. Despite its prognostic and therapeutic value, the classification is not routinely used in the clinic because of technical limitations, including insufficient tissue material or the cost of molecular analyses. Here, we assessed a self-supervised learning (SSL) model for predicting iCCA transcriptomic classes on whole-slide digital histological images (WSIs) DesignTranscriptomic classes defined from RNAseq data were available for all samples. The SSL method, called Giga-SSL, was used to train our model on a discovery set of 766 biopsy slides (n=137 cases) and surgical samples (n=109 cases) from 246 patients in a five-fold cross-validation scheme. The model was validated in The Cancer Genome Atlas (TCGA) (n= 29) and a French external validation set (n=32). ResultsOur model showed good to very good performance in predicting the four most frequent transcriptomic class in the discovery set (area under the curve [AUC]: 0.63-0.84), especially for the hepatic stem-like class (37% of cases, AUC 0.84). The model performed equally well in predicting these four transcriptomic classes in the two validation sets, with AUCs ranging from 0.76 to 0.80 in the TCGA set and 0.62 to 0.92 in the French external set. ConclusionWe developed and validated an SSL-based model for predicting iCCA transcriptomic classes on routine histological slides of biopsy and surgical samples, which may impact iCCA management by predicting prognosis and guiding the treatment strategy.

cancer biology↗

bioRxiv2020

Microplastic fibers affect dynamics and intensity of CO2 and N2O fluxes from soil differently

Microplastics may affect soil ecosystem functioning in critical ways, with previously documented effects including changes in soil structure and water dynamics; this suggests that microbial populations and the processes they mediate could also be affected. Given the importance for global carbon and nitrogen cycle and greenhouse warming potential, we here experimentally examined potential effects of plastic microfiber additions on CO2 and N2O greenhouse gas fluxes. We carried out a fully factorial laboratory experiment with the factors presence of microplastic fibers (0.4% w/w) and addition of urea fertilizer (100 mg N kg-1). The conditions in an intensively N-fertilized arable soil were simulated by adding biogas digestate at the beginning of the incubation to all samples. We continuously monitored CO2 and N2O emissions from soil before and after urea application using a custom-built flow-through steady-state system, and we assessed soil properties, including soil structure. Microplastics affected soil properties, notably increasing soil aggregate water-stability and pneumatic conductivity, and caused changes in the dynamics and overall level of emission of both gases, but in opposite directions: overall fluxes of CO2 were increased by microplastic presence, whereas N2O emission were decreased, a pattern that was intensified following urea addition. This divergent response is explained by effects of microplastic on soil structure, with the increased air permeability likely improving O2 supply: this will have stimulated CO2 production, since mineralization benefits from better aeration. Increased O2 would at the same time have inhibited denitrification, a process contributing to N2O emissions, thus likely explaining the decrease in the latter. Our results clearly suggest that microplastic consequences for greenhouse gas emissions should become an integral part of future impact assessments, and that to understand such responses, soil structure should be assessed.

ecology↗