Convolutional neural networks (CNNs) are becoming increasingly valuable tools for advanced computational histopathology, promoting precision medicine through exceptional visual decoding abilities. Meningiomas, the most prevalent primary intracranial tumors, necessitate accurate grading and classification for informed clinical decision-making. Recently, DNA methylation-based molecular classification of meningiomas has proven to be more effective in predicting tumor recurrence than traditional histopathological methods. However, DNA methylation profiling is expensive, labor-intensive, and not widely accessible. Consequently, a digital histology-based prediction of DNA methylation classes would be advantageous, complementing molecular classification. In this study, we developed and rigorously assessed an attention-based multiple-instance deep neural network for predicting meningioma methylation classes using tumor methylome data from 142 (+51) patients and corresponding hematoxylin-eosin-stained histological sections. Pairwise analysis of sample cohorts from three meningioma methylation classes demonstrated high accuracy in two combinations. The performance of our approach was validated using an independent set of 51 meningioma patient samples. Importantly, attention map visualization revealed that the algorithm primarily focuses on tumor regions deemed significant by neuropathologists, offering insights into the decision-making process of the CNN. Our findings highlight the capacity of CNNs to effectively harness phenotypic information from histological sections through computerized images for precision medicine. Notably, this study is the first demonstration of predicting clinically relevant DNA methylome information using computer vision applied to standard histopathology. The introduced AI framework holds great potential in supporting, augmenting, and expediting meningioma classification in the future.
In the era of next generation sequencing and beyond, the Sanger technique is still widely used for variant verification of inconclusive or ambiguous high-throughput sequencing results or as a low-cost molecular genetical analysis tool for single targets in many fields of study. Many analysis steps need time-consuming manual intervention. Therefore, we present here a pipeline-capable high-throughput solution with an optional Shiny web interface, that provides a binary mutation decision of hotspots together with plotted chromatograms including annotations via flat files. SangeR is freely available at https://github.com/Neuropathology-Giessen/SangeR and https://hub.docker.com/repository/docker/kaischmid/sange_r Kai.Schmid@patho.med.uni-giessen.de or Daniel.Amsel@patho.med.uni-giessen.de Supplementary data are available at Bioinformatics online.
MGMT promoter methylation is a critical biomarker for predicting alkylating chemotherapy response in IDH-wildtype glioblastoma. However, the lack of an accepted reference detection method complicates clinical implementation. Current assays differ in their target CpG sites, analytical procedures, and classification thresholds. Here, we present an expanded paired analytical comparison of EpiDirect, a bisulfite-free quantitative PCR (qPCR) assay, with 4 established or emerging methods in clinical glioblastoma samples: pyrosequencing, MGMT-STP27 derived from EPIC methylation array data, methylation-specific PCR (MSP), and methylation-specific digital PCR (MS-dPCR).
15 January 2026 in Database: The Journal of Biological Databases and Curation
The preservation of samples, whether they are from humans, cell lines, animals, plants, or other resources, usually follows a similar process. They are packaged in appropriate containers, whether tubes for cryogenic containers or boxes in freezers or other systems. For this biological sample database to be and remain useful, the samples must be appropriately cataloged and consecutively maintained in a document. After all, only when it is clear where which sample is located, the biological database has a value. In many cases this documentation is done in local spreadsheets and saved in e.g. CSV or XLSX format. In some cases, there are even handwritten records to comprehend where which sample is located. The intention behind a biological database is mainly the collection of rare material, but also the withdrawal of this material from the storage for further analysis, partly in-house but presumably also with external cooperation partners. If a sample is now taken from a container that has already been completely filled and stored, this empty space can only be re-allocated with a sample with great administrative effort, since new samples would otherwise be stored in the container that is currently active. With NORG we address this problem. NORG offers a stand-alone software solution via webservices to catalog e.g. nitrogen tanks and store the contents digitally with a color-coding for the filling level of the storages. In addition, NORG can trace who sent which sample to whom and when, for example to have it analyzed by a cooperation partner.
The emerging usage of digitalized histopathological images is leading to a novel possibility for data analysis. With the help of artificial intelligence algorithms, it is now possible to detect certain structures and morphological features on whole slide images automatically. This enables algorithms to count, measure, or evaluate those areas when trained properly. To achieve suitable training, datasets must be annotated and curated by users in programs like QuPath. The extraction of this data for artificial intelligence algorithms is still rather tedious and needs to be saved on a local hard drive. We developed a toolkit for integration into existing pipelines and tools, like U-net, for the on-the-fly extraction of annotation tiles from existing QuPath projects. The tiles can be directly used as input for artificial intelligence algorithms, and the results are directly transferred back to QuPath for visual inspection. With the toolkit, we created a convenient way to incorporate QuPath into existing AI workflows.
17 September 2026 in ESMO Real World Data and Digital Oncology