Biology subjects

Seibel, T.

Publications and source records attributed to Seibel, T..

3 recordsLinked to original sources

bioRxiv2021

DeepMed: A unified, modular pipeline for end-to-end deep learning in computational pathology

The interpretation of digitized histopathology images has been transformed thanks to artificial intelligence (AI). End-to-end AI algorithms can infer high-level features directly from raw image data, extending the capabilities of human experts. In particular, AI can predict tumor subtypes, genetic mutations and gene expression directly from hematoxylin and eosin (H&E) stained pathology slides. However, existing end-to-end AI workflows are poorly standardized and not easily adaptable to new tasks. Here, we introduce DeepMed, a Python library for predicting any high-level attribute directly from histopathological whole slide images alone, or from images coupled with additional meta-data (https://github.com/KatherLab/deepmed). Unlike earlier computational pipelines, DeepMed is highly developer-friendly: its structure is modular and separates preprocessing, training, deployment, statistics, and visualization in such a way that any one of these processes can be altered without affecting the others. Also, DeepMed scales easily from local use on laptop computers to multi-GPU clusters in cloud computing services and therefore can be used for teaching, prototyping and for large-scale applications. Finally, DeepMed is user-friendly and allows researchers to easily test multiple hypotheses in a single dataset (via cross-validation) or in multiple datasets (via external validation). Here, we demonstrate and document DeepMeds abilities to predict molecular alterations, histopathological subtypes and molecular features from routine histopathology images, using a large benchmark dataset which we release publicly. In summary, DeepMed is a fully integrated and broadly applicable end-to-end AI pipeline for the biomedical research community.

cancer biology↗

bioRxiv2021

Swarm learning for decentralized artificial intelligence in cancer histopathology

Artificial Intelligence (AI) can extract clinically actionable information from medical image data. In cancer histopathology, AI can be used to predict the presence of molecular alterations directly from routine histopathology slides. However, training robust AI systems requires large datasets whose collection faces practical, ethical and legal obstacles. These obstacles could be overcome with swarm learning (SL) where partners jointly train AI models, while avoiding data transfer and monopolistic data governance. Here, for the first time, we demonstrate the successful use of SL in large, multicentric datasets of gigapixel histopathology images comprising over 5000 patients. We show that AI models trained using Swarm Learning can predict BRAF mutational status and microsatellite instability (MSI) directly from hematoxylin and eosin (H&E)-stained pathology slides of colorectal cancer (CRC). We trained AI models on three patient cohorts from Northern Ireland, Germany and the United States of America and validated the prediction performance in two independent datasets from the United Kingdom using SL-based AI models. Our data show that SL enables us to train AI models which outperform most locally trained models and perform on par with models which are centrally trained on the merged datasets. In addition, we show that SL-based AI models are data efficient and maintain a robust performance even if only subsets of local datasets are used for training. In the future, SL can be used to train distributed AI models for any histopathology image analysis tasks, overcoming the need for data transfer and without requiring institutions to give up control of the final AI model.

bioinformatics↗

bioRxiv2021

Allosteric control of Ubp6 and the proteasome via a bidirectional switch

The proteasome is the principal cellular protease, and recognizes target proteins that have been covalently marked by ubiquitin chains. The ubiquitin signal is subject to rapid editing at the proteasome, allowing it to reject substrates based on topological features of their attached ubiquitin chains. Editing is mediated by a key regulator of the proteasome, deubiquitinating enzyme Ubp6. The proteasome activates Ubp6, whereas Ubp6 inhibits the proteasome-both by deubiquitinating proteasome-bound ubiquitin conjugates, and through a noncatalytic effect that does not involve deubiquitination. We report mutants in both Ubp6 and proteasome subunit Rpt1 that abrogate Ubp6 activation. The Ubp6 mutations fall within its ILR element, defined here, which is conserved from yeast to mammals. The ILR is a component of the BL1 blocking loop, other parts of which obstruct ubiquitin access to the catalytic groove in free Ubp6. Rpt1 docking at the ILR opens the catalytic groove by rearranging not only BL1 but also a novel network of three directly interconnected active-site-blocking loops. Ubp6 activation and noncatalytic proteasome inhibition by Ubp6 are linked in that they were eliminated by the same Ubp6 and Rpt1 mutations. Ubp6 and ubiquitin together drive the proteasome into a unique conformational state associated with proteasome inhibition. Our results identify a multicomponent allosteric switch that exerts simultaneous control over the activity of both Ubp6 and the proteasome, and suggest that their active states are in general mutually exclusive. The findings lead to a new paradigm for allosteric control of deubiquitinating enzymes.

biochemistry↗