Search

MOTIVATION: In multi-cohort machine learning studies, it is critical to differentiate between effects that are reproducible across cohorts and those that are cohort-specific. Multi-task learning (MTL) is a machine learning approach that facilitates this differentiation through the simultaneous learning of prediction tasks across cohorts. Since multi-cohort data can often not be combined into a single storage solution, there would be the substantial utility of an MTL application for geographically distributed data sources. RESULTS: Here, we describe the development of 'dsMTL', a computational framework for privacy-preserving, distributed multi-task machine learning that includes three supervised and one unsupervised algorithms. First, we derive the theoretical properties of these methods and the relevant machine learning workflows to ensure the validity of the software implementation. Second, we implement dsMTL as a library for the R programming language, building on the DataSHIELD platform that supports the federated analysis of sensitive individual-level data. Third, we demonstrate the applicability of dsMTL for comorbidity modeling in distributed data. We show that comorbidity modeling using dsMTL outperformed conventional, federated machine learning, as well as the aggregation of multiple models built on the distributed datasets individually. The application of dsMTL was computationally efficient and highly scalable when applied to moderate-size (n < 500), real expression data given the actual network latency. AVAILABILITY AND IMPLEMENTATION: dsMTL is freely available at https://github.com/transbioZI/dsMTLBase (server-side package) and https://github.com/transbioZI/dsMTLClient (client-side package). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

We present the AIMe registry, a community-driven reporting platform for AI in biomedicine. It aims to enhance the accessibility, reproducibility and usability of biomedical AI models, and allows future revisions by the community.

Traditional drug discovery faces a severe efficacy crisis. Repurposing of registered drugs provides an alternative with lower costs and faster drug development timelines. However, the data necessary for the identification of disease modules, i.e. pathways and sub-networks describing the mechanisms of complex diseases which contain potential drug targets, are scattered across independent databases. Moreover, existing studies are limited to predictions for specific diseases or non-translational algorithmic approaches. There is an unmet need for adaptable tools allowing biomedical researchers to employ network-based drug repurposing approaches for their individual use cases. We close this gap with NeDRex, an integrative and interactive platform for network-based drug repurposing and disease module discovery. NeDRex integrates ten different data sources covering genes, drugs, drug targets, disease annotations, and their relationships. NeDRex allows for constructing heterogeneous biological networks, mining them for disease modules, prioritizing drugs targeting disease mechanisms, and statistical validation. We demonstrate the utility of NeDRex in five specific use-cases.There is an unmet need for adaptable tools allowing biomedical researchers to employ network-based drug repurposing approaches for their individual use cases. Here, the authors close this gap with NeDRex, an integrative and interactive platform.

Manipulating molecules that impact T cell receptor (TCR) or cytokine signaling, such as the protein tyrosine phosphatase non-receptor type 2 (PTPN2), has significant potential for advancing T cell-based immunotherapies. Nonetheless, it remains unclear how PTPN2 impacts the activation, survival, and memory formation of T cells. We find that PTPN2 deficiency renders cells in vivo and in vitro less dependent on survival-promoting cytokines, such as interleukin (IL)-2 and IL-15. Remarkably, briefly ex vivo-activated PTPN2-deficient T cells accumulate in 3- to 11-fold higher numbers following transfer into unmanipulated, antigen-free mice. Moreover, the absence of PTPN2 augments the survival of short-lived effector T cells and allows them to robustly re-expand upon secondary challenge. Importantly, we find no evidence for impaired effector function or memory formation. Mechanistically, PTPN2 deficiency causes broad changes in the expression and phosphorylation of T cell expansion and survival-associated proteins. Altogether, our data underline the therapeutic potential of targeting PTPN2 in T cell-based therapies to augment the number and survival capacity of antigen-specific T cells.

The Z-disk or Z-line is located at the lateral borders of sarcomere, the fundamental unit of striated muscle. They provide mechanical stability and can boost contractility of cardiac myocytes. In this paper, we propose to generate a 3D model of Z-disks within single adult cardiac cells from an automated segmentation of a large serial-block-face scanning electron microscopy (SBF-SEM) dataset. The proposed fully automated segmentation scheme is comprised of three main modules including “pre-processing”, “segmentation” and “refinement”. We represent a timely-efficient, simple, yet effective model to perform segmentation and refinement steps. Contrast stretching, and Gaussian kernels are used to pre- process the dataset, and well-known “Sobel operators” are used in the segmentation module. We have validated our model by comparing segmentation results with ground-truth annotated Z-disks in terms of pixel-wise accuracy. The results show that our model correctly detects Z-disks with 90.56% accuracy. Finally, the underlying network of Z-disks are rendered in 3D using ImageJ and IMARIS.