Ensemble-GNN: federated ensemble learning with graph neural networks for disease module discovery and classification.

SUMMARY: Federated learning enables collaboration in medicine, where data is scattered across multiple centers without the need to aggregate the data in a central cloud. While, in general, machine learning models can be applied to a wide range of data types, graph neural networks (GNNs) are particularly developed for graphs, which are very common in the biomedical domain. For instance, a patient can be represented by a protein-protein interaction (PPI) network where the nodes contain the patient-specific omics features. Here, we present our Ensemble-GNN software package, which can be used to deploy federated, ensemble-based GNNs in Python. Ensemble-GNN allows to quickly build predictive models utilizing PPI networks consisting of various node features such as gene expression and/or DNA methylation. We exemplary show the results from a public dataset of 981 patients and 8469 genes from the Cancer Genome Atlas (TCGA). AVAILABILITY AND IMPLEMENTATION: The source code is available at https://github.com/pievos101/Ensemble-GNN, and the data at Zenodo (DOI: 10.5281/zenodo.8305122).

Raman Spectral Analysis in the CHx-Stretching Region as a Guiding Beacon for Non-Targeted, Disruption-Free Monitoring of Germination and Biofilm Formation in the Green Seaweed Ulva.

Raman spectroscopy was used to study the complex interactions and morphogenesis of the green seaweed Ulva (Chlorophyta) and its associated bacteria under controlled conditions in a reductionist model system. Integrating multiple imaging techniques contributes to a more comprehensive understanding of these biological processes. Therefore, Raman spectroscopy was introduced as a non-invasive, label-free tool for examining chemical information of the tripartite community Ulva mutabilis-Roseovarius sp.-Maribacter sp. The study explored cell differentiation, cell wall protrusion, and bacterial-macroalgae interactions of intact algal thalli. Using Raman spectroscopy, the analysis of the CHx-stretching wavenumber region distinguished spatial regions in Ulva germination and cellular malformations under axenic conditions and upon inoculation with a specific bacterium in bipartite communities. The spectral information was used to guide in-depth analyses within the fingerprint region and to identify substance classes such as proteins, lipids, and polysaccharides, including evidence for ulvan found in cell wall protrusions.

CLARUS: An interactive explainable AI platform for manual counterfactuals in graph neural networks.

BACKGROUND: Lack of trust in artificial intelligence (AI) models in medicine is still the key blockage for the use of AI in clinical decision support systems (CDSS). Although AI models are already performing excellently in systems medicine, their black-box nature entails that patient-specific decisions are incomprehensible for the physician. Explainable AI (XAI) algorithms aim to "explain" to a human domain expert, which input features influenced a specific recommendation. However, in the clinical domain, these explanations must lead to some degree of causal understanding by a clinician. RESULTS: We developed the CLARUS platform, aiming to promote human understanding of graph neural network (GNN) predictions. CLARUS enables the visualisation of patient-specific networks, as well as, relevance values for genes and interactions, computed by XAI methods, such as GNNExplainer. This enables domain experts to gain deeper insights into the network and more importantly, the expert can interactively alter the patient-specific network based on the acquired understanding and initiate re-prediction or retraining. This interactivity allows us to ask manual counterfactual questions and analyse the effects on the GNN prediction. CONCLUSION: We present the first interactive XAI platform prototype, CLARUS, that allows not only the evaluation of specific human counterfactual questions based on user-defined alterations of patient networks and a re-prediction of the clinical outcome but also a retraining of the entire GNN after changing the underlying graph structures. The platform is currently hosted by the GWDG on https://rshiny.gwdg.de/apps/clarus/.

The Light-activated Effect of Natural Anthraquinone Parietin against Candida auris and Other Fungal Priority Pathogens.

Antimicrobial photodynamic therapy (aPDT) is an evolving treatment strategy against human pathogenic microbes such as the Candida species, including the emerging pathogen C. auris. Using a modified EUCAST protocol, the light-enhanced antifungal activity of the natural compound parietin was explored. The photoactivity was evaluated against three separate strains of five yeasts, and its molecular mode of action was analysed via several techniques, i.e., cellular uptake, reactive electrophilic species (RES), and singlet oxygen yield. Under experimental conditions (λ = 428 nm, H = 30 J/cm2, PI = 30 min), microbial growth was inhibited by more than 90% at parietin concentrations as low as c = 0.156 mg/L (0.55 µM) for C. tropicalis and Cryptococcus neoformans, c = 0.313 mg/L (1.10 µM) for C. auris, c = 0.625 mg/L (2.20 µM) for C. glabrata, and c = 1.250 mg/L (4.40 µM) for C. albicans. Mode-of-action analysis demonstrated fungicidal activity. Parietin targets the cell membrane and induces cell death via ROS-mediated lipid peroxidation after light irradiation. In summary, parietin exhibits light-enhanced fungicidal activity against all Candida species tested (including C. auris) and Cryptococcus neoformans, covering three of the four critical threats on the WHO's most recent fungal priority list.

Sensors for Digital Transformation in Smart Forestry.

Smart forestry, an innovative approach leveraging artificial intelligence (AI), aims to enhance forest management while minimizing the environmental impact. The efficacy of AI in this domain is contingent upon the availability of extensive, high-quality data, underscoring the pivotal role of sensor-based data acquisition in the digital transformation of forestry. However, the complexity and challenging conditions of forest environments often impede data collection efforts. Achieving the full potential of smart forestry necessitates a comprehensive integration of sensor technologies throughout the process chain, ensuring the production of standardized, high-quality data essential for AI applications. This paper highlights the symbiotic relationship between human expertise and the digital transformation in forestry, particularly under challenging conditions. We emphasize the human-in-the-loop approach, which allows experts to directly influence data generation, enhancing adaptability and effectiveness in diverse scenarios. A critical aspect of this integration is the deployment of autonomous robotic systems in forests, functioning both as data collectors and processing hubs. These systems are instrumental in facilitating sensor integration and generating substantial volumes of quality data. We present our universal sensor platform, detailing our experiences and the critical importance of the initial phase in digital transformation-the generation of comprehensive, high-quality data. The selection of appropriate sensors is a key factor in this process, and our findings underscore its significance in advancing smart forestry.

Search for evolutionary roots of land plant arabinogalactan-proteins in charophytes: presence of a rhamnogalactan-protein in Spirogyra pratensis (Zygnematophyceae).

Charophyte green algae (CGA) are assigned to be the closest relatives of land plants and therefore enlighten processes in the colonization of terrestrial habitats. For the transition from water to land, plants needed significant physiological and structural changes, as well as with regard to cell wall composition. Sequential extraction of cell walls of Nitellopsis obtusa (Charophyceae) and Spirogyra pratensis (Zygnematophyceae) offered a comparative overview on cell wall composition of late branching CGA. Because arabinogalactan-proteins (AGPs) are considered common for all land plant cell walls, we were interested in whether these special glycoproteins are present in CGA. Therefore, we investigated both species with regard to characteristic features of AGPs. In the cell wall of Nitellopsis, no hydroxyproline was present and no AGP was precipitable with the ß-glucosyl Yariv's reagent (ßGlcY). By contrast, ßGlcY precipitation of the water-soluble cell wall fraction of Spirogyra yielded a glycoprotein fraction rich in hydroxyproline, indicating the presence of AGPs. Putative AGPs in the cell walls of non-conjugating Spirogyra filaments, especially in the area of transverse walls, were detected by staining with ßGlcY. Labelling increased strongly in generative growth stages, especially during zygospore development. Investigations of the fine structure of the glycan part of ßGlcY-precipitated molecules revealed that the galactan backbone resembled that of AGPs with 1,3- 1,6- and 1,3,6-linked Galp moieties. Araf was present only in small amounts and the terminating sugars consisted predominantly of pyranosidic terminal and 1,3-linked rhamnose residues. We introduce the term 'rhamnogalactan-protein' for this special AGP-modification present in S. pratensis.

GNN-SubNet: disease subnetwork detection with explainable graph neural networks.

MOTIVATION: The tremendous success of graphical neural networks (GNNs) already had a major impact on systems biology research. For example, GNNs are currently being used for drug target recognition in protein-drug interaction networks, as well as for cancer gene discovery and more. Important aspects whose practical relevance is often underestimated are comprehensibility, interpretability and explainability. RESULTS: In this work, we present a novel graph-based deep learning framework for disease subnetwork detection via explainable GNNs. Each patient is represented by the topology of a protein-protein interaction (PPI) network, and the nodes are enriched with multi-omics features from gene expression and DNA methylation. In addition, we propose a modification of the GNNexplainer that provides model-wide explanations for improved disease subnetwork detection. AVAILABILITY AND IMPLEMENTATION: The proposed methods and tools are implemented in the GNN-SubNet Python package, which we have made available on our GitHub for the international research community (https://github.com/pievos101/GNN-SubNet). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Federated Random Forests can improve local performance of predictive models for various healthcare applications.

MOTIVATION: Limited data access has hindered the field of precision medicine from exploring its full potential, e.g. concerning machine learning and privacy and data protection rules.Our study evaluates the efficacy of federated Random Forests (FRF) models, focusing particularly on the heterogeneity within and between datasets. We addressed three common challenges: (i) number of parties, (ii) sizes of datasets and (iii) imbalanced phenotypes, evaluated on five biomedical datasets. RESULTS: The FRF outperformed the average local models and performed comparably to the data-centralized models trained on the entire data. With an increasing number of models and decreasing dataset size, the performance of local models decreases drastically. The FRF, however, do not decrease significantly. When combining datasets of different sizes, the FRF vastly improve compared to the average local models. We demonstrate that the FRF remain more robust and outperform the local models by analyzing different class-imbalances.Our results support that FRF overcome boundaries of clinical research and enables collaborations across institutes without violating privacy or legal regulations. Clinicians benefit from a vast collection of unbiased data aggregated from different geographic locations, demographics and other varying factors. They can build more generalizable models to make better clinical decisions, which will have relevance, especially for patients in rural areas and rare or geographically uncommon diseases, enabling personalized treatment. In combination with secure multi-party computation, federated learning has the power to revolutionize clinical practice by increasing the accuracy and robustness of healthcare AI and thus paving the way for precision medicine. AVAILABILITY AND IMPLEMENTATION: The implementation of the federated random forests can be found at https://featurecloud.ai/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

CT texture analysis reliability in pulmonary lesions: the influence of 3D vs. 2D lesion segmentation and volume definition by a Hounsfield-unit threshold.

OBJECTIVE: Reproducibility problems are a known limitation of radiomics. The segmentation of the target lesion plays a critical role in texture analysis variability. This study's aim was to compare the interobserver reliability of manual 2D vs. 3D lung lesion segmentation with and without pre-definition of the volume using a threshold of - 50 HU. METHODS: Seventy-five patients with histopathologically proven lung lesions (15 patients each with adenocarcinoma, squamous cell carcinoma, small cell lung cancer, carcinoid, and organizing pneumonia) who underwent an unenhanced CT scan of the chest were included. Three radiologists independently segmented each lesion manually in 3D and 2D with and without pre-segmentation volume definition by a HU threshold, and shape parameters and original, Laplacian of Gaussian-filtered, and wavelet-based texture features were derived. To assess interobserver reliability and identify the most robust texture features, intraclass correlation coefficients (ICCs) for different segmentation settings were calculated. RESULTS: Shape parameters had high reliability (64-79% had excellent and good ICCs). Texture features had weak reliability levels, with the highest ICCs (38% excellent or good) found for original features in 3D segmentation without the use of a HU threshold. A small proportion (4.3-11.5%) of texture features had excellent or good ICC values at all segmentation settings. CONCLUSION: Interobserver reliability of texture features from CT scans of a heterogeneous collection of manually segmented lung lesions was low with a small proportion of features demonstrating high reliability independent of the segmentation settings. These results indicate a limited applicability of texture analysis and the need to define robust texture features in patients with lung lesions. KEY POINTS: • Our study showed a low reproducibility of texture features when 3 radiologists independently segmented lung lesions in CT images, which highlights a serious limitation of texture analysis. • Interobserver reliability of texture features was low regardless of whether the lesion was segmented in 2D and 3D with or without a HU threshold. • In contrast to texture features, shape parameters showed a high interobserver reliability when lesions were segmented in 2D vs. 3D with and without a HU threshold of - 50.

Frozen mountain pine needles: The endodermis discriminates between the ice-containing central tissue and the ice-free fully functional mesophyll.

Conifer (Pinaceae) needles are the most frost-hardy leaves. During needle freezing, the exceptional leaf anatomy, where an endodermis separates the mesophyll from the vascular tissue, could have consequences for ice management and photosynthesis. The eco-physiological importance of needle freezing behaviour was evaluated based on the measured natural freezing strain at the alpine treeline. Ice localisation and cellular responses to ice were investigated in mountain pine needles by cryo-microscopic techniques. Their consequences for photosynthetic activity were assessed by gas exchange measurements. The freezing response was related to the microchemistry of cell walls investigated by Raman microscopy. In frozen needles, ice was confined to the central vascular cylinder bordered by the endodermis. The endodermal cell walls were lignified. In the ice-free mesophyll, cells showed no freeze-dehydration and were found photosynthetically active. Mesophyll cells had lignified tangential cell walls, which adds rigidity. Ice barriers in mountain pine needles seem to be realised by a specific lignification patterning of cell walls. This, additionally, impedes freeze-dehydration of mesophyll cells and enables gas exchange of frozen needles. At the treeline, where freezing is a dominant environmental factor, the elaborate needle freezing pattern appears of ecological importance.

3D-reconstructions of zygospores in Zygnema vaginatum (Charophyta) reveal details of cell wall formation, suggesting adaptations to extreme habitats.

The streptophyte green algal class Zygnematophyceae is the immediate sister lineage to land plants. Their special form of sexual reproduction via conjugation might have played a key role during terrestrialization. Thus, studying Zygnematophyceae and conjugation is crucial for understanding the conquest of land. Moreover, sexual reproduction features are important for species determination. We present a phylogenetic analysis of a field-sampled Zygnema strain and analyze its conjugation process and zygospore morphology, both at the micro- and nanoscale, including 3D-reconstructions of the zygospore architecture. Vegetative filament size (26.18 ± 1.07 µm) and reproductive features allowed morphological determination of Zygnema vaginatum, which was combined with molecular analyses based on rbcL sequencing. Transmission electron microscopy (TEM) depicted a thin cell wall in young zygospores, while mature cells exhibited a tripartite wall, including a massive and sculptured mesospore. During development, cytological reorganizations were visualized by focused ion beam scanning electron microscopy (FIB-SEM). Pyrenoids were reorganized, and the gyroid cubic central thylakoid membranes, as well as the surrounding starch granules, degraded (starch granule volume: 3.58 ± 2.35 µm3 in young cells; 0.68 ± 0.74 µm3 at an intermediate stage of zygospore maturation). Additionally, lipid droplets (LDs) changed drastically in shape and abundance during zygospore maturation (LD/cell volume: 11.77% in young cells; 8.79% in intermediate cells, 19.45% in old cells). In summary, we provide the first TEM images and 3D-reconstructions of Zygnema zygospores, giving insights into the physiological processes involved in their maturation. These observations help to understand mechanisms that facilitated the transition from water to land in Zygnematophyceae.

Novel SYN1 Variant in Two Brothers with Focal Epilepsy and Their Prompt Response to Valproate.

Synapsins are neuron-specific phosphoproteins that modulate neurotransmitter release, synaptic plasticity, and molecular processes shaping higher brain functions. Pathogenic synapsin-1 (SYN1) variants are associated with epilepsy, intellectual disabilities, and behavioral problems. We detected a novel SYN1 variant [c.477_479delTGG (p.Gly160del)] in brothers with focal epilepsy with secondary generalization. The deleted amino acid was found to be highly conserved among mammalian species. In electroencephalography, the older brother showed a bioelectrical status epilepticus and was also diagnosed with attention deficit hyperactivity disorder. Behavioral abnormalities were seen before or after the seizures. Both patients responded quickly to treatment with valproate. Our case reports are consistent with the clinical heterogeneity of the pathogenic SYN1 variants described in the literature.

The FeatureCloud Platform for Federated Learning in Biomedicine: Unified Approach.

BACKGROUND: Machine learning and artificial intelligence have shown promising results in many areas and are driven by the increasing amount of available data. However, these data are often distributed across different institutions and cannot be easily shared owing to strict privacy regulations. Federated learning (FL) allows the training of distributed machine learning models without sharing sensitive data. In addition, the implementation is time-consuming and requires advanced programming skills and complex technical infrastructures. OBJECTIVE: Various tools and frameworks have been developed to simplify the development of FL algorithms and provide the necessary technical infrastructure. Although there are many high-quality frameworks, most focus only on a single application case or method. To our knowledge, there are no generic frameworks, meaning that the existing solutions are restricted to a particular type of algorithm or application field. Furthermore, most of these frameworks provide an application programming interface that needs programming knowledge. There is no collection of ready-to-use FL algorithms that are extendable and allow users (eg, researchers) without programming knowledge to apply FL. A central FL platform for both FL algorithm developers and users does not exist. This study aimed to address this gap and make FL available to everyone by developing FeatureCloud, an all-in-one platform for FL in biomedicine and beyond. METHODS: The FeatureCloud platform consists of 3 main components: a global frontend, a global backend, and a local controller. Our platform uses a Docker to separate the local acting components of the platform from the sensitive data systems. We evaluated our platform using 4 different algorithms on 5 data sets for both accuracy and runtime. RESULTS: FeatureCloud removes the complexity of distributed systems for developers and end users by providing a comprehensive platform for executing multi-institutional FL analyses and implementing FL algorithms. Through its integrated artificial intelligence store, federated algorithms can easily be published and reused by the community. To secure sensitive raw data, FeatureCloud supports privacy-enhancing technologies to secure the shared local models and assures high standards in data privacy to comply with the strict General Data Protection Regulation. Our evaluation shows that applications developed in FeatureCloud can produce highly similar results compared with centralized approaches and scale well for an increasing number of participating sites. CONCLUSIONS: FeatureCloud provides a ready-to-use platform that integrates the development and execution of FL algorithms while reducing the complexity to a minimum and removing the hurdles of federated infrastructure. Thus, we believe that it has the potential to greatly increase the accessibility of privacy-preserving and distributed data analyses in biomedicine and beyond.

Explainable artificial intelligence (XAI): closing the gap between image analysis and navigation in complex invasive diagnostic procedures.

LITERATURE REVIEW: Cystoscopy is the gold standard for initial macroscopic assessments of the human urinary bladder to rule out (or diagnose) bladder cancer (BCa). Despite having guidelines, cystoscopic findings are diverse and often challenging to classify. The extent of the false negatives and false positives in cystoscopic diagnosis is currently unknown. We suspect that there is a certain degree of under-diagnosis (like the failure to detect malignant tumours) and over-diagnosis (e.g. sending the patient for unnecessary transurethral resection of bladder tumors with anesthesia) that put the patient at risk. CONCLUSIONS: XAI robot-assisted cystoscopes would help to overcome the risks/flaws of conventional cystoscopy. Cystoscopy is considered a less life-threatening starting point for automation than open surgical procedures. Semi-autonomous cystoscopy requires standards and cystoscopy is a good procedure to establish a model that can then be exported/copied to other procedures of endoscopy and surgery. Standards also define the automation levels-an issue for medical product law. These cystoscopy skills do not give full autonomy to the machine, and represent a surgical parallel to 'Autonomous Driving' (where a standard requires a human supervisor to remain in the 'vehicle'). Here in robotic cystoscopy, a human supervisor remains bedside in the 'operating room' as a 'human-in-the-loop' in order to safeguard patients. The urologists will be able to delegate personal- and time-consuming cystoscopy to a specialised nurse. The result of automated diagnostic cystoscopy is a short video (with pre-processed photos from the video), which are then reviewed by the urologists at a more convenient time.

The augmented radiologist: artificial intelligence in the practice of radiology.

In medicine, particularly in radiology, there are great expectations in artificial intelligence (AI), which can "see" more than human radiologists in regard to, for example, tumor size, shape, morphology, texture and kinetics - thus enabling better care by earlier detection or more precise reports. Another point is that AI can handle large data sets in high-dimensional spaces. But it should not be forgotten that AI is only as good as the training samples available, which should ideally be numerous enough to cover all variants. On the other hand, the main feature of human intelligence is content knowledge and the ability to find near-optimal solutions. The purpose of this paper is to review the current complexity of radiology working places, to describe their advantages and shortcomings. Further, we give an AI overview of the different types and features as used so far. We also touch on the differences between AI and human intelligence in problem-solving. We present a new AI type, labeled "explainable AI," which should enable a balance/cooperation between AI and human intelligence - thus bringing both worlds in compliance with legal requirements. For support of (pediatric) radiologists, we propose the creation of an AI assistant that augments radiologists and keeps their brain free for generic tasks.

Digital Transformation in Smart Farm and Forest Operations Needs Human-Centered AI: Challenges and Future Directions.

The main impetus for the global efforts toward the current digital transformation in almost all areas of our daily lives is due to the great successes of artificial intelligence (AI), and in particular, the workhorse of AI, statistical machine learning (ML). The intelligent analysis, modeling, and management of agricultural and forest ecosystems, and of the use and protection of soils, already play important roles in securing our planet for future generations and will become irreplaceable in the future. Technical solutions must encompass the entire agricultural and forestry value chain. The process of digital transformation is supported by cyber-physical systems enabled by advances in ML, the availability of big data and increasing computing power. For certain tasks, algorithms today achieve performances that exceed human levels. The challenge is to use multimodal information fusion, i.e., to integrate data from different sources (sensor data, images, *omics), and explain to an expert why a certain result was achieved. However, ML models often react to even small changes, and disturbances can have dramatic effects on their results. Therefore, the use of AI in areas that matter to human life (agriculture, forestry, climate, health, etc.) has led to an increased need for trustworthy AI with two main components: explainability and robustness. One step toward making AI more robust is to leverage expert knowledge. For example, a farmer/forester in the loop can often bring in experience and conceptual understanding to the AI pipeline-no AI can do this. Consequently, human-centered AI (HCAI) is a combination of "artificial intelligence" and "natural intelligence" to empower, amplify, and augment human performance, rather than replace people. To achieve practical success of HCAI in agriculture and forestry, this article identifies three important frontier research areas: (1) intelligent information fusion; (2) robotics and embodied intelligence; and (3) augmentation, explanation, and verification for trusted decision support. This goal will also require an agile, human-centered design approach for three generations (G). G1: Enabling easily realizable applications through immediate deployment of existing technology. G2: Medium-term modification of existing technology. G3: Advanced adaptation and evolution beyond state-of-the-art.

Terrestrial Green Algae Show Higher Tolerance to Dehydration than Do Their Aquatic Sister-Species.

Diverse algae possess the ability to recover from extreme desiccation without forming specialized resting structures. Green algal genera such as Tetradesmus (Sphaeropleales, Chlorophyceae) contain temperate terrestrial, desert, and aquatic species, providing an opportunity to compare physiological traits associated with the transition to land in closely related taxa. We subjected six species from distinct habitats to three dehydration treatments varying in relative humidity (RH 5%, 65%, 80%) followed by short- and long-term rehydration. We tested the capacity of the algae to recover from dehydration using the effective quantum yield of photosystem II as a proxy for physiological activity. The degree of recovery was dependent both on the habitat of origin and the dehydration scenario, with terrestrial, but not aquatic, species recovering from dehydration. Distinct strains of each species responded similarly to dehydration and rehydration, with the exception of one aquatic strain that recovered from the mildest dehydration treatment. Cell ultrastructure was uniformly maintained in both aquatic and desert species during dehydration and rehydration, but staining with an amphiphilic styryl dye indicated damage to the plasma membrane from osmotically induced water loss in the aquatic species. These analyses demonstrate that terrestrial Tetradesmus possess a vegetative desiccation tolerance phenotype, making these species ideal for comparative omics studies.

Mutation-based clustering and classification analysis reveals distinctive age groups and age-related biomarkers for glioma.

BACKGROUND: Malignant brain tumor diseases exhibit differences within molecular features depending on the patient's age. METHODS: In this work, we use gene mutation data from public resources to explore age specifics about glioma. We use both an explainable clustering as well as classification approach to find and interpret age-based differences in brain tumor diseases. We estimate age clusters and correlate age specific biomarkers. RESULTS: Age group classification shows known age specifics but also points out several genes which, so far, have not been associated with glioma classification. CONCLUSIONS: We highlight mutated genes to be characteristic for certain age groups and suggest novel age-based biomarkers and targets.

Localisation and substrate specificities of transglycanases in charophyte algae relate to development and morphology.

Cell wall-modifying enzymes have been previously investigated in charophyte green algae (CGA) in cultures of uniform age, giving limited insight into their roles. Therefore, we investigated the in situ localisation and specificity of enzymes acting on hemicelluloses in CGA genera of different morphologies and developmental stages. In vivo transglycosylation between xyloglucan and an endogenous donor in filamentous Klebsormidium and Zygnema was observed in longitudinal cell walls of young (1 month) but not old cells (1 year), suggesting that it has a role in cell growth. By contrast, in parenchymatous Chara, transglycanase action occurred in all cell planes. In Klebsormidium and Zygnema, the location of enzyme action mainly occurred in regions where xyloglucans and mannans, and to a lesser extent mixed-linkage ß-glucan (MLG), were present, indicating predominantly xyloglucan:xyloglucan endotransglucosylase (XET) activity. Novel transglycosylation activities between xyloglucan and xylan, and xyloglucan and galactomannan were identified in vitro in both genera. Our results show that several cell wall-modifying enzymes are present in CGA, and that differences in morphology and cell age are related to enzyme localisation and specificity. This indicates an evolutionary significance of cell wall modifications, as similar changes are known in their immediate descendants, the land plants. This article has an associated First Person interview with the first author of the paper.

Biomedical image augmentation using Augmentor.

MOTIVATION: Image augmentation is a frequently used technique in computer vision and has been seeing increased interest since the popularity of deep learning. Its usefulness is becoming more and more recognized due to deep neural networks requiring larger amounts of data to train, and because in certain fields, such as biomedical imaging, large amounts of labelled data are difficult to come by or expensive to produce. In biomedical imaging, features specific to this domain need to be addressed. RESULTS: Here we present the Augmentor software package for image augmentation. It provides a stochastic, pipeline-based approach to image augmentation with a number of features that are relevant to biomedical imaging, such as z-stack augmentation and randomized elastic distortions. The software has been designed to be highly extensible meaning an operation that might be specific to a highly specialized task can easily be added to the library, even at runtime. Although it has been designed as a general software library, it has features that are particularly relevant to biomedical imaging and the techniques required for this domain. AVAILABILITY AND IMPLEMENTATION: Augmentor is a Python package made available under the terms of the MIT licence. Source code can be found on GitHub under https://github.com/mdbloice/Augmentor and installation is via the pip package manager (A Julia version of the package, developed in parallel by Christof Stocker, is also available under https://github.com/Evizero/Augmentor.jl).