SNF1-RELATED KINASE 1 and TARGET OF RAPAMYCIN control light-responsive splicing events and developmental characteristics in etiolated Arabidopsis seedlings.

The kinases SNF1-RELATED KINASE 1 (SnRK1) and TARGET OF RAPAMYCIN (TOR) are central sensors of the energy status, linking this information via diverse regulatory mechanisms to plant development and stress responses. Despite the well-studied functions of SnRK1 and TOR under conditions of limited or ample energy availability, respectively, little is known about the extent to which the 2 sensor systems function and how they are integrated in the same molecular process or physiological context. Here, we demonstrate that both SnRK1 and TOR are required for proper skotomorphogenesis in etiolated Arabidopsis (Arabidopsis thaliana) seedlings, light-induced cotyledon opening, and regular development in light. Furthermore, we identify SnRK1 and TOR as signaling components acting upstream of light- and sugar-regulated alternative splicing events, expanding the known action spectra for these 2 key players in energy signaling. Our findings imply that concurring SnRK1 and TOR activities are required throughout various phases of plant development. Based on the current knowledge and our findings, we hypothesize that turning points in the activities of these sensor kinases, as expected to occur upon illumination of etiolated seedlings, instead of signaling thresholds reflecting the nutritional status may modulate developmental programs in response to altered energy availability.

On cheap entropy-sparsified regression learning.

Regression learning is one of the long-standing problems in statistics, machine learning, and deep learning (DL). We show that writing this problem as a probabilistic expectation over (unknown) feature probabilities - thus increasing the number of unknown parameters and seemingly making the problem more complex-actually leads to its simplification, and allows incorporating the physical principle of entropy maximization. It helps decompose a very general setting of this learning problem (including discretization, feature selection, and learning multiple piece-wise linear regressions) into an iterative sequence of simple substeps, which are either analytically solvable or cheaply computable through an efficient second-order numerical solver with a sublinear cost scaling. This leads to the computationally cheap and robust non-DL second-order Sparse Probabilistic Approximation for Regression Task Analysis (SPARTAn) algorithm, that can be efficiently applied to problems with millions of feature dimensions on a commodity laptop, when the state-of-the-art learning tools would require supercomputers. SPARTAn is compared to a range of commonly used regression learning tools on synthetic problems and on the prediction of the El Niño Southern Oscillation, the dominant interannual mode of tropical climate variability. The obtained SPARTAn learners provide more predictive, sparse, and physically explainable data descriptions, clearly discerning the important role of ocean temperature variability at the thermocline in the equatorial Pacific. SPARTAn provides an easily interpretable description of the timescales by which these thermocline temperature features evolve and eventually express at the surface, thereby enabling enhanced predictability of the key drivers of the interannual climate.

Positioning of pyrimidine motifs around cassette exons defines their PTB-dependent splicing in Arabidopsis.

Alternative splicing (AS) is a complex process that generates transcript variants from a single pre-mRNA and is involved in numerous biological functions. Many RNA-binding proteins are known to regulate AS; however, little is known about the underlying mechanisms, especially outside the mammalian clade. Here, we show that polypyrimidine tract binding proteins (PTBs) from Arabidopsis thaliana regulate AS of cassette exons via pyrimidine (Py)-rich motifs close to the alternative splice sites. Mutational studies on three PTB-dependent cassette exon events revealed that only some of the Py motifs in this region are critical for AS. Moreover, in vitro binding of PTBs did not reflect a motif's impact on AS in vivo. Our mutational studies and bioinformatic investigation of all known PTB-regulated cassette exons from A. thaliana and human suggested that the binding position of PTBs relative to a cassette exon defines whether its inclusion or skipping is induced. Accordingly, exon skipping is associated with a higher frequency of Py stretches within the cassette exon, and in human also upstream of it, whereas exon inclusion is characterized by increased Py motif occurrence downstream of said exon. Enrichment of Py motifs downstream of PTB-activated 5' splice sites is also seen for PTB-dependent intron removal and alternative 5' splice site events from A. thaliana, suggesting this is a common step of exon definition. In conclusion, the position-dependent AS regulatory mechanism by PTB homologs has been conserved during the separate evolution of plants and mammals, while other critical features, in particular intron length, have considerably changed.

A transient in planta editing assay identifies specific binding of the splicing regulator PTB as a prerequisite for cassette exon inclusion.

The dynamic interaction of RNA-binding proteins (RBPs) with their target RNAs contributes to the diversity of ribonucleoprotein (RNP) complexes that are involved in a myriad of biological processes. Identifying the RNP components at high resolution and defining their interactions are key to understanding their regulation and function. Expressing fusions between an RBP of interest and an RNA editing enzyme can result in nucleobase changes in target RNAs, representing a recent addition to experimental approaches for profiling RBP/RNA interactions. Here, we have used the MS2 protein/RNA interaction to test four RNA editing proteins for their suitability to detect target RNAs of RBPs in planta. We have established a transient test system for fast and simple quantification of editing events and identified the hyperactive version of the catalytic domain of an adenosine deaminase (hADARcd) as the most suitable editing enzyme. Examining fusions between homologs of polypyrimidine tract binding proteins (PTBs) from Arabidopsis thaliana and hADARcd allowed determining target RNAs with high sensitivity and specificity. Moreover, almost complete editing of a splicing intermediate provided insight into the order of splicing reactions and PTB dependency of this particular splicing event. Addition of sequences for nuclear localisation of the fusion protein increased the editing efficiency, highlighting this approach's potential to identify RBP targets in a compartment-specific manner. Our studies have established the editing-based analysis of interactions between RBPs and their RNA targets in a fast and straightforward assay, offering a new system to study the intricate composition and functions of plant RNPs in vivo.

Radiofrequency ablation-Real-time visualization of lesions and their correlation with underlying parameters.

BACKGROUND: Lesion durability and transmurality are crucial for successful radiofrequency (RF) ablation. This study provides a model of real-time RF lesion visualization and insights into the role of underlying parameters, as local impedance (LI). METHODS: A force-sensing, LI-sensing catheter was used for lesion creation in an ex vivo model involving cross-sections of porcine cardiac preparations. During 60 s of RF application, one measurement per second was performed regarding lesion size and available ablation parameters. In total, 1847 measurements from n = 36 lesions were performed. Power (20-50 W) and contact force (1-5 g, 10-15 g, 20-25 g) were systematically alternated. RESULTS: Lesion formation was most prominent in the first seconds of RF application during which nonlinear lesion growth was observed (max. 1.08 mm/s for lesion depth and 2.71 mm/s for lesion diameter). Power levels determined the extent of lesion formation in the early phase. After 20 s, lesion size growth velocity approaches 0.1 mm/s at all power levels. LI changes were also highest in the first seconds (up to - 12 Ω/s) and decreased to less than - 0.1Ω/s after prolonged application. CONCLUSION: Lesion formation in irrigated RF ablation is a nonlinear process. Final lesion size resulting from an RF application is mainly influenced by high rates of lesion growth in the first seconds of ablation. LI seems to be a good surrogate for differentiating changes in lesion formation.

The influence of electrode-tissue-coverage on RF lesion formation and local impedance: Insights from an ex vivo model.

BACKGROUND: The influence of power, duration and contact force (CF) on radiofrequency (RF) lesion formation is well known, whereas data on local impedance (LI) and electrode-tissue-coverage (ETC) is scarce. The objective was to investigate their effect on lesion formation in an ex vivo model. METHODS AND RESULTS: An ex vivo model was developed utilizing cross-sections of porcine heart preparations and a force-sensing, LI-measuring catheter. N = 72 lesion were created systematically varying ETC (minor/full), CF (1-5 g, 10-15 g, 20-25 g) and power (20 W, 30 W, 40 W, 50 W). In minor ETC, the distal tip of the catheter was in electric contact with the tissue, in full ETC the whole catheter tip was embedded within the tissue. Lesion size and all parameters were measured once per second (n = 3320). LI correlated strongly with lesion depth (r = -0.742 for ΔLI; r = 0.781 for %LI-drop). Lesions in full ETC were significantly wider and deeper compared to minor ETC (p < .001) and steam pops were more likely. Baseline LI, ΔLI, and %LI-drop were significantly higher in full ETC (p < .001). In lesions resulting in steam pops, baseline LI, and ΔLI were significantly higher. The influence of CF on lesion size was higher in minor ETC than in full ETC. CONCLUSIONS: ETC is a main determinant of lesion size and occurrence of steam pops. Baseline LI and LI-drop are useful surrogate parameters for real-time assessment of ETC and ΔLI correlates strongly with lesion size.

NMD-Based Gene Regulation-A Strategy for Fitness Enhancement in Plants?

Post-transcriptional RNA quality control is a vital issue for all eukaryotes to secure accurate gene expression, both on a qualitative and quantitative level. Among the different mechanisms, nonsense-mediated mRNA decay (NMD) is an essential surveillance system that triggers degradation of both aberrant and physiological transcripts. By targeting a substantial fraction of all transcripts for degradation, including many alternative splicing variants, NMD has a major impact on shaping transcriptomes. Recent progress on the transcriptome-wide profiling and physiological analyses of NMD-deficient plant mutants revealed crucial roles for NMD in gene regulation and environmental responses. In this review, we will briefly summarize our current knowledge of the recognition and degradation of NMD targets, followed by an account of NMD's regulation and physiological functions. We will specifically discuss plant-specific aspects of RNA quality control and its functional contribution to the fitness and environmental responses of plants.

Multifactorial and Species-Specific Feedback Regulation of the RNA Surveillance Pathway Nonsense-Mediated Decay in Plants.

Nonsense-mediated decay (NMD) is an RNA surveillance mechanism that detects aberrant transcript features and triggers degradation of erroneous as well as physiological RNAs. Originally considered to be constitutive, NMD is now recognized to be tightly controlled in response to inherent signals and diverse stresses. To gain a better understanding of NMD regulation and its functional implications, we systematically examined feedback control of the central NMD components in two dicot and one monocot species. On the basis of the analysis of transcript features, turnover rates and steady-state levels, up-frameshift (UPF) 1, UPF3 and suppressor of morphological defects on genitalia (SMG) 7, but not UPF2, are under feedback control in both dicots. In the monocot investigated in this study, only SMG7 was slightly induced upon NMD inhibition. The detection of the endogenous NMD factor proteins in Arabidopsis thaliana substantiated a negative correlation between NMD activity and SMG7 amounts. Furthermore, evidence was provided that SMG7 is required for the dephosphorylation of UPF1. Our comprehensive and comparative study of NMD feedback control in plants reveals complex and species-specific attenuation of this RNA surveillance pathway, with critical implications for the numerous functions of NMD in physiology and stress responses.

Subcellular Compartmentation of Alternatively Spliced Transcripts Defines SERINE/ARGININE-RICH PROTEIN30 Expression.

Alternative splicing (AS) is prevalent in higher eukaryotes, and generation of different AS variants is tightly regulated. Widespread AS occurs in response to altered light conditions and plays a critical role in seedling photomorphogenesis, but despite its frequency and effect on plant development, the functional role of AS remains unknown for most splicing variants. Here, we characterized the light-dependent AS variants of the gene encoding the splicing regulator Ser/Arg-rich protein SR30 in Arabidopsis (Arabidopsis thaliana). We demonstrated that the splicing variant SR30.2, which is predominantly produced in darkness, is enriched within the nucleus and strongly depleted from ribosomes. Light-induced AS from a downstream 3' splice site gives rise to SR30.1, which is exported to the cytosol and translated, coinciding with SR30 protein accumulation upon seedling illumination. Constitutive expression of SR30.1 and SR30.2 fused to fluorescent proteins revealed their identical subcellular localization in the nucleoplasm and nuclear speckles. Furthermore, expression of either variant shifted splicing of a genomic SR30 reporter toward SR30.2, suggesting that an autoregulatory feedback loop affects SR30 splicing. We provide evidence that SR30.2 can be further spliced and, unlike SR30.2, the resulting cassette exon variant SR30.3 is sensitive to nonsense-mediated decay. Our work delivers insight into the complex and compartmentalized RNA processing mechanisms that control the expression of the splicing regulator SR30 in a light-dependent manner.

Alternative Splicing Substantially Diversifies the Transcriptome during Early Photomorphogenesis and Correlates with the Energy Availability in Arabidopsis.

Plants use light as source of energy and information to detect diurnal rhythms and seasonal changes. Sensing changing light conditions is critical to adjust plant metabolism and to initiate developmental transitions. Here, we analyzed transcriptome-wide alterations in gene expression and alternative splicing (AS) of etiolated seedlings undergoing photomorphogenesis upon exposure to blue, red, or white light. Our analysis revealed massive transcriptome reprogramming as reflected by differential expression of ∼20% of all genes and changes in several hundred AS events. For more than 60% of all regulated AS events, light promoted the production of a presumably protein-coding variant at the expense of an mRNA with nonsense-mediated decay-triggering features. Accordingly, AS of the putative splicing factor REDUCED RED-LIGHT RESPONSES IN CRY1CRY2 BACKGROUND1, previously identified as a red light signaling component, was shifted to the functional variant under light. Downstream analyses of candidate AS events pointed at a role of photoreceptor signaling only in monochromatic but not in white light. Furthermore, we demonstrated similar AS changes upon light exposure and exogenous sugar supply, with a critical involvement of kinase signaling. We propose that AS is an integration point of signaling pathways that sense and transmit information regarding the energy availability in plants.

Gene regulation by structured mRNA elements.

The precise temporal and spatial coordination of gene activity, based on the integration of internal and external signals, is crucial for the accurate functioning of all biological processes. Although the basic principles of gene expression were established some 60 years ago, recent research has revealed a surprising complexity in the control of gene activity. Many of these gene regulatory mechanisms occur at the level of the mRNA, including sophisticated gene control tasks mediated by structured mRNA elements. We now know that mRNA folds can serve as highly specific receptors for various types of molecules, as exemplified by metabolite-binding riboswitches, and interfere with pro- and eukaryotic gene expression at the level of transcription, translation, and RNA processing. Gene regulation by structured mRNA elements comprises versatile strategies including self-cleaving ribozymes, RNA-folding-mediated occlusion or presentation of cis-regulatory sequences, and sequestration of trans-acting factors including other RNAs and proteins.

Nonsense-mediated decay of alternative precursor mRNA splicing variants is a major determinant of the Arabidopsis steady state transcriptome.

The nonsense-mediated decay (NMD) surveillance pathway can recognize erroneous transcripts and physiological mRNAs, such as precursor mRNA alternative splicing (AS) variants. Currently, information on the global extent of coupled AS and NMD remains scarce and even absent for any plant species. To address this, we conducted transcriptome-wide splicing studies using Arabidopsis thaliana mutants in the NMD factor homologs UP FRAMESHIFT1 (UPF1) and UPF3 as well as wild-type samples treated with the translation inhibitor cycloheximide. Our analyses revealed that at least 17.4% of all multi-exon, protein-coding genes produce splicing variants that are targeted by NMD. Moreover, we provide evidence that UPF1 and UPF3 act in a translation-independent mRNA decay pathway. Importantly, 92.3% of the NMD-responsive mRNAs exhibit classical NMD-eliciting features, supporting their authenticity as direct targets. Genes generating NMD-sensitive AS variants function in diverse biological processes, including signaling and protein modification, for which NaCl stress-modulated AS-NMD was found. Besides mRNAs, numerous noncoding RNAs and transcripts derived from intergenic regions were shown to be NMD responsive. In summary, we provide evidence for a major function of AS-coupled NMD in shaping the Arabidopsis transcriptome, having fundamental implications in gene regulation and quality control of transcript processing.

A Novel Application for Low Frequency Electrochemical Impedance Spectroscopy as an Online Process Monitoring Tool for Viable Cell Concentrations.

New approaches in process monitoring during industrial fermentations are not only limited to classical pH, dO2 and offgas analysis, but use different in situ and online sensors based on different physical principles to determine biomass, product quality, lysis and far more. One of the very important approaches is the in situ accessibility of viable cell concentration (VCC). This knowledge provides increased efficiency in monitoring and controlling strategies during cultivations. Electrochemical impedance spectroscopy-EIS-is used to monitor biomass in a fermentation of E. coli BL21(DE3), producing a recombinant protein using a fed batch-based approach. Increases in the double layer capacitance (Cdl), determined at frequencies below 1 kHz, are proportional to the increase of biomass in the batch and fed batch phase, monitored in offline and online modes for different cultivations. A good correlation of Cdl with cell density is found and in order to get an appropriate verification of this method, different state-of-the-art biomass measurements are performed and compared. Since measurements in this frequency range are largely determined by the double layer region between the electrode and media, rather minor interferences with process parameters (aeration, stirring) are to be expected. It is shown that impedance spectroscopy at low frequencies is a powerful tool for cultivation monitoring.

The Arabidopsis class II sirtuin is a lysine deacetylase and interacts with mitochondrial energy metabolism.

The posttranslational regulation of proteins by lysine (Lys) acetylation has recently emerged to occur not only on histones, but also on organellar proteins in plants and animals. In particular, the catalytic activities of metabolic enzymes have been shown to be regulated by Lys acetylation. The Arabidopsis (Arabidopsis thaliana) genome encodes two predicted sirtuin-type Lys deacetylases, of which only Silent Information Regulator2 homolog (SRT2) contains a predicted presequence for mitochondrial targeting. Here, we have investigated the function of SRT2 in Arabidopsis. We demonstrate that SRT2 functions as a Lys deacetylase in vitro and in vivo. We show that SRT2 resides predominantly at the inner mitochondrial membrane and interacts with a small number of protein complexes mainly involved in energy metabolism and metabolite transport. Several of these protein complexes, such as the ATP synthase and the ATP/ADP carriers, show an increase in Lys acetylation in srt2 loss-of-function mutants. The srt2 plants display no growth phenotype but rather a metabolic phenotype with altered levels in sugars, amino acids, and ADP contents. Furthermore, coupling of respiration to ATP synthesis is decreased in these lines, while the ADP uptake into mitochondria is significantly increased. Our results indicate that SRT2 is important in fine-tuning mitochondrial energy metabolism.

Polypyrimidine tract binding protein homologs from Arabidopsis are key regulators of alternative splicing with implications in fundamental developmental processes.

Alternative splicing (AS) generates transcript variants by variable exon/intron definition and massively expands transcriptome diversity. Changes in AS patterns have been found to be linked to manifold biological processes, yet fundamental aspects, such as the regulation of AS and its functional implications, largely remain to be addressed. In this work, widespread AS regulation by Arabidopsis thaliana Polypyrimidine tract binding protein homologs (PTBs) was revealed. In total, 452 AS events derived from 307 distinct genes were found to be responsive to the levels of the splicing factors PTB1 and PTB2, which predominantly triggered splicing of regulated introns, inclusion of cassette exons, and usage of upstream 5' splice sites. By contrast, no major AS regulatory function of the distantly related PTB3 was found. Dependent on their position within the mRNA, PTB-regulated events can both modify the untranslated regions and give rise to alternative protein products. We find that PTB-mediated AS events are connected to diverse biological processes, and the functional implications of selected instances were further elucidated. Specifically, PTB misexpression changes AS of PHYTOCHROME INTERACTING FACTOR6, coinciding with altered rates of abscisic acid-dependent seed germination. Furthermore, AS patterns as well as the expression of key flowering regulators were massively changed in a PTB1/2 level-dependent manner.

Accurate detection of differential RNA processing.

Deep transcriptome sequencing (RNA-Seq) has become a vital tool for studying the state of cells in the context of varying environments, genotypes and other factors. RNA-Seq profiling data enable identification of novel isoforms, quantification of known isoforms and detection of changes in transcriptional or RNA-processing activity. Existing approaches to detect differential isoform abundance between samples either require a complete isoform annotation or fall short in providing statistically robust and calibrated significance estimates. Here, we propose a suite of statistical tests to address these open needs: a parametric test that uses known isoform annotations to detect changes in relative isoform abundance and a non-parametric test that detects differential read coverages and can be applied when isoform annotations are not available. Both methods account for the discrete nature of read counts and the inherent biological variability. We demonstrate that these tests compare favorably to previous methods, both in terms of accuracy and statistical calibrations. We use these techniques to analyze RNA-Seq libraries from Arabidopsis thaliana and Drosophila melanogaster. The identified differential RNA processing events were consistent with RT-qPCR measurements and previous studies. The proposed toolkit is available from http://bioweb.me/rdiff and enables in-depth analyses of transcriptomes, with or without available isoform annotation.

Control of alternative RNA splicing and gene expression by eukaryotic riboswitches.

Bacteria make extensive use of riboswitches to sense metabolites and control gene expression, and typically do so by modulating premature transcription termination or translation initiation. The most widespread riboswitch class known in bacteria responds to the coenzyme thiamine pyrophosphate (TPP), which is a derivative of vitamin B1. Representatives of this class have also been identified in fungi and plants, where they are predicted to control messenger RNA splicing or processing. We examined three TPP riboswitches in the filamentous fungus Neurospora crassa, and found that one activates and two repress gene expression by controlling mRNA splicing. A detailed mechanism involving riboswitch-mediated base-pairing changes and alternative splicing control was elucidated for precursor NMT1 mRNAs, which code for a protein involved in TPP metabolism. These results demonstrate that eukaryotic cells employ metabolite-binding RNAs to regulate RNA splicing events that are important for the control of key biochemical processes.

The Impact of Standard Ablation Strategies for Atrial Fibrillation on Cardiovascular Performance in a Four-Chamber Heart Model.

PURPOSE: Atrial fibrillation is one of the most frequent cardiac arrhythmias in the industrialized world and ablation therapy is the method of choice for many patients. However, ablation scars alter the electrophysiological activation and the mechanical behavior of the affected atria. Different ablation strategies with the aim to terminate atrial fibrillation and prevent its recurrence exist but their impact on the performance of the heart is often neglected. METHODS: In this work, we present a simulation study analyzing five commonly used ablation scar patterns and their combinations in the left atrium regarding their impact on the pumping function of the heart using an electromechanical whole-heart model. We analyzed how the altered atrial activation and increased stiffness due to the ablation scars affect atrial as well as ventricular contraction and relaxation. RESULTS: We found that systolic and diastolic function of the left atrium is impaired by ablation scars and that the reduction of atrial stroke volume of up to 11.43% depends linearly on the amount of inactivated tissue. Consequently, the end-diastolic volume of the left ventricle, and thus stroke volume, was reduced by up to 1.4 and 1.8%, respectively. During ventricular systole, left atrial pressure was increased by up to 20% due to changes in the atrial activation sequence and the stiffening of scar tissue. CONCLUSION: This study provides biomechanical evidence that atrial ablation has acute effects not only on atrial contraction but also on ventricular performance. Therefore, the position and extent of ablation scars is not only important for the termination of arrhythmias but is also determining long-term pumping efficiency. If confirmed in larger cohorts, these results have the potential to help tailoring ablation strategies towards minimal global cardiovascular impairment.

3D-2D Distance Maps Conversion Enhances Classification of Craniosynostosis.

OBJECTIVE: Diagnosis of craniosynostosis using photogrammetric 3D surface scans is a promising radiation-free alternative to traditional computed tomography. We propose a 3D surface scan to 2D distance map conversion enabling the usage of the first convolutional neural networks (CNNs)-based classification of craniosynostosis. Benefits of using 2D images include preserving patient anonymity, enabling data augmentation during training, and a strong under-sampling of the 3D surface with good classification performance. METHODS: The proposed distance maps sample 2D images from 3D surface scans using a coordinate transformation, ray casting, and distance extraction. We introduce a CNN-based classification pipeline and compare our classifier to alternative approaches on a dataset of 496 patients. We investigate into low-resolution sampling, data augmentation, and attribution mapping. RESULTS: Resnet18 outperformed alternative classifiers on our dataset with an F1-score of 0.964 and an accuracy of 98.4%. Data augmentation on 2D distance maps increased performance for all classifiers. Under-sampling allowed 256-fold computation reduction during ray casting while retaining an F1-score of 0.92. Attribution maps showed high amplitudes on the frontal head. CONCLUSION: We demonstrated a versatile mapping approach to extract a 2D distance map from the 3D head geometry increasing classification performance, enabling data augmentation during training on 2D distance maps, and the usage of CNNs. We found that low-resolution images were sufficient for a good classification performance. SIGNIFICANCE: Photogrammetric surface scans are a suitable craniosynostosis diagnosis tool for clinical practice. Domain transfer to computed tomography seems likely and can further contribute to reducing ionizing radiation exposure for infants.

Impact of data synthesis strategies for the classification of craniosynostosis.

Introduction: Photogrammetric surface scans provide a radiation-free option to assess and classify craniosynostosis. Due to the low prevalence of craniosynostosis and high patient restrictions, clinical data are rare. Synthetic data could support or even replace clinical data for the classification of craniosynostosis, but this has never been studied systematically. Methods: We tested the combinations of three different synthetic data sources: a statistical shape model (SSM), a generative adversarial network (GAN), and image-based principal component analysis for a convolutional neural network (CNN)-based classification of craniosynostosis. The CNN is trained only on synthetic data but is validated and tested on clinical data. Results: The combination of an SSM and a GAN achieved an accuracy of 0.960 and an F1 score of 0.928 on the unseen test set. The difference to training on clinical data was smaller than 0.01. Including a second image modality improved classification performance for all data sources. Conclusions: Without a single clinical training sample, a CNN was able to classify head deformities with similar accuracy as if it was trained on clinical data. Using multiple data sources was key for a good classification based on synthetic data alone. Synthetic data might play an important future role in the assessment of craniosynostosis.