Single-cell gene regulatory network prediction by explainable AI.

The molecular heterogeneity of cancer cells contributes to the often partial response to targeted therapies and relapse of disease due to the escape of resistant cell populations. While single-cell sequencing has started to improve our understanding of this heterogeneity, it offers a mostly descriptive view on cellular types and states. To obtain more functional insights, we propose scGeneRAI, an explainable deep learning approach that uses layer-wise relevance propagation (LRP) to infer gene regulatory networks from static single-cell RNA sequencing data for individual cells. We benchmark our method with synthetic data and apply it to single-cell RNA sequencing data of a cohort of human lung cancers. From the predicted single-cell networks our approach reveals characteristic network patterns for tumor cells and normal epithelial cells and identifies subnetworks that are observed only in (subgroups of) tumor cells of certain patients. While current state-of-the-art methods are limited by their ability to only predict average networks for cell populations, our approach facilitates the reconstruction of networks down to the level of single cells which can be utilized to characterize the heterogeneity of gene regulation within and across tumors.

Intestinal mucositis, systemic inflammation and bloodstream infections following high-dose methotrexate treatment in childhood acute lymphoblastic leukaemia: Comparison between the NOPHO ALL 2008 protocol and the ALLTogether1 protocol.

Severe intestinal mucositis (IM) increases the risk of bloodstream infections (BSI) and inflammatory toxicity during acute lymphoblastic leukaemia (ALL) induction treatment. However, the implications of IM in subsequent ALL therapy phases after achieving remission remain unknown. This study investigated the relationship between IM (measured by plasma citrulline and the chemokine CCL20) and the development of BSI and systemic inflammation (reflected by C-reactive protein, CRP) in children with ALL during high-dose methotrexate (HDMTX) treatment, an important part of ALL consolidation therapy. The study compared patients treated according to the NOPHO ALL 2008 protocol (n = 52) and the ALLTogether1 protocol (n = 42), both with identical HDMTX procedures but different scheduling. One week post-HDMTX, citrulline dropped to median levels of 14.5 and 16.9 µM for patients treated according to the NOPHO ALL 2008 and ALLTogether1 protocols, respectively (p = 0.11). In a protocol and neutrophil count-adjusted analysis, hypocitrullinaemia (<10 µmol/L) was associated with increased odds of BSI within 3 weeks from HDMTX (OR = 26.2, p = 0.0074). Patients treated according to the NOPHO ALL 2008 protocol exhibited increased mucosal- and systemic inflammation post-HDMTX compared to patients treated according to ALLTogether1, with increased CCL20 (14.6 vs. 3.7 pg/mL, p < 0.0001) and CRP levels (10.0 vs. 1.0 mg/L, p < 0.0001). Both citrulline and CCL20 correlated with CRP for these patients (rs = -0.44, p = 0.0016 and rs = 0.35, p = 0.016, respectively). These results suggest that hypocitrullinaemia following HDMTX increases the risk of BSI, confirming previous observations from more intensive treatments. Moreover, these data indicate that the patients' vulnerability to mucositis and inflammatory toxicity after chemotherapy varies with treatment protocol.

Cytomegalovirus infection is associated with thymic dysfunction and chronic graft-versus-host disease after pediatric hematopoietic stem cell transplantation.

Pediatric hematopoietic stem cell transplantation (HSCT) is challenged by chronic graft-versus-host disease (cGvHD) significantly affecting survival and long-term morbidity, but underlying mechanisms including the impact of post-HSCT CMV infection are sparsely studied. We first investigated the impact of CMV infection for development of cGvHD in 322 children undergoing standard myeloablative HSCT between 2000 and 2018. Clinically significant CMV infection (n = 61) was an independent risk factor for chronic GvHD in a multivariable Cox regression analysis (HR = 2.17, 95% CI = 1.18-3.97, P = 0.013). We next explored the underlying mechanisms in a subcohort of 39 children. CMV infection was followed by reduced concentration of recent thymic emigrants (17.5 vs. 51.9 × 106/L, P = 0.048) and naïve CD4+ and CD8+ T cells at 6 months post-HSCT (all P < 0.05). Furthermore, CD25highFOXP3+ Tregs tended to be lower in patients with CMV infection (2.9 vs. 9.6 × 106/L, P = 0.055), including Tregs expressing the naivety markers CD45RA and Helios. CD8+ T-cell numbers rose after CMV infection and was dominated by exhausted PD1-expressing cells (66% vs. 39%, P = 0.023). These findings indicate that post-HSCT CMV infection is a main risk factor for development of chronic GvHD after pediatric HSCT and suggest that this effect is caused by reduced thymic function with a persistently impaired production of naïve and regulatory T cells in combination with increased peripheral T-cell exhaustion.

DNA Methylation Profiling of Salivary Gland Tumors Supports and Expands Conventional Classification.

Tumors of the major and minor salivary glands histologically encompass a diverse and partly overlapping spectrum of frequent diagnostically challenging neoplasms. Despite recent advances in molecular testing and the identification of tumor-specific mutations or gene fusions, there is an unmet need to identify additional diagnostic biomarkers for entities lacking specific alterations. In this study, we collected a comprehensive cohort of 363 cases encompassing 20 different salivary gland tumor entities and explored the potential of DNA methylation to classify these tumors. We were able to show that most entities show specific epigenetic signatures and present a machine learning algorithm that achieved a mean balanced accuracy of 0.991. Of note, we showed that cribriform adenocarcinoma is epigenetically distinct from classical polymorphous adenocarcinoma, which could support risk stratification of these tumors. Myoepithelioma and pleomorphic adenoma form a uniform epigenetic class, supporting the theory of a single entity with a broad but continuous morphologic spectrum. Furthermore, we identified a histomorphologically heterogeneous but epigenetically distinct class that could represent a novel tumor entity. In conclusion, our study provides a comprehensive resource of the DNA methylation landscape of salivary gland tumors. Our data provide novel insight into disputed entities and show the potential of DNA methylation to identify new tumor classes. Furthermore, in future, our machine learning classifier could support the histopathologic diagnosis of salivary gland tumors.

Canonical Response Parameterization: Quantifying the structure of responses to single-pulse intracranial electrical brain stimulation.

Single-pulse electrical stimulation in the nervous system, often called cortico-cortical evoked potential (CCEP) measurement, is an important technique to understand how brain regions interact with one another. Voltages are measured from implanted electrodes in one brain area while stimulating another with brief current impulses separated by several seconds. Historically, researchers have tried to understand the significance of evoked voltage polyphasic deflections by visual inspection, but no general-purpose tool has emerged to understand their shapes or describe them mathematically. We describe and illustrate a new technique to parameterize brain stimulation data, where voltage response traces are projected into one another using a semi-normalized dot product. The length of timepoints from stimulation included in the dot product is varied to obtain a temporal profile of structural significance, and the peak of the profile uniquely identifies the duration of the response. Using linear kernel PCA, a canonical response shape is obtained over this duration, and then single-trial traces are parameterized as a projection of this canonical shape with a residual term. Such parameterization allows for dissimilar trace shapes from different brain areas to be directly compared by quantifying cross-projection magnitudes, response duration, canonical shape projection amplitudes, signal-to-noise ratios, explained variance, and statistical significance. Artifactual trials are automatically identified by outliers in sub-distributions of cross-projection magnitude, and rejected. This technique, which we call "Canonical Response Parameterization" (CRP) dramatically simplifies the study of CCEP shapes, and may also be applied in a wide range of other settings involving event-triggered data.

Bone remodeling in survivors of pediatric hematopoietic stem cell transplantation: Impact of heavy resistance training.

BACKGROUND: Early-onset osteoporosis is a frequent late effect after pediatric hematopoietic stem cell transplantation (HSCT). It remains unknown if physical training can improve bone formation in these patients, as the transplantation procedure may cause sustained dysregulation of the bone-forming osteoblast progenitor cells. OBJECTIVE: We aimed to explore the effect of resistance training on bone remodeling in long-term survivors of pediatric HSCT. PROCEDURE: In this prospective, controlled intervention study, we included seven HSCT survivors and 15 age- and sex-matched healthy controls. The participants completed a 12-week heavy load, lower extremity resistance training intervention with three weekly sessions. We measured fasting serum levels of the bone formation marker "N-terminal propeptide of type I procollagen" (P1NP), and the bone resorption marker "C-terminal telopeptide of type I collagen" (CTX). The hypothesis was planned before data collection began. The trial was registered at Clinicaltrials.gov before including the first participant, with trial registration no. NCT04922970. RESULTS: Resistance training led to significantly increased levels of fasting P1NP in both patients (from 57.62 to 114.99 ng/mL, p = .03) and controls (from 66.02 to 104.62 ng/mL, p < .001). No significant changes in fasting CTX levels were observed. CONCLUSIONS: Despite previous high-dose cytotoxic therapy, long-term survivors of pediatric HSCT respond to resistance training with improvement of bone formation, comparable to that of healthy controls. This suggests that resistance training might be a promising non-pharmacological approach to prevent the early decline in bone mass, and should be considered as part of a follow-up program to counteract long-term sequela after pediatric HSCT.

Physical capacity in children and adolescents with newly diagnosed cancer: A systematic review and meta-analysis.

OBJECTIVE: To review the body of evidence on cardiorespiratory fitness, muscle strength, and physical performance in children with newly diagnosed cancer, five databases (MEDLINE, Embase, CINAHL, CENTRAL, and Web of Science) were searched on December 19, 2022. METHODS: Thirteen studies, embodying 594 participants within 1 month of cancer diagnosis and 3674 healthy controls were included. Eighteen different outcomes on cardiorespiratory fitness (n = 2), muscle strength (n = 5), physical performance (n = 10), and adverse events (n = 1) were analyzed. RESULTS: Fifteen out of 17 outcomes on physical capacity showed severe impairments compared with healthy controls. Where possible, random-effects meta-analysis was conducted to synthesize the results. No adverse events were reported related to testing. CONCLUSION: Children with cancer have impaired cardiorespiratory fitness, muscle strength, and physical performance within the first month after diagnosis. However, the evidence is based on a small number of studies with large clinical heterogeneity, limiting the certainty of evidence.

Upregulation of Insulin-like Growth Factor-I in Response to Chemotherapy in Children with Acute Lymphoblastic Leukemia.

The treatment of childhood cancer is challenged by toxic side effects mainly due to chemotherapy-induced organ damage and infections, which are accompanied by severe systemic inflammation. Insulin-like growth factor I (IGF-I) is a key regulating factor in tissue repair. This study investigated associations between the circulating IGF-I levels and chemotherapy-related toxicity in pediatric acute lymphoblastic leukemia (ALL). In this prospective study, we included 114 patients (age: 1-17 years) with newly diagnosed ALL treated according to The Nordic Society of Paediatric Haematology and Oncology (NOPHO) ALL2008 protocol between 2013 and 2018. The patients' plasma levels of IGF-I, and the primary binding protein, IGFBP-3, were measured weekly during the first six weeks of treatment, including the induction therapy. The patients' systemic inflammation was monitored by their C-reactive protein (CRP) and interleukin (IL)-6 levels and their intestinal epithelial damage by their plasma citrulline levels. IGF-I and IGFBP-3 were converted into sex-and age-adjusted standard deviation scores (SDS) using 1621 healthy children as reference. At ALL diagnosis, IGF-I levels were decreased (median (quartiles): -1.2 SDS (-1.9 to -0.5), p = 0.001), but increased significantly following the initiation of chemotherapy, peaking on day 8 (0.0 SDS (from -0.8 to 0.7), p < 0.001). This increase correlated with the levels of CRP (rho = 0.37, p < 0.001) and IL-6 (rho = 0.39, p = 0.03) on day 15, when these markers reached maximum levels. A larger IGF-I increase from day 1 to 15 correlated with a slower recovery rate of the intestinal damage marker citrulline from day 15 to 29 (rho = -0.28, p = 0.01). Likewise, IGFBP-3 was reduced at diagnosis, followed by an increase after treatment initiation, and was highly correlated with same-day IGF-I levels. This study demonstrates a chemotherapy-induced increase in IGF-I, with a response that appears to reflect the severity of tissue damage and systemic inflammation, preceding CRP and IL-6 increases. IGF-I may have potential as an early reactive biomarker for acute toxicity in patients with ALL.

Artificial intelligence and pathology: From principles to practice and future applications in histomorphology and molecular profiling.

The complexity of diagnostic (surgical) pathology has increased substantially over the last decades with respect to histomorphological and molecular profiling. Pathology has steadily expanded its role in tumor diagnostics and beyond from disease entity identification via prognosis estimation to precision therapy prediction. It is therefore not surprising that pathology is among the disciplines in medicine with high expectations in the application of artificial intelligence (AI) or machine learning approaches given their capabilities to analyze complex data in a quantitative and standardized manner to further enhance scope and precision of diagnostics. While an obvious application is the analysis of histological images, recent applications for the analysis of molecular profiling data from different sources and clinical data support the notion that AI will enhance both histopathology and molecular pathology in the future. At the same time, current literature should not be misunderstood in a way that pathologists will likely be replaced by AI applications in the foreseeable future. Although AI will transform pathology in the coming years, recent studies reporting AI algorithms to diagnose cancer or predict certain molecular properties deal with relatively simple diagnostic problems that fall short of the diagnostic complexity pathologists face in clinical routine. Here, we review the pertinent literature of AI methods and their applications to pathology, and put the current achievements and what can be expected in the future in the context of the requirements for research and routine diagnostics.

Gastrointestinal barrier integrity and mucosal inflammation as risk factors of blood stream infections in children treated for acute lymphoblastic leukaemia.

Chemotherapy-induced mucositis increases the risk of blood stream infections (BSI) due to translocation of bacteria across the intestinal epithelium. Our study investigated if quantitative measures of intestinal mucositis severity, including plasma citrulline (a marker of functional enterocytes) and CCL20 (an intestinal immune homeostatic chemokine), could identify patients at risk of BSI. A total of 106 children with ALL undergoing induction treatment (NOPHO ALL 2008) were included and information regarding BSI episodes was collected from the patients' medical records. Twenty-seven patients (25%) developed BSI during induction. Patients with BSI had a larger decrease in citrulline after chemotherapy than patients without BSI, and nearly all BSI episodes (25/27) occurred in the group of patients exhibiting a drop in citrulline (OR = 6.4 [95% CI: 1.4-29.3], P = .008). Patients who developed BSI had higher plasma CCL20 levels on days 8, 15 and 22 than patients without BSI (all P < .05), and elevated CCL20 levels on day 8 increased the risk of subsequent BSI (OR = 1.57 [1.11-2.22] per doubling of CCL20 level, P = .01) in a multivariable logistic regression analysis. These findings suggest that children with ALL who develop BSI during chemotherapy are characterised by more severe intestinal mucositis, as measured by plasma citrulline and CCL20. These markers may be useful in early risk stratification to guide treatment decisions.

Analysing cerebrospinal fluid with explainable deep learning: From diagnostics to insights.

AIM: Analysis of cerebrospinal fluid (CSF) is essential for diagnostic workup of patients with neurological diseases and includes differential cell typing. The current gold standard is based on microscopic examination by specialised technicians and neuropathologists, which is time-consuming, labour-intensive and subjective. METHODS: We, therefore, developed an image analysis approach based on expert annotations of 123,181 digitised CSF objects from 78 patients corresponding to 15 clinically relevant categories and trained a multiclass convolutional neural network (CNN). RESULTS: The CNN classified the 15 categories with high accuracy (mean AUC 97.3%). By using explainable artificial intelligence (XAI), we demonstrate that the CNN identified meaningful cellular substructures in CSF cells recapitulating human pattern recognition. Based on the evaluation of 511 cells selected from 12 different CSF samples, we validated the CNN by comparing it with seven board-certified neuropathologists blinded for clinical information. Inter-rater agreement between the CNN and the ground truth was non-inferior (Krippendorff's alpha 0.79) compared with the agreement of seven human raters and the ground truth (mean Krippendorff's alpha 0.72, range 0.56-0.81). The CNN assigned the correct diagnostic label (inflammatory, haemorrhagic or neoplastic) in 10 out of 11 clinical samples, compared with 7-11 out of 11 by human raters. CONCLUSIONS: Our approach provides the basis to overcome current limitations in automated cell classification for routine diagnostics and demonstrates how a visual explanation framework can connect machine decision-making with cell properties and thus provide a novel versatile and quantitative method for investigating CSF manifestations of various neurological diseases.

Markers of neutrophil chemotaxis for identification of blood stream infections in children with acute lymphoblastic leukemia undergoing induction treatment.

BACKGROUND: Although neutropenic fever is frequently observed during chemotherapy, only a minor proportion is caused by blood stream infections (BSI). This study investigated measurements of neutrophil chemotaxis as risk markers for BSI in children with acute lymphoblastic leukemia (ALL). METHODS: The chemokines CXCL1 and CXCL8 were measured weekly in 106 children with ALL during induction treatment. Information regarding BSI episodes was collected from the patients' medical records. RESULTS: During induction treatment, 102 (96%) patients developed profound neutropenia and 27 (25%) were diagnosed with BSI, debuting on median day 12 (range: 4-29). Patients developing BSI had increased levels of CXCL1 on days 8 and 15 as well as increased CXCL8 on days 8, 15, 22, and 29 compared to patients without BSI (all p < 0.05). Patients with BSI < day 12 exhibited increased CXCL1 and CXCL8 levels as early as day 8 (81 vs. 4 pg/mL, p = 0.031 and 35 vs. 10 pg/mL, p < 0.0001, respectively), while CXCL1 and CXCL8 were increased on day 15 (215 vs. 57 pg/mL, p = 0.022 and 68 vs. 17 pg/mL, p = 0.0002) and after (all p < 0.01) in patients with BSI ≥ day 12. CONCLUSION: The markers of neutrophil chemotaxis, CXCL1, and CXCL8 may help to identify patients at increased risk of BSI during chemotherapy-induced neutropenia.

Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems.

Machine learning models are poised to make a transformative impact on chemical sciences by dramatically accelerating computational algorithms and amplifying insights available from computational chemistry methods. However, achieving this requires a confluence and coaction of expertise in computer science and physical sciences. This Review is written for new and experienced researchers working at the intersection of both fields. We first provide concise tutorials of computational chemistry and machine learning methods, showing how insights involving both can be achieved. We follow with a critical review of noteworthy applications that demonstrate how computational chemistry and machine learning can be used together to provide insightful (and useful) predictions in molecular and materials modeling, retrosyntheses, catalysis, and drug design.

Machine Learning Force Fields.

In recent years, the use of machine learning (ML) in computational chemistry has enabled numerous advances previously out of reach due to the computational complexity of traditional electronic-structure methods. One of the most promising applications is the construction of ML-based force fields (FFs), with the aim to narrow the gap between the accuracy of ab initio methods and the efficiency of classical FFs. The key idea is to learn the statistical relation between chemical structure and potential energy without relying on a preconceived notion of fixed chemical bonds or knowledge about the relevant interactions. Such universal ML approximations are in principle only limited by the quality and quantity of the reference data used to train them. This review gives an overview of applications of ML-FFs and the chemical insights that can be obtained from them. The core concepts underlying ML-FFs are described in detail, and a step-by-step guide for constructing and testing them from scratch is given. The text concludes with a discussion of the challenges that remain to be overcome by the next generation of ML-FFs.

Machine learning models predict the primary sites of head and neck squamous cell carcinoma metastases based on DNA methylation.

In head and neck squamous cell cancers (HNSCs) that present as metastases with an unknown primary (HNSC-CUPs), the identification of a primary tumor improves therapy options and increases patient survival. However, the currently available diagnostic methods are laborious and do not offer a sufficient detection rate. Predictive machine learning models based on DNA methylation profiles have recently emerged as a promising technique for tumor classification. We applied this technique to HNSC to develop a tool that can improve the diagnostic work-up for HNSC-CUPs. On a reference cohort of 405 primary HNSC samples, we developed four classifiers based on different machine learning models [random forest (RF), neural network (NN), elastic net penalized logistic regression (LOGREG), and support vector machine (SVM)] that predict the primary site of HNSC tumors from their DNA methylation profile. The classifiers achieved high classification accuracies (RF = 83%, NN = 88%, LOGREG = SVM = 89%) on an independent cohort of 64 HNSC metastases. Further, the NN, LOGREG, and SVM models significantly outperformed p16 status as a marker for an origin in the oropharynx. In conclusion, the DNA methylation profiles of HNSC metastases are characteristic for their primary sites, and the classifiers developed in this study, which are made available to the scientific community, can provide valuable information to guide the diagnostic work-up of HNSC-CUP. © 2021 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.

IL-7 and IL-15 Levels Reflect the Degree of T Cell Depletion during Lymphopenia and Are Associated with an Expansion of Effector Memory T Cells after Pediatric Hematopoietic Stem Cell Transplantation.

Differentially and functionally distinct T cell subsets are involved in the development of complications after allogeneic hematopoietic stem cell transplantation (HSCT), but little is known about factors regulating their recovery after HSCT. In this study, we investigated associations between immune-regulating cytokines, T cell differentiation, and clinical outcomes. We included 80 children undergoing allogeneic HSCT for acute leukemia using bone marrow or peripheral blood stem cells grafted from a matched sibling or unrelated donor. Cytokines (IL-7, IL-15, IL-18, SCF, IL-6, IL-2, and TNF-α) and active anti-thymocyte globulin (ATG) levels were longitudinally measured along with extended T cell phenotyping. The cytokine profiles showed a temporary rise in IL-7 and IL-15 during lymphopenia, which was strongly dependent on exposure to active ATG. High levels of IL-7 and IL-15 from graft infusion to day +30 were predictive of slower T cell recovery during the first 2 mo post-HSCT; however, because of a major expansion of memory T cell stages, only naive T cells remained decreased after 3 mo (p < 0.05). No differential effect was seen on polarization of CD4+ T cells into Th1, Th2, or Th17 cells or regulatory T cells. Low levels of IL-7 and IL-15 at day +14 were associated with acute graft-versus-host disease grades II-IV in ATG-treated patients (p = 0.0004 and p = 0.0002, respectively). Children with IL-7 levels comparable to healthy controls at day +14 post-HSCT were less likely to develop EBV reactivation posttransplant. These findings suggest that quantification of IL-7 and IL-15 may be useful as biomarkers in assessing the overall T cell depletion and suggest a potential for predicting complications after HSCT.

Metabolic syndrome as a late effect of childhood hematopoietic stem cell transplantation - A thorough statistical evaluation of putative risk factors.

BACKGROUND: Metabolic syndrome (MetS) is frequent among survivors of childhood hematopoietic stem-cell transplantation (HSCT), but assessment of risk factors is challenged by survivor and participation bias in long-term follow-up studies. METHODS: A cohort of 395 pediatric patients transplanted between 1980 and 2018 was investigated. MetS was assessed at follow-up between December 2018 and March 2020. Two composite outcomes ((a) combining MetS and death, (b) combining MetS, death, and nonparticipation) were considered to address the risk of selection bias. RESULTS: Among 234 survivors invited to the follow-up, 96 individuals (median age 27 years) participated. MetS prevalence was 30% among participants. The only significant HSCT risk factor was a variable combining HSCT indication and conditioning with total-body irradiation (TBI) (p = .0011). Compared to acute leukemias (AL) treated with high-grade TBI (8-12 Gy), a lower MetS prevalence was seen for nonmalignant diseases treated with no/low-grade TBI (0-4.5 Gy) (OR = 0.04, 95% confidence interval (CI): 0.00-0.23). Analyses of the composite outcomes indicated overestimation of the effect of high-grade TBI due to selection bias. Scrutiny showed strong residual confounding between HSCT indication and high-grade TBI within AL-patients. The HSCT effect on MetS reflected HSCT effects on high-density-lipoprotein (HDL) and triglycerides. Compared to AL treated with high-grade TBI, nonmalignant diagnoses treated with no/low-grade TBI had higher HDL (+40%, 95% CI: +21% to +62%) and lower triglyceride (-59%, 95% CI: -71% to -42%). CONCLUSION: The TBI effect on MetS may be overestimated in follow-up studies due to selection bias and confounding. The TBI effect was confined to the potentially modifiable MetS criteria  HDL and triglyceride.

Automatic identification of chemical moieties.

In recent years, the prediction of quantum mechanical observables with machine learning methods has become increasingly popular. Message-passing neural networks (MPNNs) solve this task by constructing atomic representations, from which the properties of interest are predicted. Here, we introduce a method to automatically identify chemical moieties (molecular building blocks) from such representations, enabling a variety of applications beyond property prediction, which otherwise rely on expert knowledge. The required representation can either be provided by a pretrained MPNN, or be learned from scratch using only structural information. Beyond the data-driven design of molecular fingerprints, the versatility of our approach is demonstrated by enabling the selection of representative entries in chemical databases, the automatic construction of coarse-grained force fields, as well as the identification of reaction coordinates.

Harmoni: A method for eliminating spurious interactions due to the harmonic components in neuronal data.

Cross-frequency synchronization (CFS) has been proposed as a mechanism for integrating spatially and spectrally distributed information in the brain. However, investigating CFS in Magneto- and Electroencephalography (MEG/EEG) is hampered by the presence of spurious neuronal interactions due to the non-sinusoidal waveshape of brain oscillations. Such waveshape gives rise to the presence of oscillatory harmonics mimicking genuine neuronal oscillations. Until recently, however, there has been no methodology for removing these harmonics from neuronal data. In order to address this long-standing challenge, we introduce a novel method (called HARMOnic miNImization - Harmoni) that removes the signal components which can be harmonics of a non-sinusoidal signal. Harmoni's working principle is based on the presence of CFS between harmonic components and the fundamental component of a non-sinusoidal signal. We extensively tested Harmoni in realistic EEG simulations. The simulated couplings between the source signals represented genuine and spurious CFS and within-frequency phase synchronization. Using diverse evaluation criteria, including ROC analyses, we showed that the within- and cross-frequency spurious interactions are suppressed significantly, while the genuine activities are not affected. Additionally, we applied Harmoni to real resting-state EEG data revealing intricate remote connectivity patterns which are usually masked by the spurious connections. Given the ubiquity of non-sinusoidal neuronal oscillations in electrophysiological recordings, Harmoni is expected to facilitate novel insights into genuine neuronal interactions in various research fields, and can also serve as a steppingstone towards the development of further signal processing methods aiming at refining within- and cross-frequency synchronization in electrophysiological recordings.

Towards the interpretability of deep learning models for multi-modal neuroimaging: Finding structural changes of the ageing brain.

Brain-age (BA) estimates based on deep learning are increasingly used as neuroimaging biomarker for brain health; however, the underlying neural features have remained unclear. We combined ensembles of convolutional neural networks with Layer-wise Relevance Propagation (LRP) to detect which brain features contribute to BA. Trained on magnetic resonance imaging (MRI) data of a population-based study (n = 2637, 18-82 years), our models estimated age accurately based on single and multiple modalities, regionally restricted and whole-brain images (mean absolute errors 3.37-3.86 years). We find that BA estimates capture ageing at both small and large-scale changes, revealing gross enlargements of ventricles and subarachnoid spaces, as well as white matter lesions, and atrophies that appear throughout the brain. Divergence from expected ageing reflected cardiovascular risk factors and accelerated ageing was more pronounced in the frontal lobe. Applying LRP, our study demonstrates how superior deep learning models detect brain-ageing in healthy and at-risk individuals throughout adulthood.