Radiomics analysis for prediction and classification of submucosal tumors based on gastrointestinal endoscopic ultrasonography.

Objectives: To identify and classify submucosal tumors by building and validating a radiomics model with gastrointestinal endoscopic ultrasonography (EUS) images. Methods: A total of 144 patients diagnosed with submucosal tumors through gastrointestinal EUS were collected between January 2019 and October 2020. There are 1952 radiomic features extracted from each patient's EUS images. The statistical test and the customized least absolute shrinkage and selection operator regression were used for feature selection. Subsequently, an extremely randomized trees algorithm was utilized to construct a robust radiomics classification model specifically tailored for gastrointestinal EUS images. The performance of the model was measured by evaluating the area under the receiver operating characteristic curve. Results: The radiomics model comprised 30 selected features that showed good discrimination performance in the validation cohorts. During validation, the area under the receiver operating characteristic curve was calculated as 0.9203 and the mean value after 10-fold cross-validation was 0.9260, indicating excellent stability and calibration. These results confirm the clinical utility of the model. Conclusions: Utilizing the dataset provided curated from gastrointestinal EUS examinations at our collaborating hospital, we have developed a well-performing radiomics model. It can be used for personalized and non-invasive prediction of the type of submucosal tumors, providing physicians with aid for early treatment and management of tumor progression.

Metabolomic and transcriptomic analyses of peach leaves and fruits in response to pruning.

BACKGROUND: Pruning is an important cultivation management option that has important effects on peach yield and quality. However, the effects of pruning on the overall genetic and metabolic changes in peach leaves and fruits are poorly understood. RESULTS: The transcriptomic and metabolomic profiles of leaves and fruits from trees subjected to pruning and unpruning treatments were measured. A total of 20,633 genes and 622 metabolites were detected. Compared with those in the control, 1,127 differentially expressed genes (DEGs) and 77 differentially expressed metabolites (DEMs) were identified in leaves from pruned and unpruned trees (pdLvsupdL), whereas 423 DEGs and 29 DEMs were identified in fruits from the pairwise comparison pdFvsupdF. The content of three auxin analogues was upregulated in the leaves of pruned trees, the content of all flavonoids detected in the leaves decreased, and the expression of almost all genes involved in the flavonoid biosynthesis pathway decreased. The phenolic acid and amino acid metabolites detected in fruits from pruned trees were downregulated, and all terpenoids were upregulated. The correlation analysis revealed that DEGs and DEMs in leaves were enriched in tryptophan metabolism, auxin signal transduction, and flavonoid biosynthesis. DEGs and DEMs in fruits were enriched in flavonoid and phenylpropanoid biosynthesis, as well as L-glutamic acid biosynthesis. CONCLUSIONS: Pruning has different effects on the leaves and fruits of peach trees, affecting mainly the secondary metabolism and hormone signalling pathways in leaves and amino acid biosynthesis in fruits.

Pest categorisation of Cenopalpus irani.

The EFSA Panel on Plant Health performed a pest categorisation of Cenopalpus irani (Trombidiformes: Tenuipalpidae), known as the Iranian false spider mite, following the commodity risk assessment of Malus domestica plants from Türkiye, in which C. irani was identified as a pest of possible concern for the territory of the European Union (EU). The pest is only known to be present in Iran and Türkiye and has not been reported from the EU. The mite primarily feeds on Rosaceae plants but is considered polyphagous. Important crops of the EU that are hosts of C. irani include apples (Malus domestica), pears (Pyrus communis) and figs (Ficus carica). Plants for planting and fruits provide potential pathways for entry into the EU. Host availability and climate suitability in southern EU countries would most probably allow this species to successfully establish and spread. This mite is not listed in Annex II of Commission Implementing Regulation (EU) 2019/2072. Phytosanitary measures are available to reduce the likelihood of entry and spread of this species into the EU. The mite C. irani satisfies the criteria that are within the remit of EFSA to assess for it to be regarded as a potential Union quarantine pest, although there is a key uncertainty over the likelihood and magnitude of impact.

Missing data imputation using classification and regression trees.

Background: Missing data are common when analyzing real data. One popular solution is to impute missing data so that one complete dataset can be obtained for subsequent data analysis. In the present study, we focus on missing data imputation using classification and regression trees (CART). Methods: We consider a new perspective on missing data in a CART imputation problem and realize the perspective through some resampling algorithms. Several existing missing data imputation methods using CART are compared through simulation studies, and we aim to investigate the methods with better imputation accuracy under various conditions. Some systematic findings are demonstrated and presented. These imputation methods are further applied to two real datasets: Hepatitis data and Credit approval data for illustration. Results: The method that performs the best strongly depends on the correlation between variables. For imputing missing ordinal categorical variables, the rpart package with surrogate variables is recommended under correlations larger than 0 with missing completely at random (MCAR) and missing at random (MAR) conditions. Under missing not at random (MNAR), chi-squared test methods and the rpart package with surrogate variables are suggested. For imputing missing quantitative variables, the iterative imputation method is most recommended under moderate correlation conditions.

A taxonomic revision of Rhizophora L. (Rhizophoraceae) in Thailand.

A taxonomic revision of Rhizophora L. (Rhizophoraceae) in Thailand is presented. Two species, R. apiculata Blume and R. mucronata Poir., are enumerated with updated morphological descriptions, illustrations and a taxonomic identification key, together with notes on distributions, habitats and ecology, phenology, conservation assessments, etymology, vernacular names, uses, and specimens examined. Three names in Rhizophora, are lectotypified: R. apiculata and two associated synonyms of R. mucronata (i.e., R. latifolia Miq. and R. macrorrhiza Griff.). R. longissima Blanco, a synonym of R. mucronata, is neotypified. All two Rhizophora species have a conservation assessment of Least Concern (LC). Based on the morphological identification, these two species can be distinguished from one another by the shape and width of the leaf laminae and the length of a terminal stiff point of the leaf laminae; the type and position of the inflorescences and the number of flowers per inflorescence; the character and color of the bracteoles; the presence or absence of the flower pedicels; the shape of the mature flower buds; the shape, color, and texture of the sepals; the shape, character, and the presence or absence of hairs of the petals; the number of stamens per flower; the size of the fruits; the color and size of the hypocotyls; the color and diameter of the cotyledonous cylindrical tubes; and the color of the colleters and exudate. The thick cuticles, sunken stomata, large hypodermal cells, and cork warts are adaptive anatomical features of leaves in Rhizophora that live in the mangrove environments. The pollen grains of Thai Rhizophora species are tricolporate, prolate spheroidal or oblate spheroidal shapes, small-sized, and reticulate exine sculpturing.

Analysis of the privacy-performance tradeoff of reference testing in Forensic Investigative Genetic Genealogy.

During an investigation using Forensic Investigative Genetic Genealogy, which is a novel approach for solving violent crimes and identifying human remains, reference testing-when law enforcement requests a DNA sample from a person in a partially constructed family tree-is sometimes used when an investigation has stalled. Because the people considered for a reference test have not opted in to allow law enforcement to use their DNA profile in this way, reference testing is viewed by many as an invasion of privacy and by some as unethical. We generalize an existing mathematical optimization model of the genealogy process by incorporating the option of reference testing. Using simulated versions of 17 DNA Doe Project cases, we find that reference testing can solve cases more quickly (although many reference tests are required to substantially hasten the investigative process), but only rarely (<1%) solves cases that cannot otherwise be solved. Through a mixture of mathematical and computational analysis, we find that the most desirable people to test are at the bottom of a path descending from an ancestral couple that is most likely to be related to the target. We also characterize the rare cases where reference testing is necessary for solving the case: when there is only one descending path from an ancestral couple, which precludes the possibility of identifying an intersection (e.g., marriage) between two descendants of two different ancestral couples.

Polymorphism-aware models in RevBayes: Species trees, disentangling Balancing Selection and CG-biased gene conversion.

The role of balancing selection is a long-standing evolutionary puzzle. Balancing selection is a crucial evolutionary process that maintains genetic variation (polymorphism) over extended periods of time; however, detecting it poses a significant challenge. Building upon the polymorphism-aware phylogenetic models (PoMos) framework rooted in the Moran model, we introduce PoMoBalance model. This novel approach is designed to disentangle the interplay of mutation, genetic drift, directional selection (GC-biased gene conversion), along with the previously unexplored balancing selection pressures on ultra-long timescales comparable with species divergence times by analysing multi-individual genomic and phylogenetic divergence data. Implemented in the open-source RevBayes Bayesian framework, PoMoBalance offers a versatile tool for inferring phylogenetic trees as well as quantifying various selective pressures. The novel aspect of our approach in studying balancing selection lies in PoMos' ability to account for ancestral polymorphisms and incorporate parameters that measure frequency-dependent selection, allowing us to determine the strength of the effect and exact frequencies under selection. We implemented validation tests and assessed the model on the data simulated with SLiM and a custom Moran model simulator. Real sequence analysis of Drosophila populations reveals insights into the evolutionary dynamics of regions subject to frequency-dependent balancing selection, particularly in the context of sex-limited colour dimorphism in Drosophila erecta.

A BERT-GNN Approach for Metastatic Breast Cancer Prediction Using Histopathology Reports.

Metastatic breast cancer (MBC) continues to be a leading cause of cancer-related deaths among women. This work introduces an innovative non-invasive breast cancer classification model designed to improve the identification of cancer metastases. While this study marks the initial exploration into predicting MBC, additional investigations are essential to validate the occurrence of MBC. Our approach combines the strengths of large language models (LLMs), specifically the bidirectional encoder representations from transformers (BERT) model, with the powerful capabilities of graph neural networks (GNNs) to predict MBC patients based on their histopathology reports. This paper introduces a BERT-GNN approach for metastatic breast cancer prediction (BG-MBC) that integrates graph information derived from the BERT model. In this model, nodes are constructed from patient medical records, while BERT embeddings are employed to vectorise representations of the words in histopathology reports, thereby capturing semantic information crucial for classification by employing three distinct approaches (namely univariate selection, extra trees classifier for feature importance, and Shapley values to identify the features that have the most significant impact). Identifying the most crucial 30 features out of 676 generated as embeddings during model training, our model further enhances its predictive capabilities. The BG-MBC model achieves outstanding accuracy, with a detection rate of 0.98 and an area under curve (AUC) of 0.98, in identifying MBC patients. This remarkable performance is credited to the model's utilisation of attention scores generated by the LLM from histopathology reports, effectively capturing pertinent features for classification.

First report of silverleaf caused by Chondrostereum purpureum in hazelnut (Corylus avellana) in Chile.

Hazelnut is among the most important nut crops in Chile, currently covering 46,000 ha. In 2023, the country exported 30,000-ton. In recent years the incidence of plants with internal discoloration, cankers and dieback has been increasing. In some cases, the trees died and had to be removed and, after a year, purple resupinate fruiting bodies were observed growing from the stumps. To determine the etiology of the symptoms and signs, wood samples (n=318) were collected since 2020, from 38 symptomatic orchards from Maule to La Araucanía Regions, primarily from the cvs. Tonda di Giffoni and Lewis. Wood sections 0.5 cm diameter were cut from the symptomatic tissues, disinfected using a sodium hypochlorite (10%) solution, and plated on a quarter-strength acidified potato dextrose agar (aPDA1/4). The plates were incubated and purified on PDA. Subsequently, isolates were identified by morphological and molecular means. Almost half of the isolates (47%) were preliminarily identified as basidiomycetes, based on mycelial features such as the presence of clamp connections, with 45% of them exhibiting abundant whitish cottony fast-growth mycelia, resembling Chondrostereum purpureum (Grinbergs et al., 2020). DNA was extracted and the 500-bp fragment, located between 5S and 18S ribosomal regions, was amplified using APN1 specific primers (Becker et al. 1999), identifying the isolates as C. purpureum. In addition, 5.8S gene of RGM1 (35°13'40.9"S 71°25'14.1"W), RGM2 (36°31'27.95"S 71°46'58.31"W), RGM3 (37°10'54.8"S 72°03'39.6"W), RGM4 (35°19'25.2"S 71°19'54.7"W) and RGM5 (36°35'30.8"S 72°05'18.8"W) isolates, representing different locations within the hazelnut growing area, was amplified using ITS1/ITS4 primers (White et al., 1990). The PCR product was sequenced, and the analysis showed 100% homology among isolates (Genebank codes: PP839283, PP839284, PP839285, PP839286 and PP839287, respectively). To determine the pathogenicity of the isolates, 30-cm healthy cuttings cv. Lewis were inoculated with mycelial plugs, while control shoots were inoculated with sterile agar plugs. Cuttings were vertically arranged in pots with 3-cm water and incubated for 60-d at 22°C. In addition, fresh cuts of 3-y potted plants cv. Lewis were inoculated with mycelial plugs and incubated for 137-d in a shadehouse. After incubation, bark was removed from inoculated cuttings and the length of necrotic lesions was measured. Although discoloration was reproduced by all the isolates in both pathogenicity tests, RGM1 isolate was the most aggressive, causing the complete discoloration of the cuttings and the death of the inoculated plants. To our knowledge this is the first report of C. purpureum causing wood disease in hazelnut. These findings are significant because the disease may not only reduce orchard longevity but also decrease fruit yield and quality, as observed in other fruit crops (Grinbergs et al., 2021).

Holistic evaluation of a machine learning-based timing calibration for PET detectors under varying data sparsity.

OBJECTIVE: Modern PET scanners offer precise TOF information, improving the SNR of the reconstructed images. Timing calibrations are performed to reduce the worsening effects of the system components and provide valuable TOF information. Traditional calibration procedures often provide static or linear corrections, with the drawback that higher-order skews or event-to-event corrections are not addressed. Novel research demonstrated significant improvements in the reachable timing resolutions when combining conventional calibration approaches with machine learning, with the disadvantage of extensive calibration times infeasible for a clinical application. In this work, we made the first steps towards an in-system application and analyzed the effects of varying data sparsity on a machine learning timing calibration, aiming to accelerate the calibration time. Furthermore, we demonstrated the versatility of our calibration concept by applying the procedure for the first time to analog readout technology. Approach. We modified experimentally acquired calibration data used for training regarding their statistical and spatial sparsity, mimicking reduced measurement time and variability of the training data. Trained models were tested on unseen test data, characterized by fine spatial sampling and rich statistics. In total, 80 decision tree models with the same hyperparameter settings, were trained and holistically evaluated regarding data scientific, physics-based, and PET-based quality criteria. Main results. The calibration procedure can be heavily reduced from several days to some minutes without sacrificing quality and still significantly improving the timing resolution from (304 ± 5) ps to (216 ± 1) ps compared to conventionally used analytical calibration methods. Significance. This work serves as the first step in making the developed machine learning-based calibration suitable for an in-system application to profit from the method's capabilities on the system level. Furthermore, this work demonstrates the functionality of the methodology on detectors using analog readout technology. The proposed holistic evaluation criteria here serve as a guideline for future evaluations of machine learning-based calibration approaches. .

Forest genomics in the Caucasus through the lens of its dominant tree species - Fagus orientalis.

The last glacial period is known to have greatly influenced the demographic history of temperate forest trees, with important range contractions and post-glacial expansions that led to the formation of multiple genetic lineages and secondary contact zones in the Northern Hemisphere. These dynamics have been extensively studied for European and North American species but are still poorly understood in other temperate regions of rich biodiversity such as the Caucasus. Our study helps filling that gap by deciphering the genomic landscapes of F. orientalis across the South Caucasus. The use of genome-wide data confirmed a past demographic history strongly influenced by the Last Glacial Maximum, revealing two disjunct glacial refugia in the Colchis and Hyrcanian regions. The resulting patterns of genetic diversity, load and differentiation are not always concordant across the region, with genetic load pinpointing the location of the glacial refugia more efficiently than genetic diversity alone. The Hyrcanian forests show depleted genetic diversity and substantial isolation, even if long-distance gene flow is still present with the main centre of diversity in the Greater Caucasus. Finally, we characterize a strong heterogeneity of genetic diversity and differentiation along the species chromosomes, with noticeably a first chromosome showing low diversity and weak differentiation.

Predicting plant disease epidemics using boosted regression trees.

Plant epidemics are often associated with weather-related variables. It is difficult to identify weather-related predictors for models predicting plant epidemics. In the article by Shah et al., to predict Fusarium head blight (FHB) epidemics of wheat, they explored a functional approach using scalar-on-function regression to model a binary outcome (FHB epidemic or non-epidemic) with respect to weather time series spanning 140 days relative to anthesis. The scalar-on-function models fit the data better than previously described logistic regression models. In this work, given the same dataset and models, we attempt to reproduce the article by Shah et al. using a different approach, boosted regression trees. After fitting, the classification accuracy and model statistics are surprisingly good.

Modeling groundwater redox conditions at national scale through integration of sediment color and water chemistry in a machine learning framework.

Redox conditions play a crucial role in determining the fate of many contaminants in groundwater, impacting ecosystem services vital for both the aquatic environment and human water supply. Geospatial machine learning has previously successfully modelled large-scale redox conditions. This study is the first to consolidate the complementary information provided by sediment color and water chemistry to enhance our understanding of redox conditions in Denmark. In the first step, the depth to the first redox interface is modelled using sediment color from 27,042 boreholes. In the second step, the depth of the first redox interface is compared against water chemistry data at 22,198 wells to classify redox complexity. The absence of nitrate containing water below the first redox interface is referred to as continuous redox conditions. In contrast, discontinuous redox conditions are identified by the presence of nitrate below the first redox interface. Both models are built using 20 covariate maps, encompassing diverse hydrologically relevant information. The first redox interface is modelled with a mean error of 0.0 m and a root-mean-squared error of 8.0 m. The redox complexity model attains an accuracy of 69.8 %. Results indicate a mean depth to the first redox interface of 8.6 m and a standard deviation of 6.5 m. 60 % of Denmark is classified as discontinuous, indicating complex redox conditions, predominantly collocated in clay rich glacial landscapes. Both maps, i.e., first redox interface and redox complexity are largely driven by the water table and hydrogeology. The developed maps contribute to our understanding of subsurface redox processes, supporting national-scale land-use and water management.

Impact of the restraint decision tree for physical restraint use in South Korean neurointensive care units.

BACKGROUND: Nurses in neurointensive care units (NCUs) commonly use physical restraint (PR) to prevent adverse events like unplanned removal of devices (URDs) or falls. However, PR use should be based on evidenced decisions as it has drawbacks. Unfortunately, there is a lack of research-based PR protocol to support decision-making for nurses, especially for neurocritical patients. AIMS: This study developed a restraint decision tree for neurocritical patients (RDT-N) to assist nurses in making PR decisions. We assessed its effectiveness in reducing PR use and adverse events. STUDY DESIGN: This study employed a baseline and post-intervention test design at a NCU with 19 beds and 45 nurses in a tertiary hospital in a metropolitan city in South Korea. Two-hundred and thirty-seven adult patients were admitted during the study period. During the intervention, nurses were trained on the RDT-N. PR use and adverse events between the baseline and post-intervention periods were compared. RESULTS: Post-intervention, total number of restrained patients decreased (20.7%-16.3%; χ2 = 7.68, p = .006), and the average number of PR applied per restrained patient decreased (2.42-1.71; t = 5.74, p < .001). The most frequently used PR type changed from extremity cuff to mitten (χ2 = 397.62, p < .001). No falls occurred during the study periods. On the other hand, URDs at baseline were 18.67 cases per 1000 patient days in the high-risk group and 5.78 cases per 1000 patient days in the moderate-risk group; however, no URD cases were reported post-intervention. CONCLUSIONS: The RDT-N effectively reduced PR use and adverse events. Its application can enhance patient-centred care based on individual condition and potential risks in NCUs. RELEVANCE TO CLINICAL PRACTICE: Nurses can use the RDT-N to assess the need for PR in caring for neurocritical patients, reducing PR use and adverse events.

Enhanced multistage deep learning for diagnosing anterior disc displacement in temporomandibular joint using magnetic resonance imaging.

OBJECTIVES: This study aimed to propose a new method for the automatic diagnosis of anterior disc displacement of the temporomandibular joint (TMJ) using magnetic resonance imaging (MRI) and deep learning. By employing a multistage approach, the factors affecting the final result can be easily identified and improved. METHODS: This study introduces a multistage automatic diagnostic technique using deep learning. This process involves segmenting the target from MR images, extracting distance parameters, and classifying the diagnosis into three classes. MRI exams of 368 TMJs from 204 patients were evaluated for anterior disc displacement. In the first stage, five algorithms were used for the semantic segmentation of the disc and condyle. In the second stage, 54 distance parameters were extracted from the segments. In the third stage, a rule-based decision model was developed to link the parameters with the expert diagnosis results. RESULTS: In the first stage, DeepLabV3+ showed the best result (95% Hausdorff distance, Dice coefficient, and sensitivity of 6.47 ± 7.22, 0.84 ± 0.07, and 0.84 ± 0.09, respectively). This study used the original MRI exams as input without preprocessing and showed high segmentation performance compared with that of previous studies. In the third stage, the combination of SegNet and a random forest model yielded an accuracy of 0.89 ± 0.06. CONCLUSIONS: An algorithm was developed to automatically diagnose TMJ-anterior disc displacement using MRI. Through a multistage approach, this algorithm facilitated the improvement of results and demonstrated high accuracy from more complex inputs. Furthermore, existing radiological knowledge was applied and validated.

Potential of reproductive traits in functional ecology: A quantitative comparison of variability in floral, fruit, and leaf traits.

Despite their claimed low intraspecific variability, plant reproductive traits are less frequently used in functional ecology. Here we focused on underrepresented plant organs, i.e. flowers and fruits, by comparing their traits with well-established leaf traits. We evaluated 16 functional traits (six floral, six fruit, and four leaf traits) in a randomly selected group of woody species under comparable environmental conditions. We aimed to assess interspecific and intraspecimen variability and explore the potential of the proposed flower and fruit traits for ecological research. Traits related to the dry mass of flowers and fruits exhibited the highest interspecific variability, while carbon content traits in flowers and leaves had the lowest. At a specimen level, specific leaf area revealed the highest variation. Carbon content traits for all organs demonstrated the least intraspecimen variability, with flower carbon content being the least variable. Our study revealed connections between the newly proposed traits and widely recognized functional traits, uncovering intriguing links between the established traits and the floral and fruit traits upon which we focused. This complements the already well-recognized variability in plant form and function with additional insights into reproductive processes.

Maximum Likelihood Estimation for Unrooted 3-Leaf Trees: An Analytic Solution for the CFN Model.

Maximum likelihood estimation is among the most widely-used methods for inferring phylogenetic trees from sequence data. This paper solves the problem of computing solutions to the maximum likelihood problem for 3-leaf trees under the 2-state symmetric mutation model (CFN model). Our main result is a closed-form solution to the maximum likelihood problem for unrooted 3-leaf trees, given generic data; this result characterizes all of the ways that a maximum likelihood estimate can fail to exist for generic data and provides theoretical validation for predictions made in Parks and Goldman (Syst Biol 63(5):798-811, 2014). Our proof makes use of both classical tools for studying group-based phylogenetic models such as Hadamard conjugation and reparameterization in terms of Fourier coordinates, as well as more recent results concerning the semi-algebraic constraints of the CFN model. To be able to put these into practice, we also give a complete characterization to test genericity.

Predicting lower limb lymphedema after cervical cancer surgery using artificial neural network and decision tree models.

PURPOSE: This study aimed to develop and validate accessible artificial neural network and decision tree models to predict the risk of lower limb lymphedema after cervical cancer surgery. METHODS: We selected 759 patients who underwent cervical cancer surgery at the Hunan Cancer Hospital from January 2010 to January 2020, collecting demographic, behavioral, clinicopathological, and disease-related data. The artificial neural network and decision tree techniques were used to construct prediction models for lower limb lymphedema after cervical cancer surgery. Then, the models' predictive efficacies were evaluated to select the optimal model using several methods, such as the area under the receiver operating characteristic curve and accuracy, sensitivity, and specificity tests. RESULTS: In the training set, the artificial neural network and decision tree model accuracies for predicting lower limb lymphedema after cervical cancer surgery were 99.80% and 88.14%, and the sensitivities 99.50% and 74.01%, respectively; the specificities were 100% and 95.20%, respectively. The area under the receiver operating characteristic curve was 1.00 for the artificial neural network and 0.92 for the decision tree model. In the test set, the artificial neural network and decision tree models' accuracies were 86.70% and 82.02%, and the sensitivities 65.70% and 67.11%, respectively; the specificities were 96.00% and 89.47%, respectively. CONCLUSION: Both models had good predictive efficacy for lower limb lymphedema after cervical cancer surgery. However, the predictive performance and stability were superior in the artificial neural network model than in the decision tree model.

Tropical Logistic Regression Model on Space of Phylogenetic Trees.

Classification of gene trees is an important task both in the analysis of multi-locus phylogenetic data, and assessment of the convergence of Markov Chain Monte Carlo (MCMC) analyses used in Bayesian phylogenetic tree reconstruction. The logistic regression model is one of the most popular classification models in statistical learning, thanks to its computational speed and interpretability. However, it is not appropriate to directly apply the standard logistic regression model to a set of phylogenetic trees, as the space of phylogenetic trees is non-Euclidean and thus contradicts the standard assumptions on covariates. It is well-known in tropical geometry and phylogenetics that the space of phylogenetic trees is a tropical linear space in terms of the max-plus algebra. Therefore, in this paper, we propose an analogue approach of the logistic regression model in the setting of tropical geometry. Our proposed method outperforms classical logistic regression in terms of Area under the ROC Curve in numerical examples, including with data generated by the multi-species coalescent model. Theoretical properties such as statistical consistency have been proved and generalization error rates have been derived. Finally, our classification algorithm is proposed as an MCMC convergence criterion for Mr Bayes. Unlike the convergence metric used by Mr Bayes which is only dependent on tree topologies, our method is sensitive to branch lengths and therefore provides a more robust metric for convergence. In a test case, it is illustrated that the tropical logistic regression can differentiate between two independently run MCMC chains, even when the standard metric cannot.

Diverging growth trends and climate sensitivities of individual pine trees after the 1976 extreme drought.

Summer droughts are affecting the productivity and functioning of central European forests, with potentially lasting consequences for species composition and carbon sequestration. Long-term recovery rates and individual growth responses that may diverge from species-specific and population-wide behaviour are, however, poorly understood. Here, we present 2052 pine (Pinus sylvestris) ring width series from 19 forest sites in south-west Germany to investigate growth responses of individual trees to the exceptionally hot and dry summer of 1976. This outstanding drought event presents a distinctive test case to examine long-term post-drought recovery dynamics. We have proposed a new classification approach to identify a distinct sub-population of trees, referred to as "temporarily affected trees", with a prevalence ranging from 9 to 33 % across the forest stands. These trees exhibited an exceptionally prolonged growth suppression, lasting over a decade, indicating significantly lower resilience to the 1976 drought and a 50 % reduced capacity to recover to pre-drought states. Furthermore, shifts in resilience and recovery dynamics are accompanied by changing climate sensitivities, notably an increased response to maximum temperatures and summer droughts in post-1976 affected pines. Our findings underscore the likely interplay between individual factors and micro-site conditions that contribute to divergent tree responses to droughts. Assessing these factors at the individual tree level is recommended to advancing our understanding of forest responses to extreme drought events. By analyzing sub-population growth patterns, our study provides valuable insights into the impacts of summer droughts on central European forests in context of increasing drought events.