Statistical Pattern Analysis Research Articles

MEASURING OSTEOARTHRITIS KNEE NOCICEPTION USING PHYSIOLOGICAL AND MOVEMENT RESPONSES AND A DEFINED THERMAL STIMULUS: A PROOF OF CONCEPT STUDY

Mechanical loading of joints with osteoarthritis (OA) results in pain-related functional impairment, altered joint mechanics and physiological nociceptor interactions leading to an experience of pain. However, the current tools to measure this are largely patient reported subjective impressions of a nociceptive impact. A direct measure of nociception may offer a more objective indicator. Specifically, movement-induced physiological responses to nociception may offer a useful way to monitor knee OA. In this study, we gathered preliminary data on healthy volunteers to analyse whether integrated biomechanical and physiological sensor datasets could display linked and quantifiable information to a nociceptive stimulus.Following ethical approval, 15 healthy volunteers completed 5 movement and stationary activities in 2 conditions; a control setting and then repeated with an applied quantified thermal pain stimulus to their right knee. An inertial measurement unit (IMU) and an electromyography (EMG) lower body marker set were tested and integrated with ground reaction force (GRF) data collection. Galvanic skin response electrodes for skin temperature and conductivity and photoplethysmography (PPG) sensors were manually timestamped to the integrated system.Pilot data showed EMG, GRF and IMU fluctuations within 0.5 seconds of each other in response to a thermal trigger. Preliminary analysis on the 15 participants tested has shown skin conductance, PPG, EMG, GRFs, joint angles and kinematics with varying increases and fluctuations during the thermal condition in comparison to the control condition.Preliminary results suggest physiological and biomechanical data outputs can be linked and identified in response to a defined nociceptive stimulus. Study data is currently founded on healthy volunteers as a proof-of-concept. Further exploratory statistical and sensor readout pattern analysis, alongside early and late-stage OA patient data collection, can provide the information for potential development of wearable nociceptive sensors to measure disease progression and treatment effectiveness.

Editorial: Modeling of COVID-19 and other infectious diseases: Mathematical, statistical and biophysical analysis of spread patterns

Editorial: Modeling of COVID-19 and other infectious diseases: Mathematical, statistical and biophysical analysis of spread patterns

Liquid Crystals as Multifunctional Interfaces for Trapping and Characterizing Colloidal Microplastics.

Identifying and removing microplastics (MPs) from the environment is a global challenge. This study explores how the colloidal fraction of MPs assemble into distinct 2D patterns at aqueous interfaces of liquid crystal (LC) films with the goal of developing surface-sensitive methods for identifying MPs. Polyethylene (PE) and polystyrene (PS) microparticles are measured to exhibit distinct aggregation patterns, with addition of anionic surfactant amplifying differences in PS/PE aggregation patterns: PS changes from a linear chain-like morphology to a singly dispersed state with increasing surfactant concentration whereas PE forms dense clusters at all surfactant concentrations. Statistical analysis of assembly patterns using deep learning image recognition models yields accurate classification, with feature importance analysis confirming that dense, multibranched assemblies are unique features of PE relative to PS. Microscopic characterization of LC ordering at the microparticle surfaces leads to predict LC-mediated interactions (due to elastic strain) with a dipolar symmetry, a prediction consistent with the interfacial organization of PS but not PE. Further analysis leads to conclude that PE microparticles, due to their polycrystalline nature, possess rough surfaces that lead to weak LC elastic interactions and enhanced capillary forces. Overall, the results highlight the potential utility of LC interfaces for rapid identification of colloidal MPs based on their surface properties.

Вплив інгібітора нітрифікації 3,4-диметилпіразолфосфату на продуктивність пшениці озимої за поєднаного використання з КАС-32

Goal. To establish the expediency and effect of using the nitrification inhibitor 3,4-dimethyl pyrazole phosphate (DMPF) in combination with urea-ammonia mixture (KAS-32) on the yield of winter wheat grain. To determine the difference in the yield of winter wheat using different norms of KAS-32 with and without the addition of DMPF. Methods. Field (stationary experiment); laboratory (agrochemical analysis of soil and plant samples); analytical (systematic analysis of long-term results of field experiments and meteorological observations using mathematical and statistical methods, correlation and regression analysis, mathematical modeling, and empirical generalization of established patterns). Results. It was confirmed that the use of DMPF together with KAS-32 significantly influenced the yield of winter wheat. At the same rate of KAS-32, 300 kg/ha in the variant with the use of DMPF, the yield increased by 4.5 t/ha, or 12% compared to the option where KAS-32 was used at the same rate, 300 kg/ha without the use of DMPF. In the variant with a reduced rate of KAS-32, 250 kg/ha with the use of DMPF compared to the option with an increased rate of KAS-32, 300 kg/ha, but without the use of DMPF, the yield increased by 4.2 c/ha or 11.2% over 4 years of research (2018–2021). Conclusions. It was established that in the variants using DMPF together with KAS-32, the productivity increased compared to the control (without fertilizers) by 25.3–25.6 t/ha (67.6–68.4%). In the variants using DMPF together with KAS-32 compared to the variant using KAS-32, but without the use of DMPF, the yield increased by 4.2–4.5 t/ha (11.2–12.0%) over 4 years of research (2018–2021)).

Point pattern analysis and classification on compact two-point homogeneous spaces evolving time.

This paper introduces a new modeling framework for the statistical analysis of point patterns on a manifold defined by a connected and compact two-point homogeneous space, including the special case of the sphere. The presented approach is based on temporal Cox processes driven by a -valued log-intensity. Different aggregation schemes on the manifold of the spatiotemporal point-referenced data are implemented in terms of the time-varying discrete Jacobi polynomial transform of the log-risk process. The n-dimensional microscale point pattern evolution in time at different manifold spatial scales is then characterized from such a transform. The simulation study undertaken illustrates the construction of spherical point process models displaying aggregation at low Legendre polynomial transform frequencies (large scale), while regularity is observed at high frequencies (small scale). K-function analysis supports these results under temporal short, intermediate and long range dependence of the log-risk process.

IPRESTO: Automated discovery of biosynthetic sub-clusters linked to specific natural product substructures.

Microbial specialised metabolism is full of valuable natural products that are applied clinically, agriculturally, and industrially. The genes that encode their biosynthesis are often physically clustered on the genome in biosynthetic gene clusters (BGCs). Many BGCs consist of multiple groups of co-evolving genes called sub-clusters that are responsible for the biosynthesis of a specific chemical moiety in a natural product. Sub-clusters therefore provide an important link between the structures of a natural product and its BGC, which can be leveraged for predicting natural product structures from sequence, as well as for linking chemical structures and metabolomics-derived mass features to BGCs. While some initial computational methodologies have been devised for sub-cluster detection, current approaches are not scalable, have only been run on small and outdated datasets, or produce an impractically large number of possible sub-clusters to mine through. Here, we constructed a scalable method for unsupervised sub-cluster detection, called iPRESTO, based on topic modelling and statistical analysis of co-occurrence patterns of enzyme-coding protein families. iPRESTO was used to mine sub-clusters across 150,000 prokaryotic BGCs from antiSMASH-DB. After annotating a fraction of the resulting sub-cluster families, we could predict a substructure for 16% of the antiSMASH-DB BGCs. Additionally, our method was able to confirm 83% of the experimentally characterised sub-clusters in MIBiG reference BGCs. Based on iPRESTO-detected sub-clusters, we could correctly identify the BGCs for xenorhabdin and salbostatin biosynthesis (which had not yet been annotated in BGC databases), as well as propose a candidate BGC for akashin biosynthesis. Additionally, we show for a collection of 145 actinobacteria how substructures can aid in linking BGCs to molecules by correlating iPRESTO-detected sub-clusters to MS/MS-derived Mass2Motifs substructure patterns. This work paves the way for deeper functional and structural annotation of microbial BGCs by improved linking of orphan molecules to their cognate gene clusters, thus facilitating accelerated natural product discovery.

Differences of injury characteristics of medial patellofemoral ligament in acute lateral patellar dislocation and multiligament knee injuries.

The injury characteristics of medial patellofemoral ligament (MPFL) in multiligament knee injuries (MLKIs) and the differences of injury patterns of MPFL in MLKIs and acute lateral patellar dislocation (LPD) remain unclear. To explore the differences of injury characteristics of MPFL after acute LPD and MLKIs. Magnetic resonance images were prospectively analyzed in 219 patients after acute LPD or MLKIs. Statistical analyses of the injury patterns of MPFL were performed between LPD and MLKIs. The incidence of partial tear and complete MPFL tear in adolescent LPD and MLKIs were 40.3% and 48.4%, and 27.9% and 16.3%, respectively. Compared with LPD, MLKIs showed lower incidence rates of partial and complete MPFL tears (both P = 0). The MLKI subgroup showed lower incidence rates of MPFL tear at the patellar insertion (PAT), femoral attachment (FEM), and multiple-site of the MPFL (COM) (9.3%, 20.9%, and 14%) when compared with the LPD subgroup (45.2%, 24.2%, and 16.1%) (all P < 0.01). The incidence of partial tear and complete MPFL tear in adult LPD and MLKIs were 41.5% and 47.2%, and 24.6% and 16.4%, respectively. Compared with LPD, MLKIs showed lower incidence rates of partial and complete MPFL tears (both P = 0). The MLKI subgroup showed lower incidence rates of MPFL tear at PAT, FEM, and COM (8.2%, 18%, and 14.8%) when compared with the LPD subgroup (20.8%, 34%, and 30.2%) (all P = 0). Compared with LPD, MPFL tears are relatively uncommon in MLKIs. Even if MPFL tears occur, partial tears and femoral-sided tears are relatively more common.

A weighted k-nearest neighbor process monitoring method based on statistical volume pattern analysis

Process monitoring technology has developed rapidly in response to the increasing demand for safer and more reliable systems in modern process operations. Online process monitoring plays an important role not only in ensuring process safety through the timely detection of process faults but also in improving process productivity and product quality. One of the outstanding features of modern manufacturing facilities, which are large in scale and highly complex, is that the processes contain numerous variables operating under closed-loop control. Fully exploiting and utilizing the valuable information in these variables will benefit early and accurate fault detection and diagnosis of processes, minimizing downtime, increasing plant operational safety, and reducing manufacturing costs. The development of process monitoring technology is of great importance to ensure the operational safety, reliability, and economy of complex industrial processes. With the continuous development of industrial processes, the collection and use of process data are gradually increasing, and data-driven multivariate statistical process monitoring methods have developed significantly. A weighted k-nearest neighbor process monitoring method based on SPA is proposed for the problem of multimodal properties of process statistics. When the covariance difference between different modes is large, the multimodal characteristics of the original variable space are retained in the statistic feature space. By introducing weights and assigning weights to the distances between statistic samples, the proposed method can regulate the distances between statistic samples in modes with larger covariance and those with smaller covariance to the same scale, overcoming the limitations of the SPA-based process monitoring method in multimodal fault detection.

Solid Waste Management Scenario in India and Illegal Dump Detection Using Deep Learning: An AI Approach towards the Sustainable Waste Management

The study is presented in four sections. The first section defines the municipal solid waste and solid waste management system. The second section illustrates the descriptive statistical analysis of waste generation patterns in India. The average waste generation in India was 160,038.9 tons per day in 2021; 95% of this total waste was collected and transported to the disposal sites. Based on scientific studies and observations, the per capita waste generation rate in 2018 was 0.490–0.626 g per day. In the last one and a half decades (1999–2000 to 2015–2016), Delhi and Bangalore have shown the highest percentage growth of 2075% and 1750%, respectively, in total waste generation among the highest population cities. The analysis of waste generation patterns concludes urbanization is a major factor that highly influences the waste generation rate. The third section describes the major issues in current solid waste management services. Some of these issues are the unavailability of web portals for citizens, no real-time monitoring of bins, collection vehicles and illegal dumping. These issues are identified based on the survey performed in a city and analysis of related research studies and scientific reports. We determined that illegal dumping is one of these major concerns and needs a technological solution. In the fourth section, we propose a multipath convolutional neural network (mp-CNN) to detect and localize the waste dumps on streets and roadsides. We constructed our dataset to train and test the proposed model, as no benchmark dataset is publicly available to obtain this objective. We applied the weakly supervised learning approach to training the model. In this approach, mp-CNN was trained according to the image class; in our case, it is two (waste and non-waste). In the testing phase, the model showed the performance evaluation matrices 97.82% of precision, 98.86% of recall, 98.34% of F1 score, 98.33% of accuracy, and 98.63% of AUROC for this binary classification. Due to the scarcity of benchmark datasets, waste localization results cannot be presented quantitatively. So, we performed a survey to compare the overlapping of the mask generated by the model with the region waste in the actual image. The average score for the generated mask obtained a score of 3.884 on a scale of 5. Based on the analysis of model performance evaluation parameters, precision-recall curve, receiver characteristic operator curve, and comparison of mask generated by the model over waste with corresponding actual images show that mp-CNN performs remarkably good in detection, classification, and localization of waste regions. Finally, two conceptual architectures in the context of developing countries are suggested to demonstrate the future practical applications of the mp-CNN model.

Working hour patterns and risk of occupational accidents. An optimal matching analysis in a hospital employee cohort

BackgroundHypothesis-free studies applying advanced statistical analysis of objective working hour patterns and occupational accidents are lacking. This study aimed to identify patterns of working hours among hospital employees and to investigate the associations between the identified patterns and the risk of an occupational accident. MethodIn this cohort study of 4419 hospital employees, we collected electronic payroll-based working hour data (i.e., timing and duration) for each participant and linked them to records of occupational accident register between 2008 and 2018. We used optimal matching to assess similarity between individual working hour patterns for a period of 7 days preceding an accident or, for employees without an accident, a random pseudo-accident date. Using cluster analysis, we categorized employees into working hour pattern clusters. Log-binomial regression was used to examine risk ratios (RR) with 95 % confidence intervals (CI) of an occupational accident between cluster memberships. Results1626 participants experienced an occupational accident which took place either at the workplace (65 %) or while commuting (35 %). Six clusters of working hour patterns were identified. Compared to the cluster with the fewest accidents, clusters with a higher proportion of accidents were characterized by late work shifts and a high proportion of quick returns (<11-hour shift interval,) and long work shifts (>12-hour shift), RR 1.31, 95 %CI 1.13–1.52 for the cluster with the most accidents. ConclusionsThis data-driven study suggests that working late and long with insufficient rest is associated with increased probability of occupational accidents. Working hour arrangements in 24/7 care of hospital merit attention to regularity and sufficient rest to support occupational safety.

Statistical properties of the entropy from ordinal patterns.

The ultimate purpose of the statistical analysis of ordinal patterns is to characterize the distribution of the features they induce. In particular, knowing the joint distribution of the pair entropy-statistical complexity for a large class of time series models would allow statistical tests that are unavailable to date. Working in this direction, we characterize the asymptotic distribution of the empirical Shannon's entropy for any model under which the true normalized entropy is neither zero nor one. We obtain the asymptotic distribution from the central limit theorem (assuming large time series), the multivariate delta method, and a third-order correction of its mean value. We discuss the applicability of other results (exact, first-, and second-order corrections) regarding their accuracy and numerical stability. Within a general framework for building test statistics about Shannon's entropy, we present a bilateral test that verifies if there is enough evidence to reject the hypothesis that two signals produce ordinal patterns with the same Shannon's entropy. We applied this bilateral test to the daily maximum temperature time series from three cities (Dublin, Edinburgh, and Miami) and obtained sensible results.

Rockfall detection using LiDAR and deep learning

Rockfall risk management has traditionally been built upon scenarios based on statistical analysis of historic frequency-magnitude rockfall patterns which allows for an estimation of the return period of rockfalls within given ranges of magnitude. Τhe availability of rockfall databases is thereby of crucial importance to quantify rockfall activity. In recent years, engineering geologists have been able to leverage light detection and ranging (LiDAR) technology with automated change detection and clustering workflows, for spatially accurate rockfall monitoring and inventorization. This wealth of digital data generates new research prospects for the development of an artificial intelligence (AI) system able to analyze change detection sequences and map spatio-temporal rockfall patterns by precisely capturing the rock slope evolution in near-real-time. However, prerequisite to such an advancement is the need to efficiently automate the process of classifying surface changes corresponding to rockfall. This task typically requires intensive human effort and is prone to multiple sources of human error like subjectivity, expertise, and experience that may differ from person to person involved in a particular project. This paper investigates the potential of integrating sophisticated deep learning architectures into dynamic rockfall database population processes, with the goal of relieving experts from the daunting task of manually classifying rockfall events within large loads of change detection data. Deep neural networks based on the pioneering PointNet and PointNet++ architectures for 3D point cloud learning are developed for this purpose based on a 5-year change detection database consisting of >8000 rock slope clusters of identified change for training, with scanning intervals ranging from 5 days to 6 months. The models are tested on the 536 clusters from the two last data acquisitions to simulate the real monitoring situation and subsequently on the most frequent of the campaigns to increase the probability of working with single-event clusters. The best-performing model achieves an accuracy of about 89% and 84% on the last and shortest campaign, respectively. The optimized deep learning models are further evaluated on a geologically different rockfall database achieving almost 93% accuracy in a location where discrete geomorphologic features such as steep rock outcrops and erosion channels are present. The study shows that although it is challenging to achieve generalization in rockfall detection, site-specific training of the proposed deep learning architecture can lead to high-level performance and support further advancements in rockfall risk management.

Statistical Analysis of Protein-Ligand Interaction Patterns in Nuclear Receptor RORγ.

The receptor RORγ belongs to the nuclear receptor superfamily that senses small signaling molecules and regulates at the gene transcription level. Since RORγ has a high basal activity and plays an important role in immune responses, inhibitors targeting this receptor have been a focus for many studies. The receptor-ligand interaction is complex, and often subtle differences in ligand structure can determine its role as an inverse agonist or an agonist. We examined more than 130 existing RORγ crystal structures that have the same receptor complexed with different ligands. We reported the features of receptor-ligand interaction patterns and the differences between agonist and inverse agonist binding. Specific changes in the contact interaction map are identified to distinguish active and inactive conformations. Further statistical analysis of the contact interaction patterns using principal component analysis reveals a dominant mode which separates allosteric binding vs. canonical binding and a second mode which may indicate active vs. inactive structures. We also studied the nature of constitutive activity by performing a 100-ns computer simulation of apo RORγ. Using constitutively active nuclear receptor CAR as a comparison, we identified a group of conserved contacts that have similar contact strength between the two receptors. These conserved contact interactions, especially a couple key contacts in H11–H12 interaction, can be considered essential to the constitutive activity of RORγ. These protein-ligand and internal protein contact interactions can be useful in the development of new drugs that direct receptor activity.

Statistical Analysis and Forecasting of Rainfall Patterns and Trends in Gombe North-Eastern Nigeria

Rainfall in Nigeria is highly dynamic and variable on a temporal and spatial scale. This has taken a more pronounced dimension due to climate change. In this study, Standard Precipitation Index (SPI) and Mann-Kendall test statistical tools were employed to analyze rainfall trends and patterns in Gombe metropolis between 1990 and 2020 and the ARIMA model was used for making the forecast for ten (10) years. Daily rainfall data of 31 years obtained from Nigerian Meteorological Agency, (NIMET) was used for the study. The daily rainfall data was subjected to several analyses. Standard precipitation index showed that alternation of wet and dry period conditions had been witnessed in the study area. The result obtained showed that there is an upward trend in the annual rainfall amount received in Gombe over the last 31 years at a rate of 3.98 mm/year. The results for the forecast shows that the annual rainfall to be received in Gombe continues in a range above the mean which serves as an indication that the decade will experience more wet years than dry years. The study concludes that the pattern of rainfall in Gombe is a cyclic pattern. The current trend may affect soil moisture, flooding and subsequently lead to ecological change. The study recommends that inhabitants of the study areas should plan their cropping season based on climatic information of their area.

Fault Detection and Isolation of Non-Gaussian and Nonlinear Processes Based on Statistics Pattern Analysis and the k-Nearest Neighbor Method.

Only low-order information of process data (i.e., mean, variance, and covariance) was considered in the principal component analysis (PCA)-based process monitoring method. Consequently, it cannot deal with continuous processes with strong dynamics, nonlinearity, and non-Gaussianity. To this aim, the statistics pattern analysis (SPA)-based process monitoring method achieves better monitoring results by extracting higher-order statistics (HOS) of the process variables. However, the extracted statistics do not strictly follow a Gaussian distribution, making the estimated control limits in Hotelling-T2 and squared prediction error (SPE) charts inaccurate, resulting in unsatisfactory monitoring performance. In order to solve this problem, this paper presents a novel process monitoring method using SPA and the k-nearest neighbor algorithm. In the proposed method, first, the statistics of process variables are calculated through SPA. Then, the k-nearest neighbor (kNN) method is used to monitor the extracted statistics. The kNN method only uses the paired distance of samples to perform fault detection. It has no strict requirements for data distribution. Hence, the proposed method can overcome the problems caused by the non-Gaussianity and nonlinearity of statistics. In addition, the potential of the proposed method in early fault detection or safety alarm and fault isolation is explored. The proposed method can isolate which variable or its statistic is faulty. Finally, the numerical examples and Tennessee Eastman benchmark process illustrate the effectiveness of the proposed method.

Integration of electroencephalogram (EEG) and motion tracking sensors for objective measure of attention-deficit hyperactivity disorder (MAHD) in pre-schoolers.

We developed an integrated device composed of a single-probe Electroencephalogram (EEG) and Charge Coupled Device (CCD) based motion sensors for objective measurement of Attention-deficit Hyperactivity Disorder (ADHD). While the measurement of attention-deficit hyperactivity disorder (MAHD) relies on the EEG signal for the assessment of attention during a given structured task, the CCD sensor depicts the movement pattern of the subjects engaged in a continuous performance task. A statistical analysis of attention and movement patterns was performed, and the accuracy of completed tasks was analyzed using indigenously developed software. The device with the embedded software is intended to improve certainty with criterion E. We used the EEG signal from a single-channel dry sensor placed on the frontal lobe of the head of the subjects (3-5 year old pre-schoolers). During the performance of the task power for delta and beta, EEG waves from the subjects are found to be correlated with relaxation and attention/cognitive load conditions. While the relaxation condition of the subject hints at hyperactivity, a more direct CCD-based motion sensor is used to track the physical movement of the subject engaged in a continuous performance task. We used our indigenously developed software for statistical analysis to derive a scale for the objective assessment of ADHD. We also compared our scale with clinical ADHD evaluations and found a significant correlation between the objective assessment of the ADHD subjects and the clinician's conventional evaluation. MAHD, the integrated device, is supposed to be an auxiliary tool to improve the accuracy of ADHD diagnosis by supporting greater criterion E certainty.

Texture Analysis in Diagnosing Skin Pigmented Lesions in Normal and Polarized Light-A Preliminary Report.

The differential diagnosis of benign nevi (BN), dysplastic nevi (DN), and melanomas (MM) represents a considerable clinical problem. These lesions are similar in clinical examination but have different prognoses and therapeutic management techniques. A texture analysis (TA) is a mathematical and statistical analysis of pixel patterns of a digital image. This study aims to demonstrate the relationship between the TA of digital images of pigmented lesions under polarized and non-polarized light and their histopathological diagnosis. Ninety pigmented lesions of 76 patients were included in this study. We obtained 166 regions of interest (ROI) images for MM, 166 for DN, and 166 for BN. The pictures were taken under polarized and non-polarized light. Selected image texture features (entropy and difference entropy and long-run emphasis) of ROIs were calculated. Those three equations were used to construct the texture index (TI) and bone index (BI). All of the presented features distinguish melanomas, benign and dysplastic lesions under polarized light very well. In non-polarized images, only the long-run emphasis moment and both indices effectively differentiated nevi from melanomas. TA is an objective method of assessing pigmented lesions and can be used in automatic diagnostic systems.

Thorough statistical analyses of breast cancer co-methylation patterns

BackgroundBreast cancer is one of the most commonly diagnosed cancers. It is associated with DNA methylation, an epigenetic event with a methyl group added to a cytosine paired with a guanine, i.e., a CG site. The methylation levels of different genes in a genome are correlated in certain ways that affect gene functions. This correlation pattern is known as co-methylation. It is still not clear how different genes co-methylate in the whole genome of breast cancer samples. Previous studies are conducted using relatively small datasets (Illumina 27K data). In this study, we analyze much larger datasets (Illumina 450K data).ResultsOur key findings are summarized below. First, normal samples have more highly correlated, or co-methylated, CG pairs than tumor samples. Both tumor and normal samples have more than 93% positive co-methylation, but normal samples have significantly more negatively correlated CG sites than tumor samples (6.6% vs. 2.8%). Second, both tumor and normal samples have about 94% of co-methylated CG pairs on different chromosomes, but normal samples have 470 million more CG pairs. Highly co-methylated pairs on the same chromosome tend to be close to each other. Third, a small proportion of CG sites’ co-methylation patterns change dramatically from normal to tumor. The percentage of differentially methylated (DM) sites among them is larger than the overall DM rate. Fourth, certain CG sites are highly correlated with many CG sites. The top 100 of such super-connector CG sites in tumor and normal samples have no overlaps. Fifth, both highly changing sites and super-connector sites’ locations are significantly different from the genome-wide CG sites’ locations. Sixth, chromosome X co-methylation patterns are very different from other chromosomes. Finally, the network analyses of genes associated with several sets of co-methylated CG sites identified above show that tumor and normal samples have different patterns.ConclusionsOur findings will provide researchers with a new understanding of co-methylation patterns in breast cancer. Our ability to thoroughly analyze co-methylation of large datasets will allow researchers to study relationships and associations between different genes in breast cancer.

Spatial point processes and neural networks: A convenient couple

Different spatial point process models and techniques have been developed in the past decades to facilitate the statistical analysis of spatial point patterns. However, in some cases the spatial point process methodology is scarce and no flexible models nor suitable statistical methods are available. For example, due to its complexity, the statistical analysis of spatial point patterns of several groups observed at a number of time instances has not been studied in-depth, and there are a few limited models and methods available for such data. In the present work, we provide a mathematical framework for coupling neural network methods with the statistical analysis of point patterns. In particular, we discuss an example of deep neural networks in the statistical analysis of highly multivariate spatial point patterns and provide a new strategy for building spatio-temporal point processes using variational autoencoder generative neural networks.

Graph neural network-based resource allocation strategies for multi-object spectroscopy

Resource allocation problems are often approached with linear programming techniques. But many concrete allocation problems in the experimental and observational sciences cannot or should not be expressed in the form of linear objective functions. Even if the objective is linear, its parameters may not be known beforehand because they depend on the results of the experiment for which the allocation is to be determined. To address these challenges, we present a bipartite graph neural network (GNN) architecture for trainable resource allocation strategies. Items of value and constraints form the two sets of graph nodes, which are connected by edges corresponding to possible allocations. The GNN is trained on simulations or past problem occurrences to maximize any user-supplied, scientifically motivated objective function, augmented by an infeasibility penalty. The amount of feasibility violation can be tuned in relation to any available slack in the system. We apply this method to optimize the astronomical target selection strategy for the highly multiplexed Subaru Prime Focus Spectrograph instrument, where it shows superior results to direct gradient descent optimization and extends the capabilities of the currently employed solver which uses linear objective functions. The development of this method enables fast adjustment and deployment of allocation strategies, statistical analyses of allocation patterns, and fully differentiable, science-driven solutions for resource allocation problems.