BN-BacArena: Bayesian network extension of BacArena for the dynamic simulation of microbial communities.

MOTIVATION: Simulating gut microbial dynamics is extremely challenging. Several computational tools, notably the widely used BacArena, enable modeling of dynamic changes in the microbial environment. These methods, however, do not comprehensively account for microbe-microbe stimulant or inhibitory effects or for nutrient-microbe inhibitory effects, typically observed in different compounds present in the daily diet. RESULTS: Here, we present BN-BacArena, an extension of BacArena consisting on the incorporation within the native computational framework of a Bayesian network model that accounts for microbe-microbe and nutrient-microbe interactions. Using in vitro experiments, 16S rRNA gene sequencing data and nutritional composition of 55 foods, the output Bayesian network showed 23 significant nutrient-bacteria interactions, suggesting the importance of compounds such as polyols, ascorbic acid, polyphenols and other phytochemicals, and 40 bacteria-bacteria significant relationships. With test data, BN-BacArena demonstrates a statistically significant improvement over BacArena to predict the time-dependent relative abundance of bacterial species involved in the gut microbiota upon different nutritional interventions. As a result, BN-BacArena opens new avenues for the dynamic modeling and simulation of the human gut microbiota metabolism. AVAILABILITY AND IMPLEMENTATION: MATLAB and R code are available in https://github.com/PlanesLab/BN-BacArena.

Learning massive interpretable gene regulatory networks of the human brain by merging Bayesian networks.

We present the Fast Greedy Equivalence Search (FGES)-Merge, a new method for learning the structure of gene regulatory networks via merging locally learned Bayesian networks, based on the fast greedy equivalent search algorithm. The method is competitive with the state of the art in terms of the Matthews correlation coefficient, which takes into account both precision and recall, while also improving upon it in terms of speed, scaling up to tens of thousands of variables and being able to use empirical knowledge about the topological structure of gene regulatory networks. To showcase the ability of our method to scale to massive networks, we apply it to learning the gene regulatory network for the full human genome using data from samples of different brain structures (from the Allen Human Brain Atlas). Furthermore, this Bayesian network model should predict interactions between genes in a way that is clear to experts, following the current trends in explainable artificial intelligence. To achieve this, we also present a new open-access visualization tool that facilitates the exploration of massive networks and can aid in finding nodes of interest for experimental tests.

Patient specific prediction of temporal lobe epilepsy surgical outcomes.

OBJECTIVE: Drug-resistant temporal lobe epilepsy (TLE) is the most common type of epilepsy for which patients undergo surgery. Despite the best clinical judgment and currently available prediction algorithms, surgical outcomes remain variable. We aimed to build and to evaluate the performance of multidimensional Bayesian network classifiers (MBCs), a type of probabilistic graphical model, at predicting probability of seizure freedom after TLE surgery. METHODS: Clinical, neurophysiological, and imaging variables were collected from 231 TLE patients who underwent surgery at the University of California, San Francisco (UCSF) or the Montreal Neurological Institute (MNI) over a 15-year period. Postsurgical Engel outcomes at year 1 (Y1), Y2, and Y5 were analyzed as primary end points. We trained an MBC model on combined data sets from both institutions. Bootstrap bias corrected cross-validation (BBC-CV) was used to evaluate the performance of the models. RESULTS: The MBC was compared with logistic regression and Cox proportional hazards according to the area under the receiver-operating characteristic curve (AUC). The MBC achieved an AUC of 0.67 at Y1, 0.72 at Y2, and 0.67 at Y5, which indicates modest performance yet superior to what has been reported in the state-of-the-art studies to date. SIGNIFICANCE: The MBC can more precisely encode probabilistic relationships between predictors and class variables (Engel outcomes), achieving promising experimental results compared to other well-known statistical methods. Multisite application of the MBC could further optimize its classification accuracy with prospective data sets. Online access to the MBC is provided, paving the way for its use as an adjunct clinical tool in aiding pre-operative TLE surgical counseling.

A regularity index for dendrites - local statistics of a neuron's input space.

Neurons collect their inputs from other neurons by sending out arborized dendritic structures. However, the relationship between the shape of dendrites and the precise organization of synaptic inputs in the neural tissue remains unclear. Inputs could be distributed in tight clusters, entirely randomly or else in a regular grid-like manner. Here, we analyze dendritic branching structures using a regularity index R, based on average nearest neighbor distances between branch and termination points, characterizing their spatial distribution. We find that the distributions of these points depend strongly on cell types, indicating possible fundamental differences in synaptic input organization. Moreover, R is independent of cell size and we find that it is only weakly correlated with other branching statistics, suggesting that it might reflect features of dendritic morphology that are not captured by commonly studied branching statistics. We then use morphological models based on optimal wiring principles to study the relation between input distributions and dendritic branching structures. Using our models, we find that branch point distributions correlate more closely with the input distributions while termination points in dendrites are generally spread out more randomly with a close to uniform distribution. We validate these model predictions with connectome data. Finally, we find that in spatial input distributions with increasing regularity, characteristic scaling relationships between branching features are altered significantly. In summary, we conclude that local statistics of input distributions and dendrite morphology depend on each other leading to potentially cell type specific branching features.

3D morphology-based clustering and simulation of human pyramidal cell dendritic spines.

The dendritic spines of pyramidal neurons are the targets of most excitatory synapses in the cerebral cortex. They have a wide variety of morphologies, and their morphology appears to be critical from the functional point of view. To further characterize dendritic spine geometry, we used in this paper over 7,000 individually 3D reconstructed dendritic spines from human cortical pyramidal neurons to group dendritic spines using model-based clustering. This approach uncovered six separate groups of human dendritic spines. To better understand the differences between these groups, the discriminative characteristics of each group were identified as a set of rules. Model-based clustering was also useful for simulating accurate 3D virtual representations of spines that matched the morphological definitions of each cluster. This mathematical approach could provide a useful tool for theoretical predictions on the functional features of human pyramidal neurons based on the morphology of dendritic spines.

Towards a supervised classification of neocortical interneuron morphologies.

BACKGROUND: The challenge of classifying cortical interneurons is yet to be solved. Data-driven classification into established morphological types may provide insight and practical value. RESULTS: We trained models using 217 high-quality morphologies of rat somatosensory neocortex interneurons reconstructed by a single laboratory and pre-classified into eight types. We quantified 103 axonal and dendritic morphometrics, including novel ones that capture features such as arbor orientation, extent in layer one, and dendritic polarity. We trained a one-versus-rest classifier for each type, combining well-known supervised classification algorithms with feature selection and over- and under-sampling. We accurately classified the nest basket, Martinotti, and basket cell types with the Martinotti model outperforming 39 out of 42 leading neuroscientists. We had moderate accuracy for the double bouquet, small and large basket types, and limited accuracy for the chandelier and bitufted types. We characterized the types with interpretable models or with up to ten morphometrics. CONCLUSION: Except for large basket, 50 high-quality reconstructions sufficed to learn an accurate model of a type. Improving these models may require quantifying complex arborization patterns and finding correlates of bouton-related features. Our study brings attention to practical aspects important for neuron classification and is readily reproducible, with all code and data available online.

New insights into the classification and nomenclature of cortical GABAergic interneurons.

A systematic classification and accepted nomenclature of neuron types is much needed but is currently lacking. This article describes a possible taxonomical solution for classifying GABAergic interneurons of the cerebral cortex based on a novel, web-based interactive system that allows experts to classify neurons with pre-determined criteria. Using Bayesian analysis and clustering algorithms on the resulting data, we investigated the suitability of several anatomical terms and neuron names for cortical GABAergic interneurons. Moreover, we show that supervised classification models could automatically categorize interneurons in agreement with experts' assignments. These results demonstrate a practical and objective approach to the naming, characterization and classification of neurons based on community consensus.

Laminar Differences in Dendritic Structure of Pyramidal Neurons in the Juvenile Rat Somatosensory Cortex.

Pyramidal cell structure varies between different cortical areas and species, indicating that the cortical circuits that these cells participate in are likely to be characterized by different functional capabilities. Structural differences between cortical layers have been traditionally reported using either the Golgi method or intracellular labeling, but the structure of pyramidal cells has not previously been systematically analyzed across all cortical layers at a particular age. In the present study, we investigated the dendritic architecture of complete basal arbors of pyramidal neurons in layers II, III, IV, Va, Vb, and VI of the hindlimb somatosensory cortical region of postnatal day 14 rats. We found that the characteristics of basal dendritic morphologies are statistically different in each cortical layer. The variations in size and branching pattern that exist between pyramidal cells of different cortical layers probably reflect the particular functional properties that are characteristic of the cortical circuit in which they participate. This new set of complete basal dendritic arbors of 3D-reconstructed pyramidal cell morphologies across each cortical layer will provide new insights into interlaminar information processing in the cerebral cortex.

Random positions of dendritic spines in human cerebral cortex.

Dendritic spines establish most excitatory synapses in the brain and are located in Purkinje cell's dendrites along helical paths, perhaps maximizing the probability to contact different axons. To test whether spine helixes also occur in neocortex, we reconstructed >500 dendritic segments from adult human cortex obtained from autopsies. With Fourier analysis and spatial statistics, we analyzed spine position along apical and basal dendrites of layer 3 pyramidal neurons from frontal, temporal, and cingulate cortex. Although we occasionally detected helical positioning, for the great majority of dendrites we could not reject the null hypothesis of spatial randomness in spine locations, either in apical or basal dendrites, in neurons of different cortical areas or among spines of different volumes and lengths. We conclude that in adult human neocortex spine positions are mostly random. We discuss the relevance of these results for spine formation and plasticity and their functional impact for cortical circuits.

Comparing supervised learning methods for classifying sex, age, context and individual Mudi dogs from barking.

Barking is perhaps the most characteristic form of vocalization in dogs; however, very little is known about its role in the intraspecific communication of this species. Besides the obvious need for ethological research, both in the field and in the laboratory, the possible information content of barks can also be explored by computerized acoustic analyses. This study compares four different supervised learning methods (naive Bayes, classification trees, [Formula: see text]-nearest neighbors and logistic regression) combined with three strategies for selecting variables (all variables, filter and wrapper feature subset selections) to classify Mudi dogs by sex, age, context and individual from their barks. The classification accuracy of the models obtained was estimated by means of [Formula: see text]-fold cross-validation. Percentages of correct classifications were 85.13 % for determining sex, 80.25 % for predicting age (recodified as young, adult and old), 55.50 % for classifying contexts (seven situations) and 67.63 % for recognizing individuals (8 dogs), so the results are encouraging. The best-performing method was [Formula: see text]-nearest neighbors following a wrapper feature selection approach. The results for classifying contexts and recognizing individual dogs were better with this method than they were for other approaches reported in the specialized literature. This is the first time that the sex and age of domestic dogs have been predicted with the help of sound analysis. This study shows that dog barks carry ample information regarding the caller's indexical features. Our computerized analysis provides indirect proof that barks may serve as an important source of information for dogs as well.

Three-dimensional spatial distribution of synapses in the neocortex: a dual-beam electron microscopy study.

In the cerebral cortex, most synapses are found in the neuropil, but relatively little is known about their 3-dimensional organization. Using an automated dual-beam electron microscope that combines focused ion beam milling and scanning electron microscopy, we have been able to obtain 10 three-dimensional samples with an average volume of 180 µm(3) from the neuropil of layer III of the young rat somatosensory cortex (hindlimb representation). We have used specific software tools to fully reconstruct 1695 synaptic junctions present in these samples and to accurately quantify the number of synapses per unit volume. These tools also allowed us to determine synapse position and to analyze their spatial distribution using spatial statistical methods. Our results indicate that the distribution of synaptic junctions in the neuropil is nearly random, only constrained by the fact that synapses cannot overlap in space. A theoretical model based on random sequential absorption, which closely reproduces the actual distribution of synapses, is also presented.

Bayesian sparse partial least squares.

Partial least squares (PLS) is a class of methods that makes use of a set of latent or unobserved variables to model the relation between (typically) two sets of input and output variables, respectively. Several flavors, depending on how the latent variables or components are computed, have been developed over the last years. In this letter, we propose a Bayesian formulation of PLS along with some extensions. In a nutshell, we provide sparsity at the input space level and an automatic estimation of the optimal number of latent components. We follow the variational approach to infer the parameter distributions. We have successfully tested the proposed methods on a synthetic data benchmark and on electrocorticogram data associated with several motor outputs in monkeys.

NeuroSuites: An online platform for running neuroscience, statistical, and machine learning tools.

Nowadays, an enormous amount of high dimensional data is available in the field of neuroscience. Handling these data is complex and requires the use of efficient tools to transform them into useful knowledge. In this work we present NeuroSuites, an easy-access web platform with its own architecture. We compare our platform with other software currently available, highlighting its main strengths. Thanks to its defined architecture, it is able to handle large-scale problems common in some neuroscience fields. NeuroSuites has different neuroscience-oriented applications and tools to integrate statistical data analysis and machine learning algorithms commonly used in this field. As future work, we want to further expand the list of available software tools as well as improve the platform interface according to user demands.

Markov blanket-based approach for learning multi-dimensional Bayesian network classifiers: an application to predict the European Quality of Life-5 Dimensions (EQ-5D) from the 39-item Parkinson's Disease Questionnaire (PDQ-39).

Multi-dimensional Bayesian network classifiers (MBCs) are probabilistic graphical models recently proposed to deal with multi-dimensional classification problems, where each instance in the data set has to be assigned to more than one class variable. In this paper, we propose a Markov blanket-based approach for learning MBCs from data. Basically, it consists of determining the Markov blanket around each class variable using the HITON algorithm, then specifying the directionality over the MBC subgraphs. Our approach is applied to the prediction problem of the European Quality of Life-5 Dimensions (EQ-5D) from the 39-item Parkinson's Disease Questionnaire (PDQ-39) in order to estimate the health-related quality of life of Parkinson's patients. Fivefold cross-validation experiments were carried out on randomly generated synthetic data sets, Yeast data set, as well as on a real-world Parkinson's disease data set containing 488 patients. The experimental study, including comparison with additional Bayesian network-based approaches, back propagation for multi-label learning, multi-label k-nearest neighbor, multinomial logistic regression, ordinary least squares, and censored least absolute deviations, shows encouraging results in terms of predictive accuracy as well as the identification of dependence relationships among class and feature variables.

Regularized logistic regression and multiobjective variable selection for classifying MEG data.

This paper addresses the question of maximizing classifier accuracy for classifying task-related mental activity from Magnetoencelophalography (MEG) data. We propose the use of different sources of information and introduce an automatic channel selection procedure. To determine an informative set of channels, our approach combines a variety of machine learning algorithms: feature subset selection methods, classifiers based on regularized logistic regression, information fusion, and multiobjective optimization based on probabilistic modeling of the search space. The experimental results show that our proposal is able to improve classification accuracy compared to approaches whose classifiers use only one type of MEG information or for which the set of channels is fixed a priori.

Autoregressive Asymmetric Linear Gaussian Hidden Markov Models.

In a real life process evolving over time, the relationship between its relevant variables may change. Therefore, it is advantageous to have different inference models for each state of the process. Asymmetric hidden Markov models fulfil this dynamical requirement and provide a framework where the trend of the process can be expressed as a latent variable. In this paper, we modify these recent asymmetric hidden Markov models to have an asymmetric autoregressive component in the case of continuous variables, allowing the model to choose the order of autoregression that maximizes its penalized likelihood for a given training set. Additionally, we show how inference, hidden states decoding and parameter learning must be adapted to fit the proposed model. Finally, we run experiments with synthetic and real data to show the capabilities of this new model.

Feature Saliencies in Asymmetric Hidden Markov Models.

Many real-life problems are stated as nonlabeled high-dimensional data. Current strategies to select features are mainly focused on labeled data, which reduces the options to select relevant features for unsupervised problems, such as clustering. Recently, feature saliency models have been introduced and developed as clustering models to select and detect relevant variables/features as the model is learned. Usually, these models assume that all variables are independent, which narrows their applicability. This article introduces asymmetric hidden Markov models with feature saliencies, i.e., models capable of simultaneously determining during their learning phase relevant variables/features and probabilistic relationships between variables. The proposed models are compared with other state-of-the-art approaches using synthetic data and real data related to grammatical face videos and wear in ball bearings. We show that the proposed models have better or equal fitness than other state-of-the-art models and provide further data insights.

On nonlinearity in neural encoding models applied to the primary visual cortex.

Within the regression framework, we show how different levels of nonlinearity influence the instantaneous firing rate prediction of single neurons. Nonlinearity can be achieved in several ways. In particular, we can enrich the predictor set with basis expansions of the input variables (enlarging the number of inputs) or train a simple but different model for each area of the data domain. Spline-based models are popular within the first category. Kernel smoothing methods fall into the second category. Whereas the first choice is useful for globally characterizing complex functions, the second is very handy for temporal data and is able to include inner-state subject variations. Also, interactions among stimuli are considered. We compare state-of-the-art firing rate prediction methods with some more sophisticated spline-based nonlinear methods: multivariate adaptive regression splines and sparse additive models. We also study the impact of kernel smoothing. Finally, we explore the combination of various local models in an incremental learning procedure. Our goal is to demonstrate that appropriate nonlinearity treatment can greatly improve the results. We test our hypothesis on both synthetic data and real neuronal recordings in cat primary visual cortex, giving a plausible explanation of the results from a biological perspective.

Comparing the Electrophysiology and Morphology of Human and Mouse Layer 2/3 Pyramidal Neurons With Bayesian Networks.

Pyramidal neurons are the most common neurons in the cerebral cortex. Understanding how they differ between species is a key challenge in neuroscience. We compared human temporal cortex and mouse visual cortex pyramidal neurons from the Allen Cell Types Database in terms of their electrophysiology and dendritic morphology. We found that, among other differences, human pyramidal neurons had a higher action potential threshold voltage, a lower input resistance, and larger dendritic arbors. We learned Gaussian Bayesian networks from the data in order to identify correlations and conditional independencies between the variables and compare them between the species. We found strong correlations between electrophysiological and morphological variables in both species. In human cells, electrophysiological variables were correlated even with morphological variables that are not directly related to dendritic arbor size or diameter, such as mean bifurcation angle and mean branch tortuosity. Cortical depth was correlated with both electrophysiological and morphological variables in both species, and its effect on electrophysiology could not be explained in terms of the morphological variables. For some variables, the effect of cortical depth was opposite in the two species. Overall, the correlations among the variables differed strikingly between human and mouse neurons. Besides identifying correlations and conditional independencies, the learned Bayesian networks might be useful for probabilistic reasoning regarding the morphology and electrophysiology of pyramidal neurons.

Identifying Parkinson's disease subtypes with motor and non-motor symptoms via model-based multi-partition clustering.

Identification of Parkinson's disease subtypes may help understand underlying disease mechanisms and provide personalized management. Although clustering methods have been previously used for subtyping, they have reported generic subtypes of limited relevance in real life practice because patients do not always fit into a single category. The aim of this study was to identify new subtypes assuming that patients could be grouped differently according to certain sets of related symptoms. To this purpose, a novel model-based multi-partition clustering method was applied on data from an international, multi-center, cross-sectional study of 402 Parkinson's disease patients. Both motor and non-motor symptoms were considered. As a result, eight sets of related symptoms were identified. Each of them provided a different way to group patients: impulse control issues, overall non-motor symptoms, presence of dyskinesias and pyschosis, fatigue, axial symptoms and motor fluctuations, autonomic dysfunction, depression, and excessive sweating. Each of these groups could be seen as a subtype of the disease. Significant differences between subtypes (P< 0.01) were found in sex, age, age of onset, disease duration, Hoehn & Yahr stage, and treatment. Independent confirmation of these results could have implications for the clinical management of Parkinson's disease patients.