How Big Data and High-performance Computing Drive Brain Science

On human nanoscale synaptome: Morphology modeling and storage estimation

One of the key challenges in neuroscience is to generate the human nanoscale connectome which requires comprehensive knowledge of synaptome forming the neural microcircuits. The synaptic architecture determines limits of individual mental capacity and provides the framework for understanding neurologic disorders. Here, I address morphology modeling and storage estimation for the human synaptome at the nanoscale. A synapse is defined as a pair of pairs [(presynaptic_neuron),(presynaptic_axonal_terminal);(postsynaptic_neuron),(postsynaptic_dendritic_terminal)]. Center coordinates, radius, and identifier characterize a dendritic or axonal terminal. A synapse comprises topology with the paired neuron and terminal identifiers, location with terminal coordinates, and geometry with terminal radii. The storage required for the synaptome depends on the number of synapses and storage necessary for a single synapse determined by a synaptic model. I introduce three synaptic models: topologic with topology, point with topology and location, and geometric with topology, location, and geometry. To accommodate for a wide range of variations in the numbers of neurons and synapses reported in the literature, four cases of neurons (30;86;100;138 billion) and three cases of synapses per neuron (1,000;10,000;30,000) are considered with three full and simplified (to reduce storage) synaptic models resulting in total 72 cases of storage estimation. The full(simplified) synaptic model of the entire human brain requires from 0.21(0.14) petabytes (PB) to 28.98(18.63) PB for the topologic model, from 0.57(0.32) PB to 78.66(43.47) PB for the point model, and from 0.69(0.38) PB to 95.22(51.75) PB for the geometric model. The full(simplified) synaptic model of the cortex needs from 86.80(55.80) TB to 2.60(1.67) PB for the topologic model, from 235.60(130.02) TB to 7.07(3.91) PB for the point model, and from 285.20(155.00) TB to 8.56(4.65) PB for the geometric model. The topologic model is sufficient to compute the connectome's topology, but it is still too big to be stored on today's top supercomputers related to neuroscience. Frontier, the world's most powerful supercomputer for 86 billion neurons can handle the nanoscale synaptome in the range of 1,000-10,000 synapses per neuron. To my best knowledge, this is the first big data work attempting to provide storage estimation for the human nanoscale synaptome.

Between neurons and networks: investigating mesoscale brain connectivity in neurological and psychiatric disorders

The study of brain connectivity has been a cornerstone in understanding the complexities of neurological and psychiatric disorders. It has provided invaluable insights into the functional architecture of the brain and how it is perturbed in disorders. However, a persistent challenge has been achieving the proper spatial resolution, and developing computational algorithms to address biological questions at the multi-cellular level, a scale often referred to as the mesoscale. Historically, neuroimaging studies of brain connectivity have predominantly focused on the macroscale, providing insights into inter-regional brain connections but often falling short of resolving the intricacies of neural circuitry at the cellular or mesoscale level. This limitation has hindered our ability to fully comprehend the underlying mechanisms of neurological and psychiatric disorders and to develop targeted interventions. In light of this issue, our review manuscript seeks to bridge this critical gap by delving into the domain of mesoscale neuroimaging. We aim to provide a comprehensive overview of conditions affected by aberrant neural connections, image acquisition techniques, feature extraction, and data analysis methods that are specifically tailored to the mesoscale. We further delineate the potential of brain connectivity research to elucidate complex biological questions, with a particular focus on schizophrenia and epilepsy. This review encompasses topics such as dendritic spine quantification, single neuron morphology, and brain region connectivity. We aim to showcase the applicability and significance of mesoscale neuroimaging techniques in the field of neuroscience, highlighting their potential for gaining insights into the complexities of neurological and psychiatric disorders.

A 3D Sparse Autoencoder for Fully Automated Quality Control of Affine Registrations in Big Data Brain MRI Studies

This paper presents a fully automated pipeline using a sparse convolutional autoencoder for quality control (QC) of affine registrations in large-scale T1-weighted (T1w) and T2-weighted (T2w) magnetic resonance imaging (MRI) studies. Here, a customized 3D convolutional encoder-decoder (autoencoder) framework is proposed and the network is trained in a fully unsupervised manner. For cross-validating the proposed model, we used 1000 correctly aligned MRI images of the human connectome project young adult (HCP-YA) dataset. We proposed that the quality of the registration is proportional to the reconstruction error of the autoencoder. Further, to make this method applicable to unseen datasets, we have proposed dataset-specific optimal threshold calculation (using the reconstruction error) from ROC analysis that requires a subset of the correctly aligned and artificially generated misalignments specific to that dataset. The calculated optimum threshold is used for testing the quality of remaining affine registrations from the corresponding datasets. The proposed framework was tested on four unseen datasets from autism brain imaging data exchange (ABIDE I, 215 subjects), information eXtraction from images (IXI, 577 subjects), Open Access Series of Imaging Studies (OASIS4, 646 subjects), and "Food and Brain" study (77 subjects). The framework has achieved excellent performance for T1w and T2w affine registrations with an accuracy of 100% for HCP-YA. Further, we evaluated the generality of the model on four unseen datasets and obtained accuracies of 81.81% for ABIDE I (only T1w), 93.45% (T1w) and 81.75% (T2w) for OASIS4, and 92.59% for "Food and Brain" study (only T1w) and in the range 88-97% for IXI (for both T1w and T2w and stratified concerning scanner vendor and magnetic field strengths). Moreover, the real failures from "Food and Brain" and OASIS4 datasets were detected with sensitivities of 100% and 80% for T1w and T2w, respectively. In addition, AUCs of > 0.88 in all scenarios were obtained during threshold calculation on the four test sets.

Overview: Research on the Genetic Architecture of the Developing Cerebral Cortex in Norms and Diseases

The human brain is characterized by high cell numbers, diverse cell types with diverse functions, and intricate connectivity with an exceedingly broad surface of the cortex. Human-specific brain development was accomplished by a long timeline for maturation from the prenatal period to the third decade of life. The long timeline makes complicated architecture and circuits of human cerebral cortex possible, and it makes human brain vulnerable to intrinsic and extrinsic insults resulting in the development of variety of neuropsychiatric disorders. Unraveling the molecular and cellular processes underlying human brain development under the elaborate regulation of gene expression in a spatiotemporally specific manner, especially that of the cortex will provide a biological understanding of human cognition and behavior in health and diseases. Global research consortia and the advancing technologies in brain science including functional genomics equipped with emergent neuroinformatics such as single-cell multiomics, novel human models, and high-volume databases with high-throughput computation facilitate the biological understanding of the development of the human brain cortex. Knowing the process of interplay of the genome and the environment in cortex development will lead us to understand the human-specific cognitive function and its individual diversity. Thus, it is worthwhile to overview the recent progress in neurotechnology to foresee further understanding of the human brain and norms and diseases.

Big data in autism research: Methodological challenges and solutions

While the concept of big data has emerged over the past decade as a hot topic in nearly all areas of scientific inquiry, it has rarely been discussed in the context of autism research. In this commentary we describe aspects of big data that are relevant to autism research and methodological issues such as confounding and data error that can hamper scientific investigation. Although big data studies can have transformative impact, bigger is not always better, and big data require the same methodological considerations and interdisciplinary collaboration as "small data" to extract useful scientific insight.

The evolution of Big Data in neuroscience and neurology

Neurological diseases are on the rise worldwide, leading to increased healthcare costs and diminished quality of life in patients. In recent years, Big Data has started to transform the fields of Neuroscience and Neurology. Scientists and clinicians are collaborating in global alliances, combining diverse datasets on a massive scale, and solving complex computational problems that demand the utilization of increasingly powerful computational resources. This Big Data revolution is opening new avenues for developing innovative treatments for neurological diseases. Our paper surveys Big Data's impact on neurological patient care, as exemplified through work done in a comprehensive selection of areas, including Connectomics, Alzheimer's Disease, Stroke, Depression, Parkinson's Disease, Pain, and Addiction (e.g., Opioid Use Disorder). We present an overview of research and the methodologies utilizing Big Data in each area, as well as their current limitations and technical challenges. Despite the potential benefits, the full potential of Big Data in these fields currently remains unrealized. We close with recommendations for future research aimed at optimizing the use of Big Data in Neuroscience and Neurology for improved patient outcomes.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40537-023-00751-2.

A Brief History of Stereotactic Atlases: Their Evolution and Importance in Stereotactic Neurosurgery

Following the recent acquisition of unprecedented anatomical details through state-of-the-art neuroimaging, stereotactic procedures such as microelectrode recording (MER) or deep brain stimulation (DBS) can now rely on direct and accurately individualized topographic targeting. Nevertheless, both modern brain atlases derived from appropriate histological techniques involving post-mortem studies of human brain tissue and the methods based on neuroimaging and functional information represent a valuable tool to avoid targeting errors due to imaging artifacts or insufficient anatomical details. Hence, they have thus far been considered a reference guide for functional neurosurgical procedures by neuroscientists and neurosurgeons. In fact, brain atlases, ranging from the ones based on histology and histochemistry to the probabilistic ones grounded on data derived from large clinical databases, are the result of a long and inspiring journey made possible thanks to genial intuitions of great minds in the field of neurosurgery and to the technical advancement of neuroimaging and computational science. The aim of this text is to review the principal characteristics highlighting the milestones of their evolution.

Fully automated quality control of rigid and affine registrations of T1w and T2w MRI in big data using machine learning

BACKGROUND

Magnetic resonance imaging (MRI)-based morphometry and relaxometry are proven methods for the structural assessment of the human brain in several neurological disorders. These procedures are generally based on T1-weighted (T1w) and/or T2-weighted (T2w) MRI scans, and rigid and affine registrations to a standard template(s) are essential steps in such studies. Therefore, a fully automatic quality control (QC) of these registrations is necessary in big data scenarios to ensure that they are suitable for subsequent processing.

METHOD

A supervised machine learning (ML) framework is proposed by computing similarity metrics such as normalized cross-correlation, normalized mutual information, and correlation ratio locally. We have used these as candidate features for cross-validation and testing of different ML classifiers. For 5-fold repeated stratified grid search cross-validation, 400 correctly aligned, 2000 randomly generated misaligned images were used from the human connectome project young adult (HCP-YA) dataset. To test the cross-validated models, the datasets from autism brain imaging data exchange (ABIDE I) and information eXtraction from images (IXI) were used.

RESULTS

The ensemble classifiers, random forest, and AdaBoost yielded best performance with F1-scores, balanced accuracies, and Matthews correlation coefficients in the range of 0.95-1.00 during cross-validation. The predictive accuracies reached 0.99 on the Test set #1 (ABIDE I), 0.99 without and 0.96 with noise on Test set #2 (IXI, stratified w.r.t scanner vendor and field strength).

CONCLUSIONS

The cross-validated and tested ML models could be used for QC of both T1w and T2w rigid and affine registrations in large-scale MRI studies.

Advanced Bioelectrical Signal Processing Methods: Past, Present and Future Approach-Part II: Brain Signals

As it was mentioned in the previous part of this work (Part I)-the advanced signal processing methods are one of the quickest and the most dynamically developing scientific areas of biomedical engineering with their increasing usage in current clinical practice. In this paper, which is a Part II work-various innovative methods for the analysis of brain bioelectrical signals were presented and compared. It also describes both classical and advanced approaches for noise contamination removal such as among the others digital adaptive and non-adaptive filtering, signal decomposition methods based on blind source separation, and wavelet transform.

Bridging the Brain and Data Sciences

Brain scientists are now capable of collecting more data in a single experiment than researchers a generation ago might have collected over an entire career. Indeed, the brain itself seems to thirst for more and more data. Such digital information not only comprises individual studies but is also increasingly shared and made openly available for secondary, confirmatory, and/or combined analyses. Numerous web resources now exist containing data across spatiotemporal scales. Data processing workflow technologies running via cloud-enabled computing infrastructures allow for large-scale processing. Such a move toward greater openness is fundamentally changing how brain science results are communicated and linked to available raw data and processed results. Ethical, professional, and motivational issues challenge the whole-scale commitment to data-driven neuroscience. Nevertheless, fueled by government investments into primary brain data collection coupled with increased sharing and community pressure challenging the dominant publishing model, large-scale brain and data science is here to stay.

Towards the Interpretability of Machine Learning Predictions for Medical Applications Targeting Personalised Therapies: A Cancer Case Survey

Artificial Intelligence is providing astonishing results, with medicine being one of its favourite playgrounds. Machine Learning and, in particular, Deep Neural Networks are behind this revolution. Among the most challenging targets of interest in medicine are cancer diagnosis and therapies but, to start this revolution, software tools need to be adapted to cover the new requirements. In this sense, learning tools are becoming a commodity but, to be able to assist doctors on a daily basis, it is essential to fully understand how models can be interpreted. In this survey, we analyse current machine learning models and other in-silico tools as applied to medicine-specifically, to cancer research-and we discuss their interpretability, performance and the input data they are fed with. Artificial neural networks (ANN), logistic regression (LR) and support vector machines (SVM) have been observed to be the preferred models. In addition, convolutional neural networks (CNNs), supported by the rapid development of graphic processing units (GPUs) and high-performance computing (HPC) infrastructures, are gaining importance when image processing is feasible. However, the interpretability of machine learning predictions so that doctors can understand them, trust them and gain useful insights for the clinical practice is still rarely considered, which is a factor that needs to be improved to enhance doctors' predictive capacity and achieve individualised therapies in the near future.

Electrophysiological Analysis of Brain Organoids: Current Approaches and Advancements

Brain organoids, or cerebral organoids, have become widely used to study the human brain in vitro. As pluripotent stem cell-derived structures capable of self-organization and recapitulation of physiological cell types and architecture, brain organoids bridge the gap between relatively simple two-dimensional human cell cultures and non-human animal models. This allows for high complexity and physiological relevance in a controlled in vitro setting, opening the door for a variety of applications including development and disease modeling and high-throughput screening. While technologies such as single cell sequencing have led to significant advances in brain organoid characterization and understanding, improved functional analysis (especially electrophysiology) is needed to realize the full potential of brain organoids. In this review, we highlight key technologies for brain organoid development and characterization, then discuss current electrophysiological methods for brain organoid analysis. While electrophysiological approaches have improved rapidly for two-dimensional cultures, only in the past several years have advances been made to overcome limitations posed by the three-dimensionality of brain organoids. Here, we review major advances in electrophysiological technologies and analytical methods with a focus on advances with applicability for brain organoid analysis.