Biological Networks Research Articles

Mathematical analysis and asymptotic predictions of chemical-driven swimming living organisms in weighted networks

This paper derives well-posedness and asymptotic results that provide qualitative information about the behavior, mechanism and strategies used by living organisms to navigate their biological networks. Chemical driven swimming is a captivating phenomenon that is observed in various living organisms like bacteria and protozoa but the problem in weighted networks is more complex, since the equations of parabolic-parabolic Keller-Segel model coupled with incompressible Navier-Stokes equations must be reformulated in a discrete setting. The starting point is to transpose the coupled system from the Euclidean case to the connected networks with certain network-theoretic simplified approaches, which yields fruitful key results. These results not only enable the construction of global solutions but also serve as a foundation for determining information about the stability and large time behavior of the system. Then, decay rates are well established to predict important features, such as how quickly weak solutions at a given point decrease over time due to dissipative processes. Additionally, the L1- convergence of cell densities towards the self-similar Gaussian solution of the heat equation is well proved by time dependent scaling, which shows that the solution maintains its shape and only scales in time and space as time evolves. Finally, this paper includes many numerical tests through a recent robust numerical scheme to illustrate the theoretical results and to develop computational control and prediction of living organisms' trajectories around central nodes in networked flows.

Real-time hardware emulation of neural cultures: A comparative study of in vitro, in silico and in duris silico models

Biological neural networks are well known for their capacity to process information with extremely low power consumption. Fields such as Artificial Intelligence, with high computational costs, are seeking for alternatives inspired in biological systems. An inspiring alternative is to implement hardware architectures that replicate the behavior of biological neurons but with the flexibility in programming capabilities of an electronic device, all combined with a relatively low operational cost. To advance in this quest, here we analyze the capacity of the HEENS hardware architecture to operate in a similar manner as an in vitro neuronal network grown in the laboratory. For that, we considered data of spontaneous activity in living neuronal cultures of about 400 neurons and compared their collective dynamics and functional behavior with those obtained from direct numerical simulations (in silico) and hardware implementations (in duris silico). The results show that HEENS is capable to mimic both the in vitro and in silico systems with high efficient-cost ratio, and on different network topological designs. Our work shows that compact low-cost hardware implementations are feasible, opening new avenues for future, highly efficient neuromorphic devices and advanced human–machine interfacing.

Optimal Inference of Hidden Markov Models Through Expert-Acquired Data.

This paper focuses on inferring a general class of hidden Markov models (HMMs) using data acquired from experts. Expert-acquired data contain decisions/actions made by humans/users for various objectives, such as navigation data reflecting drivers' behavior, cybersecurity data carrying defender decisions, and biological data containing the biologist's actions (e.g., interventions and experiments). Conventional inference methods rely on temporal changes in data without accounting for expert knowledge. This paper incorporates expert knowledge into the inference of HMMs by modeling expert behavior as an imperfect reinforcement learning agent. The proposed method optimally quantifies experts' perceptions about the system model, which, alongside the temporal changes in data, contributes to the inference process. The proposed inference method is derived through a combination of dynamic programming and optimal recursive Bayesian estimation. The applicability of this method is demonstrated to a wide range of inference criteria, such as maximum likelihood and maximum a posteriori. The performance of the proposed method is investigated through a comprehensive numerical experiment using a benchmark problem and biological networks.

Unravelling the mechanics of knitted fabrics through hierarchical geometric representation

Knitting interloops one-dimensional yarns into three-dimensional fabrics that exhibit behaviour beyond their constitutive materials. How extensibility and anisotropy emerge from the hierarchical organization of yarns into knitted fabrics has long been unresolved. We seek to unravel the mechanical roles of tensile mechanics, assembly and dynamics arising from the yarn level on fabric nonlinearity by developing a yarn-based dynamical model. This physically validated model captures the mechanical response of knitted fabrics, analogous to flexible metamaterials and biological fibre networks due to geometric nonlinearity within such hierarchical systems. Fabric anisotropy originates from observed yarn–yarn rearrangements during alignment dynamics and is topology-dependent. This yarn-based model also provides a design space of knitted fabrics to embed functionalities by varying geometric configuration and material property in instructed procedures compatible to machine manufacturing. Our hierarchical approach to build up a knitted fabric computationally modernizes an ancient craft and represents a first step towards mechanical programmability of knitted fabrics in wide engineering applications.

Self-organization toward 1/f noise in deep neural networks.

In biological neural networks, it has been well recognized that a healthy brain exhibits 1/f noise patterns. However, in artificial neural networks that are increasingly matching or even out-performing human cognition, this phenomenon has yet to be established. In this work, we found that similar to that of their biological counterparts, 1/f noise exists in artificial neural networks when trained on time series classification tasks. Additionally, we found that the activations of the neurons are the closest to 1/f noise when the neurons are highly utilized. Conversely, if the network is too large and many neurons are underutilized, the neuron activations deviate from 1/f noise patterns toward that of white noise.

Numerical analysis of coupled dynamical biological networks: Modeling electrical information exchange among nerve cells using finite volume method

An innovative approach to modeling the conduction of electrical impulses via intricate neuronal structures is introduced in this paper, which offers a theoretical and computational examination of parameter estimation in a coupled FitzHugh–Nagumo model. With this goal in mind, we present a finite volume approach to solving the FitzHugh–Nagumo model and check the numerical method’s accuracy against previous findings. To further assess and contrast the efficacy and precision of the model’s outputs, a finite difference formulation is incorporated. To clarify the basic qualitative properties of the inhibitor–activator mechanism intrinsic to the coupled FitzHugh–Nagumo model, the analysis uses dynamical system approaches and linear stability analysis. The results show that the suggested schemes are very accurate, with conditional stability, reaching fourth-order spatial and second-order temporal precision. The results are given in both tabular and graphical forms. According to numerical results, the suggested finite volume method outperforms the finite difference method in accurately and efficiently solving the nonlinear coupled FitzHugh–Nagumo model. Neuronal activity and electrical communication are complex biological systems with a lot of investigated nonlinear differential equations; this research helps us understand more about these topics.

A topological mechanism for robust and efficient global oscillations in biological networks

Long and stable timescales are often observed in complex biochemical networks, such as in emergent oscillations. How these robust dynamics persist remains unclear, given the many stochastic reactions and shorter time scales demonstrated by underlying components. We propose a topological model that produces long oscillations around the network boundary, reducing the system dynamics to a lower-dimensional current in a robust manner. Using this to model KaiC, which regulates the circadian rhythm in cyanobacteria, we compare the coherence of oscillations to that in other KaiC models. Our topological model localizes currents on the system edge, with an efficient regime of simultaneously increased precision and decreased cost. Further, we introduce a new predictor of coherence from the analysis of spectral gaps, and show that our model saturates a global thermodynamic bound. Our work presents a new mechanism and parsimonious description for robust emergent oscillations in complex biological networks.

Predicting potential microbe-disease associations based on dual branch graph convolutional network.

Studying the association between microbes and diseases not only aids in the prevention and diagnosis of diseases, but also provides crucial theoretical support for new drug development and personalized treatment. Due to the time-consuming and costly nature of laboratory-based biological tests to confirm the relationship between microbes and diseases, there is an urgent need for innovative computational frameworks to anticipate new associations between microbes and diseases. Here, we propose a novel computational approach based on a dual branch graph convolutional network (GCN) module, abbreviated as DBGCNMDA, for identifying microbe-disease associations. First, DBGCNMDA calculates the similarity matrix of diseases and microbes by integrating functional similarity and Gaussian association spectrum kernel (GAPK) similarity. Then, semantic information from different biological networks is extracted by two GCN modules from different perspectives. Finally, the scores of microbe-disease associations are predicted based on the extracted features. The main innovation of this method lies in the use of two types of information for microbe/disease similarity assessment. Additionally, we extend the disease nodes to address the issue of insufficient features due to low data dimensionality. We optimize the connectivity between the homogeneous entities using random walk with restart (RWR), and then use the optimized similarity matrix as the initial feature matrix. In terms of network understanding, we design a dual branch GCN module, namely GlobalGCN and LocalGCN, to fine-tune node representations by introducing side information, including homologous neighbour nodes. We evaluate the accuracy of the DBGCNMDA model using five-fold cross-validation (5-fold-CV) technique. The results show that the area under the receiver operating characteristic curve (AUC) and area under the precision versus recall curve (AUPR) of the DBGCNMDA model in the 5-fold-CV are 0.9559 and 0.9630, respectively. The results from the case studies using published experimental data confirm a significant number of predicted associations, indicating that DBGCNMDA is an effective tool for predicting potential microbe-disease associations.

Enhancing intestinal health with germinated oats: Bioinformatics and compound profiling insights into a novel approach for managing inflammatory bowel disease

Oats are widely recognized for their numerous health benefits, particularly regarding their anti-inflammatory properties. However, research exploring their specific effects on intestinal permeability and tight junction (TJ) integrity in the context of inflammatory bowel disease (IBD) has been limited. This study aimed to investigate the therapeutic efficacy of germinated oat extract (GOE) in managing IBD, a condition marked by persistent gastrointestinal inflammation and increasing global prevalence. The identified compounds were used to predict target biomarkers and mechanisms related to IBD via bioinformatics analysis and validated using in vitro models. In this study, we used network biology and chemical informatics approaches to predict target biomarkers and their molecular mechanisms. The predicted biomarkers were validated for their effectiveness using a cellular model of intestinal inflammation. The effectiveness of treatment with GOE was validated via in vitro studies, which demonstrated significant enhancement in transepithelial electrical resistance (TEER) and a reduction in fluorescein isothiocyanate (FITC) permeability. Analysis of the mRNA expression of IBD-associated biomarkers in Caco-2 cells demonstrated a significant increase in the mRNA levels of TJ proteins, including TJP1, TJP2, occludin, claudin-1 and claudin-3 compared to the inflammatory group. Furthermore, treatment with GOE markedly reduced the mRNA expression levels of proinflammatory cytokines such as TNF-α, IL-6, and CXCL8. The combination of COCONUT and chemical profiling analysis provided insights into the fundamental molecular mechanisms of GOE. These results underscore the potential of systematically using big data-driven network biology to analyze the effect of food components, highlighting GOE as a promising dietary intervention for IBD.

SAFER: sub-hypergraph attention-based neural network for predicting effective responses to dose combinations

BackgroundThe potential benefits of drug combination synergy in cancer medicine are significant, yet the risks must be carefully managed due to the possibility of increased toxicity. Although artificial intelligence applications have demonstrated notable success in predicting drug combination synergy, several key challenges persist: (1) Existing models often predict average synergy values across a restricted range of testing dosages, neglecting crucial dose amounts and the mechanisms of action of the drugs involved. (2) Many graph-based models rely on static protein–protein interactions, failing to adapt to dynamic and higher-order relationships. These limitations constrain the applicability of current methods.ResultsWe introduce SAFER, a Sub-hypergraph Attention-based graph model, addressing these issues by incorporating complex relationships among biological knowledge networks and considering dosing effects on subject-specific networks. SAFER outperformed previous models on the benchmark and the independent test set. The analysis of subgraph attention weight for the lung cancer cell line highlighted JAK-STAT signaling pathway, PRDM12, ZNF781, and CDC5L that have been implicated in lung fibrosis.ConclusionsSAFER presents an interpretable framework designed to identify drug-responsive signals. Tailored for comprehending dose effects on subject-specific molecular contexts, our model uniquely captures dose-level drug combination responses. This capability unlocks previously inaccessible avenues of investigation compared to earlier models. Furthermore, the SAFER framework can be leveraged by future inquiries to investigate molecular networks that uniquely characterize individual patients and can be applied to prioritize personalized effective treatment based on safe dose combinations.

Biomimetic Neuromorphic Sensory System via Electrolyte Gated Transistors.

Biomimetic neuromorphic sensing systems, inspired by the structure and function of biological neural networks, represent a major advancement in the field of sensing technology and artificial intelligence. This review paper focuses on the development and application of electrolyte gated transistors (EGTs) as the core components (synapses and neuros) of these neuromorphic systems. EGTs offer unique advantages, including low operating voltage, high transconductance, and biocompatibility, making them ideal for integrating with sensors, interfacing with biological tissues, and mimicking neural processes. Major advances in the use of EGTs for neuromorphic sensory applications such as tactile sensors, visual neuromorphic systems, chemical neuromorphic systems, and multimode neuromorphic systems are carefully discussed. Furthermore, the challenges and future directions of the field are explored, highlighting the potential of EGT-based biomimetic systems to revolutionize neuromorphic prosthetics, robotics, and human-machine interfaces. Through a comprehensive analysis of the latest research, this review is intended to provide a detailed understanding of the current status and future prospects of biomimetic neuromorphic sensory systems via EGT sensing and integrated technologies.

Cellulose nanocrystals built multiscale hydrogel electrolyte for highly reversible all-flexible zinc ion batteries

Hydrogel electrolytes are promising for flexible and stable zinc ion batteries (ZIBs), but they lack fatigue resistance and still face challenges in terms of mechanical stability and durability. Herein, inspired by the hierarchical structure of biological networks, multiscale anti-fatigue hydrogel electrolytes with high toughness, high strength, and rapid recovery are constructed by introducing nanoscale cellulose nanocrystals (CNCs) as building blocks into dual-network cross-linking hydroxypropyl chitosan (HPCS) modified polyacrylamide (PAM) hydrogel (denoted as PHC-gel). As a result, the PHC-gel achieves a high fatigue threshold up to 356 J m−2 and with a superior strength and stretchability up to 180 kPa and 3178 %, respectively. In addition, the assembled Zn//Zn cell exhibits long-term cycling stability of 1800 h at 1 mA cm−2/1 mAh cm−2 with a high Coulombic efficiency of 99.4 %. More importantly, the Zn//PHC-gel//MnO2 flexible cell shows remarkable flexibility and capacity retention under different stretching and deformation conditions. This work demonstrates a promising gel chemistry that improves anti-fatigue properties and controls zinc behavior, offering great potential for high-performance flexible and wearable ZIBs and beyond.

Heterogeneous Evolution of Breast Cancer Cells-An Endogenous Molecular-Cellular Network Study.

Breast cancer heterogeneity presents a significant challenge in clinical therapy, such as over-treatment and drug resistance. These challenges are largely due to its obscure normal epithelial origins, evolutionary stability, and transitions on the cancer subtypes. This study aims to elucidate the cellular emergence and maintenance of heterogeneous breast cancer via quantitative bio-process modeling, with potential benefit to therapeutic strategies for the disease. An endogenous molecular-cellular hypothesis posits that both pathological and physiological states are phenotypes evolved from and shaped by interactions among a number of conserved modules and cellular factors within a biological network. We hereby developed a model of core endogenous network for breast cancer in accordance with the theory, quantifying its intrinsic dynamic properties with dynamic modeling. The model spontaneously generates cell states that align with molecular classifications at both the molecular and modular level, replicating four widely recognized molecular subtypes of the cancer and validating against data extracted from the TCGA database. Further analysis shows that topologically, a singular progression gateway from normal breast cells to cancerous states is identified as the Luminal A-type breast cancer. Activated positive feedback loops are found to stabilize cellular states, while negative feedback loops facilitate state transitions. Overall, more routes are revealed on the cellular transition between stable states, and a traceable count explains the origin of breast cancer heterogeneity. Ultimately, the research intended to strength the search for therapeutic targets.

A genome-scale deep learning model to predict gene expression changes of genetic perturbations from multiplex biological networks.

Systematic characterization of biological effects to genetic perturbation is essential to the application of molecular biology and biomedicine. However, the experimental exhaustion of genetic perturbations on the genome-wide scale is challenging. Here, we show TranscriptionNet, a deep learning model that integrates multiple biological networks to systematically predict transcriptional profiles to three types of genetic perturbations based on transcriptional profiles induced by genetic perturbations in the L1000 project: RNA interference, clustered regularly interspaced short palindromic repeat, and overexpression. TranscriptionNet performs better than existing approaches in predicting inducible gene expression changes for all three types of genetic perturbations. TranscriptionNet can predict transcriptional profiles for all genes in existing biological networks and increases perturbational gene expression changes for each type of genetic perturbation from a few thousand to 26945 genes. TranscriptionNet demonstrates strong generalization ability when comparing predicted and true gene expression changes on different external tasks. Overall, TranscriptionNet can systemically predict transcriptional consequences induced by perturbing genes on a genome-wide scale and thus holds promise to systemically detect gene function and enhance drug development and target discovery.

Representing core gene expression activity relationships using the latent structure implicit in Bayesian networks.

Many types of networks, such as co-expression or ChIP-seq-based gene-regulatory networks, provide useful information for biomedical studies. However, they are often too full of connections and difficult to interpret, forming "indecipherable hairballs." To address this issue, we propose that a Bayesian network can summarize the core relationships between gene expression activities. This network, which we call the LatentDAG, is substantially simpler than conventional co-expression network and ChIP-seq networks (by two orders of magnitude). It provides clearer clusters, without extraneous cross-cluster connections, and clear separators between modules. Moreover, one can find a number of clear examples showing how it bridges the connection between steps in the transcriptional regulatory network and other networks (e.g. RNA-binding protein). In conjunction with a graph neural network, the LatentDAG works better than other biological networks in a variety of tasks, including prediction of gene conservation and clustering genes. Code is available at https://github.com/gersteinlab/LatentDAG.

Network Pharmacology-Based Virtual Screening of Chemical Constituents from Vitexnegundo Linn's Discovered Novel Molecular Targets for Breast Cancer Treatment.

The Chinese chaste tree Vitexnegundo (VN) is a popular herb in South and Southeast Asia that has several health benefits, including the ability to inhibit tumor growth and induce apoptosis in multiple tumors. Literature revealed scanty research on breast cancer, with little focus on the molecular mechanism of the disease and an emphasis on targets, biological networks, and active components. Exploring natural compounds as possible therapeutic options is an old but still promising approach for drug discovery and development. This study used a thorough computational and statistical method to screen potential drug candidates. The active ingredients and targets of VN were identified using SwissADME, SwissTargetPrediction, STITCH, IMPPAT database, KNapSAcK database, and literature. The OMIM and GeneCards databases were searched for possible targets related to breast cancer. The PASS online server was used to check the probability of active metabolite (Pa) against breast cancer. To build protein-protein interactions (PPI) networking, the intersection of disease and drug targets was uploaded to the STITCH database. Cytoscape software was used to analyze the topology parameters of networking to identify hub targets. Gene Ontology (GO) was analyzed using Metascape and ShinyGO, Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analysis was performed using the David database and SR plot, and the site of expression and protein domain were studied using FunRich. We employed AutoDockvina, Discovery Studio, and UCSF ChimeraX software and auxiliary tools for molecular docking and analysis. Zincpharmer was used for pharmacophore mapping. ADMET analysis was conducted using ADMETsar, Swiss ADME, ADMETLab servers, and mypresto using GROMACS for molecular dynamics simulation (MDS). A total of 65 targets and 21 active ingredients were identified. Further investigation was conducted on 20 hub targets selected through PPI networking construction. The enrichment analysis results indicated that the key factors were P, amyloid-beta response, cellular response to amyloid- beta, Pos. reg. of G2/M transition of the mitotic cell cycle, and response to a toxic substance. The molecular docking, pharmacophore mapping, and MD simulation results indicated that apigenin, kaempferol, and luteolin positively interacted with CDK1 and CDK6 proteins. This study is the first to use network pharmacology, molecular docking, pharmacophore mapping, and MD simulation to identify the active ingredients, molecular targets, and critical biological pathways responsible for VN anti-breast cancer. The study provides a theoretical basis for further research in this area.

Exploration of a brain-inspired photon reservoir computing network based on quantum-dot spin-VCSELs.

Based on small-world network theory, we have developed a brain-inspired photonic reservoir computing (RC) network system utilizing quantum dot spin-vertical-cavity surface-emitting lasers (QD spin-VCSELs) and formulated a comprehensive theoretical model for it. This innovative network system comprises input layers, a reservoir network layer, and output layers. The reservoir network layer features four distinct reservoir modules that are asymmetrically coupled. Each module is represented by a QD spin-VCSEL, characterized by optical feedback and optical injection. Within these modules, four chaotic polarization components, emitted from both the ground and excited states of the QD Spin-VCSEL, form four distinct reservoirs through a process of asymmetric coupling. Moreover, these components, when emitted by the ground and excited states of a driving QD spin-VCSEL within a specific parameter space, act as targets for prediction. Delving further, we investigated the correlation between various system parameters, such as the sampling period, the interval between virtual nodes, the strengths of optical injection and feedback, frequency detuning, and the predictive accuracy of each module's four photonic RCs concerning the four designated predictive targets. We also examined how these parameters influence the memory storage capabilities of the four photonics RCs within each module. Our findings indicate that when a module receives coupling injections from more than two other modules, and an RC within this module is also subject to coupling injections from over two other RCs, the system displays reduced predictive errors and enhanced memory storage capacities when the system parameters are fixed. Namely, the superior performance of the reservoir module in predictive accuracy and memory capacities follows from its complex interaction with multiple light injections and coupling injections, with its three various PCs benefiting from three, two, and one coupling injections respectively. Conversely, variations in optical injection and feedback strength, as well as frequency detuning, introduce only marginal fluctuations in the predictive errors across the four photonics RCs within each module and exert minimal impact on the memory storage capacity of individual photonics RCs within the modules. Our investigated results contribute to the development of photonic reservoir computing towards fast response biological neural networks.

Multiomics unveils extracellular vesicle-driven mechanisms of endothelial communication in human carotid atherosclerosis.

Background: Carotid atherosclerosis is orchestrated by cell-cell communication that drives progression along a clinical continuum (asymptomatic to symptomatic). Extracellular vesicles (EVs) are cell-derived nanoparticles representing a new paradigm in cellular communication. Little is known about their biological cargo, cellular origin/destination, and functional roles in human atherosclerotic plaque. Methods: EVs were enriched via size exclusion chromatography from human carotid endarterectomy samples dissected into paired plaque and marginal zones (symptomatic n=16, asymptomatic n=13). EV cargos were assessed via whole transcriptome miRNA sequencing and mass spectrometry-based proteomics. EV multi-omics were integrated with bulk and single cell RNA-sequencing (scRNA-seq) datasets to predict EV cellular origin and ligand-receptor interactions, and multi-modal biological network integration of EV-cargo was completed. EV functional impact was assessed with endothelial angiogenesis assays. Results: Carotid plaques contained more EVs than adjacent marginal zones, with differential enrichment for EV-miRNAs and EV-proteins in key atherogenic pathways. EV cellular origin analysis suggested that tissue EV signatures originated from endothelial cells (EC), smooth muscle cells (SMC), and immune cells. Integrated tissue vesiculomics and scRNA-seq indicated complex EV-vascular cell communication that changed with disease progression and plaque vulnerability (i.e., symptomatic disease). Plaques from symptomatic patients, but not asymptomatic patients, were characterized by increased involvement of endothelial pathways and more complex ligand-receptor interactions, relative to their marginal zones. Plaque-EVs were predicted to mediate communication with ECs. Pathway enrichment analysis delineated an endothelial signature with roles in angiogenesis and neovascularization - well-known indices of plaque instability. This was validated functionally, wherein human carotid symptomatic plaque EVs induced sprouting angiogenesis in comparison to their matched marginal zones. Conclusion: Our findings indicate that EVs may drive dynamic changes in plaques through EV- vascular cell communication and effector functions that typify vulnerability to rupture, precipitating symptomatic disease. The discovery of endothelial-directed angiogenic processes mediated by EVs creates new therapeutic avenues for atherosclerosis.

Exploring discrete space–time models for information transfer: Analogies from mycelial networks to the cosmic web

Fungal mycelium networks are large scale biological networks along which nutrients, metabolites flow. Recently, we discovered a rich spectrum of electrical activity in mycelium networks, including action-potential spikes and trains of spikes. Reasoning by analogy with animals and plants, where travelling patterns of electrical activity perform integrative and communicative mechanisms, we speculated that waves of electrical activity transfer information in mycelium networks. Using a new discrete space–time model with emergent radial spanning-tree topology, hypothetically comparable mycelial morphology and physically comparable information transfer, we provide physical arguments for the use of such a model, and by considering growing mycelium network by analogy with growing network of matter in the cosmic web, we develop mathematical models and theoretical concepts to characterise the parameters of the information transfer.

Circulating extracellular vesicular microRNA signatures in early gestation show an association with subsequent clinical features of pre-eclampsia

In a prospective cohort of subjects who subsequently developed preeclampsia (PE, n = 14) versus remaining healthy (NORM, n = 12), early gestation circulating extracellular vesicles (EVs) containing a panel of microRNA signatures were characterized and their biological networks of targets deciphered. Multiple microRNAs of which some arose from the placenta (19MC and 14MC) demonstrated changes in association with advancing gestation, while others expressed were pathognomonic of the subsequent development of characteristic clinical features of PE which set in as a late-onset subtype. This panel of miRNAs demonstrated a predictability with an area under the curve of 0.96 using leave-one-out cross-validation training in a logistic regression model with elastic-net regularization and precautions against overfitting. In addition, this panel of miRNAs, some of which were previously detected in either placental tissue or as maternal cell-free non-coding transcripts, lent further validation to our EV studies and the observed association with PE. Further, the identified biological networks of targets of these detected miRNAs revealed biological functions related to vascular remodeling, cellular proliferation, growth, VEGF, EGF and the PIP3/Akt signaling pathways, all mediating key cellular functions. We conclude that we have demonstrated a proof-of-principle by detecting a panel of EV packaged miRNAs in the maternal circulation early in gestation with possibilities of biological function in the placenta and other maternal tissues, along with the probability of predicting the subsequent clinical appearance of PE, particularly the late-onset subtype.