Enlightening discriminative network functional modules behind Principal Component Analysis separation in differential-omic science studies

De novo identification of universal cell mechanics gene signatures

Cell mechanical properties determine many physiological functions, such as cell fate specification, migration, or circulation through vasculature. Identifying factors that govern the mechanical properties is therefore a subject of great interest. Here, we present a mechanomics approach for establishing links between single-cell mechanical phenotype changes and the genes involved in driving them. We combine mechanical characterization of cells across a variety of mouse and human systems with machine learning-based discriminative network analysis of associated transcriptomic profiles to infer a conserved network module of five genes with putative roles in cell mechanics regulation. We validate in silico that the identified gene markers are universal, trustworthy, and specific to the mechanical phenotype across the studied mouse and human systems, and demonstrate experimentally that a selected target, CAV1, changes the mechanical phenotype of cells accordingly when silenced or overexpressed. Our data-driven approach paves the way toward engineering cell mechanical properties on demand to explore their impact on physiological and pathological cell functions.

Impact of Feed Composition on Rumen Microbial Dynamics and Phenotypic Traits in Beef Cattle

The rumen microbiome is central to feed digestion and host performance, making it an important target for improving ruminant productivity and sustainability. This study investigated how feed composition influences rumen microbial abundance and phenotypic traits in beef cattle. Fifty-nine Angus bulls were assigned to forage- and grain-based diets in a randomized block design, evaluating microbial dynamics, methane emissions, and feed efficiency. Quantitative PCR (qPCR) quantified bacterial, archaeal, fungal, and protozoal populations. Grain-based diets reduced bacterial and fungal counts compared to forage diets (1.1 × 1011 vs. 2.8 × 1011 copies of 16S rRNA genes and 1.5 × 103 vs. 3.5 × 104 copies of 18S rRNA genes/mL, respectively), while protozoan and methanogen populations remained stable. Microbial abundance correlated with feed intake metrics, including dry matter and neutral detergent fiber intakes. Methane emissions were lower in grain-fed bulls (14.8 vs. 18.0 L CH4/kg DMI), though feed efficiency metrics showed no direct association with microbial abundance. Comparative analysis revealed adaptive microbial shifts in response to dietary changes, with functional redundancy maintaining rumen stability and supporting host performance. These findings provide insights into how feed composition shapes rumen microbial dynamics and host phenotypes, highlighting the functional adaptability of the rumen microbiome during dietary transitions.

Methods for multi-omic data integration in cancer research

Multi-omics data integration is a term that refers to the process of combining and analyzing data from different omic experimental sources, such as genomics, transcriptomics, methylation assays, and microRNA sequencing, among others. Such data integration approaches have the potential to provide a more comprehensive functional understanding of biological systems and has numerous applications in areas such as disease diagnosis, prognosis and therapy. However, quantitative integration of multi-omic data is a complex task that requires the use of highly specialized methods and approaches. Here, we discuss a number of data integration methods that have been developed with multi-omics data in view, including statistical methods, machine learning approaches, and network-based approaches. We also discuss the challenges and limitations of such methods and provide examples of their applications in the literature. Overall, this review aims to provide an overview of the current state of the field and highlight potential directions for future research.

Uncovering Predictive Factors and Interventions for Restoring Microecological Diversity after Antibiotic Disturbance

Antibiotic treatment can lead to a loss of diversity of gut microbiota and may adversely affect gut microbiota composition and host health. Previous studies have indicated that the recovery of gut microbes from antibiotic-induced disruption may be guided by specific microbial species. We expect to predict recovery or non-recovery using these crucial species or other indices after antibiotic treatment only when the gut microbiota changes. This study focused on this prediction problem using a novel ensemble learning framework to identify a set of common and reasonably predictive recovery-associated bacterial species (p-RABs), enabling us to predict the host microbiome recovery status under broad-spectrum antibiotic treatment. Our findings also propose other predictive indicators, suggesting that higher taxonomic and functional diversity may correlate with an increased likelihood of successful recovery. Furthermore, to explore the validity of p-RABs, we performed a metabolic support analysis and identified Akkermansia muciniphila and Bacteroides uniformis as potential key supporting species for reconstruction interventions. Experimental results from a C57BL/6J male mouse model demonstrated the effectiveness of p-RABs in facilitating intestinal microbial reconstitution. Thus, we proved the reliability of the new p-RABs and validated a practical intervention scheme for gut microbiota reconstruction under antibiotic disturbance.

Non-Invasive Digital Technologies to Assess Wine Quality Traits and Provenance through the Bottle

Due to increased fraud rates through counterfeiting and adulteration of wines, it is important to develop novel non-invasive techniques to assess wine quality and provenance. Assessment of quality traits and provenance of wines is predominantly undertaken with complex chemical analysis and sensory evaluation, which tend to be costly and time-consuming. Therefore, this study aimed to develop a rapid and non-invasive method to assess wine vintages and quality traits using digital technologies. Samples from thirteen vintages from Dookie, Victoria, Australia (2000–2021) of Shiraz were analysed using near-infrared spectroscopy (NIR) through unopened bottles to assess the wine chemical fingerprinting. Three highly accurate machine learning (ML) models were developed using the NIR absorbance values as inputs to predict (i) wine vintage (Model 1; 97.2%), (ii) intensity of sensory descriptors (Model 2; R = 0.95), and (iii) peak area of volatile aromatic compounds (Model 3; R = 0.88). The proposed method will allow the assessment of provenance and quality traits of wines without the need to open the wine bottle, which may also be used to detect wine fraud and provenance. Furthermore, low-cost NIR devices are available in the market with required spectral range and sensitivity, which can be affordable for winemakers and retailers and can be used with the machine learning models proposed here.

Analyzing biomarker discovery: Estimating the reproducibility of biomarker sets

Many researchers try to understand a biological condition by identifying biomarkers. This is typically done using univariate hypothesis testing over a labeled dataset, declaring a feature to be a biomarker if there is a significant statistical difference between its values for the subjects with different outcomes. However, such sets of proposed biomarkers are often not reproducible – subsequent studies often fail to identify the same sets. Indeed, there is often only a very small overlap between the biomarkers proposed in pairs of related studies that explore the same phenotypes over the same distribution of subjects. This paper first defines the Reproducibility Score for a labeled dataset as a measure (taking values between 0 and 1) of the reproducibility of the results produced by a specified fixed biomarker discovery process for a given distribution of subjects. We then provide ways to reliably estimate this score by defining algorithms that produce an over-bound and an under-bound for this score for a given dataset and biomarker discovery process, for the case of univariate hypothesis testing on dichotomous groups. We confirm that these approximations are meaningful by providing empirical results on a large number of datasets and show that these predictions match known reproducibility results. To encourage others to apply this technique to analyze their biomarker sets, we have also created a publicly available website, https://biomarker.shinyapps.io/BiomarkerReprod/, that produces these Reproducibility Score approximations for any given dataset (with continuous or discrete features and binary class labels).

Xprediction: Explainable EGFR-TKIs response prediction based on drug sensitivity specific gene networks

In recent years, drug sensitivity prediction has garnered a great deal of attention due to the growing interest in precision medicine. Several computational methods have been developed for drug sensitivity prediction and the identification of related markers. However, most previous studies have ignored genetic interaction, although complex diseases (e.g., cancer) involve many genes intricately connected in a molecular network rather than the abnormality of a single gene. To effectively predict drug sensitivity and understand its mechanism, we propose a novel strategy for explainable drug sensitivity prediction based on sample-specific gene regulatory networks, designated Xprediction. Our strategy first estimates sample-specific gene regulatory networks that enable us to identify the molecular interplay underlying varying clinical characteristics of cell lines. We then, predict drug sensitivity based on the estimated sample-specific gene regulatory networks. The predictive models are based on machine learning approaches, i.e., random forest, kernel support vector machine, and deep neural network. Although the machine learning models provide remarkable results for prediction and classification, we cannot understand how the models reach their decisions. In other words, the methods suffer from the black box problem and thus, we cannot identify crucial molecular interactions that involve drug sensitivity-related mechanisms. To address this issue, we propose a method that describes the importance of each molecular interaction for the drug sensitivity prediction result. The proposed method enables us to identify crucial gene-gene interactions and thereby, interpret the prediction results based on the identified markers. To evaluate our strategy, we applied Xprediction to EGFR-TKIs prediction based on drug sensitivity specific gene regulatory networks and identified important molecular interactions for EGFR-TKIs prediction. Our strategy effectively performed drug sensitivity prediction compared with prediction based on the expression levels of genes. We also verified through literature, the EGFR-TKIs-related mechanisms of a majority of the identified markers. We expect our strategy to be a useful tool for predicting tasks and uncovering complex mechanisms related to pharmacological profiles, such as mechanisms of acquired drug resistance or sensitivity of cancer cells.

Machine Learning and Pathway Analysis-Based Discovery of Metabolomic Markers Relating to Chronic Pain Phenotypes

Recent scientific evidence suggests that chronic pain phenotypes are reflected in metabolomic changes. However, problems associated with chronic pain, such as sleep disorders or obesity, may complicate the metabolome pattern. Such a complex phenotype was investigated to identify common metabolomics markers at the interface of persistent pain, sleep, and obesity in 71 men and 122 women undergoing tertiary pain care. They were examined for patterns in d = 97 metabolomic markers that segregated patients with a relatively benign pain phenotype (low and little bothersome pain) from those with more severe clinical symptoms (high pain intensity, more bothersome pain, and co-occurring problems such as sleep disturbance). Two independent lines of data analysis were pursued. First, a data-driven supervised machine learning-based approach was used to identify the most informative metabolic markers for complex phenotype assignment. This pointed primarily at adenosine monophosphate (AMP), asparagine, deoxycytidine, glucuronic acid, and propionylcarnitine, and secondarily at cysteine and nicotinamide adenine dinucleotide (NAD) as informative for assigning patients to clinical pain phenotypes. After this, a hypothesis-driven analysis of metabolic pathways was performed, including sleep and obesity. In both the first and second line of analysis, three metabolic markers (NAD, AMP, and cysteine) were found to be relevant, including metabolic pathway analysis in obesity, associated with changes in amino acid metabolism, and sleep problems, associated with downregulated methionine metabolism. Taken together, present findings provide evidence that metabolomic changes associated with co-occurring problems may play a role in the development of severe pain. Co-occurring problems may influence each other at the metabolomic level. Because the methionine and glutathione metabolic pathways are physiologically linked, sleep problems appear to be associated with the first metabolic pathway, whereas obesity may be associated with the second.

Machine-Learning Analysis of Serum Proteomics in Neuropathic Pain after Nerve Injury in Breast Cancer Surgery Points at Chemokine Signaling via SIRT2 Regulation

BACKGROUND

Persistent postsurgical neuropathic pain (PPSNP) can occur after intraoperative damage to somatosensory nerves, with a prevalence of 29-57% in breast cancer surgery. Proteomics is an active research field in neuropathic pain and the first results support its utility for establishing diagnoses or finding therapy strategies.

METHODS

57 women (30 non-PPSNP/27 PPSNP) who had experienced a surgeon-verified intercostobrachial nerve injury during breast cancer surgery, were examined for patterns in 74 serum proteomic markers that allowed discrimination between subgroups with or without PPSNP. Serum samples were obtained both before and after surgery.

RESULTS

Unsupervised data analyses, including principal component analysis and self-organizing maps of artificial neurons, revealed patterns that supported a data structure consistent with pain-related subgroup (non-PPSPN vs. PPSNP) separation. Subsequent supervised machine learning-based analyses revealed 19 proteins (CD244, SIRT2, CCL28, CXCL9, CCL20, CCL3, IL.10RA, MCP.1, TRAIL, CCL25, IL10, uPA, CCL4, DNER, STAMPB, CCL23, CST5, CCL11, FGF.23) that were informative for subgroup separation. In cross-validated training and testing of six different machine-learned algorithms, subgroup assignment was significantly better than chance, whereas this was not possible when training the algorithms with randomly permuted data or with the protein markers not selected. In particular, sirtuin 2 emerged as a key protein, presenting both before and after breast cancer treatments in the PPSNP compared with the non-PPSNP subgroup.

CONCLUSIONS

The identified proteins play important roles in immune processes such as cell migration, chemotaxis, and cytokine-signaling. They also have considerable overlap with currently known targets of approved or investigational drugs. Taken together, several lines of unsupervised and supervised analyses pointed to structures in serum proteomics data, obtained before and after breast cancer surgery, that relate to neuroinflammatory processes associated with the development of neuropathic pain after an intraoperative nerve lesion.

Early Detection of Medical Image Analysis by Using Machine Learning Method

We develop effective medical image classification techniques, with an emphasis on histopathology and magnetic resonance imaging (MRI). The trainer utilized the curriculum as a starting point for a set of data and a restricted number of samples, and we used it as a starting point for a set of data. As calibrating a machine learning model is difficult, we used alternative methods as unsupervised feature extracts or weight-conditioning factors for identifying pathological histology pictures. As a result, the pretrained models will be trained on 3-channel RGB pictures, while the MRI sample has more slices. To alter the working model using the MRI data, the convolutional neural network (CNN) must be fine-tuned. Pretrained models are placed and then used as feature snippets. However, there is a scarcity of well-done medical photos, making training machine learning models a difficult endeavor to begin with. In any case, data augmentation aids in the generation of sufficient training samples; however, it is unclear if data augmentation aids in the prediction of unknown data samples. As a result, we fine-tuned machine learning models without using any additional data. Furthermore, rather than utilizing a standard machine learning classifier for the MRI data, we created a unique CNN that uses both 3D shear descriptors and deep features as input. This custom network identifies the MRI sample after processing our representation of the characteristics from beginning to end. On the hidden MRI dataset, our bespoke CNN outperforms traditional machine learning. Our CNN model is less prone to overfitting as a result of this. Furthermore, we have given cutting-edge outcomes employing machine learning.

Medial prefrontal and occipito-temporal activity at encoding determines enhanced recognition of threatening faces after 1.5 years

Studies demonstrated that faces with threatening emotional expressions are better remembered than non-threatening faces. However, whether this memory advantage persists over years and which neural systems underlie such an effect remains unknown. Here, we employed an individual difference approach to examine whether the neural activity during incidental encoding was associated with differential recognition of faces with emotional expressions (angry, fearful, happy, sad and neutral) after a retention interval of > 1.5 years (N = 89). Behaviorally, we found a better recognition for threatening (angry, fearful) versus non-threatening (happy and neutral) faces after a delay of > 1.5 years, which was driven by forgetting of non-threatening faces compared with immediate recognition after encoding. Multivariate principal component analysis (PCA) on the behavioral responses further confirmed the discriminative recognition performance between threatening and non-threatening faces. A voxel-wise whole-brain analysis on the concomitantly acquired functional magnetic resonance imaging (fMRI) data during incidental encoding revealed that neural activity in bilateral inferior occipital gyrus (IOG) and ventromedial prefrontal/orbitofrontal cortex (vmPFC/OFC) was associated with the individual differences in the discriminative emotional face recognition performance measured by an innovative behavioral pattern similarity analysis (BPSA). The left fusiform face area (FFA) was additionally determined using a regionally focused analysis. Overall, the present study provides evidence that threatening facial expressions lead to persistent face recognition over periods of > 1.5 years, and that differential encoding-related activity in the medial prefrontal cortex and occipito-temporal cortex may underlie this effect.

Toxic effects of shale gas fracturing flowback fluid on microbial communities in polluted soil

A large amount of shale gas fracturing flowback fluid (FFBF) from the process of shale gas exploitation causes obvious ecological harm to health of soil and water. However, biological hazard of soil microbial populations by fracturing flowback fluid remains rarely reported. In this study, the microbiological compositions were assessed via analyzing diversity of microbial populations. The results showed significant differences between polluted soil by fracturing flowback fluid and unpolluted soil in different pH and temperature conditions. And then, the microbe-index of biological integrity (M-IBI) was used to evaluate the toxicity of the fracturing flowback fluid based on analysis of microbial integrity. The results showed that polluted soil lacks key microbial species known to be beneficial to soil health, including denitrifying bacteria and cellulose-decomposing bacteria, and 35 °C is a critical value for estimating poor and sub-healthy level of damage to microbial integrity by fracturing flowback fluid. Our results provide a valuable reference for the evaluation of soil damage by fracturing flowback fluid.

Cell Mechanics Based Computational Classification of Red Blood Cells Via Machine Intelligence Applied to Morpho-Rheological Markers

Despite fluorescent cell-labelling being widely employed in biomedical studies, some of its drawbacks are inevitable, with unsuitable fluorescent probes or probes inducing a functional change being the main limitations. Consequently, the demand for and development of label-free methodologies to classify cells is strong and its impact on precision medicine is relevant. Towards this end, high-throughput techniques for cell mechanical phenotyping have been proposed to get a multidimensional biophysical characterization of single cells. With this motivation, our goal here is to investigate the extent to which an unsupervised machine learning methodology, which is applied exclusively on morpho-rheological markers obtained by real-time deformability and fluorescence cytometry (RT-FDC), can address the difficult task of providing label-free discrimination of reticulocytes from mature red blood cells. We focused on this problem, since the characterization of reticulocytes (their percentage and cellular features) in the blood is vital in multiple human disease conditions, especially bone-marrow disorders such as anemia and leukemia. Our approach reports promising label-free results in the classification of reticulocytes from mature red blood cells, and it represents a step forward in the development of high-throughput morpho-rheological-based methodologies for the computational categorization of single cells. Besides, our methodology can be an alternative but also a complementary method to integrate with existing cell-labelling techniques.

Biomechanical Properties of Cancer Cells

Since the crucial role of the microenvironment has been highlighted, many studies have been focused on the role of biomechanics in cancer cell growth and the invasion of the surrounding environment. Despite the search in recent years for molecular biomarkers to try to classify and stratify cancers, much effort needs to be made to take account of morphological and nanomechanical parameters that could provide supplementary information concerning tissue complexity adaptation during cancer development. The biomechanical properties of cancer cells and their surrounding extracellular matrix have actually been proposed as promising biomarkers for cancer diagnosis and prognosis. The present review first describes the main methods used to study the mechanical properties of cancer cells. Then, we address the nanomechanical description of cultured cancer cells and the crucial role of the cytoskeleton for biomechanics linked with cell morphology. Finally, we depict how studying interaction of tumor cells with their surrounding microenvironment is crucial to integrating biomechanical properties in our understanding of tumor growth and local invasion.

Nonlinear machine learning pattern recognition and bacteria-metabolite multilayer network analysis of perturbed gastric microbiome

The stomach is inhabited by diverse microbial communities, co-existing in a dynamic balance. Long-term use of drugs such as proton pump inhibitors (PPIs), or bacterial infection such as Helicobacter pylori, cause significant microbial alterations. Yet, studies revealing how the commensal bacteria re-organize, due to these perturbations of the gastric environment, are in early phase and rely principally on linear techniques for multivariate analysis. Here we disclose the importance of complementing linear dimensionality reduction techniques with nonlinear ones to unveil hidden patterns that remain unseen by linear embedding. Then, we prove the advantages to complete multivariate pattern analysis with differential network analysis, to reveal mechanisms of bacterial network re-organizations which emerge from perturbations induced by a medical treatment (PPIs) or an infectious state (H. pylori). Finally, we show how to build bacteria-metabolite multilayer networks that can deepen our understanding of the metabolite pathways significantly associated to the perturbed microbial communities.

Coupling Machine Learning and Lipidomics as a Tool to Investigate Metabolic Dysfunction-Associated Fatty Liver Disease. A General Overview

Hepatic biopsy is the gold standard for staging nonalcoholic fatty liver disease (NAFLD). Unfortunately, accessing the liver is invasive, requires a multidisciplinary team and is too expensive to be conducted on large segments of the population. NAFLD starts quietly and can progress until liver damage is irreversible. Given this complex situation, the search for noninvasive alternatives is clinically important. A hallmark of NAFLD progression is the dysregulation in lipid metabolism. In this context, recent advances in the area of machine learning have increased the interest in evaluating whether multi-omics data analysis performed on peripheral blood can enhance human interpretation. In the present review, we show how the use of machine learning can identify sets of lipids as predictive biomarkers of NAFLD progression. This approach could potentially help clinicians to improve the diagnosis accuracy and predict the future risk of the disease. While NAFLD has no effective treatment yet, the key to slowing the progression of the disease may lie in predictive robust biomarkers. Hence, to detect this disease as soon as possible, the use of computational science can help us to make a more accurate and reliable diagnosis. We aimed to provide a general overview for all readers interested in implementing these methods.

Tumor-stroma biomechanical crosstalk: a perspective on the role of caveolin-1 in tumor progression

Tumor stiffening is a hallmark of malignancy that actively drives tumor progression and aggressiveness. Recent research has shed light onto several molecular underpinnings of this biomechanical process, which has a reciprocal crosstalk between tumor cells, stromal fibroblasts, and extracellular matrix remodeling at its core. This dynamic communication shapes the tumor microenvironment; significantly determines disease features including therapeutic resistance, relapse, or metastasis; and potentially holds the key for novel antitumor strategies. Caveolae and their components emerge as integrators of different aspects of cell function, mechanotransduction, and ECM-cell interaction. Here, we review our current knowledge on the several pivotal roles of the essential caveolar component caveolin-1 in this multidirectional biomechanical crosstalk and highlight standing questions in the field.

Machine-learning-based knowledge discovery in rheumatoid arthritis-related registry data to identify predictors of persistent pain

Early detection of patients with chronic diseases at risk of developing persistent pain is clinically desirable for timely initiation of multimodal therapies. Quality follow-up registries may provide the necessary clinical data; however, their design is not focused on a specific research aim, which poses challenges on the data analysis strategy. Here, machine-learning was used to identify early parameters that provide information about a future development of persistent pain in rheumatoid arthritis (RA). Data of 288 patients were queried from a registry based on the Swedish Epidemiological Investigation of RA. Unsupervised data analyses identified the following 3 distinct patient subgroups: low-, median-, and high-persistent pain intensity. Next, supervised machine-learning, implemented as random forests followed by computed ABC analysis-based item categorization, was used to select predictive parameters among 21 different demographic, patient-rated, and objective clinical factors. The selected parameters were used to train machine-learned algorithms to assign patients pain-related subgroups (1000 random resamplings, 2/3 training, and 1/3 test data). Algorithms trained with 3-month data of the patient global assessment and health assessment questionnaire provided pain group assignment at a balanced accuracy of 70%. When restricting the predictors to objective clinical parameters of disease severity, swollen joint count and tender joint count acquired at 3 months provided a balanced accuracy of RA of 59%. Results indicate that machine-learning is suited to extract knowledge from data queried from pain- and disease-related registries. Early functional parameters of RA are informative for the development and degree of persistent pain.

Mechanical Adaptability of Tumor Cells in Metastasis

The most dangerous aspect of cancer lies in metastatic progression. Tumor cells will successfully form life-threatening metastases when they undergo sequential steps along a journey from the primary tumor to distant organs. From a biomechanics standpoint, growth, invasion, intravasation, circulation, arrest/adhesion, and extravasation of tumor cells demand particular cell-mechanical properties in order to survive and complete the metastatic cascade. With metastatic cells usually being softer than their non-malignant counterparts, high deformability for both the cell and its nucleus is thought to offer a significant advantage for metastatic potential. However, it is still unclear whether there is a finely tuned but fixed mechanical state that accommodates all mechanical features required for survival throughout the cascade or whether tumor cells need to dynamically refine their properties and intracellular components at each new step encountered. Here, we review the various mechanical requirements successful cancer cells might need to fulfill along their journey and speculate on the possibility that they dynamically adapt their properties accordingly. The mechanical signature of a successful cancer cell might actually be its ability to adapt to the successive microenvironmental constraints along the different steps of the journey.

Sensitization of drug resistant sarcoma tumors by membrane modulation via short chain sphingolipid-containing nanoparticles

Nanoparticles such as liposomes are able to overcome cancer treatment challenges such as multidrug resistance by increasing the bioavailability of the encapsulated drug, bypassing drug pumps or through targeting resistant cells. Here, we merge enhanced drug delivery by nanotechnology with tumor cell membrane modulation combined in a single formulation. This is achieved through the incorporation of Short chain sphingolipids (SCSs) in the liposomal composition, which permeabilizes cell membranes to amphiphilic drugs such as Doxorubicin (Dxr). To study the mechanism and capability of SCS-containing nanodevices to overcome Dxr resistance, a sensitive uterine sarcoma cell line, MES-SA, and a resistant derived cell line, MES-SA/MX2, were used. The mechanism of resistance was explored by lipidomics and flow cytometry, revealing significant differences in lipid composition and in P glycoprotein (Pgp) expression. In vitro assays show that SCS liposomes were able to reverse cell resistance, and importantly, display a higher net effect on resistant than sensitive cells. SCS lipids modulated the cell membrane of MES-SA/MX2 drug resistant cells, while Pgp expression was not affected. Furthermore, SCS-modified liposomes were evaluated in a sarcoma xenograft model on drug accumulation, pharmacokinetics and efficacy. SCS liposomes improved Dxr levels in tumor nuclei of MES-SA/MX2 tumor cells, which was accompanied by a delay in tumor growth of the resistant model. Here we show that Dxr accumulation in tumor cells by SCS-modified liposomes was especially improved in Dxr resistant cells, rendering Dxr as effective as in sensitive cells. Moreover, this phenomenon translated to improved efficacy when Dxr liposomes where modified with SCSs in the drug resistant tumor model, while no benefit was seen in the sensitive tumors.

Multi-omics integration-a comparison of unsupervised clustering methodologies

With the recent developments in the field of multi-omics integration, the interest in factors such as data preprocessing, choice of the integration method and the number of different omics considered had increased. In this work, the impact of these factors is explored when solving the problem of sample classification, by comparing the performances of five unsupervised algorithms: Multiple Canonical Correlation Analysis, Multiple Co-Inertia Analysis, Multiple Factor Analysis, Joint and Individual Variation Explained and Similarity Network Fusion. These methods were applied to three real data sets taken from literature and several ad hoc simulated scenarios to discuss classification performance in different conditions of noise and signal strength across the data types. The impact of experimental design, feature selection and parameter training has been also evaluated to unravel important conditions that can affect the accuracy of the result.

Unveiling new disease, pathway, and gene associations via multi-scale neural network

Diseases involve complex modifications to the cellular machinery. The gene expression profile of the affected cells contains characteristic patterns linked to a disease. Hence, new biological knowledge about a disease can be extracted from these profiles, improving our ability to diagnose and assess disease risks. This knowledge can be used for drug re-purposing, or by physicians to evaluate a patient’s condition and co-morbidity risk. Here, we consider differential gene expressions obtained by microarray technology for patients diagnosed with various diseases. Based on these data and cellular multi-scale organization, we aim at uncovering disease–disease, disease–gene and disease–pathway associations. We propose a neural network with structure based on the multi-scale organization of proteins in a cell into biological pathways. We show that this model is able to correctly predict the diagnosis for the majority of patients. Through the analysis of the trained model, we predict disease–disease, disease–pathway, and disease–gene associations and validate the predictions by comparisons to known interactions and literature search, proposing putative explanations for the predictions.

Machine-learned analysis of global and glial/opioid intersection-related DNA methylation in patients with persistent pain after breast cancer surgery

BACKGROUND

Glial cells in the central nervous system play a key role in neuroinflammation and subsequent central sensitization to pain. They are therefore involved in the development of persistent pain. One of the main sites of interaction of the immune system with persistent pain has been identified as neuro-immune crosstalk at the glial-opioid interface. The present study examined a potential association between the DNA methylation of two key players of glial/opioid intersection and persistent postoperative pain.

METHODS

In a cohort of 140 women who had undergone breast cancer surgery, and were assigned based on a 3-year follow-up to either a persistent or non-persistent pain phenotype, the role of epigenetic regulation of key players in the glial-opioid interface was assessed. The methylation of genes coding for the Toll-like receptor 4 (TLR4) as a major mediator of glial contributions to persistent pain or for the μ-opioid receptor (OPRM1) was analyzed and its association with the pain phenotype was compared with that conferred by global genome-wide DNA methylation assessed via quantification of the methylation in the retrotransposon LINE1.

RESULTS

Training of machine learning algorithms indicated that the global DNA methylation provided a similar diagnostic accuracy for persistent pain as previously established non-genetic predictors. However, the diagnosis can be based on a single DNA based marker. By contrast, the methylation of TLR4 or OPRM1 genes could not contribute further to the allocation of the patients to the pain-related phenotype groups.

CONCLUSIONS

While clearly supporting a predictive utility of epigenetic testing, the present analysis cannot provide support for specific epigenetic modulation of persistent postoperative pain via methylation of two key genes of the glial-opioid interface.

Cardiomyocyte mechanodynamics under conditions of actin remodelling

The mechanical performance of cardiomyocytes (CMs) is an important indicator of their maturation state and of primary importance for the development of therapies based on cardiac stem cells. As the mechanical analysis of adherent cells at high-throughput remains challenging, we explore the applicability of real-time deformability cytometry (RT-DC) to probe cardiomyocytes in suspension. RT-DC is a microfluidic technology allowing for real-time mechanical analysis of thousands of cells with a throughput exceeding 1000 cells per second. For CMs derived from human-induced pluripotent stem cells, we determined a Young's modulus of 1.25 ± 0.08 kPa which is in close range to previous reports. Upon challenging the cytoskeleton with cytochalasin D (CytoD) to induce filamentous actin depolymerization, we distinguish three different regimes in cellular elasticity. Transitions are observed below 10 nM and above 103 nM and are characterized by a decrease in Young's modulus. These regimes can be linked to cytoskeletal and sarcomeric actin contributions by CM contractility measurements at varying CytoD concentrations, where we observe a significant reduction in pulse duration only above 103 nM while no change is found for compound exposure at lower concentrations. Comparing our results to mechanical cell measurements using atomic force microscopy, we demonstrate for the first time to our knowledge, the feasibility of using a microfluidic technique to measure mechanical properties of large samples of adherent cells while linking our results to the composition of the cytoskeletal network. This article is part of a discussion meeting issue 'Single cell ecology'.

Machine learning of human plasma lipidomes for obesity estimation in a large population cohort

Obesity is associated with changes in the plasma lipids. Although simple lipid quantification is routinely used, plasma lipids are rarely investigated at the level of individual molecules. We aimed at predicting different measures of obesity based on the plasma lipidome in a large population cohort using advanced machine learning modeling. A total of 1,061 participants of the FINRISK 2012 population cohort were randomly chosen, and the levels of 183 plasma lipid species were measured in a novel mass spectrometric shotgun approach. Multiple machine intelligence models were trained to predict obesity estimates, i.e., body mass index (BMI), waist circumference (WC), waist-hip ratio (WHR), and body fat percentage (BFP), and validated in 250 randomly chosen participants of the Malmö Diet and Cancer Cardiovascular Cohort (MDC-CC). Comparison of the different models revealed that the lipidome predicted BFP the best (R2 = 0.73), based on a Lasso model. In this model, the strongest positive and the strongest negative predictor were sphingomyelin molecules, which differ by only 1 double bond, implying the involvement of an unknown desaturase in obesity-related aberrations of lipid metabolism. Moreover, we used this regression to probe the clinically relevant information contained in the plasma lipidome and found that the plasma lipidome also contains information about body fat distribution, because WHR (R2 = 0.65) was predicted more accurately than BMI (R2 = 0.47). These modeling results required full resolution of the lipidome to lipid species level, and the predicting set of biomarkers had to be sufficiently large. The power of the lipidomics association was demonstrated by the finding that the addition of routine clinical laboratory variables, e.g., high-density lipoprotein (HDL)- or low-density lipoprotein (LDL)- cholesterol did not improve the model further. Correlation analyses of the individual lipid species, controlled for age and separated by sex, underscores the multiparametric and lipid species-specific nature of the correlation with the BFP. Lipidomic measurements in combination with machine intelligence modeling contain rich information about body fat amount and distribution beyond traditional clinical assays.

Review of applications of high-throughput sequencing in personalized medicine: barriers and facilitators of future progress in research and clinical application

There has been an exponential growth in the performance and output of sequencing technologies (omics data) with full genome sequencing now producing gigabases of reads on a daily basis. These data may hold the promise of personalized medicine, leading to routinely available sequencing tests that can guide patient treatment decisions. In the era of high-throughput sequencing (HTS), computational considerations, data governance and clinical translation are the greatest rate-limiting steps. To ensure that the analysis, management and interpretation of such extensive omics data is exploited to its full potential, key factors, including sample sourcing, technology selection and computational expertise and resources, need to be considered, leading to an integrated set of high-performance tools and systems. This article provides an up-to-date overview of the evolution of HTS and the accompanying tools, infrastructure and data management approaches that are emerging in this space, which, if used within in a multidisciplinary context, may ultimately facilitate the development of personalized medicine.

Systems Network Genomic Analysis Reveals Cardioprotective Effect of MURC/Cavin-4 Deletion Against Ischemia/Reperfusion Injury

Background

Ischemia/reperfusion (I/R) injury is a critical issue in the development of treatment strategies for ischemic heart disease. MURC (muscle‐restricted coiled‐coil protein)/Cavin‐4 (caveolae‐associated protein 4), which is a component of caveolae, is involved in the pathophysiology of dilated cardiomyopathy and cardiac hypertrophy. However, the role of MURC in cardiac I/R injury remains unknown.

Methods and Results

The systems network genomic analysis based on PC‐corr network inference on microarray data between wild‐type and MURC knockout mouse hearts predicted a network of discriminating genes associated with reactive oxygen species. To demonstrate the prediction, we analyzed I/R‐injured mouse hearts. MURC deletion decreased infarct size and preserved heart contraction with reactive oxygen species–related molecule EGR1 (early growth response protein 1) and DDIT4 (DNA‐damage‐inducible transcript 4) suppression in I/R‐injured hearts. Because PC‐corr network inference integrated with a protein–protein interaction network prediction also showed that MURC is involved in the apoptotic pathway, we confirmed the upregulation of STAT3 (signal transducer and activator of transcription 3) and BCL2 (B‐cell lymphoma 2) and the inactivation of caspase 3 in I/R‐injured hearts of MURC knockout mice compared with those of wild‐type mice. STAT3 inhibitor canceled the cardioprotective effect of MURC deletion in I/R‐injured hearts. In cardiomyocytes exposed to hydrogen peroxide, MURC overexpression promoted apoptosis and MURC knockdown inhibited apoptosis. STAT3 inhibitor canceled the antiapoptotic effect of MURC knockdown in cardiomyocytes.

Conclusions

Our findings, obtained by prediction from systems network genomic analysis followed by experimental validation, suggested that MURC modulates cardiac I/R injury through the regulation of reactive oxygen species–induced cell death and STAT3‐meditated antiapoptosis. Functional inhibition of MURC may be effective in reducing cardiac I/R injury.

Ceruloplasmin replacement therapy ameliorates neurological symptoms in a preclinical model of aceruloplasminemia

Aceruloplasminemia is a monogenic disease caused by mutations in the ceruloplasmin gene that result in loss of protein ferroxidase activity. Ceruloplasmin plays a role in iron homeostasis, and its activity impairment leads to iron accumulation in liver, pancreas, and brain. Iron deposition promotes diabetes, retinal degeneration, and progressive neurodegeneration. Current therapies mainly based on iron chelation, partially control systemic iron deposition but are ineffective on neurodegeneration. We investigated the potential of ceruloplasmin replacement therapy in reducing the neurological pathology in the ceruloplasmin-knockout (CpKO) mouse model of aceruloplasminemia. CpKO mice were intraperitoneal administered for 2 months with human ceruloplasmin that was able to enter the brain inducing replacement of the protein levels and rescue of ferroxidase activity. Ceruloplasmin-treated mice showed amelioration of motor incoordination that was associated with diminished loss of Purkinje neurons and reduced brain iron deposition, in particular in the choroid plexus. Computational analysis showed that ceruloplasmin-treated CpKO mice share a similar pattern with wild-type animals, highlighting the efficacy of the therapy. These data suggest that enzyme replacement therapy may be a promising strategy for the treatment of aceruloplasminemia.

A Data Science-Based Analysis Points at Distinct Patterns of Lipid Mediator Plasma Concentrations in Patients With Dementia

Based on accumulating evidence of a role of lipid signaling in many physiological and pathophysiological processes including psychiatric diseases, the present data driven analysis was designed to gather information needed to develop a prospective biomarker, using a targeted lipidomics approach covering different lipid mediators. Using unsupervised methods of data structure detection, implemented as hierarchal clustering, emergent self-organizing maps of neuronal networks, and principal component analysis, a cluster structure was found in the input data space comprising plasma concentrations of d = 35 different lipid-markers of various classes acquired in n = 94 subjects with the clinical diagnoses depression, bipolar disorder, ADHD, dementia, or in healthy controls. The structure separated patients with dementia from the other clinical groups, indicating that dementia is associated with a distinct lipid mediator plasma concentrations pattern possibly providing a basis for a future biomarker. This hypothesis was subsequently assessed using supervised machine-learning methods, implemented as random forests or principal component analysis followed by computed ABC analysis used for feature selection, and as random forests, k-nearest neighbors, support vector machines, multilayer perceptron, and naïve Bayesian classifiers to estimate whether the selected lipid mediators provide sufficient information that the diagnosis of dementia can be established at a higher accuracy than by guessing. This succeeded using a set of d = 7 markers comprising GluCerC16:0, Cer24:0, Cer20:0, Cer16:0, Cer24:1, C16 sphinganine, and LacCerC16:0, at an accuracy of 77%. By contrast, using random lipid markers reduced the diagnostic accuracy to values of 65% or less, whereas training the algorithms with randomly permuted data was followed by complete failure to diagnose dementia, emphasizing that the selected lipid mediators were display a particular pattern in this disease possibly qualifying as biomarkers.

Systematic Analysis and Biomarker Study for Alzheimer's Disease

Revealing the relationship between dysfunctional genes in blood and brain tissues from patients with Alzheimer’s Disease (AD) will help us to understand the pathology of this disease. In this study, we conducted the first such large systematic analysis to identify differentially expressed genes (DEGs) in blood samples from 245 AD cases, 143 mild cognitive impairment (MCI) cases, and 182 healthy control subjects, and then compare these with DEGs in brain samples. We evaluated our findings using two independent AD blood datasets and performed a gene-based genome-wide association study to identify potential novel risk genes. We identified 789 and 998 DEGs common to both blood and brain of AD and MCI subjects respectively, over 77% of which had the same regulation directions across tissues and disease status, including the known ABCA7, and the novel TYK2 and TCIRG1. A machine learning classification model containing NDUFA1, MRPL51, and RPL36AL, implicating mitochondrial and ribosomal function, was discovered which discriminated between AD patients and controls with 85.9% of area under the curve and 78.1% accuracy (sensitivity = 77.6%, specificity = 78.9%). Moreover, our findings strongly suggest that mitochondrial dysfunction, NF-κB signalling and iNOS signalling are important dysregulated pathways in AD pathogenesis.

Modelling Self-Organization in Complex Networks Via a Brain-Inspired Network Automata Theory Improves Link Reliability in Protein Interactomes

Protein interactomes are epitomes of incomplete and noisy networks. Methods for assessing link-reliability using exclusively topology are valuable in network biology, and their investigation facilitates the general understanding of topological mechanisms and models to draw and correct complex network connectivity. Here, I revise and extend the local-community-paradigm (LCP). Initially detected in brain-network topological self-organization and afterward generalized to any complex network, the LCP is a theory to model local-topology-dependent link-growth in complex networks using network automata. Four novel LCP-models are compared versus baseline local-topology-models. It emerges that the reliability of an interaction between two proteins is higher: (i) if their common neighbours are isolated in a complex (local-community) that has low tendency to interact with other external proteins; (ii) if they have a low propensity to link with other proteins external to the local-community. These two rules are mathematically combined in C1*: a proposed mechanistic model that, in fact, outperforms the others. This theoretical study elucidates basic topological rules behind self-organization principia of protein interactomes and offers the conceptual basis to extend this theory to any class of complex networks. The link-reliability improvement, based on the mere topology, can impact many applied domains such as systems biology and network medicine.

Lipidomics in Major Depressive Disorder

Omic sciences coupled with novel computational approaches such as machine intelligence offer completely new approaches to major depressive disorder (MDD) research. The complexity of MDD's pathophysiology is being integrated into studies examining MDD's biology within the omic fields. Lipidomics, as a late-comer among other omic fields, is increasingly being recognized in psychiatric research because it has allowed the investigation of global lipid perturbations in patients suffering from MDD and indicated a crucial role of specific patterns of lipid alterations in the development and progression of MDD. Combinatorial lipid-markers with high classification power are being developed in order to assist MDD diagnosis, while rodent models of depression reveal lipidome changes and thereby unveil novel treatment targets for depression. In this systematic review, we provide an overview of current breakthroughs and future trends in the field of lipidomics in MDD research and thereby paving the way for precision medicine in MDD.

Machine-learning based lipid mediator serum concentration patterns allow identification of multiple sclerosis patients with high accuracy

Based on increasing evidence suggesting that MS pathology involves alterations in bioactive lipid metabolism, the present analysis was aimed at generating a complex serum lipid-biomarker. Using unsupervised machine-learning, implemented as emergent self-organizing maps of neuronal networks, swarm intelligence and Minimum Curvilinear Embedding, a cluster structure was found in the input data space comprising serum concentrations of d = 43 different lipid-markers of various classes. The structure coincided largely with the clinical diagnosis, indicating that the data provide a basis for the creation of a biomarker (classifier). This was subsequently assessed using supervised machine-learning, implemented as random forests and computed ABC analysis-based feature selection. Bayesian statistics-based biomarker creation was used to map the diagnostic classes of either MS patients (n = 102) or healthy subjects (n = 301). Eight lipid-markers passed the feature selection and comprised GluCerC16, LPA20:4, HETE15S, LacCerC24:1, C16Sphinganine, biopterin and the endocannabinoids PEA and OEA. A complex classifier or biomarker was developed that predicted MS at a sensitivity, specificity and accuracy of approximately 95% in training and test data sets, respectively. The present successful application of serum lipid marker concentrations to MS data is encouraging for further efforts to establish an MS biomarker based on serum lipidomics.

High-throughput single-cell mechanical phenotyping with real-time deformability cytometry

Mechanical properties of cells can serve as a label-free marker of cell state and function and their alterations have been implicated in processes such as cancer metastasis, leukocyte activation, or stem cell differentiation. Over recent years, new techniques for single-cell mechanical characterization at high throughput have been developed to accelerate discovery in the field of mechanical phenotyping. One such technique is real-time deformability cytometry (RT-DC), a robust technology based on microfluidics that performs continuous mechanical characterization of cells in a contactless manner at rates of up to 1000 cells per second. This tremendous throughput allows for comparison of large sample numbers and precise characterization of heterogeneous cell populations. Additionally, parameters acquired in RT-DC measurements can be used to determine the apparent Young's modulus of individual cells. In this chapter, we present practical aspects important for the implementation of the RT-DC methodology, including a description of the setup, operation principles, and experimental protocols. In the latter, we describe a variety of preparation procedures for samples originating from different sources including 2D and 3D cell cultures as well as blood and tissue-derived primary cells, and discuss obstacles that may arise during their measurements. Finally, we provide insights into standard data analysis procedures and discuss the method's performance in light of other available techniques.

Reward-enhanced encoding improves relearning of forgotten associations

Research on human memory has shown that monetary incentives can enhance hippocampal memory consolidation and thereby protect memory traces from forgetting. However, it is not known whether initial reward may facilitate the recovery of already forgotten memories weeks after learning. Here, we investigated the influence of monetary reward on later relearning. Nineteen healthy human participants learned object-location associations, for half of which we offered money. Six weeks later, most of these associations had been forgotten as measured by a test of declarative memory. Yet, relearning in the absence of any reward was faster for the originally rewarded associations. Thus, associative memories encoded in a state of monetary reward motivation may persist in a latent form despite the failure to retrieve them explicitly. Alternatively, such facilitation could be analogous to the renewal effect observed in animal conditioning, whereby a reward-associated cue can reinstate anticipatory arousal, which would in turn modulate relearning. This finding has important implications for learning and education, suggesting that even when learned information is no longer accessible via explicit retrieval, the enduring effects of a past prospect of reward could facilitate its recovery.

Machine learning for epigenetics and future medical applications

Understanding epigenetic processes holds immense promise for medical applications. Advances in Machine Learning (ML) are critical to realize this promise. Previous studies used epigenetic data sets associated with the germline transmission of epigenetic transgenerational inheritance of disease and novel ML approaches to predict genome-wide locations of critical epimutations. A combination of Active Learning (ACL) and Imbalanced Class Learning (ICL) was used to address past problems with ML to develop a more efficient feature selection process and address the imbalance problem in all genomic data sets. The power of this novel ML approach and our ability to predict epigenetic phenomena and associated disease is suggested. The current approach requires extensive computation of features over the genome. A promising new approach is to introduce Deep Learning (DL) for the generation and simultaneous computation of novel genomic features tuned to the classification task. This approach can be used with any genomic or biological data set applied to medicine. The application of molecular epigenetic data in advanced machine learning analysis to medicine is the focus of this review.