A robust microbiome signature for autism spectrum disorder across different studies using machine learning.

Autism spectrum disorder (ASD) is a highly complex neurodevelopmental disorder characterized by deficits in sociability and repetitive behaviour, however there is a great heterogeneity within other comorbidities that accompany ASD. Recently, gut microbiome has been pointed out as a plausible contributing factor for ASD development as individuals diagnosed with ASD often suffer from intestinal problems and show a differentiated intestinal microbial composition. Nevertheless, gut microbiome studies in ASD rarely agree on the specific bacterial taxa involved in this disorder. Regarding the potential role of gut microbiome in ASD pathophysiology, our aim is to investigate whether there is a set of bacterial taxa relevant for ASD classification by using a sibling-controlled dataset. Additionally, we aim to validate these results across two independent cohorts as several confounding factors, such as lifestyle, influence both ASD and gut microbiome studies. A machine learning approach, recursive ensemble feature selection (REFS), was applied to 16S rRNA gene sequencing data from 117 subjects (60 ASD cases and 57 siblings) identifying 26 bacterial taxa that discriminate ASD cases from controls. The average area under the curve (AUC) of this specific set of bacteria in the sibling-controlled dataset was 81.6%. Moreover, we applied the selected bacterial taxa in a tenfold cross-validation scheme using two independent cohorts (a total of 223 samples-125 ASD cases and 98 controls). We obtained average AUCs of 74.8% and 74%, respectively. Analysis of the gut microbiome using REFS identified a set of bacterial taxa that can be used to predict the ASD status of children in three distinct cohorts with AUC over 80% for the best-performing classifiers. Our results indicate that the gut microbiome has a strong association with ASD and should not be disregarded as a potential target for therapeutic interventions. Furthermore, our work can contribute to use the proposed approach for identifying microbiome signatures across other 16S rRNA gene sequencing datasets.

Methodology for biomarker discovery with reproducibility in microbiome data using machine learning.

BACKGROUND: In recent years, human microbiome studies have received increasing attention as this field is considered a potential source for clinical applications. With the advancements in omics technologies and AI, research focused on the discovery for potential biomarkers in the human microbiome using machine learning tools has produced positive outcomes. Despite the promising results, several issues can still be found in these studies such as datasets with small number of samples, inconsistent results, lack of uniform processing and methodologies, and other additional factors lead to lack of reproducibility in biomedical research. In this work, we propose a methodology that combines the DADA2 pipeline for 16s rRNA sequences processing and the Recursive Ensemble Feature Selection (REFS) in multiple datasets to increase reproducibility and obtain robust and reliable results in biomedical research. RESULTS: Three experiments were performed analyzing microbiome data from patients/cases in Inflammatory Bowel Disease (IBD), Autism Spectrum Disorder (ASD), and Type 2 Diabetes (T2D). In each experiment, we found a biomarker signature in one dataset and applied to 2 other as further validation. The effectiveness of the proposed methodology was compared with other feature selection methods such as K-Best with F-score and random selection as a base line. The Area Under the Curve (AUC) was employed as a measure of diagnostic accuracy and used as a metric for comparing the results of the proposed methodology with other feature selection methods. Additionally, we use the Matthews Correlation Coefficient (MCC) as a metric to evaluate the performance of the methodology as well as for comparison with other feature selection methods. CONCLUSIONS: We developed a methodology for reproducible biomarker discovery for 16s rRNA microbiome sequence analysis, addressing the issues related with data dimensionality, inconsistent results and validation across independent datasets. The findings from the three experiments, across 9 different datasets, show that the proposed methodology achieved higher accuracy compared to other feature selection methods. This methodology is a first approach to increase reproducibility, to provide robust and reliable results.

A robust mRNA signature obtained via recursive ensemble feature selection predicts the responsiveness of omalizumab in moderate-to-severe asthma.

BACKGROUND: Not being well controlled by therapy with inhaled corticosteroids and long-acting ß2 agonist bronchodilators is a major concern for severe-asthma patients. The current treatment option for these patients is the use of biologicals such as anti-IgE treatment, omalizumab, as an add-on therapy. Despite the accepted use of omalizumab, patients do not always benefit from it. Therefore, there is a need to identify reliable biomarkers as predictors of omalizumab response. METHODS: Two novel computational algorithms, machine-learning based Recursive Ensemble Feature Selection (REFS) and rule-based algorithm Logic Explainable Networks (LEN), were used on open accessible mRNA expression data from moderate-to-severe asthma patients to identify genes as predictors of omalizumab response. RESULTS: With REFS, the number of features was reduced from 28,402 genes to 5 genes while obtaining a cross-validated accuracy of 0.975. The 5 responsiveness predictive genes encode the following proteins: Coiled-coil domain- containing protein 113 (CCDC113), Solute Carrier Family 26 Member 8 (SLC26A), Protein Phosphatase 1 Regulatory Subunit 3D (PPP1R3D), C-Type lectin Domain Family 4 member C (CLEC4C) and LOC100131780 (not annotated). The LEN algorithm found 4 identical genes with REFS: CCDC113, SLC26A8 PPP1R3D and LOC100131780. Literature research showed that the 4 identified responsiveness predicting genes are associated with mucosal immunity, cell metabolism, and airway remodeling. CONCLUSION AND CLINICAL RELEVANCE: Both computational methods show 4 identical genes as predictors of omalizumab response in moderate-to-severe asthma patients. The obtained high accuracy indicates that our approach has potential in clinical settings. Future studies in relevant cohort data should validate our computational approach.

An Innovative AI-based primer design tool for precise and accurate detection of SARS-CoV-2 variants of concern.

As the COVID-19 pandemic winds down, it leaves behind the serious concern that future, even more disruptive pandemics may eventually surface. One of the crucial steps in handling the SARS-CoV-2 pandemic was being able to detect the presence of the virus in an accurate and timely manner, to then develop policies counteracting the spread. Nevertheless, as the pandemic evolved, new variants with potentially dangerous mutations appeared. Faced by these developments, it becomes clear that there is a need for fast and reliable techniques to create highly specific molecular tests, able to uniquely identify VOCs. Using an automated pipeline built around evolutionary algorithms, we designed primer sets for SARS-CoV-2 (main lineage) and for VOC, B.1.1.7 (Alpha) and B.1.1.529 (Omicron). Starting from sequences openly available in the GISAID repository, our pipeline was able to deliver the primer sets for the main lineage and each variant in a matter of hours. Preliminary in-silico validation showed that the sequences in the primer sets featured high accuracy. A pilot test in a laboratory setting confirmed the results: the developed primers were favorably compared against existing commercial versions for the main lineage, and the specific versions for the VOCs B.1.1.7 and B.1.1.529 were clinically tested successfully.

In Silico Screening of Drugs That Target Different Forms of E Protein for Potential Treatment of COVID-19.

Recently the E protein of SARS-CoV-2 has become a very important target in the potential treatment of COVID-19 since it is known to regulate different stages of the viral cycle. There is biochemical evidence that E protein exists in two forms, as monomer and homopentamer. An in silico screening analysis was carried out employing 5852 ligands (from Zinc databases), and performing an ADMET analysis, remaining a set of 2155 compounds. Furthermore, docking analysis was performed on specific sites and different forms of the E protein. From this study we could identify that the following ligands showed the highest binding affinity: nilotinib, dutasteride, irinotecan, saquinavir and alectinib. We carried out some molecular dynamics simulations and free energy MM-PBSA calculations of the protein-ligand complexes (with the mentioned ligands). Of worthy interest is that saquinavir, nilotinib and alectinib are also considered as a promising multitarget ligand because it seems to inhibit three targets, which play an important role in the viral cycle. On the other side, saquinavir was shown to be able to bind to E protein both in its monomeric as well as pentameric forms. Finally, further experimental assays are needed to probe our hypothesis derived from in silico studies.

Classifying asthma control using salivary and fecal bacterial microbiome in children with moderate-to-severe asthma.

BACKGROUND: Uncontrolled asthma can lead to severe exacerbations and reduced quality of life. Research has shown that the microbiome may be linked with asthma characteristics; however, its association with asthma control has not been explored. We aimed to investigate whether the gastrointestinal microbiome can be used to discriminate between uncontrolled and controlled asthma in children. METHODS: 143 and 103 feces samples were obtained from 143 children with moderate-to-severe asthma aged 6 to 17 years from the SysPharmPediA study. Patients were classified as controlled or uncontrolled asthmatics, and their microbiome at species level was compared using global (alpha/beta) diversity, conventional differential abundance analysis (DAA, analysis of compositions of microbiomes with bias correction), and machine learning [Recursive Ensemble Feature Selection (REFS)]. RESULTS: Global diversity and DAA did not find significant differences between controlled and uncontrolled pediatric asthmatics. REFS detected a set of taxa, including Haemophilus and Veillonella, differentiating uncontrolled and controlled asthma with an average classification accuracy of 81% (saliva) and 86% (feces). These taxa showed enrichment in taxa previously associated with inflammatory diseases for both sampling compartments, and with COPD for the saliva samples. CONCLUSION: Controlled and uncontrolled children with asthma can be differentiated based on their gastrointestinal microbiome using machine learning, specifically REFS. Our results show an association between asthma control and the gastrointestinal microbiome. This suggests that the gastrointestinal microbiome may be a potential biomarker for treatment responsiveness and thereby help to improve asthma control in children.

A combination of immune cell types identified through ensemble machine learning strategy detects altered profile in recurrent pregnancy loss: a pilot study.

OBJECTIVE: To compare the immunologic profiles of peripheral and menstrual blood (MB) of women who experience recurrent pregnancy loss and women without pregnancy complications. DESIGN: Explorative case-control study. Cross-sectional assessment of flow cytometry-derived immunologic profiles. SETTING: Academic medical center. PATIENT(S): Women who experienced more than 2 consecutive miscarriages. INTERVENTION(S): None. MAIN OUTCOME MEASURE(S): Flow cytometry-based immune profiles of uterine and systemic immunity (recurrent pregnancy loss, n = 18; control, n = 14) assessed by machine learning classifiers in an ensemble strategy, followed by recursive feature selection. RESULT(S): In peripheral blood, the combination of 4 cell types (nonswitched memory B cells, CD8+ T cells, CD56bright CD16- natural killer [NKbright] cells, and CD4+ effector T cells) classified samples correctly to their respective cohort. The identified classifying cell types in peripheral blood differed from the results observed in MB, where a combination of 6 cell types (Ki67+CD8+ T cells, (Human leukocyte antigen-DR+) regulatory T cells, CD27+ B cells, NKbright cells, regulatory T cells, and CD24HiCD38Hi B cells) plus age allowed for assigning samples correctly to their respective cohort. Based on the combination of these features, the average area under the curve of a receiver operating characteristic curve and the associated accuracy were >0.8 for both sample sources. CONCLUSION(S): A combination of immune subsets for cohort classification allows for robust identification of immune parameters with possible diagnostic value. The noninvasive source of MB holds several opportunities to assess and monitor reproductive health.

Analysing the protection from respiratory tract infections and allergic diseases early in life by human milk components: the PRIMA birth cohort.

BACKGROUND: Many studies support the protective effect of breastfeeding on respiratory tract infections. Although infant formulas have been developed to provide adequate nutritional solutions, many components in human milk contributing to the protection of newborns and aiding immune development still need to be identified. In this paper we present the methodology of the "Protecting against Respiratory tract lnfections through human Milk Analysis" (PRIMA) cohort, which is an observational, prospective and multi-centre birth cohort aiming to identify novel functions of components in human milk that are protective against respiratory tract infections and allergic diseases early in life. METHODS: For the PRIMA human milk cohort we aim to recruit 1000 mother-child pairs in the first month postpartum. At one week, one, three, and six months after birth, fresh human milk samples will be collected and processed. In order to identify protective components, the level of pathogen specific antibodies, T cell composition, Human milk oligosaccharides, as well as extracellular vesicles (EVs) will be analysed, in the milk samples in relation to clinical data which are collected using two-weekly parental questionnaires. The primary outcome of this study is the number of parent-reported medically attended respiratory infections. Secondary outcomes that will be measured are physician diagnosed (respiratory) infections and allergies during the first year of life. DISCUSSION: The PRIMA human milk cohort will be a large prospective healthy birth cohort in which we will use an integrated, multidisciplinary approach to identify the longitudinal effect human milk components that play a role in preventing (respiratory) infections and allergies during the first year of life. Ultimately, we believe that this study will provide novel insights into immunomodulatory components in human milk. This may allow for optimizing formula feeding for all non-breastfed infants.

Antibiotic Intervention Affects Maternal Immunity During Gestation in Mice.

Background: Pregnancy is a portentous stage in life, during which countless events are precisely orchestrated to ensure a healthy offspring. Maternal microbial communities are thought to have a profound impact on development. Although antibiotic drugs may interfere in these processes, they constitute the most frequently prescribed medication during pregnancy to prohibit detrimental consequences of infections. Gestational antibiotic intervention is linked to preeclampsia and negative effects on neonatal immunity. Even though perturbations in the immune system of the mother can affect reproductive health, the impact of microbial manipulation on maternal immunity is still unknown. Aim: To assess whether antibiotic treatment influences maternal immunity during pregnancy. Methods: Pregnant mice were treated with broad-spectrum antibiotics. The maternal gut microbiome was assessed. Numerous immune parameters throughout the maternal body, including placenta and amniotic fluid were investigated and a novel machine-learning ensemble strategy was used to identify immunological parameters that allow distinction between the control and antibiotic-treated group. Results: Antibiotic treatment reduced diversity of maternal microbiota, but litter sizes remained unaffected. Effects of antibiotic treatment on immunity reached as far as the placenta. Four immunological features were identified by recursive feature selection to contribute to the most robust classification (splenic T helper 17 cells and CD5+ B cells, CD4+ T cells in mesenteric lymph nodes and RORγT mRNA expression in placenta). Conclusion: In the present study, antibiotic treatment was able to affect the carefully coordinated immunity during pregnancy. These findings highlight the importance of inclusion of immunological parameters when studying the effects of medication used during gestation.

Recursive ensemble feature selection provides a robust mRNA expression signature for myalgic encephalomyelitis/chronic fatigue syndrome.

Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a chronic disorder characterized by disabling fatigue. Several studies have sought to identify diagnostic biomarkers, with varying results. Here, we innovate this process by combining both mRNA expression and DNA methylation data. We performed recursive ensemble feature selection (REFS) on publicly available mRNA expression data in peripheral blood mononuclear cells (PBMCs) of 93 ME/CFS patients and 25 healthy controls, and found a signature of 23 genes capable of distinguishing cases and controls. REFS highly outperformed other methods, with an AUC of 0.92. We validated the results on a different platform (AUC of 0.95) and in DNA methylation data obtained from four public studies on ME/CFS (99 patients and 50 controls), identifying 48 gene-associated CpGs that predicted disease status as well (AUC of 0.97). Finally, ten of the 23 genes could be interpreted in the context of the derailed immune system of ME/CFS.

Classification and specific primer design for accurate detection of SARS-CoV-2 using deep learning.

In this paper, deep learning is coupled with explainable artificial intelligence techniques for the discovery of representative genomic sequences in SARS-CoV-2. A convolutional neural network classifier is first trained on 553 sequences from the National Genomics Data Center repository, separating the genome of different virus strains from the Coronavirus family with 98.73% accuracy. The network's behavior is then analyzed, to discover sequences used by the model to identify SARS-CoV-2, ultimately uncovering sequences exclusive to it. The discovered sequences are validated on samples from the National Center for Biotechnology Information and Global Initiative on Sharing All Influenza Data repositories, and are proven to be able to separate SARS-CoV-2 from different virus strains with near-perfect accuracy. Next, one of the sequences is selected to generate a primer set, and tested against other state-of-the-art primer sets, obtaining competitive results. Finally, the primer is synthesized and tested on patient samples (n = 6 previously tested positive), delivering a sensitivity similar to routine diagnostic methods, and 100% specificity. The proposed methodology has a substantial added value over existing methods, as it is able to both automatically identify promising primer sets for a virus from a limited amount of data, and deliver effective results in a minimal amount of time. Considering the possibility of future pandemics, these characteristics are invaluable to promptly create specific detection methods for diagnostics.

Dietary Supplementation throughout Life with Non-Digestible Oligosaccharides and/or n-3 Poly-Unsaturated Fatty Acids in Healthy Mice Modulates the Gut-Immune System-Brain Axis.

The composition and activity of the intestinal microbial community structures can be beneficially modulated by nutritional components such as non-digestible oligosaccharides and omega-3 poly-unsaturated fatty acids (n-3 PUFAs). These components affect immune function, brain development and behaviour. We investigated the additive effect of a dietary combination of scGOS:lcFOS and n-3 PUFAs on caecal content microbial community structures and development of the immune system, brain and behaviour from day of birth to early adulthood in healthy mice. Male BALB/cByJ mice received a control or enriched diet with a combination of scGOS:lcFOS (9:1) and 6% tuna oil (n-3 PUFAs) or individually scGOS:lcFOS (9:1) or 6% tuna oil (n-3 PUFAs). Behaviour, caecal content microbiota composition, short-chain fatty acid levels, brain monoamine levels, enterochromaffin cells and immune parameters in the mesenteric lymph nodes (MLN) and spleen were assessed. Caecal content microbial community structures displayed differences between the control and dietary groups, and between the dietary groups. Compared to control diet, the scGOS:lcFOS and combination diets increased caecal saccharolytic fermentation activity. The diets enhanced the number of enterochromaffin cells. The combination diet had no effects on the immune cells. Although the dietary effect on behaviour was limited, serotonin and serotonin metabolite levels in the amygdala were increased in the combination diet group. The combination and individual interventions affected caecal content microbial profiles, but had limited effects on behaviour and the immune system. No apparent additive effect was observed when scGOS:lcFOS and n-3 PUFAs were combined. The results suggest that scGOS:lcFOS and n-3 PUFAs together create a balance-the best of both in a healthy host.

Machine Learning-Based Ensemble Recursive Feature Selection of Circulating miRNAs for Cancer Tumor Classification.

Circulating microRNAs (miRNA) are small noncoding RNA molecules that can be detected in bodily fluids without the need for major invasive procedures on patients. miRNAs have shown great promise as biomarkers for tumors to both assess their presence and to predict their type and subtype. Recently, thanks to the availability of miRNAs datasets, machine learning techniques have been successfully applied to tumor classification. The results, however, are difficult to assess and interpret by medical experts because the algorithms exploit information from thousands of miRNAs. In this work, we propose a novel technique that aims at reducing the necessary information to the smallest possible set of circulating miRNAs. The dimensionality reduction achieved reflects a very important first step in a potential, clinically actionable, circulating miRNA-based precision medicine pipeline. While it is currently under discussion whether this first step can be taken, we demonstrate here that it is possible to perform classification tasks by exploiting a recursive feature elimination procedure that integrates a heterogeneous ensemble of high-quality, state-of-the-art classifiers on circulating miRNAs. Heterogeneous ensembles can compensate inherent biases of classifiers by using different classification algorithms. Selecting features then further eliminates biases emerging from using data from different studies or batches, yielding more robust and reliable outcomes. The proposed approach is first tested on a tumor classification problem in order to separate 10 different types of cancer, with samples collected over 10 different clinical trials, and later is assessed on a cancer subtype classification task, with the aim to distinguish triple negative breast cancer from other subtypes of breast cancer. Overall, the presented methodology proves to be effective and compares favorably to other state-of-the-art feature selection methods.

Function Based Brain Modeling and Simulation of an Ischemic Region in Post-Stroke Patients using the Bidomain.

BACKGROUND: Several studies have shown that post-stroke patients develop divergent activity in the sensorimotor areas of the affected hemisphere of the brain compared to healthy people during motor tasks. Proper mathematical models will help us understand this activity and clarify the associated underlying mechanisms. New Method. This research describes an anatomically based brain computer model in post-stroke patients. We simulate an ischemic region for arm motion using the bidomain approach. Two scenarios are considered: a healthy subject and a post-stroke patient with motion impairment. Next, we limit the volume of propagation considering only the sensorimotor area of the brain. Comparison with existing methods. In comparison to existing methods, we combine the use of the bidomain for modeling the propagation of the electrical activity across the brain volume with functional information to limit the volume of propagation and the position of the expected stimuli, given a specific task. Whereas just using the bidomain without limiting the functional volume, propagates the electrical activity into non-expected areas. RESULTS: To validate the simulation, we compare the activity with patient measurements using functional near-infrared spectroscopy during arm motion (n=5) against controls (n=3). The results are consistent with empirical measurements and previous research and show that there is a disparity between position and number of spikes in post-stroke patients in contrast to healthy subjects. CONCLUSIONS: These results hold promise in improving the understanding of brain deterioration in stroke patients and the re-arrangement of brain networks. Furthermore, shows the use of functionality based brain modeling.

Automatic discovery of 100-miRNA signature for cancer classification using ensemble feature selection.

BACKGROUND: MicroRNAs (miRNAs) are noncoding RNA molecules heavily involved in human tumors, in which few of them circulating the human body. Finding a tumor-associated signature of miRNA, that is, the minimum miRNA entities to be measured for discriminating both different types of cancer and normal tissues, is of utmost importance. Feature selection techniques applied in machine learning can help however they often provide naive or biased results. RESULTS: An ensemble feature selection strategy for miRNA signatures is proposed. miRNAs are chosen based on consensus on feature relevance from high-accuracy classifiers of different typologies. This methodology aims to identify signatures that are considerably more robust and reliable when used in clinically relevant prediction tasks. Using the proposed method, a 100-miRNA signature is identified in a dataset of 8023 samples, extracted from TCGA. When running eight-state-of-the-art classifiers along with the 100-miRNA signature against the original 1046 features, it could be detected that global accuracy differs only by 1.4%. Importantly, this 100-miRNA signature is sufficient to distinguish between tumor and normal tissues. The approach is then compared against other feature selection methods, such as UFS, RFE, EN, LASSO, Genetic Algorithms, and EFS-CLA. The proposed approach provides better accuracy when tested on a 10-fold cross-validation with different classifiers and it is applied to several GEO datasets across different platforms with some classifiers showing more than 90% classification accuracy, which proves its cross-platform applicability. CONCLUSIONS: The 100-miRNA signature is sufficiently stable to provide almost the same classification accuracy as the complete TCGA dataset, and it is further validated on several GEO datasets, across different types of cancer and platforms. Furthermore, a bibliographic analysis confirms that 77 out of the 100 miRNAs in the signature appear in lists of circulating miRNAs used in cancer studies, in stem-loop or mature-sequence form. The remaining 23 miRNAs offer potentially promising avenues for future research.

The inverse problem in electroencephalography using the bidomain model of electrical activity.

BACKGROUND: Acquiring information about the distribution of electrical sources in the brain from electroencephalography (EEG) data remains a significant challenge. An accurate solution would provide an understanding of the inner mechanisms of the electrical activity in the brain and information about damaged tissue. NEW METHOD: In this paper, we present a methodology for reconstructing brain electrical activity from EEG data by using the bidomain formulation. The bidomain model considers continuous active neural tissue coupled with a nonlinear cell model. Using this technique, we aim to find the brain sources that give rise to the scalp potential recorded by EEG measurements taking into account a non-static reconstruction. COMPARISON WITH EXISTING METHODS: We simulate electrical sources in the brain volume and compare the reconstruction to the minimum norm estimates (MNEs) and low resolution electrical tomography (LORETA) results. Then, with the EEG dataset from the EEG Motor Movement/Imagery Database of the Physiobank, we identify the reaction to visual stimuli by calculating the time between stimulus presentation and the spike in electrical activity. Finally, we compare the activation in the brain with the registered activation using the LinkRbrain platform. RESULTS/CONCLUSION: Our methodology shows an improved reconstruction of the electrical activity and source localization in comparison with MNE and LORETA. For the Motor Movement/Imagery Database, the reconstruction is consistent with the expected position and time delay generated by the stimuli. Thus, this methodology is a suitable option for continuously reconstructing brain potentials.