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

Identifying miRNA as biomarker for breast cancer subtyping using association rule

- This paper presents a comprehensive study focused on breast cancer subtyping, utilizing a multifaceted approach that integrates feature selection, machine learning classifiers, and miRNA regulatory networks. The feature selection process begins with the CFS algorithm, followed by the Apriori algorithm for association rule generation, resulting in the identification of significant features tailored to Luminal A, Luminal B, HER-2 enriched, and Basal-like subtypes. The subsequent application of Random Forest (RF) and Support Vector Machine (SVM) classifiers yielded promising results, with the SVM model achieving an overall accuracy of 76.60 % and the RF model demonstrating robust performance at 80.85 %. Detailed accuracy metrics revealed strengths and areas for refinement, emphasizing the potential for optimizing subtype-specific recall. To explore the regulatory landscape in depth, an analysis of selected miRNAs was conducted using MIENTURNET, a tool for visualizing miRNA-target interactions. While FDR analysis raised concerns for HER-2 and Basal-like subtypes, Luminal A and Luminal B subtypes showcased significant miRNA-gene interactions. Functional enrichment analysis for Luminal A highlighted the role of Ovarian steroidogenesis, implicating specific miRNAs such as hsa-let-7c-5p and hsa-miR-125b-5p as potential diagnostic biomarkers and regulators of Luminal A breast cancer. Luminal B analysis uncovered associations with the MAPK signaling pathway, with miRNAs like hsa-miR-203a-3p and hsa-miR-19a-3p exhibiting potential diagnostic and therapeutic significance. In conclusion, this integrative approach combines machine learning techniques with miRNA analysis to provide a holistic understanding of breast cancer subtypes. The identified miRNAs and associated pathways offer insights into potential diagnostic biomarkers and therapeutic targets, contributing to the ongoing efforts to improve breast cancer diagnostics and personalized treatment strategies.

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 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.

microRNA-Based Cancer Diagnosis and Therapy

MicroRNAs (miRNAs) are small non-coding RNA molecules that regulate gene expression post-transcriptionally by impeding mRNA translation or stability [...].

New class of RNA biomarker for endometriosis diagnosis: The potential of salivary piRNA expression

OBJECTIVES

In contrast to miRNA expression, little attention has been given to piwiRNA (piRNA) expression among endometriosis patients. The aim of the present study was to explore the human piRNAome and to investigate a potential piRNA saliva-based diagnostic signature for endometriosis.

METHODS

Data from the prospective "ENDOmiRNA" study (ClinicalTrials.gov Identifier: NCT04728152) were used. Saliva samples from 200 patients were analyzed in order to evaluate human piRNA expression using the piRNA bank. Next Generation Sequencing (NGS), barcoding of unique molecular identifiers and both Artificial Intelligence (AI) and machine learning (ML) were used. For each piRNA, sensitivity, specificity, and ROC AUC values were calculated for the diagnosis of endometriosis.

RESULTS

201 piRNAs were identified, none had an AUC ≥ 0.70, and only three piRNAs (piR-004153, piR001918, piR-020401) had an AUC between ≥ 0.6 and < 0.70. Seven were differentially expressed: piR-004153, piR-001918, piR-020401, piR-012864, piR-017716, piR-020326 and piR-016904. The respective correlation and accuracy to diagnose endometriosis according to the F1-score, sensitivity, specificity, and AUC ranged from 0 to 0.862 %, 0-0.961 %, 0.085-1, and 0.425-0.618. A correlation was observed between the patients' age (≥35 years) and piR-004153 (p = 0.002) and piR-017716 (p = 0.030). Among the 201 piRNAs, four were differentially expressed in patients with and without hormonal treatment: piR-004153 (p = 0.015), piR-020401 (p = 0.001), piR-012864 (p = 0.036) and piR-017716 (p = 0.009).

CONCLUSION

Our results support the link between piRNAs and endometriosis physiopathology and establish its utility as a potential diagnostic biomarker using saliva samples. Per se, piRNA expression should be analyzed along with the clinical status of a patient.

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 β2 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.

Discovery of potential biomarkers for lung cancer classification based on human proteome microarrays using Stochastic Gradient Boosting approach

PURPOSE

Early identification of lung cancer (LC) will considerably facilitate the intervention and prevention of LC. The human proteome micro-arrays approach can be used as a "liquid biopsy" to diagnose LC to complement conventional diagnosis, which needs advanced bioinformatics methods such as feature selection (FS) and refined machine learning models.

METHODS

A two-stage FS methodology by infusing Pearson's Correlation (PC) with a univariate filter (SBF) or recursive feature elimination (RFE) was used to reduce the redundancy of the original dataset. The Stochastic Gradient Boosting (SGB), Random Forest (RF), and Support Vector Machine (SVM) techniques were applied to build ensemble classifiers based on four subsets. The synthetic minority oversampling technique (SMOTE) was used in the preprocessing of imbalanced data.

RESULTS

FS approach with SBF and RFE extracted 25 and 55 features, respectively, with 14 overlapped ones. All three ensemble models demonstrate superior accuracy (ranging from 0.867 to 0.967) and sensitivity (0.917 to 1.00) in the test datasets with SGB of SBF subset outperforming others. The SMOTE technique has improved the model performance in the training process. Three of the top selected candidate biomarkers (LGR4, CDC34, and GHRHR) were highly suggested to play a role in lung tumorigenesis.

CONCLUSION

A novel hybrid FS method with classical ensemble machine learning algorithms was first used in the classification of protein microarray data. The parsimony model constructed by the SGB algorithm with the appropriate FS and SMOTE approach performs well in the classification task with higher sensitivity and specificity. Standardization and innovation of bioinformatics approach for protein microarray analysis need further exploration and validation.

Selecting optimum miRNA panel for miRNA signature-based companion diagnostic model to predict the response of R-CHOP treatment in diffuse large B-cell lymphoma

Diffuse large B-cell lymphoma (DLBCL) is the most common type of malignant lymphoma. Although the first-line treatment, R-CHOP treatment, shows efficacy in approximately 80% of patients with DLBCL, some patients have refractory disease or relapse after the initial response to therapy, resulting in a significantly poorer prognosis. In this study, we developed a microRNA (miRNA) signature-based companion diagnostic model to predict the response of patients with DLBCL to R-CHOP treatment by integrating two clinical study datasets. To select the optimum miRNA combination as a panel, we examined three feature selection methods (p-value-based ranking, stepwise method, and Boruta), together with 11 types of classifiers systematically. Boruta selection enabled a higher area under the curve (AUC) with a lower number of miRNAs compared with other feature selection methods, leading to an AUC of 0.751 via the random forest classifier using 36 miRNAs. Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis suggested that Boruta avoided multiple selection of miRNAs with similar functions, thereby preventing the decrease in diagnostic ability via collinearity. The AUC value first increased with an increasing number of miRNAs and then became almost constant at approximately 30 miRNAs, suggesting the existence of the optimum number of miRNAs as a panel for future clinical translation of multiple miRNA-based diagnostics.

Endometriosis-associated infertility diagnosis based on saliva microRNA signatures

RESEARCH QUESTION

Can a saliva-based miRNA signature for endometriosis-associated infertility be designed and validated by analysing the human miRNome?

DESIGN

The prospective ENDOmiARN study (NCT04728152) included 200 saliva samples obtained between January 2021 and June 2021 from women with pelvic pain suggestive of endometriosis. All patients underwent either laparoscopy, magnetic resonance imaging, or both. Patients diagnosed with endometriosis were allocated to one of two groups according to their fertility status. Data analysis consisted of identifying a set of miRNA biomarkers using next-generation sequencing, and development of a saliva-based miRNA signature of infertility among patients with endometriosis based on a random forest model.

RESULTS

Among the 153 patients diagnosed with endometriosis, 24% (n = 36) were infertile and 76% (n = 117) were fertile. Small RNA-sequencing of the 153 saliva samples yielded approximately 3712 M raw sequencing reads (from ∼13.7 M to ∼39.3 M reads/sample). Of the 2561 known miRNAs, the feature selection method generated a signature of 34 miRNAs linked to endometriosis-associated infertility. After validation, the most accurate signature model had a sensitivity, specificity and area under the curve of 100%.

CONCLUSION

A saliva-based miRNA signature for endometriosis-associated infertility is reported. Although the results still require external validation before using the signature in routine practice, this non-invasive tool is likely to have a major effect on care provided to women with endometriosis.

Breast Cancer Detection Using Automated Segmentation and Genetic Algorithms

Breast cancer is the most common cancer among women worldwide, after lung cancer. However, early detection of breast cancer can help to reduce death rates in breast cancer patients and also prevent cancer from spreading to other parts of the body. This work proposes a new method to design a bio-marker integrating Bayesian predictive models, pyRadiomics System and genetic algorithms to classify the benign and malignant lesions. The method allows one to evaluate two types of images: The radiologist-segmented lesion, and a novel automated breast cancer detection by the analysis of the whole breast. The results demonstrate only a difference of 12% of effectiveness for the cases of calcification between the radiologist generated segmentation and the automatic whole breast analysis, and a 25% of difference between the lesion and the breast for the cases of masses. In addition, our approach was compared against other proposed methods in the literature, providing an AUC = 0.86 for the analysis of images with lesions in breast calcification, and AUC = 0.96 for masses.

Addressing the Clinical Feasibility of Adopting Circulating miRNA for Breast Cancer Detection, Monitoring and Management with Artificial Intelligence and Machine Learning Platforms

Detecting breast cancer (BC) at the initial stages of progression has always been regarded as a lifesaving intervention. With modern technology, extensive studies have unraveled the complexity of BC, but the current standard practice of early breast cancer screening and clinical management of cancer progression is still heavily dependent on tissue biopsies, which are invasive and limited in capturing definitive cancer signatures for more comprehensive applications to improve outcomes in BC care and treatments. In recent years, reviews and studies have shown that liquid biopsies in the form of blood, containing free circulating and exosomal microRNAs (miRNAs), have become increasingly evident as a potential minimally invasive alternative to tissue biopsy or as a complement to biomarkers in assessing and classifying BC. As such, in this review, the potential of miRNAs as the key BC signatures in liquid biopsy are addressed, including the role of artificial intelligence (AI) and machine learning platforms (ML), in capitalizing on the big data of miRNA for a more comprehensive assessment of the cancer, leading to practical clinical utility in BC management.

Value of genomics- and radiomics-based machine learning models in the identification of breast cancer molecular subtypes: a systematic review and meta-analysis

Background

In the era of precision therapy, early classification of breast cancer (BRCA) molecular subtypes has clinical significance for disease management and prognosis. We explored the accuracy of machine learning (ML) models for early classification of BRCA molecular subtypes through a systematic review of the literature currently available.

Methods

We retrieved relevant studies published in PubMed, EMBASE, Cochrane, and Web of Science until 15 April 2022. A prediction model risk of bias assessment tool (PROBAST) was applied for the assessment of risk of bias of a genomics-based ML model, and the Radiomics Quality Score (RQS) was simultaneously used to evaluate the quality of this radiomics-based ML model. A random effects model was adopted to analyze the predictive accuracy of genomics-based ML and radiomics-based ML for Luminal A, Luminal B, Basal-like or triple-negative breast cancer (TNBC), and human epidermal growth factor receptor 2 (HER2). The PROSPERO of our study was prospectively registered (CRD42022333611).

Results

Of the 38 studies were selected for analysis, 14 ML models were based on gene-transcriptomic, with only 4 external validations; and 43 ML models were based on radiomics, with only 14 external validations. Meta-analysis results showed that c-statistic values of the ML based on radiomics for the identification of BRCA molecular subtypes Luminal A, Luminal B, Basal-like or TNBC, and HER2 were 0.76 [95% confidence interval (CI): 0.60-0.96], 0.78 (95% CI: 0.69-0.87), 0.89 (95% CI: 0.83-0.91), and 0.83 (95% CI: 0.81-0.86), respectively. The c-statistic values of ML based on the gene-transcriptomic analysis cohort for the identification of the previously described BRCA molecular subtypes were 0.96 (95% CI: 0.93-0.99), 0.96 (95% CI: 0.93-0.99), 0.98 (95% CI: 0.95-1.00), and 0.97 (95% CI: 0.96-0.98) respectively. Additionally, the sensitivity of the ML model based on radiomics for each molecular subtype ranged from 0.79 to 0.85, while the sensitivity of the ML model based on gene-transcriptomic was between 0.92 and 0.99.

Conclusions

Both radiomics and gene transcriptomics produced ideal effects on BRCA molecular subtype prediction. Compared with radiomics, gene transcriptomics yielded better prediction results, but radiomics was simpler and more convenient from a clinical point of view.

Metabolomics by NMR Combined with Machine Learning to Predict Neoadjuvant Chemotherapy Response for Breast Cancer

Simple Summary

Neoadjuvant chemotherapy (NACT) is offered to breast cancer (BC) patients to downstage the disease. However, some patients may not respond to NACT, being resistant. We used the serum metabolic profile by Nuclear Magnetic Resonance (NMR) combined with disease characteristics to differentiate between sensitive and resistant BC patients. We obtained accuracy above 80% for the response prediction and showcased how NMR can substantially enhance the prediction of response to NACT.

Abstract

Neoadjuvant chemotherapy (NACT) is offered to patients with operable or inoperable breast cancer (BC) to downstage the disease. Clinical responses to NACT may vary depending on a few known clinical and biological features, but the diversity of responses to NACT is not fully understood. In this study, 80 women had their metabolite profiles of pre-treatment sera analyzed for potential NACT response biomarker candidates in combination with immunohistochemical parameters using Nuclear Magnetic Resonance (NMR). Sixty-four percent of the patients were resistant to chemotherapy. NMR, hormonal receptors (HR), human epidermal growth factor receptor 2 (HER2), and the nuclear protein Ki67 were combined through machine learning (ML) to predict the response to NACT. Metabolites such as leucine, formate, valine, and proline, along with hormone receptor status, were discriminants of response to NACT. The glyoxylate and dicarboxylate metabolism was found to be involved in the resistance to NACT. We obtained an accuracy in excess of 80% for the prediction of response to NACT combining metabolomic and tumor profile data. Our results suggest that NMR data can substantially enhance the prediction of response to NACT when used in combination with already known response prediction factors.

A Bioinformatics Approach to MicroRNA-Sequencing Analysis Based on Human Saliva Samples of Patients with Endometriosis

Endometriosis, defined by the presence of endometrium-like tissue outside the uterus, affects 2–10% of the female population, i.e., around 190 million women, worldwide. The aim of the prospective ENDO-miRNA study was to develop a bioinformatics approach for microRNA-sequencing analysis of 200 saliva samples for miRNAome expression and to test its diagnostic accuracy for endometriosis. Among the 200 patients, 76.5% (n = 153) had confirmed endometriosis and 23.5% (n = 47) had no endometriosis (controls). Small RNA-seq of 200 saliva samples yielded ~4642 M raw sequencing reads (from ~13.7 M to ~39.3 M reads/sample). The number of expressed miRNAs ranged from 1250 (outlier) to 2561 per sample. Some 2561 miRNAs were found to be differentially expressed in the saliva samples of patients with endometriosis compared with the control patients. Among these, 1.17% (n = 30) were up- or downregulated. Among these, the F1-score, sensitivity, specificity, and AUC ranged from 11–86.8%, 5.8–97.4%, 10.6–100%, and 39.3–69.2%, respectively. Here, we report a bioinformatic approach to saliva miRNA sequencing and analysis. We underline the advantages of using saliva over blood in terms of ease of collection, reproducibility, stability, safety, non-invasiveness. This report describes the whole saliva transcriptome to make miRNA quantification a validated, standardized, and reliable technique for routine use. The methodology could be applied to build a saliva signature of endometriosis.

Hybrid Rider Optimization with Deep Learning Driven Biomedical Liver Cancer Detection and Classification

Biomedical engineering is the application of the principles and problem-solving methods of engineering to biology along with medicine. Computation intelligence is the study of design of intelligent agents which are systems acting perceptively. The computation intelligence paradigm offers more advantages to the enhancement and maintenance of the field of biomedical engineering. Liver cancer is the major reason of mortality worldwide. Earlier-stage diagnosis and treatment might increase the survival rate of liver cancer patients. Manual recognition of the cancer tissue is a time-consuming and difficult task. Hence, a computer-aided diagnosis (CAD) is employed in decision making procedures for accurate diagnosis and effective treatment. In contrast to classical image-dependent "semantic" feature evaluation from human expertise, deep learning techniques could learn feature representation automatically from sample images using convolutional neural network (CNN). This study introduces a Hybrid Rider Optimization with Deep Learning Driven Biomedical Liver Cancer Detection and Classification (HRO-DLBLCC) model. The proposed HRO-DLBLCC model majorly focuses on the identification of liver cancer in the medical images. To do so, the proposed HRO-DLBLCC model employs preprocessing in two stages, namely, Gabor filtering (GF) based noise removal and watershed transform based segmentation. In addition, the proposed HRO-DLBLCC model involves NAdam optimizer with DenseNet-201 based feature extractor to generate an optimal set of feature vectors. Finally, the HRO algorithm with recurrent neural network-long short-term memory (RNN-LSTM) model is applied for liver cancer classification, in which the hyperparameters of the RNN-LSTM model are tuned by the use of HRO algorithm. The HRO-DLBLCC model is experimentally validated and compared with existing models. The experimental results assured the promising performance of the HRO-DLBLCC model over recent approaches.

Endometriosis Associated-miRNome Analysis of Blood Samples: A Prospective Study

The aim of our study was to describe the bioinformatics approach to analyze miRNome with Next Generation Sequencing (NGS) of 200 plasma samples from patients with and without endometriosis. Patients were prospectively included in the ENDO-miRNA study that selected patients with pelvic pain suggestive of endometriosis. miRNA sequencing was performed using an Novaseq6000 sequencer (Illumina, San Diego, CA, USA). Small RNA-seq of 200 plasma samples yielded ~4228 M raw sequencing reads. A total of 2633 miRNAs were found differentially expressed. Among them, 8.6% (n = 229) were up- or downregulated. For these 229 miRNAs, the F1-score, sensitivity, specificity, and AUC ranged from 0–88.2%, 0–99.4%, 4.3–100%, and 41.5–68%, respectively. Utilizing the combined bioinformatic and NGS approach, a specific and broad panel of miRNAs was detected as being potentially suitable for building a blood signature of endometriosis.

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.

MicroRNome analysis generates a blood-based signature for endometriosis

Endometriosis, characterized by endometrial-like tissue outside the uterus, is thought to affect 2–10% of women of reproductive age: representing about 190 million women worldwide. Numerous studies have evaluated the diagnostic value of blood biomarkers but with disappointing results. Thus, the gold standard for diagnosing endometriosis remains laparoscopy. We performed a prospective trial, the ENDO-miRNA study, using both Artificial Intelligence (AI) and Machine Learning (ML), to analyze the current human miRNome to differentiate between patients with and without endometriosis, and to develop a blood-based microRNA (miRNA) diagnostic signature for endometriosis. Here, we present the first blood-based diagnostic signature obtained from a combination of two robust and disruptive technologies merging the intrinsic quality of miRNAs to condense the endometriosis phenotype (and its heterogeneity) with the modeling power of AI. The most accurate signature provides a sensitivity, specificity, and Area Under the Curve (AUC) of 96.8%, 100%, and 98.4%, respectively, and is sufficiently robust and reproducible to replace the gold standard of diagnostic surgery. Such a diagnostic approach for this debilitating disorder could impact recommendations from national and international learned societies.

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.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12879-022-07107-w.

Developing and validating a deep learning and radiomic model for glioma grading using multiplanar reconstructed magnetic resonance contrast-enhanced T1-weighted imaging: a robust, multi-institutional study

Background

Although surgical pathology or biopsy are considered the gold standard for glioma grading, these procedures have limitations. This study set out to evaluate and validate the predictive performance of a deep learning radiomics model based on contrast-enhanced T1-weighted multiplanar reconstruction images for grading gliomas.

Methods

Patients from three institutions who diagnosed with gliomas by surgical specimen and multiplanar reconstructed (MPR) images were enrolled in this study. The training cohort included 101 patients from institution 1, including 43 high-grade glioma (HGG) patients and 58 low-grade glioma (LGG) patients, while the test cohorts consisted of 50 patients from institutions 2 and 3 (25 HGG patients, 25 LGG patients). We then extracted radiomics features and deep learning features using six pretrained models from the MPR images. The Spearman correlation test and the recursive elimination feature selection method were used to reduce the redundancy and select most predictive features. Subsequently, three classifiers were used to construct classification models. The performance of the grading models was evaluated using the area under the receiver operating curve, sensitivity, specificity, accuracy, precision, and negative predictive value. Finally, the prediction performances of the test cohort were compared to determine the optimal classification model.

Results

For the training cohort, 62% (13 out of 21) of the classification models constructed with MPR images from multiple planes outperformed those constructed with single-plane MPR images, and 61% (11 out of 18) of classification models constructed with both radiomics features and deep learning features had higher area under the curve (AUC) values than those constructed with only radiomics or deep learning features. The optimal model was a random forest model that combined radiomic features and VGG16 deep learning features derived from MPR images, which achieved AUC of 0.847 in the training cohort and 0.898 in the test cohort. In the test cohort, the sensitivity, specificity, and accuracy of the optimal model were 0.840, 0.760, and 0.800, respectively.

Conclusions

Multiplanar CE-T1W MPR imaging features are more effective than features from single planes when differentiating HGG and LGG. The combination of deep learning features and radiomics features can effectively grade glioma and assist clinical decision-making.

Salivary MicroRNA Signature for Diagnosis of Endometriosis

BACKGROUND

Endometriosis diagnosis constitutes a considerable economic burden for the healthcare system with diagnostic tools often inconclusive with insufficient accuracy. We sought to analyze the human miRNAome to define a saliva-based diagnostic miRNA signature for endometriosis.

METHODS

We performed a prospective ENDO-miRNA study involving 200 saliva samples obtained from 200 women with chronic pelvic pain suggestive of endometriosis collected between January and June 2021. The study consisted of two parts: (i) identification of a biomarker based on genome-wide miRNA expression profiling by small RNA sequencing using next-generation sequencing (NGS) and (ii) development of a saliva-based miRNA diagnostic signature according to expression and accuracy profiling using a Random Forest algorithm.

RESULTS

Among the 200 patients, 76.5% (n = 153) were diagnosed with endometriosis and 23.5% (n = 47) without (controls). Small RNA-seq of 200 saliva samples yielded ~4642 M raw sequencing reads (from ~13.7 M to ~39.3 M reads/sample). Quantification of the filtered reads and identification of known miRNAs yielded ~190 M sequences that were mapped to 2561 known miRNAs. Of the 2561 known miRNAs, the feature selection with Random Forest algorithm generated after internally cross validation a saliva signature of endometriosis composed of 109 miRNAs. The respective sensitivity, specificity, and AUC for the diagnostic miRNA signature were 96.7%, 100%, and 98.3%.

CONCLUSIONS

The ENDO-miRNA study is the first prospective study to report a saliva-based diagnostic miRNA signature for endometriosis. This could contribute to improving early diagnosis by means of a non-invasive tool easily available in any healthcare system.

Clues for Improving the Pathophysiology Knowledge for Endometriosis Using Plasma Micro-RNA Expression

The pathophysiology of endometriosis remains poorly understood. The aim of the present study was to investigate functions and pathways associated with the various miRNAs differentially expressed in patients with endometriosis. Plasma samples of the 200 patients from the prospective "ENDO-miRNA" study were analyzed and all known human miRNAs were sequenced. For each miRNA, sensitivity, specificity, and ROC AUC values were calculated for the diagnosis of endometriosis. miRNAs with an AUC ≥ 0.6 were selected for further analysis. A comprehensive review of recent articles from the PubMed, Clinical Trials.gov, Cochrane Library, and Web of Science databases was performed to identify functions and pathways associated with the selected miRNAs. In total, 2633 miRNAs were found in the patients with endometriosis. Among the 57 miRNAs with an AUC ≥ 0.6: 20 had never been reported before; one (miR-124-3p) had previously been observed in endometriosis; and the remaining 36 had been reported in benign and malignant disorders. miR-124-3p is involved in ectopic endometrial cell proliferation and invasion and plays a role in the following pathways: mTOR, STAT3, PI3K/Akt, NF-κB, ERK, PLGF-ROS, FGF2-FGFR, MAPK, GSK3B/β-catenin. Most of the remaining 36 miRNAs are involved in carcinogenesis through cell proliferation, apoptosis, and invasion. The three main pathways involved are Wnt/β-catenin, PI3K/Akt, and NF-KB. Our results provide evidence of the relation between the miRNA profiles of patients with endometriosis and various signaling pathways implicated in its pathophysiology.

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.

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.

MicroRNAs: understanding their role in gene expression and cancer

MicroRNAs are small RNA molecules that regulate gene expression in cells. These small molecules comprise 17 to 25 nucleotides and are able to recognize target messenger RNAs by sequence complementarity and regulate their protein translation. Different microRNAs are expressed in all human cells. There is over 2,500 microRNAs described in humans that are involved in virtually all biological processes. Given their role as gene expression regulators, these molecules have been widely investigated and are thought to be associated with some specific physiological and pathological conditions, being proposed as biomarkers. It has recently been reported that microRNAs are secreted outside cells and are involved in intercellular communication. MicroRNAs in biological fluids are named circulating and have been detected in all body fluids, although the expression profile is specific for each type. The major advantages of using circulating microRNAs as biological markers are the high stability of those molecules and the wide availability of samples. Also, given the individual nature of microRNA expression changes, these molecules have a high potential for use in personalized medicine. In fact, microRNA expression profile determination may support disease recognition and diagnosis, and can be used to monitor therapeutic responses and establish patient prognosis, assisting in choice of treatment. This review provides a general overview of microRNAs and discusses the importance of those molecules in cancer, for deeper understanding of their role in this disease.

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.