Inflammatory bowel disease biomarkers of human gut microbiota selected via different feature selection methods

The gut microbiome is associated with susceptibility to febrile malaria in Malian children

Malaria is a major public health problem, but many of the factors underlying the pathogenesis of this disease are not well understood, including protection from the development of febrile symptoms, which is observed in individuals residing in areas with moderate-to-high transmission by early adolescence. Here, we demonstrate that susceptibility to febrile malaria following Plasmodium falciparum infection is associated with the composition of the gut microbiome prior to the malaria season in 10-year-old Malian children, but not in younger children. Gnotobiotic mice colonized with the fecal samples of malaria-susceptible children were shown to have a significantly higher parasite burden following Plasmodium infection compared to gnotobiotic mice colonized with the fecal samples of malaria-resistant children. The fecal microbiome of the susceptible children was determined to be enriched for bacteria associated with inflammation, mucin degradation and gut permeability, and to have increased levels of nitric oxide-derived DNA adducts and lower levels of mucus phospholipids compared to the resistant children. Overall, these results indicate that the composition of the gut microbiome is associated with the prospective risk of febrile malaria in Malian children and suggest that modulation of the gut microbiome could decrease malaria morbidity in endemic areas.

Integrating machine learning and bioinformatics approaches for identifying novel diagnostic gene biomarkers in colorectal cancer

This study aimed to identify diagnostic gene biomarkers for colorectal cancer (CRC) by analyzing differentially expressed genes (DEGs) in tumor and adjacent normal samples across five colon cancer gene-expression profiles (GSE10950, GSE25070, GSE41328, GSE74602, GSE142279) from the Gene Expression Omnibus (GEO) database. Intersecting identified DEGs with the module with the highest correlation to gene expression patterns of tumor samples in the gene co-expression network analysis revealed 283 overlapped genes. Centrality measures were calculated for these genes in the reconstructed STRING protein-protein interaction network. Applying LASSO logistic regression, eleven genes were ultimately recognized as candidate diagnostic genes. Among these genes, the area under the receiver operating characteristic curve (AUROC) values for nine genes (CDC25B, CDK4, IQGAP3, MMP1, MMP7, SLC7A5, TEAD4, TRIB3, and UHRF1) surpassed the threshold of 0.92 in both the training and validation sets. We evaluated the diagnostic performance of these genes with four machine learning algorithms: random forest (RF), support vector machines (SVM), artificial neural network (ANN), and gradient boosting machine (GBM). In the testing dataset (GSE21815 and GSE106582), the AUROC scores were greater than 0.95 for all of the machine learning algorithms, indicating the high diagnostic performance of the nine genes. Besides, these nine genes are also significantly correlated to twelve immune cells, namely Mast cells activated, Macrophages M0, M1, and M2, Neutrophils, T cells CD4 memory activated, T cells follicular helper, T cells CD8, T cells CD4 memory resting, B cells memory, Plasma cells, and Mast cells resting (P < 0.05). These results strongly suggest that all of the nine genes have the potential to serve as reliable diagnostic biomarkers for CRC.

Integrating ADMET, enrichment analysis, and molecular docking approach to elucidate the mechanism of Artemisia herba alba for the treatment of inflammatory bowel disease-associated arthritis

Inflammatory Bowel Disease-Associated Arthritis (IBD-associated arthritis) poses a significant challenge, intertwining the complexities of both inflammatory bowel disease (IBD) and arthritis, significantly compromising patient quality of life. While existing medications offer relief, these drugs often initiate adverse effects, necessitating the requirement for safer therapeutic alternatives. Artemisia herba-alba, a traditional medicinal plant known for its anti-inflammatory properties, emerges as a potential candidate. Our computational study focused on examining 20 bioactive compounds derived from A. herba-alba for potential treatment of IBD-associated arthritis. These compounds detected in A. herba-alba include camphor, alpha-thujone, eucalyptol, cis-chrysanthenyl acetate, vicenin-2, 4,5-di-O-caffeoylquinic acid, chlorogenic acid, hispidulin, isoschaftoside, isovitexin, patuletin-3-glucoside, vanillic acid, rutin, schaftoside, lopinavir, nelfinavir, quercetin, artemisinin, gallic acid, and cinnamic acid. Following rigorous analysis encompassing pharmacokinetics, toxicity profiles, and therapeutic targets, compounds with favorable, beneficial characteristics were identified. In addition, comparative analysis with disease-gene associations demonstrated the interconnectedness of inflammatory pathways across diseases. Molecular docking studies provided mechanistic insights indicating this natural plant components potential to modulate critical inflammatory pathways. Overall, our findings indicate that A. herba-alba-derived compounds may be considered as therapeutic agents for IBD-associated arthritis, warranting further experimental validation and clinical exploration.

Artificial intelligence and machine learning technologies in ulcerative colitis

Interest in artificial intelligence (AI) applications for ulcerative colitis (UC) has grown tremendously in recent years. In the past 5 years, there have been over 80 studies focused on machine learning (ML) tools to address a wide range of clinical problems in UC, including diagnosis, prognosis, identification of new UC biomarkers, monitoring of disease activity, and prediction of complications. AI classifiers such as random forest, support vector machines, neural networks, and logistic regression models have been used to model UC clinical outcomes using molecular (transcriptomic) and clinical (electronic health record and laboratory) datasets with relatively high performance (accuracy, sensitivity, and specificity). Application of ML algorithms such as computer vision, guided image filtering, and convolutional neural networks have also been utilized to analyze large and high-dimensional imaging datasets such as endoscopic, histologic, and radiological images for UC diagnosis and prediction of complications (post-surgical complications, colorectal cancer). Incorporation of these ML tools to guide and optimize UC clinical practice is promising but will require large, high-quality validation studies that overcome the risk of bias as well as consider cost-effectiveness compared to standard of care.

Bifidobacterium bifidum Strain BB1 Inhibits Tumor Necrosis Factor-α-Induced Increase in Intestinal Epithelial Tight Junction Permeability via Toll-Like Receptor-2/Toll-Like Receptor-6 Receptor Complex-Dependent Stimulation of Peroxisome Proliferator-Activated Receptor γ and Suppression of NF-κB p65

Bifidobacterium bifidum strain BB1 causes a strain-specific enhancement in intestinal epithelial tight junction (TJ) barrier. Tumor necrosis factor (TNF)-α induces an increase in intestinal epithelial TJ permeability and promotes intestinal inflammation. The major purpose of this study was to delineate the protective effect of BB1 against the TNF-α-induced increase in intestinal TJ permeability and to unravel the intracellular mechanisms involved. TNF-α produces an increase in intestinal epithelial TJ permeability in Caco-2 monolayers and in mice. Herein, the addition of BB1 inhibited the TNF-α increase in Caco-2 intestinal TJ permeability and mouse intestinal permeability in a strain-specific manner. BB1 inhibited the TNF-α-induced increase in intestinal TJ permeability by interfering with TNF-α-induced enterocyte NF-κB p50/p65 and myosin light chain kinase (MLCK) gene activation. The BB1 protective effect against the TNF-α-induced increase in intestinal permeability was mediated by toll-like receptor-2/toll-like receptor-6 heterodimer complex activation of peroxisome proliferator-activated receptor γ (PPAR-γ) and PPAR-γ pathway inhibition of TNF-α-induced inhibitory kappa B kinase α (IKK-α) activation, which, in turn, resulted in a step-wise inhibition of NF-κB p50/p65, MLCK gene, MLCK kinase activity, and MLCK-induced opening of the TJ barrier. In conclusion, these studies unraveled novel intracellular mechanisms of BB1 protection against the TNF-α-induced increase in intestinal TJ permeability. The current data show that BB1 protects against the TNF-α-induced increase in intestinal epithelial TJ permeability via a PPAR-γ-dependent inhibition of NF-κB p50/p65 and MLCK gene activation.

How Diet and Lifestyle Can Fine-Tune Gut Microbiomes for Healthy Aging

Many physical, social, and psychological changes occur during aging that raise the risk of developing chronic diseases, frailty, and dependency. These changes adversely affect the gut microbiota, a phenomenon known as microbe-aging. Those microbiota alterations are, in turn, associated with the development of age-related diseases. The gut microbiota is highly responsive to lifestyle and dietary changes, displaying a flexibility that also provides anactionable tool by which healthy aging can be promoted. This review covers, firstly, the main lifestyle and socioeconomic factors that modify the gut microbiota composition and function during healthy or unhealthy aging and, secondly, the advances being made in defining and promoting healthy aging, including microbiome-informed artificial intelligence tools, personalized dietary patterns, and food probiotic systems.

Susceptibility to febrile malaria is associated with an inflammatory gut microbiome

Malaria is a major public health problem, but many of the factors underlying the pathogenesis of this disease are not well understood. Here, we demonstrate in Malian children that susceptibility to febrile malaria following infection with Plasmodium falciparum is associated with the composition of the gut microbiome prior to the malaria season. Gnotobiotic mice colonized with the fecal samples of malaria-susceptible children had a significantly higher parasite burden following Plasmodium infection compared to gnotobiotic mice colonized with the fecal samples of malaria-resistant children. The fecal microbiome of the susceptible children was enriched for bacteria associated with inflammation, mucin degradation, gut permeability and inflammatory bowel disorders (e.g., Ruminococcus gauvreauii, Ruminococcus torques, Dorea formicigenerans, Dorea longicatena, Lachnoclostridium phocaeense and Lachnoclostridium sp. YL32). However, the susceptible children also had a greater abundance of bacteria known to produce anti-inflammatory short-chain fatty acids and those associated with favorable prognosis and remission following dysbiotic intestinal events (e.g., Anaerobutyricum hallii, Blautia producta and Sellimonas intestinalis). Metabolomics analysis of the human fecal samples corroborated the existence of inflammatory and recovery-associated features within the gut microbiome of the susceptible children. There was an enrichment of nitric oxide-derived DNA adducts (deoxyinosine and deoxyuridine) and long-chain fatty acids, the absorption of which has been shown to be inhibited by inflamed intestinal epithelial cells, and a decrease in the abundance of mucus phospholipids. Nevertheless, there were also increased levels of pseudouridine and hypoxanthine, which have been shown to be regulated in response to cellular stress and to promote recovery following injury or hypoxia. Overall, these results indicate that the gut microbiome may contribute malaria pathogenesis and suggest that therapies targeting intestinal inflammation could decrease malaria susceptibility.

A comprehensive overview of microbiome data in the light of machine learning applications: categorization, accessibility, and future directions

Metagenomics, Metabolomics, and Metaproteomics have significantly advanced our knowledge of microbial communities by providing culture-independent insights into their composition and functional potential. However, a critical challenge in this field is the lack of standard and comprehensive metadata associated with raw data, hindering the ability to perform robust data stratifications and consider confounding factors. In this comprehensive review, we categorize publicly available microbiome data into five types: shotgun sequencing, amplicon sequencing, metatranscriptomic, metabolomic, and metaproteomic data. We explore the importance of metadata for data reuse and address the challenges in collecting standardized metadata. We also, assess the limitations in metadata collection of existing public repositories collecting metagenomic data. This review emphasizes the vital role of metadata in interpreting and comparing datasets and highlights the need for standardized metadata protocols to fully leverage metagenomic data's potential. Furthermore, we explore future directions of implementation of Machine Learning (ML) in metadata retrieval, offering promising avenues for a deeper understanding of microbial communities and their ecological roles. Leveraging these tools will enhance our insights into microbial functional capabilities and ecological dynamics in diverse ecosystems. Finally, we emphasize the crucial metadata role in ML models development.

From-Toilet-to-Freezer: A Review on Requirements for an Automatic Protocol to Collect and Store Human Fecal Samples for Research Purposes

The composition, viability and metabolic functionality of intestinal microbiota play an important role in human health and disease. Studies on intestinal microbiota are often based on fecal samples, because these can be sampled in a non-invasive way, although procedures for sampling, processing and storage vary. This review presents factors to consider when developing an automated protocol for sampling, processing and storing fecal samples: donor inclusion criteria, urine-feces separation in smart toilets, homogenization, aliquoting, usage or type of buffer to dissolve and store fecal material, temperature and time for processing and storage and quality control. The lack of standardization and low-throughput of state-of-the-art fecal collection procedures promote a more automated protocol. Based on this review, an automated protocol is proposed. Fecal samples should be collected and immediately processed under anaerobic conditions at either room temperature (RT) for a maximum of 4 h or at 4 °C for no more than 24 h. Upon homogenization, preferably in the absence of added solvent to allow addition of a buffer of choice at a later stage, aliquots obtained should be stored at either -20 °C for up to a few months or -80 °C for a longer period-up to 2 years. Protocols for quality control should characterize microbial composition and viability as well as metabolic functionality.

Review of feature selection approaches based on grouping of features

With the rapid development in technology, large amounts of high-dimensional data have been generated. This high dimensionality including redundancy and irrelevancy poses a great challenge in data analysis and decision making. Feature selection (FS) is an effective way to reduce dimensionality by eliminating redundant and irrelevant data. Most traditional FS approaches score and rank each feature individually; and then perform FS either by eliminating lower ranked features or by retaining highly-ranked features. In this review, we discuss an emerging approach to FS that is based on initially grouping features, then scoring groups of features rather than scoring individual features. Despite the presence of reviews on clustering and FS algorithms, to the best of our knowledge, this is the first review focusing on FS techniques based on grouping. The typical idea behind FS through grouping is to generate groups of similar features with dissimilarity between groups, then select representative features from each cluster. Approaches under supervised, unsupervised, semi supervised and integrative frameworks are explored. The comparison of experimental results indicates the effectiveness of sequential, optimization-based (i.e., fuzzy or evolutionary), hybrid and multi-method approaches. When it comes to biological data, the involvement of external biological sources can improve analysis results. We hope this work's findings can guide effective design of new FS approaches using feature grouping.

Results and lessons learned from the sbv IMPROVER metagenomics diagnostics for inflammatory bowel disease challenge

A growing body of evidence links gut microbiota changes with inflammatory bowel disease (IBD), raising the potential benefit of exploiting metagenomics data for non-invasive IBD diagnostics. The sbv IMPROVER metagenomics diagnosis for inflammatory bowel disease challenge investigated computational metagenomics methods for discriminating IBD and nonIBD subjects. Participants in this challenge were given independent training and test metagenomics data from IBD and nonIBD subjects, which could be wither either raw read data (sub-challenge 1, SC1) or processed Taxonomy- and Function-based profiles (sub-challenge 2, SC2). A total of 81 anonymized submissions were received between September 2019 and March 2020. Most participants' predictions performed better than random predictions in classifying IBD versus nonIBD, Ulcerative Colitis (UC) versus nonIBD, and Crohn's Disease (CD) versus nonIBD. However, discrimination between UC and CD remains challenging, with the classification quality similar to the set of random predictions. We analyzed the class prediction accuracy, the metagenomics features by the teams, and computational methods used. These results will be openly shared with the scientific community to help advance IBD research and illustrate the application of a range of computational methodologies for effective metagenomic classification.

Identifying microbial signatures for patients with postmenopausal osteoporosis using gut microbiota analyses and feature selection approaches

Osteoporosis (OP) is a metabolic bone disorder characterized by low bone mass and deterioration of micro-architectural bone tissue. The most common type of OP is postmenopausal osteoporosis (PMOP), with fragility fractures becoming a global burden for women. Recently, the gut microbiota has been connected to bone metabolism. The aim of this study was to characterize the gut microbiota signatures in PMOP patients and controls. Fecal samples from 21 PMOP patients and 37 controls were collected and analyzed using amplicon sequencing of the V3-V4 regions of the 16S rRNA gene. The bone mineral density (BMD) measurement and laboratory biochemical test were performed on all participants. Two feature selection algorithms, maximal information coefficient (MIC) and XGBoost, were employed to identify the PMOP-related microbial features. Results showed that the composition of gut microbiota changed in PMOP patients, and microbial abundances were more correlated with total hip BMD/T-score than lumbar spine BMD/T-score. Using the MIC and XGBoost methods, we identified a set of PMOP-related microbes; a logistic regression model revealed that two microbial markers (Fusobacteria and Lactobacillaceae) had significant abilities in disease classification between the PMOP and control groups. Taken together, the findings of this study provide new insights into the etiology of OP/PMOP, as well as modulating gut microbiota as a therapeutic target in the diseases. We also highlight the application of feature selection approaches in biological data mining and data analysis, which may improve the research in medical and life sciences.

Machine learning-based feature selection to search stable microbial biomarkers: application to inflammatory bowel disease

BACKGROUND

Biomarker discovery exploiting feature importance of machine learning has risen recently in the microbiome landscape with its high predictive performance in several disease states. To have a concrete selection among a high number of features, recursive feature elimination (RFE) has been widely used in the bioinformatics field. However, machine learning-based RFE has factors that decrease the stability of feature selection. In this article, we suggested methods to improve stability while sustaining performance.

RESULTS

We exploited the abundance matrices of the gut microbiome (283 taxa at species level and 220 at genus level) to classify between patients with inflammatory bowel disease (IBD) and healthy control (1,569 samples). We found that applying an already published data transformation before RFE improves feature stability significantly. Moreover, we performed an in-depth evaluation of different variants of the data transformation and identify those that demonstrate better improvement in stability while not sacrificing classification performance. To ensure a robust comparison, we evaluated stability using various similarity metrics, distances, the common number of features, and the ability to filter out noise features. We were able to confirm that the mapping by the Bray-Curtis similarity matrix before RFE consistently improves the stability while maintaining good performance. Multilayer perceptron algorithm exhibited the highest performance among 8 different machine learning algorithms when a large number of features (a few hundred) were considered based on the best performance across 100 bootstrapped internal test sets. Conversely, when utilizing only a limited number of biomarkers as a trade-off between optimal performance and method generalizability, the random forest algorithm demonstrated the best performance. Using the optimal pipeline we developed, we identified 14 biomarkers for IBD at the species level and analyzed their roles using Shapley additive explanations.

CONCLUSION

Taken together, our work not only showed how to improve biomarker discovery in the metataxonomic field without sacrificing classification performance but also provided useful insights for future comparative studies.

Diagnosis of Inflammatory Bowel Disease and Colorectal Cancer through Multi-View Stacked Generalization Applied on Gut Microbiome Data

Most of the microbiome studies suggest that using ensemble models such as Random Forest results in best predictive power. In this study, we empirically evaluate a more powerful ensemble learning algorithm, multi-view stacked generalization, on pediatric inflammatory bowel disease and adult colorectal cancer patients’ cohorts. We aim to check whether stacking would lead to better results compared to using a single best machine learning algorithm. Stacking achieves the best test set Average Precision (AP) on inflammatory bowel disease dataset reaching AP = 0.69, outperforming both the best base classifier (AP = 0.61) and the baseline meta learner built on top of base classifiers (AP = 0.63). On colorectal cancer dataset, the stacked classifier also outperforms (AP = 0.81) both the best base classifier (AP = 0.79) and the baseline meta learner (AP = 0.75). Stacking achieves best predictive performance on test set outperforming the best classifiers on both patient cohorts. Application of the stacking solves the issue of choosing the most appropriate machine learning algorithm by automating the model selection procedure. Clinical application of such a model is not limited to diagnosis task only, but it also can be extended to biomarker selection thanks to feature selection procedure.

Compositional Data Analysis of 16S rRNA Gene Sequencing Results from Hospital Airborne Microbiome Samples

The compositional analysis of 16S rRNA gene sequencing datasets is applied to characterize the bacterial structure of airborne samples collected in different locations of a hospital infection disease department hosting COVID-19 patients, as well as to investigate the relationships among bacterial taxa at the genus and species level. The exploration of the centered log-ratio transformed data by the principal component analysis via the singular value decomposition has shown that the collected samples segregated with an observable separation depending on the monitoring location. More specifically, two main sample clusters were identified with regards to bacterial genera (species), consisting of samples mostly collected in rooms with and without COVID-19 patients, respectively. Human pathogenic genera (species) associated with nosocomial infections were mostly found in samples from areas hosting patients, while non-pathogenic genera (species) mainly isolated from soil were detected in the other samples. Propionibacterium acnes, Staphylococcus pettenkoferi, Corynebacterium tuberculostearicum, and jeikeium were the main pathogenic species detected in COVID-19 patients' rooms. Samples from these locations were on average characterized by smaller richness/evenness and diversity than the other ones, both at the genus and species level. Finally, the ρ metrics revealed that pairwise positive associations occurred either between pathogenic or non-pathogenic taxa.

PSO-Based Evolutionary Approach to Optimize Head and Neck Biomedical Image to Detect Mesothelioma Cancer

Mesothelioma is a form of cancer that is aggressive and fatal. It is a thin layer of tissue that covers the majority of the patient's internal organs. The treatments are available; however, a cure is not attainable for the majority of patients. So, a lot of research is being done on detection of mesothelioma cancer using various different approaches; but this paper focuses on optimization techniques for optimizing the biomedical images to detect the cancer. With the restricted number of samples in the medical field, a Relief-PSO head and mesothelioma neck cancer pathological image feature selection approach is proposed. The approach reduces multilevel dimensionality. To begin, the relief technique picks different feature weights depending on the relationship between features and categories. Second, the hybrid binary particle swarm optimization (HBPSO) is suggested to automatically determine the optimum feature subset for candidate feature subsets. The technique outperforms seven other feature selection algorithms in terms of morphological feature screening, dimensionality reduction, and classification performance.

Identification of useful genes from multiple microarrays for ulcerative colitis diagnosis based on machine learning methods

Ulcerative colitis (UC) is a chronic relapsing inflammatory bowel disease with an increasing incidence and prevalence worldwide. The diagnosis for UC mainly relies on clinical symptoms and laboratory examinations. As some previous studies have revealed that there is an association between gene expression signature and disease severity, we thereby aim to assess whether genes can help to diagnose UC and predict its correlation with immune regulation. A total of ten eligible microarrays (including 387 UC patients and 139 healthy subjects) were included in this study, specifically with six microarrays (GSE48634, GSE6731, GSE114527, GSE13367, GSE36807, and GSE3629) in the training group and four microarrays (GSE53306, GSE87473, GSE74265, and GSE96665) in the testing group. After the data processing, we found 87 differently expressed genes. Furthermore, a total of six machine learning methods, including support vector machine, least absolute shrinkage and selection operator, random forest, gradient boosting machine, principal component analysis, and neural network were adopted to identify potentially useful genes. The synthetic minority oversampling (SMOTE) was used to adjust the imbalanced sample size for two groups (if any). Consequently, six genes were selected for model establishment. According to the receiver operating characteristic, two genes of OLFM4 and C4BPB were finally identified. The average values of area under curve for these two genes are higher than 0.8, either in the original datasets or SMOTE-adjusted datasets. Besides, these two genes also significantly correlated to six immune cells, namely Macrophages M1, Macrophages M2, Mast cells activated, Mast cells resting, Monocytes, and NK cells activated (P  <  0.05). OLFM4 and C4BPB may be conducive to identifying patients with UC. Further verification studies could be conducted.