Faecal microbiome-based machine learning for multi-class disease diagnosis

A review of machine learning methods for cancer characterization from microbiome data

Recent studies have shown that the microbiome can impact cancer development, progression, and response to therapies suggesting microbiome-based approaches for cancer characterization. As cancer-related signatures are complex and implicate many taxa, their discovery often requires Machine Learning approaches. This review discusses Machine Learning methods for cancer characterization from microbiome data. It focuses on the implications of choices undertaken during sample collection, feature selection and pre-processing. It also discusses ML model selection, guiding how to choose an ML model, and model validation. Finally, it enumerates current limitations and how these may be surpassed. Proposed methods, often based on Random Forests, show promising results, however insufficient for widespread clinical usage. Studies often report conflicting results mainly due to ML models with poor generalizability. We expect that evaluating models with expanded, hold-out datasets, removing technical artifacts, exploring representations of the microbiome other than taxonomical profiles, leveraging advances in deep learning, and developing ML models better adapted to the characteristics of microbiome data will improve the performance and generalizability of models and enable their usage in the clinic.

Classification performance assessment for imbalanced multiclass data

The evaluation of diagnostic systems is pivotal for ensuring the deployment of high-quality solutions, especially given the pronounced context-sensitivity of certain systems, particularly in fields such as biomedicine. Of notable importance are predictive models where the target variable can encompass multiple values (multiclass), especially when these classes exhibit substantial frequency disparities (imbalance). In this study, we introduce the Imbalanced Multiclass Classification Performance (IMCP) curve, specifically designed for multiclass datasets (unlike the ROC curve), and characterized by its resilience to class distribution variations (in contrast to accuracy or Fβ -score). Moreover, the IMCP curve facilitates individual performance assessment for each class within the diagnostic system, shedding light on the confidence associated with each prediction-an aspect of particular significance in medical diagnosis. Empirical experiments conducted with real-world data in a multiclass context (involving 35 types of tumors) featuring a high level of imbalance demonstrate that both the IMCP curve and the area under the IMCP curve serve as excellent indicators of classification quality.

The gut microbiome associates with phenotypic manifestations of post-acute COVID-19 syndrome

The mechanisms underlying the many phenotypic manifestations of post-acute COVID-19 syndrome (PACS) are poorly understood. Herein, we characterized the gut microbiome in heterogeneous cohorts of subjects with PACS and developed a multi-label machine learning model for using the microbiome to predict specific symptoms. Our processed data covered 585 bacterial species and 500 microbial pathways, explaining 12.7% of the inter-individual variability in PACS. Three gut-microbiome-based enterotypes were identified in subjects with PACS and associated with different phenotypic manifestations. The trained model showed an accuracy of 0.89 in predicting individual symptoms of PACS in the test set and maintained a sensitivity of 86% and a specificity of 82% in predicting upcoming symptoms in an independent longitudinal cohort of subjects before they developed PACS. This study demonstrates that the gut microbiome is associated with phenotypic manifestations of PACS, which has potential clinical utility for the prediction and diagnosis of PACS.

The colon targeting efficacies of mesalazine medications and their impacts on the gut microbiome

Successful treatment of ulcerative colitis (UC) is highly dependent on several parameters, including dosing regimen and the ability to deliver drugs to the disease site. In this study two strategies for delivering mesalazine (5-aminosalicylic acid, 5-ASA) to the colon were compared in an advanced in vitro model of the human gastrointestinal (GI) tract, the SHIME® system. Herein, a prodrug strategy employing bacteria-mediated drug release (sulfasalazine, Azulfidine®) was evaluated alongside a formulation strategy that utilised pH and bacteria-mediated release (5-ASA, Octasa® 1600 mg). SHIME® experiments were performed simulating both the GI physiology and colonic microbiota under healthy and inflammatory bowel disease (IBD) conditions, to study the impact of the disease state and ileal pH variability on colonic 5-ASA delivery. In addition, the effects of the products on the colonic microbiome were investigated by monitoring bacterial growth and metabolites. Results demonstrated that both the prodrug and formulation approaches resulted in a similar percentage of 5-ASA recovery under healthy conditions. On the contrary, during experiments simulating the GI physiology and microbiome of IBD patients (the target population) the formulation strategy resulted in a higher proportion of 5-ASA delivery to the colonic region as compared to the prodrug approach (P < 0.0001). Interestingly, the two products had distinct effects on the synthesis of key bacterial metabolites, such as lactate and short chain fatty acids, which varied according to disease state and ileal pH variability. Further, both 5-ASA and sulfasalazine significantly reduced the growth of the faecal microbiota sourced from six healthy humans. The findings support that the approach selected for colonic drug delivery could significantly influence the effectiveness of UC treatment, and highlight that drugs licensed for UC may differentially impact the growth and functioning of the colonic microbiota.

Exopolysaccharides Produced by Bifidobacterium longum subsp. longum YS108R Ameliorates DSS-Induced Ulcerative Colitis in Mice by Improving the Gut Barrier and Regulating the Gut Microbiota

Ulcerative colitis (UC) is a major disease that has endangered human health. Our previous study demonstrated that Bifidobacterium longum subsp. longum YS108R, a ropy exopolysaccharide (EPS)-producing bacterium, could alleviate UC in mice, but it is unclear whether EPS is the key substance responsible for its action. In this study, we proposed to investigate the remitting effect of EPS from B. longum subsp. longum YS108R on UC in a DSS-induced UC mouse model. Water extraction and alcohol precipitation were applied to extract EPS from the supernatant of B. longum subsp. longum YS108R culture. Then the animal trial was performed, and the results indicated that YS108R EPS ameliorated colonic pathological damage and the intestinal barrier. YS108R EPS suppressed inflammation via NF-κB signaling pathway inhibition and attenuated oxidative stress via the Nrf2 signaling pathway activation. Remarkably, YS108R EPS regulated gut microbiota, as evidenced by an increase in short-chain fatty acid (SCFA)-producing bacteria and a decline in Gram-negative bacteria, resulting in an increase of propionate and butyrate and a reduction of lipopolysaccharide (LPS). Collectively, YS108R EPS manipulated the intestinal microbiota and its metabolites, which further improved the intestinal barrier and inhibited inflammation and oxidative stress, thereby alleviating UC.

Pan-Cancer Single-Cell and Spatial-Resolved Profiling Reveals the Immunosuppressive Role of APOE+ Macrophages in Immune Checkpoint Inhibitor Therapy

The heterogeneity of macrophages influences the response to immune checkpoint inhibitor (ICI) therapy. However, few studies explore the impact of APOE+ macrophages on ICI therapy using single-cell RNA sequencing (scRNA-seq) and machine learning methods. The scRNA-seq and bulk RNA-seq data are Integrated to construct an M.Sig model for predicting ICI response based on the distinct molecular signatures of macrophage and machine learning algorithms. Comprehensive single-cell analysis as well as in vivo and in vitro experiments are applied to explore the potential mechanisms of the APOE+ macrophage in affecting ICI response. The M.Sig model shows clear advantages in predicting the efficacy and prognosis of ICI therapy in pan-cancer patients. The proportion of APOE+ macrophages is higher in ICI non-responders of triple-negative breast cancer compared with responders, and the interaction and longer distance between APOE+ macrophages and CD8+ exhausted T (Tex) cells affecting ICI response is confirmed by multiplex immunohistochemistry. In a 4T1 tumor-bearing mice model, the APOE inhibitor combined with ICI treatment shows the best efficacy. The M.Sig model using real-world immunotherapy data accurately predicts the ICI response of pan-cancer, which may be associated with the interaction between APOE+ macrophages and CD8+ Tex cells.

Electro-Optical Multiclassification Platform for Minimizing Occasional Inaccuracy in Point-of-Care Biomarker Detection

On-site diagnostic tests that accurately identify disease biomarkers lay the foundation for self-healthcare applications. However, these tests routinely rely on single-mode signals and suffer from insufficient accuracy, especially for multiplexed point-of-care tests (POCTs) within a few minutes. Here, this work develops a dual-mode multiclassification diagnostic platform that integrates an electrochemiluminescence sensor and a field-effect transistor sensor in a microfluidic chip. The microfluidic channel guides the testing samples to flow across electro-optical sensor units, which produce dual-mode readouts by detecting infectious biomarkers of tuberculosis (TB), human rhinovirus (HRV), and group B streptococcus (GBS). Then, machine-learning classifiers generate three-dimensional (3D) hyperplanes to diagnose different diseases. Dual-mode readouts derived from distinct mechanisms enhance the anti-interference ability physically, and machine-learning-aided diagnosis in high-dimensional space reduces the occasional inaccuracy mathematically. Clinical validation studies with 501 unprocessed samples indicate that the platform has an accuracy approaching 99%, higher than the 77%-93% accuracy of rapid point-of-care testing technologies at 100% statistical power (>150 clinical tests). Moreover, the diagnosis time is 5 min without a trade-off of accuracy. This work solves the occasional inaccuracy issue of rapid on-site diagnosis, endowing POCT systems with the same accuracy as laboratory tests and holding unique prospects for complicated scenes of personalized healthcare.

Past, present, and future of microbiome-based therapies

Technological advances in studying the human microbiome in depth have enabled the identification of microbial signatures associated with health and disease. This confirms the crucial role of microbiota in maintaining homeostasis and the host health status. Nowadays, there are several ways to modulate the microbiota composition to effectively improve host health; therefore, the development of therapeutic treatments based on the gut microbiota is experiencing rapid growth. In this review, we summarize the influence of the gut microbiota on the development of infectious disease and cancer, which are two of the main targets of microbiome-based therapies currently being developed. We analyze the two-way interaction between the gut microbiota and traditional drugs in order to emphasize the influence of gut microbial composition on drug effectivity and treatment response. We explore the different strategies currently available for modulating this ecosystem to our benefit, ranging from 1st generation intervention strategies to more complex 2nd generation microbiome-based therapies and their regulatory framework. Lastly, we finish with a quick overview of what we believe is the future of these strategies, that is 3rd generation microbiome-based therapies developed with the use of artificial intelligence (AI) algorithms.

Gut microbiota predicts the diagnosis of ulcerative colitis in Saudi children

BACKGROUND

Ulcerative colitis (UC) is an immune-mediated chronic inflammatory condition with a worldwide distribution. Although the etiology of this disease is still unknown, the understanding of the role of the microbiota is becoming increasingly strong.

AIM

To investigate the predictive power of the gut microbiota for the diagnosis of UC in a cohort of newly diagnosed treatment-naïve Saudi children with UC.

METHODS

The study population included 20 children with a confirmed diagnosis of UC and 20 healthy controls. Microbial DNA was extracted and sequenced, and shotgun metagenomic analysis was performed for bacteria and bacteriophages. Biostatistics and bioinformatics demonstrated significant dysbiosis in the form of reduced alpha diversity, beta diversity, and significant difference of abundance of taxa between children with UC and control groups. The receiver operating characteristic curve, a probability curve, was used to determine the difference between the UC and control groups. The area under the curve (AUC) represents the degree of separability between the UC group and the control group. The AUC was calculated for all identified bacterial species and for bacterial species identified by the random forest classification algorithm as important potential biomarkers of UC. A similar method of AUC calculation for all bacteriophages and important species was used.

RESULTS

The median age and range were 14 (0.5-21) and 12.9 (6.8-16.3) years for children with UC and controls, respectively, and 40% and 35% were male for children with UC and controls, respectively. The AUC for all identified bacterial species was 89.5%. However, when using the bacterial species identified as important by random forest classification algorithm analysis, the accuracy increased to 97.6%. Similarly, the AUC for all the identified bacteriophages was 87.4%, but this value increased to 94.5% when the important bacteriophage biomarkers were used.

CONCLUSION

The very high to excellent AUCs of fecal bacterial and viral species suggest the potential use of noninvasive microbiota-based tests for the diagnosis of unusual cases of UC in children. In addition, the identification of important bacteria and bacteriophages whose abundance is reduced in children with UC suggests the potential of preventive and adjuvant microbial therapy for UC.

Construction and validation of a machine learning model for the diagnosis of juvenile idiopathic arthritis based on fecal microbiota

Purpose

Human gut microbiota has been shown to be significantly associated with various inflammatory diseases. Therefore, this study aimed to develop an excellent auxiliary tool for the diagnosis of juvenile idiopathic arthritis (JIA) based on fecal microbial biomarkers.

Method

The fecal metagenomic sequencing data associated with JIA were extracted from NCBI, and the sequencing data were transformed into the relative abundance of microorganisms by professional data cleaning (KneadData, Trimmomatic and Bowtie2) and comparison software (Kraken2 and Bracken). After that, the fecal microbes with high abundance were extracted for subsequent analysis. The extracted fecal microbes were further screened by least absolute shrinkage and selection operator (LASSO) regression, and the selected fecal microbe biomarkers were used for model training. In this study, we constructed six different machine learning (ML) models, and then selected the best model for constructing a JIA diagnostic tool by comparing the performance of the models based on a combined consideration of area under receiver operating characteristic curve (AUC), accuracy, specificity, F1 score, calibration curves and clinical decision curves. In addition, to further explain the model, Permutation Importance analysis and Shapley Additive Explanations (SHAP) were performed to understand the contribution of each biomarker in the prediction process.

Result

A total of 231 individuals were included in this study, including 203 JIA patients and Non-JIA individuals. In the analysis of diversity at the genus level, the alpha diversity represented by Shannon value was not significantly different between the two groups, while the belt diversity was slightly different. After selection by LASSO regression, 10 fecal microbe biomarkers were selected for model training. By comparing six different models, the XGB model showed the best performance, which average AUC, accuracy and F1 score were 0.976, 0.914 and 0.952, respectively, thus being used to construct the final JIA diagnosis model.

Conclusion

A JIA diagnosis model based on XGB algorithm was constructed with excellent performance, which may assist physicians in early detection of JIA patients and improve the prognosis of JIA patients.

Union With Recursive Feature Elimination: A Feature Selection Framework to Improve the Classification Performance of Multicategory Causes of Death in Colorectal Cancer

Despite the use of machine learning tools, it is challenging to properly model cause-specific deaths in colorectal cancer (CRC) patients and choose appropriate treatments. Here, we propose an interesting feature selection framework, namely union with recursive feature elimination (U-RFE), to select the union feature sets that are crucial in CRC progression-specific mortality using The Cancer Genome Atlas (TCGA) dataset. Based on the union feature sets, we compared the performance of 5 classification algorithms, including logistic regression (LR), support vector machines (SVM), random forest (RF), eXtreme gradient boosting (XGBoost), and Stacking, to identify the best model for classifying 4-category deaths. In the first stage of U-RFE, LR, SVM, and RF were used as base estimators to obtain subsets containing the same number of features but not exactly the same specific features. Union analysis of the subsets was then performed to determine the final union feature set, effectively combining the advantages of different algorithms. We found that the U-RFE framework could improve various models' performance. Stacking outperformed LR, SVM, RF, and XGBoost in most scenarios. When the target feature number of the RFE was set to 50 and the union feature set contained 298 deterministic features, the Stacking model achieved F1_weighted, Recall_weighted, Precision_weighted, Accuracy, and Matthews correlation coefficient of 0.851, 0.864, 0.854, 0.864, and 0.717, respectively. The performance of the minority categories was also significantly improved. Therefore, this recursive feature elimination-based approach of feature selection improves performances of classifying CRC deaths using clinical and omics data or those using other data with high feature redundancy and imbalance.

Nine (not so simple) steps: a practical guide to using machine learning in microbial ecology

Due to the complex nature of microbiome data, the field of microbial ecology has many current and potential uses for machine learning (ML) modeling. With the increased use of predictive ML models across many disciplines, including microbial ecology, there is extensive published information on the specific ML algorithms available and how those algorithms have been applied. Thus, our goal is not to summarize the breadth of ML models available or compare their performances. Rather, our goal is to provide more concrete and actionable information to guide microbial ecologists in how to select, run, and interpret ML algorithms to predict the taxa or genes associated with particular sample categories or environmental gradients of interest. Such microbial data often have unique characteristics that require careful consideration of how to apply ML models and how to interpret the associated results. This review is intended for practicing microbial ecologists who may be unfamiliar with some of the intricacies of ML models. We provide examples and discuss common opportunities and pitfalls specific to applying ML models to the types of data sets most frequently collected by microbial ecologists.

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.

A novel infant microbiome formula (SIM03) improved eczema severity and quality of life in preschool children

Altered gut microbiome composition has been reported in children with eczema and interventions that restore beneficial bacteria in the gut may improve eczema. This open-label pilot study aimed to investigate the efficacy of a novel infant microbiome formula (SIM03) in young children with eczema. Pre-school Chinese children aged 1-5 years old with eczema received SIM03 twice daily for three months. The novelty of SIM03 consists of both the use of a patented microencapsulation technology to protect the viability of unique Bifidobacterium bifidum and Bifidobacterium breve strains identified through big data analysis of large metagenomic datasets of young Chinese children. Paired stool samples at baseline and following SIM03 were analyzed by metagenomics sequencing. Generalized estimating equation was used to analyze changes in eczema severity, skin biophysical parameters, quality of life and stool microbiome. Twenty children aged 3.0 ± 1.6 years (10 with severe eczema) were recruited. Treatment compliance was ≥ 98%. SCORing Atopic Dermatitis score decreased significantly at two months (P = 0.008) and three months (P < 0.001), while quality of life improved significantly at 1, 2, and 3 months. The relative abundance of B. breve and microbial pathways on acetate and acetyl-CoA synthesis were enriched in stool samples at one month (P = 0.0014). Children who demonstrated increased B. bifidum after SIM03 showed improvement in sleep loss (P = 0.045). Relative abundance of B. breve correlated inversely with eczema extent (P = 0.023) and intensity (P = 0.019) only among patients with increased B. breve at Month 3. No serious adverse event was observed. In conclusion, SIM03 is well tolerated. This patented microbiome formula improves disease severity and quality of life in young eczematous children by enhancing the delivery of B. bifidum and B. breve in the gut. SIM03 is a potential treatment option for childhood eczema.

PM-CNN: microbiome status recognition and disease detection model based on phylogeny and multi-path neural network

Motivation

The human microbiome, found throughout various body parts, plays a crucial role in health dynamics and disease development. Recent research has highlighted microbiome disparities between patients with different diseases and healthy individuals, suggesting the microbiome's potential in recognizing health states. Traditionally, microbiome-based status classification relies on pre-trained machine learning (ML) models. However, most ML methods overlook microbial relationships, limiting model performance.

Results

To address this gap, we propose PM-CNN (Phylogenetic Multi-path Convolutional Neural Network), a novel phylogeny-based neural network model for multi-status classification and disease detection using microbiome data. PM-CNN organizes microbes based on their phylogenetic relationships and extracts features using a multi-path convolutional neural network. An ensemble learning method then fuses these features to make accurate classification decisions. We applied PM-CNN to human microbiome data for status and disease detection, demonstrating its significant superiority over existing ML models. These results provide a robust foundation for microbiome-based state recognition and disease prediction in future research and applications.

Availability and implementation

PM-CNN software is available at https://github.com/qdu-bioinfo/PM_CNN.

Deep learning enhanced the diagnostic merit of serum glycome for multiple cancers

Protein glycosylation is associated with the pathogenesis of various cancers. The utilization of certain glycans in cancer diagnosis models holds promise, yet their accuracy is not always guaranteed. Here, we investigated the utility of deep learning techniques, specifically random forests combined with transfer learning, in enhancing serum glycome's discriminative power for cancer diagnosis (including ovarian cancer, non-small cell lung cancer, gastric cancer, and esophageal cancer). We started with ovarian cancer and demonstrated that transfer learning can achieve superior performance in data-disadvantaged cohorts (AUROC >0.9), outperforming the approach of PLS-DA. We identified a serum glycan-biomarker panel including 18 serum N-glycans and 4 glycan derived traits, most of which were featured with sialylation. Furthermore, we validated advantage of the transfer learning scheme across other cancer groups. These findings highlighted the superiority of transfer learning in improving the performance of glycans-based cancer diagnosis model and identifying cancer biomarkers, providing a new high-fidelity cancer diagnosis venue.

Gut microbiome for predicting immune checkpoint blockade-associated adverse events

BACKGROUND

The impact of the gut microbiome on the initiation and intensity of immune-related adverse events (irAEs) prompted by immune checkpoint inhibitors (ICIs) is widely acknowledged. Nevertheless, there is inconsistency in the gut microbial associations with irAEs reported across various studies.

METHODS

We performed a comprehensive analysis leveraging a dataset that included published microbiome data (n = 317) and in-house generated data from 16S rRNA and shotgun metagenome samples of irAEs (n = 115). We utilized a machine learning-based approach, specifically the Random Forest (RF) algorithm, to construct a microbiome-based classifier capable of distinguishing between non-irAEs and irAEs. Additionally, we conducted a comprehensive analysis, integrating transcriptome and metagenome profiling, to explore potential underlying mechanisms.

RESULTS

We identified specific microbial species capable of distinguishing between patients experiencing irAEs and non-irAEs. The RF classifier, developed using 14 microbial features, demonstrated robust discriminatory power between non-irAEs and irAEs (AUC = 0.88). Moreover, the predictive score from our classifier exhibited significant discriminative capability for identifying non-irAEs in two independent cohorts. Our functional analysis revealed that the altered microbiome in non-irAEs was characterized by an increased menaquinone biosynthesis, accompanied by elevated expression of rate-limiting enzymes menH and menC. Targeted metabolomics analysis further highlighted a notably higher abundance of menaquinone in the serum of patients who did not develop irAEs compared to the irAEs group.

CONCLUSIONS

Our study underscores the potential of microbial biomarkers for predicting the onset of irAEs and highlights menaquinone, a metabolite derived from the microbiome community, as a possible selective therapeutic agent for modulating the occurrence of irAEs.

Machine Learning Made Easy (MLme): a comprehensive toolkit for machine learning-driven data analysis

BACKGROUND

Machine learning (ML) has emerged as a vital asset for researchers to analyze and extract valuable information from complex datasets. However, developing an effective and robust ML pipeline can present a real challenge, demanding considerable time and effort, thereby impeding research progress. Existing tools in this landscape require a profound understanding of ML principles and programming skills. Furthermore, users are required to engage in the comprehensive configuration of their ML pipeline to obtain optimal performance.

RESULTS

To address these challenges, we have developed a novel tool called Machine Learning Made Easy (MLme) that streamlines the use of ML in research, specifically focusing on classification problems at present. By integrating 4 essential functionalities-namely, Data Exploration, AutoML, CustomML, and Visualization-MLme fulfills the diverse requirements of researchers while eliminating the need for extensive coding efforts. To demonstrate the applicability of MLme, we conducted rigorous testing on 6 distinct datasets, each presenting unique characteristics and challenges. Our results consistently showed promising performance across different datasets, reaffirming the versatility and effectiveness of the tool. Additionally, by utilizing MLme's feature selection functionality, we successfully identified significant markers for CD8+ naive (BACH2), CD16+ (CD16), and CD14+ (VCAN) cell populations.

CONCLUSION

MLme serves as a valuable resource for leveraging ML to facilitate insightful data analysis and enhance research outcomes, while alleviating concerns related to complex coding scripts. The source code and a detailed tutorial for MLme are available at https://github.com/FunctionalUrology/MLme.

Incorporating metabolic activity, taxonomy and community structure to improve microbiome-based predictive models for host phenotype prediction

We developed MicroKPNN, a prior-knowledge guided interpretable neural network for microbiome-based human host phenotype prediction. The prior knowledge used in MicroKPNN includes the metabolic activities of different bacterial species, phylogenetic relationships, and bacterial community structure, all in a shallow neural network. Application of MicroKPNN to seven gut microbiome datasets (involving five different human diseases including inflammatory bowel disease, type 2 diabetes, liver cirrhosis, colorectal cancer, and obesity) shows that incorporation of the prior knowledge helped improve the microbiome-based host phenotype prediction. MicroKPNN outperformed fully connected neural network-based approaches in all seven cases, with the most improvement of accuracy in the prediction of type 2 diabetes. MicroKPNN outperformed a recently developed deep-learning based approach DeepMicro, which selects the best combination of autoencoder and machine learning approach to make predictions, in all of the seven cases. Importantly, we showed that MicroKPNN provides a way for interpretation of the predictive models. Using importance scores estimated for the hidden nodes, MicroKPNN could provide explanations for prior research findings by highlighting the roles of specific microbiome components in phenotype predictions. In addition, it may suggest potential future research directions for studying the impacts of microbiome on host health and diseases. MicroKPNN is publicly available at https://github.com/mgtools/MicroKPNN.

A Machine Learning-Based Diagnostic Model for Crohn's Disease and Ulcerative Colitis Utilizing Fecal Microbiome Analysis

Recent research has demonstrated the potential of fecal microbiome analysis using machine learning (ML) in the diagnosis of inflammatory bowel disease (IBD), mainly Crohn's disease (CD) and ulcerative colitis (UC). This study employed the sparse partial least squares discriminant analysis (sPLS-DA) ML technique to develop a robust prediction model for distinguishing among CD, UC, and healthy controls (HCs) based on fecal microbiome data. Using data from multicenter cohorts, we conducted 16S rRNA gene sequencing of fecal samples from patients with CD (n = 671) and UC (n = 114) while forming an HC cohort of 1462 individuals from the Kangbuk Samsung Hospital Healthcare Screening Center. A streamlined pipeline based on HmmUFOTU was used. After a series of filtering steps, 1517 phylotypes and 1846 samples were retained for subsequent analysis. After 100 rounds of downsampling with age, sex, and sample size matching, and division into training and test sets, we constructed two binary prediction models to distinguish between IBD and HC and CD and UC using the training set. The binary prediction models exhibited high accuracy and area under the curve (for differentiating IBD from HC (mean accuracy, 0.950; AUC, 0.992) and CD from UC (mean accuracy, 0.945; AUC, 0.988)), respectively, in the test set. This study underscores the diagnostic potential of an ML model based on sPLS-DA, utilizing fecal microbiome analysis, highlighting its ability to differentiate between IBD and HC and distinguish CD from UC.

Machine learning-based meta-analysis of colorectal cancer and inflammatory bowel disease

Colorectal cancer (CRC) is a major global health concern, resulting in numerous cancer-related deaths. CRC detection, treatment, and prevention can be improved by identifying genes and biomarkers. Despite extensive research, the underlying mechanisms of CRC remain elusive, and previously identified biomarkers have not yielded satisfactory insights. This shortfall may be attributed to the predominance of univariate analysis methods, which overlook potential combinations of variants and genes contributing to disease development. Here, we address this knowledge gap by presenting a novel multivariate machine-learning strategy to pinpoint genes associated with CRC. Additionally, we applied our analysis pipeline to Inflammatory Bowel Disease (IBD), as IBD patients face substantial CRC risk. The importance of the identified genes was substantiated by rigorous validation across numerous independent datasets. Several of the discovered genes have been previously linked to CRC, while others represent novel findings warranting further investigation. A Python implementation of our pipeline can be accessed publicly at https://github.com/AriaSar/CRCIBD-ML.

MiTree: A Unified Web Cloud Analytic Platform for User-Friendly and Interpretable Microbiome Data Mining Using Tree-Based Methods

The advent of next-generation sequencing has greatly accelerated the field of human microbiome studies. Currently, investigators are seeking, struggling and competing to find new ways to diagnose, treat and prevent human diseases through the human microbiome. Machine learning is a promising approach to help such an effort, especially due to the high complexity of microbiome data. However, many of the current machine learning algorithms are in a "black box", i.e., they are difficult to understand and interpret. In addition, clinicians, public health practitioners and biologists are not usually skilled at computer programming, and they do not always have high-end computing devices. Thus, in this study, we introduce a unified web cloud analytic platform, named MiTree, for user-friendly and interpretable microbiome data mining. MiTree employs tree-based learning methods, including decision tree, random forest and gradient boosting, that are well understood and suited to human microbiome studies. We also stress that MiTree can address both classification and regression problems through covariate-adjusted or unadjusted analysis. MiTree should serve as an easy-to-use and interpretable data mining tool for microbiome-based disease prediction modeling, and should provide new insights into microbiome-based diagnostics, treatment and prevention. MiTree is an open-source software that is available on our web server.

The long-term health outcomes, pathophysiological mechanisms and multidisciplinary management of long COVID

There have been hundreds of millions of cases of coronavirus disease 2019 (COVID-19), which is caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). With the growing population of recovered patients, it is crucial to understand the long-term consequences of the disease and management strategies. Although COVID-19 was initially considered an acute respiratory illness, recent evidence suggests that manifestations including but not limited to those of the cardiovascular, respiratory, neuropsychiatric, gastrointestinal, reproductive, and musculoskeletal systems may persist long after the acute phase. These persistent manifestations, also referred to as long COVID, could impact all patients with COVID-19 across the full spectrum of illness severity. Herein, we comprehensively review the current literature on long COVID, highlighting its epidemiological understanding, the impact of vaccinations, organ-specific sequelae, pathophysiological mechanisms, and multidisciplinary management strategies. In addition, the impact of psychological and psychosomatic factors is also underscored. Despite these crucial findings on long COVID, the current diagnostic and therapeutic strategies based on previous experience and pilot studies remain inadequate, and well-designed clinical trials should be prioritized to validate existing hypotheses. Thus, we propose the primary challenges concerning biological knowledge gaps and efficient remedies as well as discuss the corresponding recommendations.

Mucosal Microbiome in Patients with Early Bowel Polyps: Inferences from Short-Read and Long-Read 16S rRNA Sequencing

Numerous studies have correlated dysbiosis in stool microbiota with colorectal cancer (CRC); however, fewer studies have investigated the mucosal microbiome in pre-cancerous bowel polyps. The short-read sequencing of variable regions in the 16S rRNA gene has commonly been used to infer bacterial taxonomy, and this has led, in part, to inconsistent findings between studies. Here, we examined mucosal microbiota from patients who presented with one or more polyps, compared to patients with no polyps, at the time of colonoscopy. We evaluated the results obtained using both short-read and PacBio long-read 16S rRNA sequencing. Neither sequencing technology identified significant differences in microbial diversity measures between patients with or without bowel polyps. Differential abundance measures showed that amplicon sequence variants (ASVs) associated with Ruminococcus gnavus and Escherichia coli were elevated in mucosa from polyp patients, while ASVs associated with Parabacteroides merdae, Veillonella nakazawae, and Sutterella wadsworthensis were relatively decreased. Only R. gnavus was consistently identified using both sequencing technologies as being altered between patients with polyps compared to patients without polyps, suggesting differences in technologies and bioinformatics processing impact study findings. Several of the differentially abundant bacteria identified using either sequencing technology are associated with inflammatory bowel diseases despite these patients being excluded from the current study, which suggests that early bowel neoplasia may be associated with a local inflammatory niche.

Dynamics of the Microbiota and Its Relationship with Post-COVID-19 Syndrome

Coronavirus disease (COVID-19) is an infection caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), which can be asymptomatic or present with multiple organ dysfunction. Many infected individuals have chronic alterations associated with neuropsychiatric, endocrine, gastrointestinal, and musculoskeletal symptoms, even several months after disease onset, developing long-COVID or post-acute COVID-19 syndrome (PACS). Microbiota dysbiosis contributes to the onset and progression of many viral diseases, including COVID-19 and post-COVID-19 manifestations, which could serve as potential diagnostic and prognostic biomarkers. This review aimed to discuss the most recent findings on gut microbiota dysbiosis and its relationship with the sequelae of PACS. Elucidating these mechanisms could help develop personalized and non-invasive clinical strategies to identify individuals at a higher risk of experiencing severe disease progression or complications associated with PACS. Moreover, the review highlights the importance of targeting the gut microbiota composition to avoid dysbiosis and to develop possible prophylactic and therapeutic measures against COVID-19 and PACS in future studies.

The distribution variation of pathogens and virulence factors in different geographical populations of giant pandas

Intestinal diseases caused by opportunistic pathogens seriously threaten the health and survival of giant pandas. However, our understanding of gut pathogens in different populations of giant pandas, especially in the wild populations, is still limited. Here, we conducted a study based on 52 giant panda metagenomes to investigate the composition and distribution of gut pathogens and virulence factors (VFs) in five geographic populations (captive: GPCD and GPYA; wild: GPQIN, GPQIO, and GPXXL). The results of the beta-diversity analyzes revealed a close relationship and high similarity in pathogen and VF compositions within the two captive groups. Among all groups, Proteobacteria, Firmicutes, and Bacteroidetes emerged as the top three abundant phyla. By using the linear discriminant analysis effect size method, we identified pathogenic bacteria unique to different populations, such as Klebsiella in GPCD, Salmonella in GPYA, Hafnia in GPQIO, Pedobacter in GPXXL, and Lactococcus in GPQIN. In addition, we identified 12 VFs that play a role in the intestinal diseases of giant pandas, including flagella, CsrA, enterobactin, type IV pili, alginate, AcrAB, capsule, T6SS, urease, type 1 fimbriae, polar flagella, allantoin utilization, and ClpP. These VFs influence pathogen motility, adhesion, iron uptake, acid resistance, and protein regulation, thereby contributing to pathogen infection and pathogenicity. Notably, we also found a difference in virulence of Pseudomonas aeruginosa between GPQIN and non-GPQIN wild populations, in which the relative abundance of VFs (0.42%) of P. aeruginosa was the lowest in GPQIN and the highest in non-GPQIN wild populations (GPXXL: 23.55% and GPQIO: 10.47%). In addition to enhancing our understanding of gut pathogens and VFs in different geographic populations of giant pandas, the results of this study provide a specific theoretical basis and data support for the development of effective conservation measures for giant pandas.

Lower gut abundance of Eubacterium rectale is linked to COVID-19 mortality

Introduction

Emerging preclinical and clinical studies suggest that altered gut microbiome composition and functions are associated with coronavirus 2019 (COVID- 19) severity and its long-term complications. We hypothesize that COVID-19 outcome is associated with gut microbiome status in population-based settings.

Methods

Gut metagenomic data of the adult population consisting of 2871 subjects from 16 countries were obtained from ExperimentHub through R, while the dynamic death data of COVID-19 patients between January 22, 2020 and December 8, 2020 in each country was acquired from Johns Hopkins Coronavirus Resource Center. An adjusted stable mortality rate (SMR) was used to represent these countries' mortality and correlated with the mean relative abundance (mRA) of healthy adult gut microbiome species.

Results

After excluding bacterial species with low prevalence (prevalence <0.2 in the included countries), the β-diversity was significantly higher in the countries with high SMR when compared with those with median or low SMR (p <0.001). We then identified the mRA of two butyrate producers, Eubacterium rectale and Roseburia intestinalis, that were negatively correlated with SMR during the study period. And the reduction of these species was associated with severer COVID-19 manifestation.

Conclusion

Population-based microbiome signatures with the stable mortality rate of COVID-19 in different countries suggest that altered gut microbiome composition and functions are associated with mortality of COVID-19.

Identification of microbial markers associated with lung cancer based on multi-cohort 16 s rRNA analyses: A systematic review and meta-analysis

BACKGROUND

The relationship between commensal microbiota and lung cancer (LC) has been studied extensively. However, developing replicable microbiological markers for early LC diagnosis across multiple populations has remained challenging. Current studies are limited to a single region, single LC subtype, and small sample size. Therefore, we aimed to perform the first large-scale meta-analysis for identifying micro biomarkers for LC screening by integrating gut and respiratory samples from multiple studies and building a machine-learning classifier.

METHODS

In total, 712 gut and 393 respiratory samples were assessed via 16 s rRNA amplicon sequencing. After identifying the taxa of differential biomarkers, we established random forest models to distinguish between LC populations and normal controls. We validated the robustness and specificity of the model using external cohorts. Moreover, we also used the KEGG database for the predictive analysis of colony-related functions.

RESULTS

The α and β diversity indices indicated that LC patients' gut microbiota (GM) and lung microbiota (LM) differed significantly from those of the healthy population. Linear discriminant analysis (LDA) of effect size (LEfSe) helped us identify the top-ranked biomarkers, Enterococcus, Lactobacillus, and Escherichia, in two microbial niches. The area under the curve values of the diagnostic model for the two sites were 0.81 and 0.90, respectively. KEGG enrichment analysis also revealed significant differences in microbiota-associated functions between cancer-affected and healthy individuals that were primarily associated with metabolic disturbances.

CONCLUSIONS

GM and LM profiles were significantly altered in LC patients, compared to healthy individuals. We identified the taxa of biomarkers at the two loci and constructed accurate diagnostic models. This study demonstrates the effectiveness of LC-specific microbiological markers in multiple populations and contributes to the early diagnosis and screening of LC.

Machine Learning Made Easy (MLme): A Comprehensive Toolkit for Machine Learning-Driven Data Analysis

Background

Machine learning (ML) has emerged as a vital asset for researchers to analyze and extract valuable information from complex datasets. However, developing an effective and robust ML pipeline can present a real challenge, demanding considerable time and effort, thereby impeding research progress. Existing tools in this landscape require a profound understanding of ML principles and programming skills. Furthermore, users are required to engage in the comprehensive configuration of their ML pipeline to obtain optimal performance.

Results

To address these challenges, we have developed a novel tool called Machine Learning Made Easy (MLme) that streamlines the use of ML in research, specifically focusing on classification problems at present. By integrating four essential functionalities, namely Data Exploration, AutoML, CustomML, and Visualization, MLme fulfills the diverse requirements of researchers while eliminating the need for extensive coding efforts. To demonstrate the applicability of MLme, we conducted rigorous testing on six distinct datasets, each presenting unique characteristics and challenges. Our results consistently showed promising performance across different datasets, reaffirming the versatility and effectiveness of the tool. Additionally, by utilizing MLme's feature selection functionality, we successfully identified significant markers for CD8+ naive (BACH2), CD16+ (CD16), and CD14+ (VCAN) cell populations.

Conclusion

MLme serves as a valuable resource for leveraging machine learning (ML) to facilitate insightful data analysis and enhance research outcomes, while alleviating concerns related to complex coding scripts. The source code and a detailed tutorial for MLme are available at https://github.com/FunctionalUrology/MLme.

Colonic drug delivery: Formulating the next generation of colon-targeted therapeutics

Colonic drug delivery can facilitate access to unique therapeutic targets and has the potential to enhance drug bioavailability whilst reducing off-target effects. Delivering drugs to the colon requires considered formulation development, as both oral and rectal dosage forms can encounter challenges if the colon's distinct physiological environment is not appreciated. As the therapeutic opportunities surrounding colonic drug delivery multiply, the success of novel pharmaceuticals lies in their design. This review provides a modern insight into the key parameters determining the effective design and development of colon-targeted medicines. Influential physiological features governing the release, dissolution, stability, and absorption of drugs in the colon are first discussed, followed by an overview of the most reliable colon-targeted formulation strategies. Finally, the most appropriate in vitro, in vivo, and in silico preclinical investigations are presented, with the goal of inspiring strategic development of new colon-targeted therapeutics.

Emerging roles of the gut microbiota in cancer immunotherapy

Gut microbiota represents a hidden treasure vault encompassing trillions of microorganisms that inhabit the intestinal epithelial barrier of the host. In the past decade, numerous in-vitro, animal and clinical studies have revealed the profound roles of gut microbiota in maintaining the homeostasis of various physiological functions, especially immune modulation, and remarkable differences in the configuration of microbial communities between cancers and healthy individuals. In addition, although considerable efforts have been devoted to cancer treatments, there remain many patients succumb to their disease with the incremental cancer burden worldwide. Nevertheless, compared with the stability of human genome, the plasticity of gut microbiota renders it a promising opportunity for individualized treatment. Meanwhile, burgeoning findings indicate that gut microbiota is involved in close interactions with the outcomes of diverse cancer immunotherapy protocols, including immune checkpoint blockade therapy, allogeneic hematopoietic stem cell transplantation, and chimeric antigen receptor T cell therapy. Here, we reviewed the evidence for the capacity of gut microflora to modulate cancer immunotherapies, and highlighted the opportunities of microbiota-based prognostic prediction, as well as microbiotherapy by targeting the microflora to potentiate anticancer efficacy while attenuating toxicity, which will be pivotal to the development of personalized cancer treatment strategies.

Machine Learning and COVID-19: Lessons from SARS-CoV-2

Currently, methods in machine learning have opened a significant number of applications to construct classifiers with capacities to recognize, identify, and interpret patterns hidden in massive amounts of data. This technology has been used to solve a variety of social and health issues against coronavirus disease 2019 (COVID-19). In this chapter, we present some supervised and unsupervised machine learning techniques that have contributed in three aspects to supplying information to health authorities and diminishing the deadly effects of the current worldwide outbreak on the population. First is the identification and construction of powerful classifiers capable of predicting severe, moderate, or asymptomatic responses in COVID-19 patients starting from clinical or high-throughput technologies. Second is the identification of groups of patients with similar physiological responses to improve the triage classification and inform treatments. The final aspect is the combination of machine learning methods and schemes from systems biology to link associative studies with mechanistic frameworks. This chapter aims to discuss some practical applications in the use of machine learning techniques to handle data coming from social behavior and high-throughput technologies, associated with COVID-19 evolution.

Performance of Gut Microbiome as an Independent Diagnostic Tool for 20 Diseases: Cross-Cohort Validation of Machine-Learning Classifiers

Cross-cohort validation is essential for gut-microbiome-based disease stratification but was only performed for limited diseases. Here, we systematically evaluated the cross-cohort performance of gut microbiome-based machine-learning classifiers for 20 diseases. Using single-cohort classifiers, we obtained high predictive accuracies in intra-cohort validation (~0.77 AUC), but low accuracies in cross-cohort validation, except the intestinal diseases (~0.73 AUC). We then built combined-cohort classifiers trained on samples combined from multiple cohorts to improve the validation of non-intestinal diseases, and estimated the required sample size to achieve validation accuracies of >0.7. In addition, we observed higher validation performance for classifiers using metagenomic data than 16S amplicon data in intestinal diseases. We further quantified the cross-cohort marker consistency using a Marker Similarity Index and observed similar trends. Together, our results supported the gut microbiome as an independent diagnostic tool for intestinal diseases and revealed strategies to improve cross-cohort performance based on identified determinants of consistent cross-cohort gut microbiome alterations.

Pediatric Crohn's disease diagnosis aid via genomic analysis and machine learning

Introduction

Determination of pediatric Crohn's disease (CD) remains a major diagnostic challenge. However, the rapidly emerging field of artificial intelligence has demonstrated promise in developing diagnostic models for intractable diseases.

Methods

We propose an artificial neural network model of 8 gene markers identified by 4 classification algorithms based on Gene Expression Omnibus database for diagnostic of pediatric CD.

Results

The model achieved over 85% accuracy and area under ROC curve value in both training set and testing set for diagnosing pediatric CD. Additionally, immune infiltration analysis was performed to address why these markers can be integrated to develop a diagnostic model.

Conclusion

This study supports further clinical facilitation of precise disease diagnosis by integrating genomics and machine learning algorithms in open-access database.