Search

Background/Objectives: The study of microbiome composition shows positive indications for application in the diagnosis and treatment of many conditions and diseases. One such condition is autism spectrum disorder (ASD). We aimed to analyze gut microbiome samples from children in Bosnia and Herzegovina to identify microbial differences between neurotypical children and those with ASD. Additionally, we developed machine learning classifiers to differentiate between the two groups using microbial abundance and predicted functional pathways. Methods: A total of 60 gut microbiome samples (16S rRNA sequences) were analyzed, with 44 from children with ASD and 16 from neurotypical children. Four machine learning algorithms (Random Forest, Support Vector Classification, Gradient Boosting, and Extremely Randomized Tree Classifier) were applied to create eight classification models based on bacterial abundance at the genus level and KEGG pathways. Model accuracy was evaluated, and an external dataset was introduced to test model generalizability. Results: The highest classification accuracy (80%) was achieved with Random Forest and Extremely Randomized Tree Classifier using genus-level taxa. The Random Forest model also performed well (78%) with KEGG pathways. When tested on an independent dataset, the model maintained high accuracy (79%), confirming its generalizability. Conclusions: This study identified significant microbial differences between neurotypical children and children with ASD. Machine learning classifiers, particularly Random Forest and Extremely Randomized Tree Classifier, achieved strong accuracy. Validation with external data demonstrated that the models could generalize across different datasets, highlighting their potential use.

Abstract Background A decade ago, the advancements in the microbiome data sequencing techniques initiated the development of research of the microbiome and its relationship with the host organism. The development of sophisticated bioinformatics and data science tools for the analysis of large amounts of data followed. Since then, the analyzed gut microbiome data, where microbiome is defined as a network of microorganisms inhabiting the human intestinal system, has been associated with several conditions such as irritable bowel syndrome - IBS, colorectal cancer, diabetes, obesity, and metabolic syndrome, and lately in the study of Parkinson’s and Alzheimer’s diseases as well. This paper aims to provide an understanding of differences between microbial data of individuals who have been diagnosed with multiple sclerosis and those who were not by exploiting data science techniques on publicly available data. Methods This study examines the relationship between multiple sclerosis (MS), an autoimmune central nervous system disease, and gut microbial community composition, using the samples acquired by 16s rRNA sequencing technique. We have used three different sets of MS samples sequenced during three independent studies (Jangi et al, Nat Commun 7:1–11, 2016), (Miyake et al, PLoS ONE 10:0137429, 2015), (McDonald et al, Msystems 3:00031–18, 2018) and this approach strengthens our results. Analyzed sequences were from healthy control and MS groups of sequences. The extracted set of statistically significant bacteria from the (Jangi et al, Nat Commun 7:1–11, 2016) dataset samples and their statistically significant predictive functions were used to develop a Random Forest classifier. In total, 8 models based on two criteria: bacteria abundance (at six taxonomic levels) and predictive functions (at two levels), were constructed and evaluated. These include using taxa abundances at different taxonomy levels as well as predictive function analysis at different hierarchical levels of KEGG pathways. Results The highest accuracy of the classification model was obtained at the genus level of taxonomy (76.82%) and the third hierarchical level of KEGG pathways (70.95%). The second dataset’s 18 MS samples (Miyake et al, PLoS ONE 10:0137429, 2015) and 18 self-reported healthy samples from the (McDonald et al, Msystems 3:00031–18, 2018) dataset were used to validate the developed classification model. The significance of this step is to show that the model is not overtrained for a specific dataset but can also be used on other independent datasets. Again, the highest classification model accuracy for both validating datasets combined was obtained at the genus level of taxonomy (70.98%) and third hierarchical level of KEGG pathways (67.24%). The accuracy of the independent set remained very relevant. Conclusions Our results demonstrate that the developed classification model provides a good tool that can be used to suggest the presence or absence of MS condition by collecting and analyzing gut microbiome samples. The accuracy of the model can be further increased by using sequencing methods that allow higher taxa resolution (i.e. shotgun metagenomic sequencing).

The number of microbiome-related studies has notably increased the availability of data on human microbiome composition and function. These studies provide the essential material to deeply explore host-microbiome associations and their relation to the development and progression of various complex diseases. Improved data-analytical tools are needed to exploit all information from these biological datasets, taking into account the peculiarities of microbiome data, i.e., compositional, heterogeneous and sparse nature of these datasets. The possibility of predicting host-phenotypes based on taxonomy-informed feature selection to establish an association between microbiome and predict disease states is beneficial for personalized medicine. In this regard, machine learning (ML) provides new insights into the development of models that can be used to predict outputs, such as classification and prediction in microbiology, infer host phenotypes to predict diseases and use microbial communities to stratify patients by their characterization of state-specific microbial signatures. Here we review the state-of-the-art ML methods and respective software applied in human microbiome studies, performed as part of the COST Action ML4Microbiome activities. This scoping review focuses on the application of ML in microbiome studies related to association and clinical use for diagnostics, prognostics, and therapeutics. Although the data presented here is more related to the bacterial community, many algorithms could be applied in general, regardless of the feature type. This literature and software review covering this broad topic is aligned with the scoping review methodology. The manual identification of data sources has been complemented with: (1) automated publication search through digital libraries of the three major publishers using natural language processing (NLP) Toolkit, and (2) an automated identification of relevant software repositories on GitHub and ranking of the related research papers relying on learning to rank approach.

The application of machine learning (ML) techniques could facilitate the identification of predictive biomarkers of somatostatin analog (SSA) efficacy in patients with neuroendocrine tumors (NETs). We collected data from 74 patients with a pancreatic or gastrointestinal NET who received SSA as first-line therapy. We developed three classification models to predict whether the patient would experience a progressive disease (PD) after 12 or 18 months based on clinic-pathological factors at the baseline. The dataset included 70 samples and 15 features. We initially developed three classification models with accuracy ranging from 55% to 70%. We then compared ten different ML algorithms. In all but one case, the performance of the Multinomial Naïve Bayes algorithm (80%) was the highest. The support vector machine classifier (SVC) had a higher performance for the recall metric of the progression-free outcome (97% vs. 94%). Overall, for the first time, we documented that the factors that mainly influenced progression-free survival (PFS) included age, the number of metastatic sites and the primary site. In addition, the following factors were also isolated as important: adverse events G3–G4, sex, Ki67, metastatic site (liver), functioning NET, the primary site and the stage. In patients with advanced NETs, ML provides a predictive model that could potentially be used to differentiate prognostic groups and to identify patients for whom SSA therapy as a single agent may not be sufficient to achieve a long-lasting PFS.

The rapid development of machine learning (ML) techniques has opened up the data-dense field of microbiome research for novel therapeutic, diagnostic, and prognostic applications targeting a wide range of disorders, which could substantially improve healthcare practices in the era of precision medicine. However, several challenges must be addressed to exploit the benefits of ML in this field fully. In particular, there is a need to establish “gold standard” protocols for conducting ML analysis experiments and improve interactions between microbiome researchers and ML experts. The Machine Learning Techniques in Human Microbiome Studies (ML4Microbiome) COST Action CA18131 is a European network established in 2019 to promote collaboration between discovery-oriented microbiome researchers and data-driven ML experts to optimize and standardize ML approaches for microbiome analysis. This perspective paper presents the key achievements of ML4Microbiome, which include identifying predictive and discriminatory ‘omics’ features, improving repeatability and comparability, developing automation procedures, and defining priority areas for the novel development of ML methods targeting the microbiome. The insights gained from ML4Microbiome will help to maximize the potential of ML in microbiome research and pave the way for new and improved healthcare practices.