Explainable AI reveals changes in skin microbiome composition linked to phenotypic differences

A hybrid forecasting approach for China's national carbon emission allowance prices with balanced accuracy and interpretability

A significant milestone in China's carbon market was reached with the official launch and operation of the National Carbon Emission Trading Market. The accurate prediction of the carbon price in this market is crucial for the government to formulate scientific policies regarding the carbon market and for companies to participate effectively. Nevertheless, it remains challenging to accurately predict price fluctuations in the carbon market because of the volatility and instability caused by several complex factors. This paper proposes a new carbon price forecasting framework that considers the potential factors influencing national carbon prices, including data decomposition and reconstruction techniques, feature selection techniques, machine learning forecasting techniques for intelligent optimisation, and research on model interpretability. This comprehensive framework aims to improve the accuracy and understandability of carbon price projections to respond better to the complexity and uncertainty of carbon markets. The results indicate that (1) the hybrid forecasting framework is highly accurate in forecasting national carbon market prices and far superior to other comparative models; (2) the factors driving national carbon prices vary according to the time scale. High-frequency series are sensitive to short-term economic and energy market indicators. Medium- and low-frequency series are more susceptible to financial markets and long-term economic conditions than high-frequency series. This study provides insights into the factors affecting China's national carbon market price and serves as a reference for companies and governments to develop carbon price forecasting tools.

A multi-study analysis enables identification of potential microbial features associated with skin aging signs

Introduction: During adulthood, the skin microbiota can be relatively stable if environmental conditions are also stable, yet physiological changes of the skin with age may affect the skin microbiome and its function. The microbiome is an important factor to consider in aging since it constitutes most of the genes that are expressed on the human body. However, severity of specific aging signs (one of the parameters used to measure "apparent" age) and skin surface quality (e.g., texture, hydration, pH, sebum, etc.) may not be indicative of chronological age. For example, older individuals can have young looking skin (young apparent age) and young individuals can be of older apparent age. Methods: Here we aim to identify microbial taxa of interest associated to skin quality/aging signs using a multi-study analysis of 13 microbiome datasets consisting of 16S rRNA amplicon sequence data and paired skin clinical data from the face. Results: We show that there is a negative relationship between microbiome diversity and transepidermal water loss, and a positive association between microbiome diversity and age. Aligned with a tight link between age and wrinkles, we report a global positive association between microbiome diversity and Crow's feet wrinkles, but with this relationship varying significantly by sub-study. Finally, we identify taxa potentially associated with wrinkles, TEWL and corneometer measures. Discussion: These findings represent a key step towards understanding the implication of the skin microbiota in skin aging signs.

eXplainable Artificial Intelligence (XAI) in aging clock models

XAI is a rapidly progressing field of machine learning, aiming to unravel the predictions of complex models. XAI is especially required in sensitive applications, e.g. in health care, when diagnosis, recommendations and treatment choices might rely on the decisions made by artificial intelligence systems. AI approaches have become widely used in aging research as well, in particular, in developing biological clock models and identifying biomarkers of aging and age-related diseases. However, the potential of XAI here awaits to be fully appreciated. We discuss the application of XAI for developing the "aging clocks" and present a comprehensive analysis of the literature categorized by the focus on particular physiological systems.

The promise of explainable deep learning for omics data analysis: Adding new discovery tools to AI

Deep learning has already revolutionised the way a wide range of data is processed in many areas of daily life. The ability to learn abstractions and relationships from heterogeneous data has provided impressively accurate prediction and classification tools to handle increasingly big datasets. This has a significant impact on the growing wealth of omics datasets, with the unprecedented opportunity for a better understanding of the complexity of living organisms. While this revolution is transforming the way these data are analyzed, explainable deep learning is emerging as an additional tool with the potential to change the way biological data is interpreted. Explainability addresses critical issues such as transparency, so important when computational tools are introduced especially in clinical environments. Moreover, it empowers artificial intelligence with the capability to provide new insights into the input data, thus adding an element of discovery to these already powerful resources. In this review, we provide an overview of the transformative effects explainable deep learning is having on multiple sectors, ranging from genome engineering and genomics, from radiomics to drug design and clinical trials. We offer a perspective to life scientists, to better understand the potential of these tools, and a motivation to implement them in their research, by suggesting learning resources they can use to move their first steps in this field.

Skin microbiome profile in people living with HIV/AIDS in Cameroon

The presence of pathogens and the state of diseases, particularly skin diseases, may alter the composition of human skin microbiome. HIV infection has been reported to impair gut microbiome that leads to severe consequences. However, with cutaneous manifestations, that can be life-threatening, due to the opportunistic pathogens, little is known whether HIV infection might influence the skin microbiome and affect the skin homeostasis. This study catalogued the profile of skin microbiome of healthy Cameroonians, at three different skin sites, and compared them to the HIV-infected individuals. Taking advantage on the use of molecular assay coupled with next-generation sequencing, this study revealed that alpha-diversity of the skin microbiome was higher and beta-diversity was altered significantly in the HIV-infected Cameroonians than in the healthy ones. The relative abundance of skin microbes such as Micrococcus and Kocuria species was higher and Cutibacterium species was significantly lower in HIV-infected people, indicating an early change in the human skin microbiome in response to the HIV infection. This phenotypical shift was not related to the number of CD4 T cell count thus the cause remains to be identified. Overall, these data may offer an important lead on the role of skin microbiome in the determination of cutaneous disease state and the discovery of safe pharmacological preparations to treat microbial-related skin disorders.

Machine learning: a powerful tool for identifying key microbial agents associated with specific cancer types

Machine learning (ML) includes a broad class of computer programs that improve with experience and shows unique strengths in performing tasks such as clustering, classification and regression. Over the past decade, microbial communities have been implicated in influencing the onset, progression, metastasis, and therapeutic response of multiple cancers. Host-microbe interaction may be a physiological pathway contributing to cancer development. With the accumulation of a large number of high-throughput data, ML has been successfully applied to the study of human cancer microbiomics in an attempt to reveal the complex mechanism behind cancer. In this review, we begin with a brief overview of the data sources included in cancer microbiomics studies. Then, the characteristics of the ML algorithm are briefly introduced. Secondly, the application progress of ML in cancer microbiomics is also reviewed. Finally, we highlight the challenges and future prospects facing ML in cancer microbiomics. On this basis, we conclude that the development of cancer microbiomics can not be achieved without ML, and that ML can be used to develop tumor-targeting microbial therapies, ultimately contributing to personalized and precision medicine.

Advancing microbiome research with machine learning: key findings from the ML4Microbiome COST action

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.

Machine learning approaches in microbiome research: challenges and best practices

Microbiome data predictive analysis within a machine learning (ML) workflow presents numerous domain-specific challenges involving preprocessing, feature selection, predictive modeling, performance estimation, model interpretation, and the extraction of biological information from the results. To assist decision-making, we offer a set of recommendations on algorithm selection, pipeline creation and evaluation, stemming from the COST Action ML4Microbiome. We compared the suggested approaches on a multi-cohort shotgun metagenomics dataset of colorectal cancer patients, focusing on their performance in disease diagnosis and biomarker discovery. It is demonstrated that the use of compositional transformations and filtering methods as part of data preprocessing does not always improve the predictive performance of a model. In contrast, the multivariate feature selection, such as the Statistically Equivalent Signatures algorithm, was effective in reducing the classification error. When validated on a separate test dataset, this algorithm in combination with random forest modeling, provided the most accurate performance estimates. Lastly, we showed how linear modeling by logistic regression coupled with visualization techniques such as Individual Conditional Expectation (ICE) plots can yield interpretable results and offer biological insights. These findings are significant for clinicians and non-experts alike in translational applications.

Bioprospecting the Skin Microbiome: Advances in Therapeutics and Personal Care Products

Bioprospecting is the discovery and exploration of biological diversity found within organisms, genetic elements or produced compounds with prospective commercial or therapeutic applications. The human skin is an ecological niche which harbours a rich and compositional diversity microbiome stemming from the multifactorial interactions between the host and microbiota facilitated by exploitable effector compounds. Advances in the understanding of microbial colonisation mechanisms alongside species and strain interactions have revealed a novel chemical and biological understanding which displays applicative potential. Studies elucidating the organismal interfaces and concomitant understanding of the central processes of skin biology have begun to unravel a potential wealth of molecules which can exploited for their proposed functions. A variety of skin-microbiome-derived compounds display prospective therapeutic applications, ranging from antioncogenic agents relevant in skin cancer therapy to treatment strategies for antimicrobial-resistant bacterial and fungal infections. Considerable opportunities have emerged for the translation to personal care products, such as topical agents to mitigate various skin conditions such as acne and eczema. Adjacent compound developments have focused on cosmetic applications such as reducing skin ageing and its associated changes to skin properties and the microbiome. The skin microbiome contains a wealth of prospective compounds with therapeutic and commercial applications; however, considerable work is required for the translation of in vitro findings to relevant in vivo models to ensure translatability.

Compositional Variations between Adult and Infant Skin Microbiome: An Update

Human skin and its commensal microbiome form the first layer of protection to the outside world. A dynamic microbial ecosystem of bacteria, fungi and viruses, with the potential to respond to external insult, the skin microbiome has been shown to evolve over the life course with an alteration in taxonomic composition responding to altered microenvironmental conditions on human skin. This work sought to investigate the taxonomic, diversity and functional differences between infant and adult leg skin microbiomes. A 16S rRNA gene-based metataxonomic analysis revealed significant differences between the infant and adult skin groups, highlighting differential microbiome profiles at both the genus and species level. Diversity analysis reveals differences in the overall community structure and associated differential predicted functional profiles between the infant and adult skin microbiome suggest differing metabolic processes are present between the groups. These data add to the available information on the dynamic nature of skin microbiome during the life course and highlight the predicted differential microbial metabolic process that exists on infant and adult skin, which may have an impact on the future design and use of cosmetic products that are produced to work in consort with the skin microbiome.

Evolving approaches to profiling the microbiome in skin disease

Despite its harsh and dry environment, human skin is home to diverse microbes, including bacteria, fungi, viruses, and microscopic mites. These microbes form communities that may exist at the skin surface, deeper skin layers, and within microhabitats such as the hair follicle and sweat glands, allowing complex interactions with the host immune system. Imbalances in the skin microbiome, known as dysbiosis, have been linked to various inflammatory skin disorders, including atopic dermatitis, acne, and psoriasis. The roles of abundant commensal bacteria belonging to Staphylococcus and Cutibacterium taxa and the fungi Malassezia, where particular species or strains can benefit the host or cause disease, are increasingly appreciated in skin disorders. Furthermore, recent research suggests that the interactions between microorganisms and the host's immune system on the skin can have distant and systemic effects on the body, such as on the gut and brain, known as the "skin-gut" or "skin-brain" axes. Studies on the microbiome in skin disease have typically relied on 16S rRNA gene sequencing methods, which cannot provide accurate information about species or strains of microorganisms on the skin. However, advancing technologies, including metagenomics and other functional 'omic' approaches, have great potential to provide more comprehensive and detailed information about the skin microbiome in health and disease. Additionally, inter-species and multi-kingdom interactions can cause cascading shifts towards dysbiosis and are crucial but yet-to-be-explored aspects of many skin disorders. Better understanding these complex dynamics will require meta-omic studies complemented with experiments and clinical trials to confirm function. Evolving how we profile the skin microbiome alongside technological advances is essential to exploring such relationships. This review presents the current and emerging methods and their findings for profiling skin microbes to advance our understanding of the microbiome in skin disease.

Explainable AI for unveiling deep learning pollen classification model based on fusion of scattered light patterns and fluorescence spectroscopy

Pollen monitoring have become data-intensive in recent years as real-time detectors are deployed to classify airborne pollen grains. Machine learning models with a focus on deep learning, have an essential role in the pollen classification task. Within this study we developed an explainable framework to unveil a deep learning model for pollen classification. Model works on data coming from single particle detector (Rapid-E) that records for each particle optical fingerprint with scattered light and laser induced fluorescence. Morphological properties of a particle are sensed with the light scattering process, while chemical properties are encoded with fluorescence spectrum and fluorescence lifetime induced by high-resolution laser. By utilizing these three data modalities, scattering, spectrum, and lifetime, deep learning-based models with millions of parameters are learned to distinguish different pollen classes, but a proper understanding of such a black-box model decisions demands additional methods to employ. Our study provides the first results of applied explainable artificial intelligence (xAI) methodology on the pollen classification model. Extracted knowledge on the important features that attribute to the predicting particular pollen classes is further examined from the perspective of domain knowledge and compared to available reference data on pollen sizes, shape, and laboratory spectrofluorometer measurements.

Artificial Intelligence in microbiomes analysis: A review of applications in dermatology

Microorganisms are closely related to skin diseases, and microbiological imbalances or invasions of exogenous pathogens can be a source of various skin diseases. The development and prognosis of such skin diseases are also closely related to the type and composition ratio of microorganisms present. Therefore, through detection of the characteristics and changes in microorganisms, the possibility for diagnosis and prediction of skin diseases can be markedly improved. The abundance of microorganisms and an understanding of the vast amount of biological information associated with these microorganisms has been a formidable task. However, with advances in large-scale sequencing, artificial intelligence (AI)-related machine learning can serve as a means to analyze large-scales of data related to microorganisms along with determinations regarding the type and status of diseases. In this review, we describe some uses of this exciting, new emerging field. In specific, we described the recognition of fungi with convolutional neural networks (CNN), the combined application of microbial genome sequencing and machine learning and applications of AI in the diagnosis of skin diseases as related to the gut-skin axis.

Interpreting tree ensemble machine learning models with endoR

Tree ensemble machine learning models are increasingly used in microbiome science as they are compatible with the compositional, high-dimensional, and sparse structure of sequence-based microbiome data. While such models are often good at predicting phenotypes based on microbiome data, they only yield limited insights into how microbial taxa may be associated. We developed endoR, a method to interpret tree ensemble models. First, endoR simplifies the fitted model into a decision ensemble. Then, it extracts information on the importance of individual features and their pairwise interactions, displaying them as an interpretable network. Both the endoR network and importance scores provide insights into how features, and interactions between them, contribute to the predictive performance of the fitted model. Adjustable regularization and bootstrapping help reduce the complexity and ensure that only essential parts of the model are retained. We assessed endoR on both simulated and real metagenomic data. We found endoR to have comparable accuracy to other common approaches while easing and enhancing model interpretation. Using endoR, we also confirmed published results on gut microbiome differences between cirrhotic and healthy individuals. Finally, we utilized endoR to explore associations between human gut methanogens and microbiome components. Indeed, these hydrogen consumers are expected to interact with fermenting bacteria in a complex syntrophic network. Specifically, we analyzed a global metagenome dataset of 2203 individuals and confirmed the previously reported association between Methanobacteriaceae and Christensenellales. Additionally, we observed that Methanobacteriaceae are associated with a network of hydrogen-producing bacteria. Our method accurately captures how tree ensembles use features and interactions between them to predict a response. As demonstrated by our applications, the resultant visualizations and summary outputs facilitate model interpretation and enable the generation of novel hypotheses about complex systems.

Standardized multi-omics of Earth's microbiomes reveals microbial and metabolite diversity

Despite advances in sequencing, lack of standardization makes comparisons across studies challenging and hampers insights into the structure and function of microbial communities across multiple habitats on a planetary scale. Here we present a multi-omics analysis of a diverse set of 880 microbial community samples collected for the Earth Microbiome Project. We include amplicon (16S, 18S, ITS) and shotgun metagenomic sequence data, and untargeted metabolomics data (liquid chromatography-tandem mass spectrometry and gas chromatography mass spectrometry). We used standardized protocols and analytical methods to characterize microbial communities, focusing on relationships and co-occurrences of microbially related metabolites and microbial taxa across environments, thus allowing us to explore diversity at extraordinary scale. In addition to a reference database for metagenomic and metabolomic data, we provide a framework for incorporating additional studies, enabling the expansion of existing knowledge in the form of an evolving community resource. We demonstrate the utility of this database by testing the hypothesis that every microbe and metabolite is everywhere but the environment selects. Our results show that metabolite diversity exhibits turnover and nestedness related to both microbial communities and the environment, whereas the relative abundances of microbially related metabolites vary and co-occur with specific microbial consortia in a habitat-specific manner. We additionally show the power of certain chemistry, in particular terpenoids, in distinguishing Earth's environments (for example, terrestrial plant surfaces and soils, freshwater and marine animal stool), as well as that of certain microbes including Conexibacter woesei (terrestrial soils), Haloquadratum walsbyi (marine deposits) and Pantoea dispersa (terrestrial plant detritus). This Resource provides insight into the taxa and metabolites within microbial communities from diverse habitats across Earth, informing both microbial and chemical ecology, and provides a foundation and methods for multi-omics microbiome studies of hosts and the environment.

Machine learning for data integration in human gut microbiome

Recent studies have demonstrated that gut microbiota plays critical roles in various human diseases. High-throughput technology has been widely applied to characterize the microbial ecosystems, which led to an explosion of different types of molecular profiling data, such as metagenomics, metatranscriptomics and metabolomics. For analysis of such data, machine learning algorithms have shown to be useful for identifying key molecular signatures, discovering potential patient stratifications, and particularly for generating models that can accurately predict phenotypes. In this review, we first discuss how dysbiosis of the intestinal microbiota is linked to human disease development and how potential modulation strategies of the gut microbial ecosystem can be used for disease treatment. In addition, we introduce categories and workflows of different machine learning approaches, and how they can be used to perform integrative analysis of multi-omics data. Finally, we review advances of machine learning in gut microbiome applications and discuss related challenges. Based on this we conclude that machine learning is very well suited for analysis of gut microbiome and that these approaches can be useful for development of gut microbe-targeted therapies, which ultimately can help in achieving personalized and precision medicine.

Towards standardized and reproducible research in skin microbiomes

Skin is a complex organ serving a critical role as a barrier and mediator of interactions between the human body and its environment. Recent studies have uncovered how resident microbial communities play a significant role in maintaining the normal healthy function of the skin and the immune system. In turn, numerous host-associated and environmental factors influence these communities' composition and diversity across the cutaneous surface. In addition, specific compositional changes in skin microbiota have also been connected to the development of several chronic diseases. The current era of microbiome research is characterized by its reliance on large data sets of nucleotide sequences produced with high-throughput sequencing of sample-extracted DNA. These approaches have yielded new insights into many previously uncharacterized microbial communities. Application of standardized practices in the study of skin microbial communities could help us understand their complex structures, functional capacities, and health associations and increase the reproducibility of the research. Here, we overview the current research in human skin microbiomes and outline challenges specific to their study. Furthermore, we provide perspectives on recent advances in methods, analytical tools and applications of skin microbiomes in medicine and forensics.

Machine Learning Data Analysis Highlights the Role of Parasutterella and Alloprevotella in Autism Spectrum Disorders

In recent years, the involvement of the gut microbiota in disease and health has been investigated by sequencing the 16S gene from fecal samples. Dysbiotic gut microbiota was also observed in Autism Spectrum Disorder (ASD), a neurodevelopmental disorder characterized by gastrointestinal symptoms. However, despite the relevant number of studies, it is still difficult to identify a typical dysbiotic profile in ASD patients. The discrepancies among these studies are due to technical factors (i.e., experimental procedures) and external parameters (i.e., dietary habits). In this paper, we collected 959 samples from eight available projects (540 ASD and 419 Healthy Controls, HC) and reduced the observed bias among studies. Then, we applied a Machine Learning (ML) approach to create a predictor able to discriminate between ASD and HC. We tested and optimized three algorithms: Random Forest, Support Vector Machine and Gradient Boosting Machine. All three algorithms confirmed the importance of five different genera, including Parasutterella and Alloprevotella. Furthermore, our results show that ML algorithms could identify common taxonomic features by comparing datasets obtained from countries characterized by latent confounding variables.

Using Explainable Artificial Intelligence to Discover Interactions in an Ecological Model for Obesity

Ecological theories suggest that environmental, social, and individual factors interact to cause obesity. Yet, many analytic techniques, such as multilevel modeling, require manual specification of interacting factors, making them inept in their ability to search for interactions. This paper shows evidence that an explainable artificial intelligence approach, commonly employed in genomics research, can address this problem. The method entails using random intersection trees to decode interactions learned by random forest models. Here, this approach is used to extract interactions between features of a multi-level environment from random forest models of waist-to-height ratios using 11,112 participants from the Adolescent Brain Cognitive Development study. This study shows that methods used to discover interactions between genes can also discover interacting features of the environment that impact obesity. This new approach to modeling ecosystems may help shine a spotlight on combinations of environmental features that are important to obesity, as well as other health outcomes.

Metagenomic Predictions: A Review 10 years on

Metagenomic predictions use variation in the metagenome (microbiome profile) to predict the unknown phenotype of the associated host. Metagenomic predictions were first developed 10 years ago, where they were used to predict which cattle would produce high or low levels of enteric methane. Since then, the approach has been applied to several traits and species including residual feed intake in cattle, and carcass traits, body mass index and disease state in pigs. Additionally, the method has been extended to include predictions based on other multi-dimensional data such as the metabolome, as well to combine genomic and metagenomic information. While there is still substantial optimisation required, the use of metagenomic predictions is expanding as DNA sequencing costs continue to fall and shows great promise particularly for traits heavily influenced by the microbiome such as feed efficiency and methane emissions.

Prediction of Smoking Habits From Class-Imbalanced Saliva Microbiome Data Using Data Augmentation and Machine Learning

Human microbiome research is moving from characterization and association studies to translational applications in medical research, clinical diagnostics, and others. One of these applications is the prediction of human traits, where machine learning (ML) methods are often employed, but face practical challenges. Class imbalance in available microbiome data is one of the major problems, which, if unaccounted for, leads to spurious prediction accuracies and limits the classifier's generalization. Here, we investigated the predictability of smoking habits from class-imbalanced saliva microbiome data by combining data augmentation techniques to account for class imbalance with ML methods for prediction. We collected publicly available saliva 16S rRNA gene sequencing data and smoking habit metadata demonstrating a serious class imbalance problem, i.e., 175 current vs. 1,070 non-current smokers. Three data augmentation techniques (synthetic minority over-sampling technique, adaptive synthetic, and tree-based associative data augmentation) were applied together with seven ML methods: logistic regression, k-nearest neighbors, support vector machine with linear and radial kernels, decision trees, random forest, and extreme gradient boosting. K-fold nested cross-validation was used with the different augmented data types and baseline non-augmented data to validate the prediction outcome. Combining data augmentation with ML generally outperformed baseline methods in our dataset. The final prediction model combined tree-based associative data augmentation and support vector machine with linear kernel, and achieved a classification performance expressed as Matthews correlation coefficient of 0.36 and AUC of 0.81. Our method successfully addresses the problem of class imbalance in microbiome data for reliable prediction of smoking habits.

SeqScreen: accurate and sensitive functional screening of pathogenic sequences via ensemble learning

The COVID-19 pandemic has emphasized the importance of accurate detection of known and emerging pathogens. However, robust characterization of pathogenic sequences remains an open challenge. To address this need we developed SeqScreen, which accurately characterizes short nucleotide sequences using taxonomic and functional labels and a customized set of curated Functions of Sequences of Concern (FunSoCs) specific to microbial pathogenesis. We show our ensemble machine learning model can label protein-coding sequences with FunSoCs with high recall and precision. SeqScreen is a step towards a novel paradigm of functionally informed synthetic DNA screening and pathogen characterization, available for download at www.gitlab.com/treangenlab/seqscreen .

Explainable Machine Learning for Longitudinal Multi-Omic Microbiome

Over the years, research studies have shown there is a key connection between the microbial community in the gut, genes, and immune system. Understanding this association may help discover the cause of complex chronic idiopathic disorders such as inflammatory bowel disease. Even though important efforts have been put into the field, the functions, dynamics, and causation of dysbiosis state performed by the microbial community remains unclear. Machine learning models can help elucidate important connections and relationships between microbes in the human host. Our study aims to extend the current knowledge of associations between the human microbiome and health and disease through the application of dynamic Bayesian networks to describe the temporal variation of the gut microbiota and dynamic relationships between taxonomic entities and clinical variables. We develop a set of preprocessing steps to clean, filter, select, integrate, and model informative metagenomics, metatranscriptomics, and metabolomics longitudinal data from the Human Microbiome Project. This study accomplishes novel network models with satisfactory predictive performance (accuracy = 0.648) for each inflammatory bowel disease state, validating Bayesian networks as a framework for developing interpretable models to help understand the basic ways the different biological entities (taxa, genes, metabolites) interact with each other in a given environment (human gut) over time. These findings can serve as a starting point to advance the discovery of novel therapeutic approaches and new biomarkers for precision medicine.

SKIOME Project: a curated collection of skin microbiome datasets enriched with study-related metadata

Large amounts of data from microbiome-related studies have been (and are currently being) deposited on international public databases. These datasets represent a valuable resource for the microbiome research community and could serve future researchers interested in integrating multiple datasets into powerful meta-analyses. However, this huge amount of data lacks harmonization and it is far from being completely exploited in its full potential to build a foundation that places microbiome research at the nexus of many subdisciplines within and beyond biology. Thus, it urges the need for data accessibility and reusability, according to findable, accessible, interoperable and reusable (FAIR) principles, as supported by National Microbiome Data Collaborative and FAIR Microbiome. To tackle the challenge of accelerating discovery and advances in skin microbiome research, we collected, integrated and organized existing microbiome data resources from human skin 16S rRNA amplicon-sequencing experiments. We generated a comprehensive collection of datasets, enriched in metadata, and organized this information into data frames ready to be integrated into microbiome research projects and advanced post-processing analyses, such as data science applications (e.g. machine learning). Furthermore, we have created a data retrieval and curation framework built on three different stages to maximize the retrieval of datasets and metadata associated with them. Lastly, we highlighted some caveats regarding metadata retrieval and suggested ways to improve future metadata submissions. Overall, our work resulted in a curated skin microbiome datasets collection accompanied by a state-of-the-art analysis of the last 10 years of the skin microbiome field. Database URL:  https://github.com/giuliaago/SKIOMEMetadataRetrieval.

EasyMap - An Interactive Web Tool for Evaluating and Comparing Associations of Clinical Variables and Microbiome Composition

One of the most common tasks in microbiome studies is comparing microbial profiles across various groups of people (e.g., sick vs. healthy). Routinely, researchers use multivariate linear regression models to address these challenges, such as linear regression packages, MaAsLin2, LEfSe, etc. In many cases, it is unclear which metadata variables should be included in the linear model, as many human-associated variables are correlated with one another. Thus, multiple models are often tested, each including a different set of variables, however the challenge of selecting the metadata variables in the final model remains. Here, we present EasyMap, an interactive online tool allowing for (1) running multiple multivariate linear regression models, on the same features and metadata; (2) visualizing the associations between microbial features and clinical metadata found in each model; and (3) comparing across the various models to identify the critical metadata variables and select the optimal model. EasyMap provides a side-by-side visualization of association results across the various models, each with additional metadata variables, enabling us to evaluate the impact of each metadata variable on the associated feature. EasyMap’s interface enables filtering associations by significance, focusing on specific microbes and finding the robust associations that are found across multiple models. While EasyMap was designed to analyze microbiome data, it can handle any other tabular data with numeric features and metadata variables. EasyMap takes the common task of multivariate linear regression to the next level, with an intuitive and simple user interface, allowing for wide comparisons of multiple models to identify the robust microbial feature associations. EasyMap is available at http://yassour.rcs.huji.ac.il/easymap.

Combining explainable machine learning, demographic and multi-omic data to inform precision medicine strategies for inflammatory bowel disease

Inflammatory bowel diseases (IBDs), including ulcerative colitis and Crohn’s disease, affect several million individuals worldwide. These diseases are heterogeneous at the clinical, immunological and genetic levels and result from complex host and environmental interactions. Investigating drug efficacy for IBD can improve our understanding of why treatment response can vary between patients. We propose an explainable machine learning (ML) approach that combines bioinformatics and domain insight, to integrate multi-modal data and predict inter-patient variation in drug response. Using explanation of our models, we interpret the ML models’ predictions to infer unique combinations of important features associated with pharmacological responses obtained during preclinical testing of drug candidates in ex vivo patient-derived fresh tissues. Our inferred multi-modal features that are predictive of drug efficacy include multi-omic data (genomic and transcriptomic), demographic, medicinal and pharmacological data. Our aim is to understand variation in patient responses before a drug candidate moves forward to clinical trials. As a pharmacological measure of drug efficacy, we measured the reduction in the release of the inflammatory cytokine TNFα from the fresh IBD tissues in the presence/absence of test drugs. We initially explored the effects of a mitogen-activated protein kinase (MAPK) inhibitor; however, we later showed our approach can be applied to other targets, test drugs or mechanisms of interest. Our best model predicted TNFα levels from demographic, medicinal and genomic features with an error of only 4.98% on unseen patients. We incorporated transcriptomic data to validate insights from genomic features. Our results showed variations in drug effectiveness (measured by ex vivo assays) between patients that differed in gender, age or condition and linked new genetic polymorphisms to patient response variation to the anti-inflammatory treatment BIRB796 (Doramapimod). Our approach models IBD drug response while also identifying its most predictive features as part of a transparent ML precision medicine strategy.

On the Construction of Group Equivariant Non-Expansive Operators via Permutants and Symmetric Functions

Group Equivariant Operators (GEOs) are a fundamental tool in the research on neural networks, since they make available a new kind of geometric knowledge engineering for deep learning, which can exploit symmetries in artificial intelligence and reduce the number of parameters required in the learning process. In this paper we introduce a new method to build non-linear GEOs and non-linear Group Equivariant Non-Expansive Operators (GENEOs), based on the concepts of symmetric function and permutant. This method is particularly interesting because of the good theoretical properties of GENEOs and the ease of use of permutants to build equivariant operators, compared to the direct use of the equivariance groups we are interested in. In our paper, we prove that the technique we propose works for any symmetric function, and benefits from the approximability of continuous symmetric functions by symmetric polynomials. A possible use in Topological Data Analysis of the GENEOs obtained by this new method is illustrated.

Interpretable machine learning for genomics

High-throughput technologies such as next-generation sequencing allow biologists to observe cell function with unprecedented resolution, but the resulting datasets are too large and complicated for humans to understand without the aid of advanced statistical methods. Machine learning (ML) algorithms, which are designed to automatically find patterns in data, are well suited to this task. Yet these models are often so complex as to be opaque, leaving researchers with few clues about underlying mechanisms. Interpretable machine learning (iML) is a burgeoning subdiscipline of computational statistics devoted to making the predictions of ML models more intelligible to end users. This article is a gentle and critical introduction to iML, with an emphasis on genomic applications. I define relevant concepts, motivate leading methodologies, and provide a simple typology of existing approaches. I survey recent examples of iML in genomics, demonstrating how such techniques are increasingly integrated into research workflows. I argue that iML solutions are required to realize the promise of precision medicine. However, several open challenges remain. I examine the limitations of current state-of-the-art tools and propose a number of directions for future research. While the horizon for iML in genomics is wide and bright, continued progress requires close collaboration across disciplines.

Interpreting machine learning models to investigate circadian regulation and facilitate exploration of clock function

The circadian clock is an internal molecular 24-h timer that is critical to life on Earth. We describe a series of artificial intelligence (AI)– and machine learning (ML)–based approaches that enable more cost-effective analysis and insight into circadian regulation and function. Throughout the manuscript, we illuminate what is inside the ML “black box” via explanation or interpretation of predictive ML models. Using this interpretation of our models, we derive biological insights into why a prediction was made, alongside accurate predictions. Most innovatively, we use only DNA sequence features for accurate circadian gene expression prediction. Using explainable AI, we define possible, responsible regulatory elements as we make these predictions; this critically requires no prior knowledge of regulatory elements.

The circadian clock is an important adaptation to life on Earth. Here, we use machine learning to predict complex, temporal, and circadian gene expression patterns in Arabidopsis. Most significantly, we classify circadian genes using DNA sequence features generated de novo from public, genomic resources, facilitating downstream application of our methods with no experimental work or prior knowledge needed. We use local model explanation that is transcript specific to rank DNA sequence features, providing a detailed profile of the potential circadian regulatory mechanisms for each transcript. Furthermore, we can discriminate the temporal phase of transcript expression using the local, explanation-derived, and ranked DNA sequence features, revealing hidden subclasses within the circadian class. Model interpretation/explanation provides the backbone of our methodological advances, giving insight into biological processes and experimental design. Next, we use model interpretation to optimize sampling strategies when we predict circadian transcripts using reduced numbers of transcriptomic timepoints. Finally, we predict the circadian time from a single, transcriptomic timepoint, deriving marker transcripts that are most impactful for accurate prediction; this could facilitate the identification of altered clock function from existing datasets.

Predicting drug-microbiome interactions with machine learning

Pivotal work in recent years has cast light on the importance of the human microbiome in maintenance of health and physiological response to drugs. It is now clear that gastrointestinal microbiota have the metabolic power to promote, inactivate, or even toxify the efficacy of a drug to a level of clinically relevant significance. At the same time, it appears that drug intake has the propensity to alter gut microbiome composition, potentially affecting health and response to other drugs. Since the precise composition of an individual's microbiome is unique, one's drug-microbiome relationship is similarly unique. Thus, in the age of evermore personalised medicine, the ability to predict individuals' drug-microbiome interactions is highly sought. Machine learning (ML) offers a powerful toolkit capable of characterising and predicting drug-microbiota interactions at the individual patient level. ML techniques have the potential to learn the mechanisms operating drug-microbiome activities and measure patients' risk of such occurrences. This review will outline current knowledge at the drug-microbiota interface, and present ML as a technique for examining and forecasting personalised drug-microbiome interactions. When harnessed effectively, ML could alter how the pharmaceutical industry and healthcare professionals consider the drug-microbiome axis in patient care.

Explaining multivariate molecular diagnostic tests via Shapley values

Background

Machine learning (ML) can be an effective tool to extract information from attribute-rich molecular datasets for the generation of molecular diagnostic tests. However, the way in which the resulting scores or classifications are produced from the input data may not be transparent. Algorithmic explainability or interpretability has become a focus of ML research. Shapley values, first introduced in game theory, can provide explanations of the result generated from a specific set of input data by a complex ML algorithm.

Methods

For a multivariate molecular diagnostic test in clinical use (the VeriStrat® test), we calculate and discuss the interpretation of exact Shapley values. We also employ some standard approximation techniques for Shapley value computation (local interpretable model-agnostic explanation (LIME) and Shapley Additive Explanations (SHAP) based methods) and compare the results with exact Shapley values.

Results

Exact Shapley values calculated for data collected from a cohort of 256 patients showed that the relative importance of attributes for test classification varied by sample. While all eight features used in the VeriStrat® test contributed equally to classification for some samples, other samples showed more complex patterns of attribute importance for classification generation. Exact Shapley values and Shapley-based interaction metrics were able to provide interpretable classification explanations at the sample or patient level, while patient subgroups could be defined by comparing Shapley value profiles between patients. LIME and SHAP approximation approaches, even those seeking to include correlations between attributes, produced results that were quantitatively and, in some cases qualitatively, different from the exact Shapley values.

Conclusions

Shapley values can be used to determine the relative importance of input attributes to the result generated by a multivariate molecular diagnostic test for an individual sample or patient. Patient subgroups defined by Shapley value profiles may motivate translational research. However, correlations inherent in molecular data and the typically small ML training sets available for molecular diagnostic test development may cause some approximation methods to produce approximate Shapley values that differ both qualitatively and quantitatively from exact Shapley values. Hence, caution is advised when using approximate methods to evaluate Shapley explanations of the results of molecular diagnostic tests.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12911-021-01569-9.

In-vivo impact of common cosmetic preservative systems in full formulation on the skin microbiome

Preservatives play an essentially role in ensuring that cosmetic formulations remain safe for use via control of microbial contamination. Commonly used preservatives include organic acids, alcohols and phenols and these play an essential role in controlling the growth of bacteria, fungi and moulds in substrates that can potentially act as a rich food source for microbial contaminants. Whilst the activity of these compounds is clear, both in vitro and in formulation, little information exists on the potential impact that common preservative systems, in full formulation, have on the skin's resident microbiome. Dysbiosis of the skin's microbiome has been associated with a number of cosmetic conditions but there currently are no in vivo studies investigating the potential for preservative ingredients, when included in personal care formulations under normal use conditions, to impact the cutaneous microbiome. Here we present an analysis of four in vivo studies that examine the impact of different preservation systems in full formulation, in different products formats, with varying durations of application. This work demonstrates that despite the antimicrobial efficacy of the preservatives in vitro, the skin microbiome is not impacted by preservative containing products in vivo.

The Effects of Dietary Supplementation of Lactococcus lactis Strain Plasma on Skin Microbiome and Skin Conditions in Healthy Subjects-A Randomized, Double-Blind, Placebo-Controlled Trial

(1) Background: Lactococcus lactis strain Plasma (LC-Plasma) is a unique strain which directly activates plasmacytoid dendritic cells, resulting in the prevention against broad spectrum of viral infection. Additionally, we found that LC-Plasma intake stimulated skin immunity and prevents Staphylococcus aureus epicutaneous infection. The aim of this study was to investigate the effect of LC-Plasma dietary supplementation on skin microbiome, gene expression in the skin, and skin conditions in healthy subjects. (2) Method: A randomized, double-blind, placebo-controlled, parallel-group trial was conducted. Seventy healthy volunteers were enrolled and assigned into two groups receiving either placebo or LC-Plasma capsules (approximately 1 × 10¹¹ cells/day) for 8 weeks. The skin microbiome was analyzed by NGS and qPCR. Gene expression was analyzed by qPCR and skin conditions were diagnosed by dermatologists before and after intervention. (3) Result: LC-Plasma supplementation prevented the decrease of Staphylococcus epidermidis and Staphylococcus pasteuri and overgrowth of Propionibacterium acnes. In addition, LC-Plasma supplementation suggested to increase the expression of antimicrobial peptide genes but not tight junction genes. Furthermore, the clinical scores of skin conditions were ameliorated by LC-Plasma supplementation. (4) Conclusions: Our findings provided the insights that the dietary supplementation of LC-Plasma might have stabilizing effects on seasonal change of skin microbiome and skin conditions in healthy subjects.