Predicting microbiome compositions from species assemblages through deep learning

Biobased short chain fatty acid production - Exploring microbial community dynamics and metabolic networks through kinetic and microbial modeling approaches

In recent years, there has been growing interest in harnessing anaerobic digestion technology for resource recovery from waste streams. This approach has evolved beyond its traditional role in energy generation to encompass the production of valuable carboxylic acids, especially volatile fatty acids (VFAs) like acetic acid, propionic acid, and butyric acid. VFAs hold great potential for various industries and biobased applications due to their versatile properties. Despite increasing global demand, over 90% of VFAs are currently produced synthetically from petrochemicals. Realizing the potential of large-scale biobased VFA production from waste streams offers significant eco-friendly opportunities but comes with several key challenges. These include low VFA production yields, unstable acid compositions, complex and expensive purification methods, and post-processing needs. Among these, production yield and acid composition stand out as the most critical obstacles impacting economic viability and competitiveness. This paper seeks to offer a comprehensive view of combining complementary modeling approaches, including kinetic and microbial modeling, to understand the workings of microbial communities and metabolic pathways in VFA production, enhance production efficiency, and regulate acid profiles through the integration of omics and bioreactor data.

Deep learning methods in metagenomics: a review

The ever-decreasing cost of sequencing and the growing potential applications of metagenomics have led to an unprecedented surge in data generation. One of the most prevalent applications of metagenomics is the study of microbial environments, such as the human gut. The gut microbiome plays a crucial role in human health, providing vital information for patient diagnosis and prognosis. However, analysing metagenomic data remains challenging due to several factors, including reference catalogues, sparsity and compositionality. Deep learning (DL) enables novel and promising approaches that complement state-of-the-art microbiome pipelines. DL-based methods can address almost all aspects of microbiome analysis, including novel pathogen detection, sequence classification, patient stratification and disease prediction. Beyond generating predictive models, a key aspect of these methods is also their interpretability. This article reviews DL approaches in metagenomics, including convolutional networks, autoencoders and attention-based models. These methods aggregate contextualized data and pave the way for improved patient care and a better understanding of the microbiome's key role in our health.

Effects of operational parameters on bacterial communities in Hong Kong and global wastewater treatment plants

Wastewater treatment plants (WWTPs) are indispensable biotechnology facilities for modern cities and play an essential role in modern urban infrastructure by employing microorganisms to remove pollutants in wastewater, thus protecting public health and the environment. This study conducted a 13-month bacterial community survey of six full-scale WWTPs in Hong Kong with samples of influent, activated sludge (AS), and effluent to explore their synchronism and asynchronism of bacterial community. Besides, we compared AS results of six Hong Kong WWTPs with data from 1,186 AS amplicon data in 269 global WWTPs and a 9-year metagenomic sequencing survey of a Hong Kong WWTP. Our results showed the compositions of bacterial communities varied and the bacterial community structure of AS had obvious differences across Hong Kong WWTPs. The co-occurrence analysis identified 40 pairs of relationships that existed among Hong Kong WWTPs to show solid associations between two species and stochastic processes took large proportions for the bacterial community assembly of six WWTPs. The abundance and distribution of the functional bacteria in worldwide and Hong Kong WWTPs were examined and compared, and we found that ammonia-oxidizing bacteria had more diversity than nitrite-oxidizing bacteria. Besides, Hong Kong WWTPs could make great contributions to the genome mining of microbial dark matter in the global "wanted list." Operational parameters had important effects on OTUs' abundance, such as the temperature to the genera of Tetrasphaera, Gordonia and Nitrospira. All these results obtained from this study can deepen our understanding of the microbial ecology in WWTPs and provide foundations for further studies.

IMPORTANCE

Wastewater treatment plants (WWTPs) are an indispensable component of modern cities, as they can remove pollutants in wastewater to prevent anthropogenic activities. Activated sludge (AS) is a fundamental wastewater treatment process and it harbors a highly complex microbial community that forms the main components and contains functional groups. Unveiling "who is there" is a long-term goal of the research on AS microbiology. High-throughput sequencing provides insights into the inventory diversity of microbial communities to an unprecedented level of detail. At present, the analysis of communities in WWTPs usually comes from a specific WWTP and lacks comparisons and verification among different WWTPs. The wide-scale and long-term sampling project and research in this study could help us evaluate the AS community more accurately to find the similarities and different results for different WWTPs in Hong Kong and other regions of the world.

Data-driven prediction of colonization outcomes for complex microbial communities

Microbial interactions can lead to different colonization outcomes of exogenous species, be they pathogenic or beneficial in nature. Predicting the colonization of exogenous species in complex communities remains a fundamental challenge in microbial ecology, mainly due to our limited knowledge of the diverse mechanisms governing microbial dynamics. Here, we propose a data-driven approach independent of any dynamics model to predict colonization outcomes of exogenous species from the baseline compositions of microbial communities. We systematically validate this approach using synthetic data, finding that machine learning models can predict not only the binary colonization outcome but also the post-invasion steady-state abundance of the invading species. Then we conduct colonization experiments for commensal gut bacteria species Enterococcus faecium and Akkermansia muciniphila in hundreds of human stool-derived in vitro microbial communities, confirming that the data-driven approaches can predict the colonization outcomes in experiments. Furthermore, we find that while most resident species are predicted to have a weak negative impact on the colonization of exogenous species, strongly interacting species could significantly alter the colonization outcomes, e.g., Enterococcus faecalis inhibits the invasion of E. faecium invasion. The presented results suggest that the data-driven approaches are powerful tools to inform the ecology and management of microbial communities.

Learning beyond-pairwise interactions enables the bottom-up prediction of microbial community structure

Understanding the assembly of multispecies microbial communities represents a significant challenge in ecology and has wide applications in agriculture, wastewater treatment, and human healthcare domains. Traditionally, studies on the microbial community assembly focused on analyzing pairwise relationships among species; however, neglecting higher-order interactions, i.e., the change of pairwise relationships in the community context, may lead to substantial deviation from reality. Herein, we have proposed a simple framework that incorporates higher-order interactions into a bottom-up prediction of the microbial community assembly and examined its accuracy using a seven-member synthetic bacterial community on a host plant, duckweed. Although the synthetic community exhibited emergent properties that cannot be predicted from pairwise coculturing results, our results demonstrated that incorporating information from three-member combinations allows the acceptable prediction of the community structure and actual interaction forces within it. This reflects that the occurrence of higher-order effects follows consistent patterns, which can be predicted even from trio combinations, the smallest unit of higher-order interactions. These results highlight the possibility of predicting, explaining, and understanding the microbial community structure from the bottom-up by learning interspecies interactions from simple beyond-pairwise combinations.

Model-free prediction of microbiome compositions

BACKGROUND

The recent recognition of the importance of the microbiome to the host's health and well-being has yielded efforts to develop therapies that aim to shift the microbiome from a disease-associated state to a healthier one. Direct manipulation techniques of the species' assemblage are currently available, e.g., using probiotics or narrow-spectrum antibiotics to introduce or eliminate specific taxa. However, predicting the species' abundances at the new state remains a challenge, mainly due to the difficulties of deciphering the delicate underlying network of ecological interactions or constructing a predictive model for such complex ecosystems.

RESULTS

Here, we propose a model-free method to predict the species' abundances at the new steady state based on their presence/absence configuration by utilizing a multi-dimensional k-nearest-neighbors (kNN) regression algorithm. By analyzing data from numeric simulations of ecological dynamics, we show that our predictions, which consider the presence/absence of all species holistically, outperform both the null model that uses the statistics of each species independently and a predictive neural network model. We analyze real metagenomic data of human-associated microbial communities and find that by relying on a small number of "neighboring" samples, i.e., samples with similar species assemblage, the kNN predicts the species abundance better than the whole-cohort average. By studying both real metagenomic and simulated data, we show that the predictability of our method is tightly related to the dissimilarity-overlap relationship of the training data.

CONCLUSIONS

Our results demonstrate how model-free methods can prove useful in predicting microbial communities and may facilitate the development of microbial-based therapies. Video Abstract.

Identifying keystone species in microbial communities using deep learning

Previous studies suggested that microbial communities can harbour keystone species whose removal can cause a dramatic shift in microbiome structure and functioning. Yet, an efficient method to systematically identify keystone species in microbial communities is still lacking. Here we propose a data-driven keystone species identification (DKI) framework based on deep learning to resolve this challenge. Our key idea is to implicitly learn the assembly rules of microbial communities from a particular habitat by training a deep-learning model using microbiome samples collected from this habitat. The well-trained deep-learning model enables us to quantify the community-specific keystoneness of each species in any microbiome sample from this habitat by conducting a thought experiment on species removal. We systematically validated this DKI framework using synthetic data and applied DKI to analyse real data. We found that those taxa with high median keystoneness across different communities display strong community specificity. The presented DKI framework demonstrates the power of machine learning in tackling a fundamental problem in community ecology, paving the way for the data-driven management of complex microbial communities.

Sparsity of higher-order landscape interactions enables learning and prediction for microbiomes

Microbiome engineering offers the potential to leverage microbial communities to improve outcomes in human health, agriculture, and climate. To translate this potential into reality, it is crucial to reliably predict community composition and function. But a brute force approach to cataloging community function is hindered by the combinatorial explosion in the number of ways we can combine microbial species. An alternative is to parameterize microbial community outcomes using simplified, mechanistic models, and then extrapolate these models beyond where we have sampled. But these approaches remain data-hungry, as well as requiring an a priori specification of what kinds of mechanisms are included and which are omitted. Here, we resolve both issues by introducing a mechanism-agnostic approach to predicting microbial community compositions and functions using limited data. The critical step is the identification of a sparse representation of the community landscape. We then leverage this sparsity to predict community compositions and functions, drawing from techniques in compressive sensing. We validate this approach on in silico community data, generated from a theoretical model. By sampling just [Formula: see text]1% of all possible communities, we accurately predict community compositions out of sample. We then demonstrate the real-world application of our approach by applying it to four experimental datasets and showing that we can recover interpretable, accurate predictions on composition and community function from highly limited data.

Microbial community assembly and functional profiles along the soil-root continuum of salt-tolerant Suaeda glauca and Suaeda salsa

Developing and planting salt-tolerant plants has become a promising way to utilize saline-alkali land resources and ensure food security. Root-associated microbes of salt-tolerant plants have been shown to promote plant growth and alleviate high salt stress, yet very little is known about the salt resistance mechanisms of core microbes in different niches. This study characterized the microbial community structures, assembly processes, and functional profiles in four root-related compartments of two salt-tolerant plants by amplicon and shotgun metagenomic sequencing. The results showed that both plants significantly altered the microbial community structure of saline soils, with greater microbial alpha diversity in the rhizosphere or rhizoplane compared with bulk soils. Stochastic process dominated the microbial assembly processes, and the impact was stronger in Suaeda salsa than in S. glauca, indicating that S. salsa may have stronger resistance abilities to changing soil properties. Keystone species, such as Pseudomonas in the endosphere of S. glauca and Sphingomonas in the endosphere of S. salsa, which may play key roles in helping plants alleviate salt stress, were identified by using microbial co-occurrence network analysis. Furthermore, the microbiomes in the rhizoplane soils had more abundant genes involved in promoting growth of plants and defending against salt stress than those in bulk soils, especially in salt-tolerant S. salsa. Moreover, microbes in the rhizoplane of S. salsa exhibited higher functional diversities, with notable enrichment of genes involved in carbon fixation, dissimilar nitrate reduction to ammonium, and sulfite oxidation. These findings revealed differences and similarities in the microbial community assembly, functional profiles and keystone species closely related to salt alleviation of the two salt-tolerant plants. Overall, our study provides new insights into the ecological functions and varied strategies of rhizosphere microbes in different plants under salt stress and highlights the potential use of keystone microbes for enhancing salt resistance of plants.

Assembly archetypes in ecological communities

An instrumental discovery in comparative and developmental biology is the existence of assembly archetypes that synthesize the vast diversity of organisms' body plans-from legs and wings to human arms-into simple, interpretable and general design principles. Here, we combine a novel mathematical formalism based on category theory with experimental data to show that similar 'assembly archetypes' exist at the larger organization scale of ecological communities when assembling a species pool across diverse environmental contexts, particularly when species interactions are highly structured. We applied our formalism to clinical data discovering two assembly archetypes that differentiate between healthy and unhealthy human gut microbiota. The concept of assembly archetypes and the methods to synthesize them can pave the way to discovering the general assembly principles of the ecological communities we observe in nature.

Data-driven prediction of colonization outcomes for complex microbial communities

Complex microbial interactions can lead to different colonization outcomes of exogenous species, be they pathogenic or beneficial in nature. Predicting the colonization of exogenous species in complex communities remains a fundamental challenge in microbial ecology, mainly due to our limited knowledge of the diverse physical, biochemical, and ecological processes governing microbial dynamics. Here, we proposed a data-driven approach independent of any dynamics model to predict colonization outcomes of exogenous species from the baseline compositions of microbial communities. We systematically validated this approach using synthetic data, finding that machine learning models (including Random Forest and neural ODE) can predict not only the binary colonization outcome but also the post-invasion steady-state abundance of the invading species. Then we conducted colonization experiments for two commensal gut bacteria species Enterococcus faecium and Akkermansia muciniphila in hundreds of human stool-derived in vitro microbial communities, confirming that the data-driven approach can successfully predict the colonization outcomes. Furthermore, we found that while most resident species were predicted to have a weak negative impact on the colonization of exogenous species, strongly interacting species could significantly alter the colonization outcomes, e.g., the presence of Enterococcus faecalis inhibits the invasion of E. faecium . The presented results suggest that the data-driven approach is a powerful tool to inform the ecology and management of complex microbial communities.

Algal community structure prediction by machine learning

The algal community structure is vital for aquatic management. However, the complicated environmental and biological processes make modeling challenging. To cope with this difficulty, we investigated using random forests (RF) to predict phytoplankton community shifting based on multi-source environmental factors (including physicochemical, hydrological, and meteorological variables). The RF models robustly predicted the algal communities composed by 13 major classes (Bray-Curtis dissimilarity = 9.2 ± 7.0%, validation NRMSE mostly <10%), with accurate simulations to the total biomass (validation R² > 0.74) in Norway's largest lake, Lake Mjosa. The importance analysis showed that the hydro-meteorological variables (Standardized MSE and Node Purity mostly >0.5) were the most influential factors in regulating the phytoplankton. Furthermore, an in-depth ecological interpretation uncovered the interactive stress-response effect on the algal community learned by the RF models. The interpretation results disclosed that the environmental drivers (i.e., temperature, lake inflow, and nutrients) can jointly pose strong influence on the algal community shifts. This study highlighted the power of machine learning in predicting complex algal community structures and provided insights into the model interpretability.

Identifying keystone species in microbial communities using deep learning

Previous studies suggested that microbial communities harbor keystone species whose removal can cause a dramatic shift in microbiome structure and functioning. Yet, an efficient method to systematically identify keystone species in microbial communities is still lacking. This is mainly due to our limited knowledge of microbial dynamics and the experimental and ethical difficulties of manipulating microbial communities. Here, we propose a Data-driven Keystone species Identification (DKI) framework based on deep learning to resolve this challenge. Our key idea is to implicitly learn the assembly rules of microbial communities from a particular habitat by training a deep learning model using microbiome samples collected from this habitat. The well-trained deep learning model enables us to quantify the community-specific keystoneness of each species in any microbiome sample from this habitat by conducting a thought experiment on species removal. We systematically validated this DKI framework using synthetic data generated from a classical population dynamics model in community ecology. We then applied DKI to analyze human gut, oral microbiome, soil, and coral microbiome data. We found that those taxa with high median keystoneness across different communities display strong community specificity, and many of them have been reported as keystone taxa in literature. The presented DKI framework demonstrates the power of machine learning in tackling a fundamental problem in community ecology, paving the way for the data-driven management of complex microbial communities.

Interactions between Culturable Bacteria Are Predicted by Individual Species' Growth

Predicting interspecies interactions is a key challenge in microbial ecology given that interactions shape the composition and functioning of microbial communities. However, predicting microbial interactions is challenging because they can vary considerably depending on species' metabolic capabilities and environmental conditions. Here, we employ machine learning models to predict pairwise interactions between culturable bacteria based on their phylogeny, monoculture growth capabilities, and interactions with other species. We trained our models on one of the largest available pairwise interactions data set containing over 7,500 interactions between 20 species from two taxonomic groups that were cocultured in 40 different carbon environments. Our models accurately predicted both the sign (accuracy of 88%) and the strength of effects (R² of 0.87) species had on each other's growth. Encouragingly, predictions with comparable accuracy could be made even when not relying on information about interactions with other species, which are often hard to measure. However, species' monoculture growth was essential to the model, as predictions based solely on species' phylogeny and inferred metabolic capabilities were significantly less accurate. These results bring us one step closer to a predictive understanding of microbial communities, which is essential for engineering beneficial microbial consortia. IMPORTANCE In order to understand the function and structure of microbial communities, one must know all pairwise interactions that occur between the different species within the community, as these interactions shape the community's structure and functioning. However, measuring all pairwise interactions can be an extremely difficult task especially when dealing with big complex communities. Because of that, predicting interspecies interactions is a key challenge in microbial ecology. Here, we use machine learning models in order to accurately predict the type and strength of interactions. We trained our models on one of the largest available pairwise interactions data set, containing over 7,500 interactions between 20 different species that were cocultured in 40 different environments. Our results show that, in general, accurate predictions can be made, and that the ability of each species to grow on its own in the given environment contributes the most to predictions. Being able to predict microbial interactions would put us one step closer to predicting the functionality of microbial communities and to rationally microbiome engineering.

Metagenomic and machine learning-aided identification of biomarkers driving distinctive Cd accumulation features in the root-associated microbiome of two rice cultivars

Developing low-cadmium (Cd) rice cultivars has emerged as a promising avenue for food safety in Cd-contaminated farmlands. The root-associated microbiomes of rice have been shown to enhance rice growth and alleviate Cd stress. However, the microbial taxon-specific Cd resistance mechanisms underlying different Cd accumulation characteristics between different rice cultivars remain largely unknown. This study compared low-Cd cultivar XS14 and hybrid rice cultivar YY17 for Cd accumulation with five soil amendments. The results showed that XS14 was characterized by more variable community structures and stable co-occurrence networks in the soil-root continuum compared to YY17. The stronger stochastic processes in assembly of the XS14 (~25%) rhizosphere community than that of YY17 (~12%) suggested XS14 may have higher resistance to changes in soil properties. Microbial co-occurrence networks and machine learning models jointly identified keystone indicator microbiota, such as Desulfobacteria in XS14 and Nitrospiraceae in YY17. Meanwhile, genes involved in sulfur cycling and nitrogen cycling were observed among the root-associated microbiome of these two cultivars, respectively. Microbiomes in the rhizosphere and root of XS14 showed a higher diversity in functioning, with the significant enrichment of functional genes related to amino acid and carbohydrate transport and metabolism, and sulfur cycling. Our findings revealed differences and similarities in the microbial communities associated with two rice cultivars, as well as bacterial biomarkers predictive of Cd-accumulation capacity. Thus, we provide new insights into taxon-specific recruitment strategies of two rice cultivars under Cd stress and highlight the utility of biomarkers in offering clues for enhancing crop resilience to Cd stresses in the future.

Controlling the human microbiome

We coexist with a vast number of microbes that live in and on our bodies. Those microbes and their genes are collectively known as the human microbiome, which plays important roles in human physiology and diseases. We have acquired extensive knowledge of the organismal compositions and metabolic functions of the human microbiome. However, the ultimate proof of our understanding of the human microbiome is reflected in our ability to manipulate it for health benefits. To facilitate the rational design of microbiome-based therapies, there are many fundamental questions to be addressed at the systems level. Indeed, we need a deep understanding of the ecological dynamics associated with such a complex ecosystem before we rationally design control strategies. In light of this, this review discusses progress from various fields, e.g., community ecology, network science, and control theory, that are helping us make progress toward the ultimate goal of controlling the human microbiome.

BiGAMi: Bi-Objective Genetic Algorithm Fitness Function for Feature Selection on Microbiome Datasets

The relationship between the host and the microbiome, or the assemblage of microorganisms (including bacteria, archaea, fungi, and viruses), has been proven crucial for its health and disease development. The high dimensionality of microbiome datasets has often been addressed as a major difficulty for data analysis, such as the use of machine-learning (ML) and deep-learning (DL) models. Here, we present BiGAMi, a bi-objective genetic algorithm fitness function for feature selection in microbial datasets to train high-performing phenotype classifiers. The proposed fitness function allowed us to build classifiers that outperformed the baseline performance estimated by the original studies by using as few as 0.04% to 2.32% features of the original dataset. In 35 out of 42 performance comparisons between BiGAMi and other feature selection methods evaluated here (sequential forward selection, SelectKBest, and GARS), BiGAMi achieved its results by selecting 6–93% fewer features. This study showed that the application of a bi-objective GA fitness function against microbiome datasets succeeded in selecting small subsets of bacteria whose contribution to understood diseases and the host state was already experimentally proven. Applying this feature selection approach to novel diseases is expected to quickly reveal the microbes most relevant to a specific condition.

iMeta: Integrated meta-omics for biology and environments

The cover of iMeta's inaugural issue. The galaxy represents the complexity and value of bioinformatics and metagenomics. DNA, which represents genetic components that guide biological diversity, is at the center of the galaxy. The spiral arms are the microbiome welcoming scientists from all over the world to make novel discoveries. Let us usher in the metaverse era of the microbiome.