Decoding gut microbiota by imaging analysis of fecal samples

AI for rapid identification of major butyrate-producing bacteria in rhesus macaques (Macaca mulatta)

BACKGROUND

The gut microbiome plays a crucial role in health and disease, influencing digestion, metabolism, and immune function. Traditional microbiome analysis methods are often expensive, time-consuming, and require specialized expertise, limiting their practical application in clinical settings. Evolving artificial intelligence (AI) technologies present opportunities for developing alternative methods. However, the lack of transparency in these technologies limits the ability of clinicians to incorporate AI-driven diagnostic tools into their healthcare systems. The aim of this study was to investigate an AI approach that rapidly predicts different bacterial genera and bacterial groups, specifically butyrate producers, from digital images of fecal smears of rhesus macaques (Macaca mulatta). In addition, to improve transparency, we employed explainability analysis to uncover the image features influencing the model's predictions.

RESULTS

By integrating fecal image data with corresponding metagenomic sequencing information, the deep learning (DL) and machine learning (ML) algorithms successfully predicted 16 individual bacterial genera (area under the curve (AUC) > 0.7) among the 50 most abundant genera in rhesus macaques (Macaca mulatta). The model was successful in predicting functional groups, major butyrate producers (AUC 0.75) and a mixed group including fermenters and short-chain fatty acid (SCFA) producers (AUC 0.81). For both models of butyrate producers and mixed fermenters, the explainability experiments revealed no decline in the AUC when random noise was added to the images. Increased blurring led to a gradual decline in the AUC. The model's performance was robust against the impact of fecal shape from smearing, with a stable AUC maintained until patch 4 for all groups, as assessed through scrambling. No significant correlation was detected between the prediction probabilities and the total fecal weight used in the smear; r = 0.30 ± 0.3 (p > 0.1) and r = 0.04 ± 0.36 (p > 0.8) for the butyrate producers and mixed fermenters, respectively.

CONCLUSION

Our approach demonstrated the ability to predict a wide range of clinically relevant microbial genera and microbial groups in the gut microbiome based on digital images from a fecal smear. The models proved to be robust to the smearing method, random noise and the amount of fecal matter. This study introduces a rapid, non-invasive, and cost-effective method for microbiome profiling, with potential applications in veterinary diagnostics.

Gut microbiota as a potential therapeutic target for children with cerebral palsy and epilepsy

Gut microbiota (GM), the "second genome," exerts influence on human health by impacting brain function through the gut-brain axis. This interaction involves various mechanisms, including immune regulation, metabolites, and neuronal pathways. The application of the next-generation sequencing technology provides a revolutionary tool for the study of GM, which contributes to a deeper comprehension of the GM-host relationship. Children with cerebral palsy (CP), a common neurological disorder in children, are more likely to develop epilepsy, which can exacerbate CP symptoms, particularly those related to cognitive impairment and gastrointestinal tract, such as constipation. The current study identified specific changes in the GM of children with CP accompanied by epilepsy. Furthermore, both diet and oral microbiota have the potential to influence the composition of the GM. Interventions with probiotics and dietary fiber based on GM can improve constipation and cognition, and this approach may be a potential therapeutic strategy.

Gastrointestinal tract-based implicit measures for cognition, emotion and behavior

Implicit physiological measures such as heart rate and skin conductance convey information about someone's cognitive or affective state. Currently, gastrointestinal (GI) tract-based markers are not yet considered while both the organs involved as well as the microbiota populating the GI tract are bidirectionally connected to the brain and have a relation to emotion, cognition and behavior. This makes GI tract-based measures relevant and interesting, especially because the relation may be causal, and because they have a different timescale than current physiological measures. This perspective paper (1) presents the (mechanistic) involvement of the GI tract and its microbiota in emotion, cognition and behavior; (2) explores the added value of microbiome-based implicit measures as complementary to existing measures; and (3) sets the priorities to move forward. Five potential measures are proposed and discussed in more detail: bowel movement, short-chain fatty acids, tyrosine and tryptophan, GI tract flora composition, and cytokine levels. We conclude (1) that the involvement of the GI tract in emotion, cognition and behavior is undisputed, (2) that GI tract-based implicit measures are still in a conceptual phase of development but show potential and (3) that the first step to bring this field forward is to start validation studies in healthy humans and that are designed in the context of implicit measurements.

Deep Learning Encoding for Rapid Sequence Identification on Microbiome Data

We present a novel approach for rapidly identifying sequences that leverages the representational power of Deep Learning techniques and is applied to the analysis of microbiome data. The method involves the creation of a latent sequence space, training a convolutional neural network to rapidly identify sequences by mapping them into that space, and we leverage the novel encoded latent space for denoising to correct sequencing errors. Using mock bacterial communities of known composition, we show that this approach achieves single nucleotide resolution, generating results for sequence identification and abundance estimation that match the best available microbiome algorithms in terms of accuracy while vastly increasing the speed of accurate processing. We further show the ability of this approach to support phenotypic prediction at the sample level on an experimental data set for which the ground truth for sequence identities and abundances is unknown, but the expected phenotypes of the samples are definitive. Moreover, this approach offers a potential solution for the analysis of data from other types of experiments that currently rely on computationally intensive sequence identification.