Oral microbiome-systemic link studies: perspectives on current limitations and future artificial intelligence-based approaches

Non-Targeted RNA Sequencing: Towards the Development of Universal Clinical Diagnosis Methods for Human and Veterinary Infectious Diseases

Metagenomics offers the potential to replace and simplify classical methods used in the clinical diagnosis of human and veterinary infectious diseases. Metagenomics boasts a high pathogen discovery rate and high specificity, advantages absent in most classical approaches. However, its widespread adoption in clinical settings is still pending, with a slow transition from research to routine use. While longer turnaround times and higher costs were once concerns, these issues are currently being addressed by automation, better chemistries, improved sequencing platforms, better databases, and automated bioinformatics analysis. However, many technical options and steps, each producing highly variable outcomes, have reduced the technology's operational value, discouraging its implementation in diagnostic labs. We present a case for utilizing non-targeted RNA sequencing (NT-RNA-seq) as an ideal metagenomics method for the detection of infectious disease-causing agents in humans and animals. Additionally, to create operational value, we propose to identify best practices for the "core" of steps that are invariably shared among many human and veterinary protocols. Reference materials, sequencing procedures, and bioinformatics standards should accelerate the validation processes necessary for the widespread adoption of this technology. Best practices could be determined through "implementation research" by a consortium of interested institutions working on common samples.

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.

Improved diagnosis of rheumatoid arthritis using an artificial neural network

Rheumatoid arthritis (RA) is chronic systemic disease that can cause joint damage, disability and destructive polyarthritis. Current diagnosis of RA is based on a combination of clinical and laboratory features. However, RA diagnosis can be difficult at its disease onset on account of overlapping symptoms with other arthritis, so early recognition and diagnosis of RA permit the better management of patients. In order to improve the medical diagnosis of RA and evaluate the effects of different clinical features on RA diagnosis, we applied an artificial neural network (ANN) as the training algorithm, and used fivefold cross-validation to evaluate its performance. From each sample, we obtained data on 6 features: age, sex, rheumatoid factor, anti-citrullinated peptide antibody (CCP), 14-3-3η, and anti-carbamylated protein (CarP) antibodies. After training, this ANN model assigned each sample a probability for being either an RA patient or a non-RA patient. On the validation dataset, the F1 for all samples by this ANN model was 0.916, which was higher than the 0.906 we previously reported using an optimal threshold algorithm. Therefore, this ANN algorithm not only improved the accuracy of RA diagnosis, but also revealed that anti-CCP had the greatest effect while age and anti-CarP had a weaker on RA diagnosis.

Oral Fungal Infections: Past, Present, and Future

Oral fungal infections have afflicted humans for millennia. Hippocrates (ca. 460-370 BCE) described two cases of oral aphthae associated with severe underlying diseases that could well have been oral candidiasis. While oral infections caused by other fungi such as cryptococcosis, aspergillosis, mucormycosis, histoplasmosis, blastomycosis, and coccidioidomycosis occur infrequently, oral candidiasis came to the fore during the AIDS epidemic as a sentinel opportunistic infection signaling the transition from HIV infection to AIDS. The incidence of candidiasis in immunocompromised AIDS patients highlighted the importance of host defenses in preventing oral fungal infections. A greater understanding of the nuances of human immune systems has revealed that mucosal immunity in the mouth delivers a unique response to fungal pathogens. Oral fungal infection does not depend solely on the fungus and the host, however, and attention has now focussed on interactions with other members of the oral microbiome. It is evident that there is inter-kingdom signaling that affects microbial pathogenicity. The last decade has seen significant advances in the rapid qualitative and quantitative analysis of oral microbiomes and in the simultaneous quantification of immune cells and cytokines. The time is ripe for the application of machine learning and artificial intelligence to integrate more refined analyses of oral microbiome composition (including fungi, bacteria, archaea, protozoa and viruses—including SARS-CoV-2 that causes COVID-19). This analysis should incorporate the quantification of immune cells, cytokines, and microbial cell signaling molecules with signs of oral fungal infections in order to better diagnose and predict susceptibility to oral fungal disease.

Is There a Link between COVID-19 Infection, Periodontal Disease and Acute Myocardial Infarction?

Both periodontal disease and atherosclerosis are chronic disorders with an inflammatory substrate that leads to alteration of the host's immune response. In PD, inflammation is responsible for bone tissue destruction, while in atherosclerosis, it leads to atheromatous plaque formation. These modifications result from the action of pro-inflammatory cytokines that are secreted both locally at gingival or coronary sites, and systemically. Recently, it was observed that in patients with PD or with cardiovascular disease, COVID-19 infection is prone to be more severe. While the association between PD, inflammation and cardiovascular disease is well-known, the impact of COVID-19-related inflammation on the systemic complications of these conditions has not been established yet. The purpose of this review is to bring light upon the latest advances in understanding the link between periodontal-cardiovascular diseases and COVID-19 infection.

Predicting Treatment Nonresponse in Hispanic/Latino Children Receiving Silver Diamine Fluoride for Caries Arrest: A Pilot Study Using Machine Learning

Objectives: Silver diamine fluoride (SDF) is a nonsurgical therapy for the arrest and prevention of dental caries with demonstrated clinical efficacy. Approximately 20% of children receiving SDF fail to respond to treatment. The objective of this study was to develop a predictive model of treatment non-response using machine learning. Methods: An observational pilot study (N = 20) consisting of children with and without active decay and who did and did not respond to silver diamine fluoride provided salivary samples and plaque from infected and contralateral sites. 16S rRNA genes from samples were amplified and sequenced on an Illumina Miseq and analyzed using QIIME. The association between operational taxonomic units and treatment non-response was assessed using lasso regression and artificial neural networks. Results: Bivariate group comparisons of bacterial abundance indicate a number of genera were significantly different between non-responders and those who responded to SDF therapy. No differences were found between non-responders and caries-active subjects. Prevotella pallens and Veillonella denticariosi were retained in full lasso models and combined with clinical variables in a six-input multilayer perceptron. Discussion: The acidogenic and acid-tolerant nature of retained bacterial species may overcome the antimicrobial effects of SDF. Further research to validate the model in larger external samples is needed.

The oral microbiome in early rheumatoid arthritis patients and individuals at risk differs from healthy controls

OBJECTIVE

It has been suggested that rheumatoid arthritis (RA) may originate at the oral mucosa. Our aim was to assess the oral microbiome and the periodontal condition in patients with early rheumatoid arthritis (ERA) and individuals at risk of RA.

METHODS

Three groups were recruited (50 participants each): (1) ERA patients (2010 ACR/EULAR criteria), (2) at-risk individuals (arthralgia and autoantibodies), and (3) healthy controls. A periodontal examination resulted in scores for bleeding on probing (BOP), pocket probing depth (PPD), and periodontal inflamed surface area (PISA). The microbial composition of subgingival dental plaque, saliva, and tongue coating was assessed using 16S rDNA amplicon sequencing, and compared between groups with permutational multivariate analyses of variance (PERMANOVA).

RESULTS

There was no difference between the groups on the periodontal variables (BOP p=0.70; PPD p=0.30; PISA p=0.56). PERMANOVA showed a difference between the groups in the microbial composition of saliva (F=2.08, p<0.001) and tongue coating (F=2.04, p=0.008), but not plaque (p=0.51). Post-hoc tests showed no difference between the ERA group and at-risk group (saliva F=1.12, p=0.28; tongue coating F=0.834, p=0.59). Discriminative zero-radius operational taxonomic units (zOTUs) were identified: in ERA patients and at-risk individuals, Prevotella in saliva and Veillonella in saliva and tongue coating were at higher relative abundance compared to healthy controls.

CONCLUSION

The results show similarities in the oral microbiome between ERA patients and at-risk individuals, both presenting with increased relative abundance of potentially pro-inflammatory species compared to healthy controls, suggesting a possible association between the oral microbiome and RA onset.

Future directions for studying resilience of the oral ecosystem

The oral ecosystem is shaped by complex interactions between systemic health disease and the resident oral microbiota. Research in the last two decades has produced datasets describing the genetics and physiology of the host and the oral microbiome in health and disease. There are inter-individual differences in the ability to tolerate oral disease-promoting challenges. Identification of the key factors that drive a healthy and resilient oral ecosystem is urgently needed. So far, progress is being made towards replicating the host-microbiota interplay in vitro. Clinical studies may shed light on the mechanisms of oral health resilience. However, most clinical studies are cross-sectional and are insufficient for understanding resilience or for identifying biomarkers that correlate with the point of transition from oral health to dysbiosis. Mathematical and computational models, including artificial intelligence approaches, offer an opportunity to inform the design of clinical studies by identifying key biomarkers and interaction networks in complex datasets and predicting important parameters. This paper discusses some of the challenges and opportunities for understanding the biological basis of resilience of the oral ecosystem. It discusses the current status and challenges, and proposes a way forward to better understand resilience towards oral diseases.