Synthetic molecular communication (SMC) is a key enabler for future healthcare systems in which Internet of Bio-Nano-Things (IoBNT) devices facilitate the continuous monitoring of a patient's biochemical signals. To close the loop between sensing and actuation, both the detection and the generation of in-body molecular communication (MC) signals is key. However, generating signals inside the human body, e.g., via synthetic nanodevices, poses a challenge in SMC, due to technological obstacles as well as legal, safety, and ethical issues. Hence, this paper considers an SMC system in which signals are generated indirectly via the modulation of a natural in-body MC system, namely the gut-brain axis (GBA). Therapeutic GBA modulation is already established as treatment for neurological diseases, e.g., drug refractory epilepsy (DRE), and performed via the administration of nutritional supplements or specific diets. However, the molecular signaling pathways that mediate the effect of such treatments are mostly unknown. Consequently, existing treatments are standardized or designed heuristically and able to help only some patients while failing to help others. In this paper, we propose to leverage personal health data, e.g., gathered by in-body IoBNT devices, to design more versatile and robust GBA modulation-based treatments as compared to the existing ones. To show the feasibility of our approach, we define a catalog of theoretical requirements for therapeutic GBA modulation. Then, we propose a machine learning model to verify these requirements for practical scenarios when only limited data on the GBA modulation exists. By evaluating the proposed model on several datasets, we confirm its excellent accuracy in identifying different modulators of the GBA. Finally, we utilize the proposed model to identify specific modulatory pathways that play an important role for therapeutic GBA modulation.

Analyzing high-dimensional count data is a challenge and statistical model-based approaches provide an adequate and efficient framework that preserves explainability. The (multivariate) Poisson-Log-Normal (PLN) model is one such model: it assumes count data are driven by an underlying structured latent Gaussian variable, so that the dependencies between counts solely stems from the latent dependencies. However PLN doesn't account for zero-inflation, a feature frequently observed in real-world datasets. Here we introduce the Zero-Inflated PLN (ZIPLN) model, adding a multivariate zero-inflated component to the model, as an additional Bernoulli latent variable. The Zero-Inflation can be fixed, site-specific, feature-specific or depends on covariates. We estimate model parameters using variational inference that scales up to datasets with a few thousands variables and compare two approximations: (i) independent Gaussian and Bernoulli variational distributions or (ii) Gaussian variational distribution conditioned on the Bernoulli one. The method is assessed on synthetic data and the efficiency of ZIPLN is established even when zero-inflation concerns up to $90\%$ of the observed counts. We then apply both ZIPLN and PLN to a cow microbiome dataset, containing $90.6\%$ of zeroes. Accounting for zero-inflation significantly increases log-likelihood and reduces dispersion in the latent space, thus leading to improved group discrimination.

Machine learning (ML) is set to accelerate innovations in clinical microbiomics, such as in disease diagnostics and prognostics. This will require high-quality, reproducible, interpretable workflows whose predictive capabilities meet or exceed the high thresholds set for clinical tools by regulatory agencies. Here, we capture a snapshot of current practices in the application of supervised ML to microbiomics data, through an in-depth analysis of 100 peer-reviewed journal articles published in 2021-2022. We apply a data-driven approach to steer discussion of the merits of varied approaches to experimental design, including key considerations such as how to mitigate the effects of small dataset size while avoiding data leakage. We further provide guidance on how to avoid common experimental design pitfalls that can hurt model performance, trustworthiness, and reproducibility. Discussion is accompanied by an interactive online tutorial that demonstrates foundational principles of ML experimental design, tailored to the microbiomics community. Formalizing community best practices for supervised ML in microbiomics is an important step towards improving the success and efficiency of clinical research, to the benefit of patients and other stakeholders.

"health resides in the overall organisation of the meta-organism that integrates the host and the microbiota". Let's see now the hallmarks of health by Carlos and Guido and some AI tolls that can help us stay healthy. We exist only because we have barriers (i.e. the intestinal, respiratory and cutaneous barrier) that shield us from our environment, and because we have subcellular, cellular and inter-cellular compartments, that they are allowing the formation of electrophysiological and chemical gradients at the level of organelles (i.e. It is this compartmentalisation in every living organism, a consequence of the reduction of entropy (the amount of entropy is a measure of the molecular disorder, or randomness, of a system), that is actually allowing the maintenance of health. Any alterations or deficiencies in the structural and/or regulatory components of the network just described, can cause severe skin pathologies.

Researchers have been using artificial intelligence to study how the microbiome interacts with the human system to improve vaccine response. A team of researchers at Iowa State University, US, are employing innovative artificial intelligence (AI) to investigate how the microbiome interacts with the immune system. The team, led by Dr Gregory Phillips, said that they are focusing on gut bacteria that have adapted to live in the human digestive system to improve vaccine response. We want to go beyond associations to get causes, something in the microbiota that influences the host whereby vaccines can be improved" The team are leading trials in mice monitoring changes in microbiota spurred by vaccine delivery and immune response. As the interactions they will be observing are so complex, the team have collaborated with Indiana University, US, to apply machine learning to find patterns in vast amounts of data.

The human microbiome consists of a community of trillions of micro-organisms, such as bacteria, fungi, viruses, and live all over the body including on the skin, in the mouth and along the digestive tract. A balanced microbiome is important for an individual's health and wellbeing, including proper functionality the digestive and immune systems. The human microbiome is constantly evolving and has been observed to change with age. The presence of unusually early microbiome aging patterns, relative to chronological age, could potentially signal altered susceptibility for age-related diseases. Conversely, a "young" microbiome might offer clues on how to decelerate the aging process1.

There are hundreds of trillions of microbes within the human body, which have a profound impact on modulating host function. Many of these microbes reside in the gastrointestinal tract and have been shown to influence normal physiology across all body systems ([ 1 ][1]). Disruptions in the delicate balance of microbes within the gut and other niches are associated with numerous disease states—including neurologic disorders, cardiovascular disease, gastrointestinal disorders, and even cancer ([ 2 ][2]). Accordingly, there is intense interest in targeting these microbes to promote overall health and to abrogate disease, with considerable advances made recently. Strategies to modulate gut microbes include fecal microbiota transplant (FMT), which involves the transfer of fecal material from one individual to another for a desired physiologic effect. This approach, among other gut microbiota modulation strategies, has shown promise in treating several disease conditions, although opportunities exist to iterate and build on these approaches. The idea that disruptions in the gastrointestinal tract could contribute to systemic disease was championed centuries ago by Hippocrates, a physician in ancient Greece. Strategies to modulate the composition of the gut have also been around for centuries, with the first reports of the use of FMT dating back to the fourth century BCE in China where fecal preparations were used to treat gastrointestinal disorders ([ 3 ][3]). Parallels have also been observed in the animal kingdom, where coprophagia (ingesting fecal material) is common and may confer an increase in gut microbial diversity and associated enhancements in host function for digestion and other physiologic processes. However, the first successful clinical application of FMT was not published until 1958 with the report of FMT from healthy donors used for patients with pseudomembranous enterocolitis from Clostridioides difficile infection (CDI) ([ 4 ][4]). Numerous clinical trials have since been undertaken, using FMT and other gut microbiota modulation strategies to treat diseases of the gut (such as CDI, and inflammatory bowel disease, IBD) as well as other systemic diseases—including metabolic syndrome, autism, multiple sclerosis, Parkinson's disease, and even cancer ([ 2 ][2]). ![Figure][5] Strategies to alter gut microbiota Fecal microbiota transplant (FMT) involves transfer of fecal microbiota from a donor to another individual . Alternatively, microbial consortia (targeted formulations used to augment host microbiota) are being developed. Diet, prebiotics, and postbiotics can also influence the microbial community. GRAPHIC: N. CARYI/ SCIENCE To date, many of the strategies to target gut microbes have involved the two extremes: either transfer of entire microbial communities (by using FMT) or transfer of a single microbial taxon. However, a growing number of approaches are now being developed as more is learned about the functional aspects and physiologic impact of microbes throughout the body. These iterative approaches transcend efforts that focus on taxonomic characterization of microbial niches through next-generation genomic sequencing, incorporating interrogation of functional characteristics of gut microbes (by metabolomic profiling and studies in preclinical models) to mediate the desired physiologic response. This has led to a host of therapeutic strategies from microbial consortia to pre-, pro-, and postbiotic interventions. Nonetheless, much still needs to be learned to implement true “precision” modulation of the gut microbiota. When considering strategies to modulate the gut microbiota, the indication for intervention in the intended population must be considered. Gut dysbiosis, an imbalance in the composition of commensal microbial communities, has been linked to numerous disease states, substantiating the use of FMT and other gut microbiota modulation strategies ([ 5 ][6]). This link is fortified by data demonstrating that although there has been a decrease in infectious diseases over the past several decades with the widespread use of antibiotics, there has been a concurrent increase in allergy and autoimmune diseases ([ 6 ][7]) presumably at least partially due to disruption of the gut microbiota. Notably, some of the diseases being treated by gut microbiota modulation have a profound dysbiosis (such as CDI), whereas others have a more subtle disruption of gut microbes, which has implications for choosing the appropriate strategy for gut microbiota modulation. Numerous other factors should be taken into account when contemplating modulation of the gut microbiota. These include the means of gut microbiota modulation, preparative regimen, measurement of engraftment of gut microbes and of the desired physiologic effect, and concurrent dietary intake ([ 7 ][8]). In general, the approach aims to restore a more “healthy” gut microbial community—although the definition of a “healthy” gut microbiota is not clearly established. However, data suggest that a diverse microbial community with a high degree of functional redundancy is associated with better overall health ([ 2 ][2]) and better outcomes in several disease states ([ 8 ][9], [ 9 ][10]). The most successful application of FMT thus far is in the treatment of refractory CDI, where treatment with FMT has been shown to be generally safe and highly effective ([ 2 ][2]). Nonetheless, guidelines for proper treatment and screening of donor stool are critical for safety and include screening for infectious diseases and disorders that are associated with perturbations of the gut microbiota, as well as the use of medications that can affect gut microbes such as antibiotics and proton pump inhibitors ([ 10 ][11]). Notably, these guidelines are iterative, as new recommendations are made to expand screening and testing of donors based on insights gained from ongoing trials. For example, screening of donors for multidrug-resistant organisms and severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is now recommended. This follows reports of several patients with CDI who developed systemic infection with antibiotic-resistant bacterial infections following FMT ([ 11 ][12]), as well as concerns about possible infections with SARS-CoV-2. The use of FMT is being investigated across numerous other disease conditions, although most of these are associated with a less profound dysbiosis and greater heterogeneity in assessed endpoints and outcomes. However, there is clear evidence of success in some trials across a number of indications, including IBD, after hematopoietic stem cell transplant and in autism spectrum disorders ([ 5 ][6]). Limitations in measuring efficacy in FMT trials may arise from “true negative” results, or from numerous other confounding factors, including features not dependent on gut microbes that contribute to the development and persistence of disease in the recipient, as well as variability in trial design and outcome measures. Additionally, there may be factors inherent to the FMT donor that may affect efficacy (such as composition and functional aspects of the transplanted microbiota); however, such “donor effects” may be less prominent for indications in which a more profound dysbiosis is present, such as in CDI and even IBD ([ 12 ][13]). Optimal dosing and route of delivery for FMT are also incompletely understood and may be context dependent. Additional studies are critically needed to interrogate the success (or failure) of this approach for these indications and to develop optimal strategies for use of FMT. One attribute of FMT not possessed by other strategies to modulate the gut microbiota is the diversity of microbes that may be administered (including not only bacteria, but also viruses, fungi, and archaea) (see the figure). This provides potential functional redundancy for favorable impact on host physiology. In a profoundly dysbiotic state, this diversity represents a potential advantage over strategies that administer minimal-complexity microbial consortia, which may not engraft and may not be sufficient in reestablishing a “favorable” gut microbiota. However, the same attribute of increased diversity and complexity of FMT is also a limitation that creates issues with reproducibility and scalability. There are also concerted efforts under way to develop consortia of microbes that can be reliably and consistently manufactured and administered to favorably modulate the gut microbiota to address gastrointestinal and systemic disease, offering improved scalability over FMT. This includes commercially available probiotics, which are live microorganism preparations with presumed health benefits. The impact of administration of many of these formulations across disease indications has been studied in clinical trials with mixed results, and to date none of these commercially available formulations are approved for use by major regulatory bodies such as the U.S. Food and Drug Administration ([ 13 ][14]). However, next-generation live biotherapeutics (live microorganisms developed as therapeutic agents with defined clinical benefit claims) are now being developed based on insights gained from sequencing data in human cohorts and from studies in preclinical models ([ 13 ][14])—with many now in clinical trials. The first wave of these next-generation live biotherapeutics focused mainly on taxonomy—incorporating single or several bacterial taxa within a consortia based on insights gained from profiling gut microbial species in human cohort studies and in preclinical models. An example of this is in cancer immunotherapy: Clinical trials are now under way using modulation of the gut microbiota through administration of microbial consortia ([ 7 ][8]). These formulations range from simple (monoclonal microbial formulations) to complex (involving consortia of 50 or more bacterial taxa and strains). However, there is a growing appreciation that focusing on the functional aspects of these microbes may be far more important than simply focusing on taxonomy, and genetically modified organisms are now being developed with a wide range of functional attributes ([ 13 ][14]). Although overall these formulations are generally well-tolerated, safety still needs to be taken into account because there are reports of bacterial translocation of these organisms from the gut into the bloodstream in critically ill patients receiving gut microbiota modulation through administration of commercially available probiotics ([ 14 ][15]). Another strong consideration in gut microbiota modulation is the role of diet and prebiotics, as these can profoundly influence existing commensal gut microbes and those administered for therapeutic intent. These may ultimately serve as a stand-alone intervention in appropriate individuals with more subtle gut dysbiosis. Short-term studies have shown that large changes in diet can have a marked impact on gut microbes and associated physiology in the short term ([ 15 ][16]). However, this reliably reverts to a preintervention state if the instituted change in diet is not sustained. Nonetheless, numerous dietary intervention studies are currently under way ([ 7 ][8]), ranging from a somewhat simple intervention of adding one cup of canned beans per day to existing diets (NCT02843425) to extended (or longer-term) dietary interventions, where meals are prepared for (and shipped to) participants (NCT03950635). Such dietary modifications have potential relevance even if recipients are also treated with other gut microbiota modulation strategies such as FMT or live biotherapeutics, as they may sustain and promote optimal function of the transferred gut microbes, although optimal approaches of dietary intervention in these scenarios has yet to be defined. The use of prebiotic supplementation (such as resistant starches, polyphenols, and polyunsaturated fatty acids) is also being studied, because these compounds may provide optimal substrate to beneficial commensal (or administered) microbes. It is becoming evident that modulation of gut microbes will be increasingly employed to promote overall health and to help treat disease, although optimal strategies for “precision” gut microbiota modulation remain incompletely understood. It is probable that a personalized approach will be needed, incorporating strategies such as FMT, administration of live biotherapeutics, dietary strategies, and prebiotics—although it is not inconceivable that an ideal “one-size-fits-all” approach could be identified. Through additional research and collaborative efforts, the true definition of dysbiosis in the gut microbiota as it relates to disease states can be better understood, as well as what constitutes an optimal gut microbiota to promote overall health, which could have broad impact for public health. 1. [↵][17]1. I. Cho, 2. M. J. Blaser , Nat. Rev. Genet. 13, 260 (2012). [OpenUrl][18][CrossRef][19][PubMed][20] 2. [↵][21]1. J. R. Allegretti, 2. B. H. Mullish, 3. C. Kelly, 4. M. Fischer , Lancet 394, 420 (2019). [OpenUrl][22][CrossRef][23][PubMed][24] 3. [↵][25]1. F. Zhang et al ., Am. J. Gastroenterol. 107, 1755 (2012). [OpenUrl][26][CrossRef][27][PubMed][28] 4. [↵][29]1. B. Eiseman, 2. W. Silen, 3. G. S. Bascom, 4. A. J. Kauvar , Surgery 44, 854 (1958). [OpenUrl][30][PubMed][31][Web of Science][32] 5. [↵][33]1. S. W. Olesen et al ., Lancet Gastroenterol. Hepatol. 5, 241 (2020). [OpenUrl][34] 6. [↵][35]1. J. F. Bach , N. Engl. J. Med. 347, 911 (2002). [OpenUrl][36][CrossRef][37][PubMed][38][Web of Science][39] 7. [↵][40]1. J. L. McQuade, 2. C. R. Daniel, 3. B. A. Helmink, 4. J. A. Wargo , Lancet Oncol. 20, e77 (2019). [OpenUrl][41][CrossRef][42][PubMed][43] 8. [↵][44]1. J. U. Peled et al ., N. Engl. J. Med. 382, 822 (2020). [OpenUrl][45][CrossRef][46][PubMed][47] 9. [↵][48]1. V. Gopalakrishnan et al ., Science 359, 97 (2018). [OpenUrl][49][Abstract/FREE Full Text][50] 10. [↵][51]1. G. Cammarota et al ., Gut 68, 2111 (2019). [OpenUrl][52][Abstract/FREE Full Text][53] 11. [↵][54]1. Z. DeFilipp et al ., N. Engl. J. Med. 381, 2043 (2019). [OpenUrl][55][CrossRef][56][PubMed][24] 12. [↵][57]1. S. W. Olesen, 2. Y. Gerardin , medRxiv 19011635 (2019). 13. [↵][58]1. J. Suez, 2. N. Zmora, 3. E. Segal, 4. E. Elinav , Nat. Med. 25, 716 (2019). [OpenUrl][59][CrossRef][60] 14. [↵][61]1. I. Yelin et al ., Nat. Med. 25, 1728 (2019). [OpenUrl][62][CrossRef][63] 15. [↵][64]1. L. A. David et al ., Nature 505, 559 (2014). [OpenUrl][65][CrossRef][66][PubMed][67][Web of Science][68] Acknowledgments: J.A.W. is supported by the National Institutes of Health (1R01CA219896-01A1), the Melanoma Research Alliance (4022024), American Association for Cancer Research Stand Up To Cancer (SU2C-AACR-IRG-19-17), and the MD Anderson Melanoma Moonshot Program. J.A.W. is an inventor on U.S. patent application (PCT/US17/53.717) and receives compensation from and is on the advisory boards for Imedex, Dava Oncology, Omniprex, Illumina, Gilead, PeerView, Physician Education Resource, AstraZeneca, Bristol-Myers Squibb, and Ella Therapeutics. [1]: #ref-1 [2]: #ref-2 [3]: #ref-3 [4]: #ref-4 [5]: pending:yes [6]: #ref-5 [7]: #ref-6 [8]: #ref-7 [9]: #ref-8 [10]: #ref-9 [11]: #ref-10 [12]: #ref-11 [13]: #ref-12 [14]: #ref-13 [15]: #ref-14 [16]: #ref-15 [17]: #xref-ref-1-1 "View reference 1 in text" [18]: {openurl}?query=rft.jtitle%253DNature%2Breviews.%2BGenetics%26rft.stitle%253DNat%2BRev%2BGenet%26rft.aulast%253DCho%26rft.auinit1%253DI.%26rft.volume%253D13%26rft.issue%253D4%26rft.spage%253D260%26rft.epage%253D270%26rft.atitle%253DThe%2Bhuman%2Bmicrobiome%253A%2Bat%2Bthe%2Binterface%2Bof%2Bhealth%2Band%2Bdisease.%26rft_id%253Dinfo%253Adoi%252F10.1038%252Fnrg3182%26rft_id%253Dinfo%253Apmid%252F22411464%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [19]: /lookup/external-ref?access_num=10.1038/nrg3182&link_type=DOI [20]: /lookup/external-ref?access_num=22411464&link_type=MED&atom=%2Fsci%2F369%2F6509%2F1302.atom [21]: #xref-ref-2-1 "View reference 2 in text" [22]: {openurl}?query=rft.jtitle%253DLancet%26rft.volume%253D394%26rft.spage%253D420%26rft_id%253Dinfo%253Adoi%252F10.1016%252FS0140-6736%252819%252931266-8%26rft_id%253Dinfo%253Apmid%252Fhttp%253A%252F%252Fwww.n%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [23]: /lookup/external-ref?access_num=10.1016/S0140-6736(19)31266-8&link_type=DOI [24]: /lookup/external-ref?access_num=http://www.n&link_type=MED&atom=%2Fsci%2F369%2F6509%2F1302.atom [25]: #xref-ref-3-1 "View reference 3 in text" [26]: {openurl}?query=rft.jtitle%253DThe%2BAmerican%2Bjournal%2Bof%2Bgastroenterology%26rft.stitle%253DAm%2BJ%2BGastroenterol%26rft.aulast%253DBrandt%26rft.auinit1%253DL.%2BJ.%26rft.volume%253D107%26rft.issue%253D11%26rft.spage%253D1755%26rft.epage%253D1755%26rft.atitle%253DShould%2Bwe%2Bstandardize%2Bthe%2B1%252C700-year-old%2Bfecal%2Bmicrobiota%2Btransplantation%253F%26rft_id%253Dinfo%253Adoi%252F10.1038%252Fajg.2012.251%26rft_id%253Dinfo%253Apmid%252F23160295%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [27]: /lookup/external-ref?access_num=10.1038/ajg.2012.251&link_type=DOI [28]: /lookup/external-ref?access_num=23160295&link_type=MED&atom=%2Fsci%2F369%2F6509%2F1302.atom [29]: #xref-ref-4-1 "View reference 4 in text" [30]: {openurl}?query=rft.jtitle%253DSurgery%26rft.stitle%253DSurgery%26rft.aulast%253DEiseman%26rft.auinit1%253DB.%26rft.volume%253D44%26rft.issue%253D5%26rft.spage%253D854%26rft.epage%253D859%26rft.atitle%253DFecal%2Benema%2Bas%2Ban%2Badjunct%2Bin%2Bthe%2Btreatment%2Bof%2Bpseudomembranous%2Benterocolitis.%26rft_id%253Dinfo%253Apmid%252F13592638%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [31]: /lookup/external-ref?access_num=13592638&link_type=MED&atom=%2Fsci%2F369%2F6509%2F1302.atom [32]: /lookup/external-ref?access_num=A1958WF27500011&link_type=ISI [33]: #xref-ref-5-1 "View reference 5 in text" [34]: {openurl}?query=rft.jtitle%253DLancet%2BGastroenterol.%2BHepatol.%26rft.volume%253D5%26rft.spage%253D241%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [35]: #xref-ref-6-1 "View reference 6 in text" [36]: {openurl}?query=rft.jtitle%253DNew%2BEngland%2BJournal%2Bof%2BMedicine%26rft.stitle%253DNEJM%26rft.aulast%253DBach%26rft.auinit1%253DJ.-F.%26rft.volume%253D347%26rft.issue%253D12%26rft.spage%253D911%26rft.epage%253D920%26rft.atitle%253DThe%2BEffect%2Bof%2BInfections%2Bon%2BSusceptibility%2Bto%2BAutoimmune%2Band%2BAllergic%2BDiseases%26rft_id%253Dinfo%253Adoi%252F10.1056%252FNEJMra020100%26rft_id%253Dinfo%253Apmid%252F12239261%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [37]: /lookup/external-ref?access_num=10.1056/NEJMra020100&link_type=DOI [38]: /lookup/external-ref?access_num=12239261&link_type=MED&atom=%2Fsci%2F369%2F6509%2F1302.atom [39]: /lookup/external-ref?access_num=000178040700008&link_type=ISI [40]: #xref-ref-7-1 "View reference 7 in text" [41]: {openurl}?query=rft.jtitle%253DLancet%2BOncol.%26rft.volume%253D20%26rft.spage%253De77%26rft_id%253Dinfo%253Adoi%252F10.1016%252FS1470-2045%252818%252930952-5%26rft_id%253Dinfo%253Apmid%252F30712808%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [42]: /lookup/external-ref?access_num=10.1016/S1470-2045(18)30952-5&link_type=DOI [43]: /lookup/external-ref?access_num=30712808&link_type=MED&atom=%2Fsci%2F369%2F6509%2F1302.atom [44]: #xref-ref-8-1 "View reference 8 in text" [45]: {openurl}?query=rft.jtitle%253DN.%2BEngl.%2BJ.%2BMed.%26rft.volume%253D382%26rft.spage%253D822%26rft_id%253Dinfo%253Adoi%252F10.1056%252FNEJMoa1900623%26rft_id%253Dinfo%253Apmid%252F32101664%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [46]: /lookup/external-ref?access_num=10.1056/NEJMoa1900623&link_type=DOI [47]: /lookup/external-ref?access_num=32101664&link_type=MED&atom=%2Fsci%2F369%2F6509%2F1302.atom [48]: #xref-ref-9-1 "View reference 9 in text" [49]: {openurl}?query=rft.jtitle%253DScience%26rft_id%253Dinfo%253Adoi%252F10.1126%252Fscience.aan4236%26rft_id%253Dinfo%253Apmid%252F29097493%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [50]: /lookup/ijlink/YTozOntzOjQ6InBhdGgiO3M6MTQ6Ii9sb29rdXAvaWpsaW5rIjtzOjU6InF1ZXJ5IjthOjQ6e3M6ODoibGlua1R5cGUiO3M6NDoiQUJTVCI7czoxMToiam91cm5hbENvZGUiO3M6Mzoic2NpIjtzOjU6InJlc2lkIjtzOjExOiIzNTkvNjM3MS85NyI7czo0OiJhdG9tIjtzOjIzOiIvc2NpLzM2OS82NTA5LzEzMDIuYXRvbSI7fXM6ODoiZnJhZ21lbnQiO3M6MDoiIjt9 [51]: #xref-ref-10-1 "View reference 10 in text" [52]: {openurl}?query=rft.jtitle%253DGut%26rft_id%253Dinfo%253Adoi%252F10.1136%252Fgutjnl-2019-319548%26rft_id%253Dinfo%253Apmid%252F31563878%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [53]: /lookup/ijlink/YTozOntzOjQ6InBhdGgiO3M6MTQ6Ii9sb29rdXAvaWpsaW5rIjtzOjU6InF1ZXJ5IjthOjQ6e3M6ODoibGlua1R5cGUiO3M6NDoiQUJTVCI7czoxMToiam91cm5hbENvZGUiO3M6NjoiZ3V0am5sIjtzOjU6InJlc2lkIjtzOjEwOiI2OC8xMi8yMTExIjtzOjQ6ImF0b20iO3M6MjM6Ii9zY2kvMzY5LzY1MDkvMTMwMi5hdG9tIjt9czo4OiJmcmFnbWVudCI7czowOiIiO30= [54]: #xref-ref-11-1 "View reference 11 in text" [55]: {openurl}?query=rft.jtitle%253DN.%2BEngl.%2BJ.%2BMed.%26rft.volume%253D381%26rft.spage%253D2043%26rft_id%253Dinfo%253Adoi%252F10.1056%252FNEJMoa1910437%26rft_id%253Dinfo%253Apmid%252Fhttp%253A%252F%252Fwww.n%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [56]: /lookup/external-ref?access_num=10.1056/NEJMoa1910437&link_type=DOI [57]: #xref-ref-12-1 "View reference 12 in text" [58]: #xref-ref-13-1 "View reference 13 in text" [59]: {openurl}?query=rft.jtitle%253DNat.%2BMed.%26rft.volume%253D25%26rft.spage%253D716%26rft_id%253Dinfo%253Adoi%252F10.1038%252Fs41591-019-0439-x%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [60]: /lookup/external-ref?access_num=10.1038/s41591-019-0439-x&link_type=DOI [61]: #xref-ref-14-1 "View reference 14 in text" [62]: {openurl}?query=rft.jtitle%253DNat.%2BMed.%26rft.volume%253D25%26rft.spage%253D1728%26rft_id%253Dinfo%253Adoi%252F10.1038%252Fs41591-019-0626-9%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [63]: /lookup/external-ref?access_num=10.1038/s41591-019-0626-9&link_type=DOI [64]: #xref-ref-15-1 "View reference 15 in text" [65]: {openurl}?query=rft.jtitle%253DNature%26rft.volume%253D505%26rft.spage%253D559%26rft_id%253Dinfo%253Adoi%252F10.1038%252Fnature12820%26rft_id%253Dinfo%253Apmid%252F24336217%26rft.genre%253Darticle%26rft_val_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Ajournal%26ctx_ver%253DZ39.88-2004%26url_ver%253DZ39.88-2004%26url_ctx_fmt%253Dinfo%253Aofi%252Ffmt%253Akev%253Amtx%253Actx [66]: /lookup/external-ref?access_num=10.1038/nature12820&link_type=DOI [67]: /lookup/external-ref?access_num=24336217&link_type=MED&atom=%2Fsci%2F369%2F6509%2F1302.atom [68]: /lookup/external-ref?access_num=000329995000042&link_type=ISI

The tremendous boost in the next generation sequencing and in the omics technologies makes it possible to characterize human gut microbiome (the collective genomes of the microbial community that reside in our gastrointestinal tract). While some of these microorganisms are considered as essential regulators of our immune system, some others can cause several diseases such as Inflammatory Bowel Diseases (IBD), diabetes, and cancer. IBD, is a gut related disorder where the deviations from the healthy gut microbiome are considered to be associated with IBD. Although existing studies attempt to unveal the composition of the gut microbiome in relation to IBD diseases, a comprehensive picture is far from being complete. Due to the complexity of metagenomic studies, the applications of the state of the art machine learning techniques became popular to address a wide range of questions in the field of metagenomic data analysis. In this regard, using IBD associated metagenomics dataset, this study utilizes both supervised and unsupervised machine learning algorithms, i) to generate a classification model that aids IBD diagnosis, ii) to discover IBD associated biomarkers, iii) to find subgroups of IBD patients using k means and hierarchical clustering. To deal with the high dimensionality of features, we applied robust feature selection algorithms such as Conditional Mutual Information Maximization (CMIM), Fast Correlation Based Filter (FCBF), min redundancy max relevance (mRMR) and Extreme Gradient Boosting (XGBoost). In our experiments with 10 fold cross validation, XGBoost had a considerable effect in terms of minimizing the microbiota used for the diagnosis of IBD and thus reducing the cost and time. We observed that compared to the single classifiers, ensemble methods such as kNN and logitboost resulted in better performance measures for the classification of IBD.

Image has been cropped and resized. Scientists have developed machine-learning algorithms that can identify patterns in the bacteria of a patient's gut to determine whether the patient is likely to get infected if exposed to cholera. The researchers believe such artificial intelligence (AI) could be critical in areas of high cholera risk, since it can analyze trillions of bacteria, much more than can be done by humans. The study also demonstrates the power of machine learning to uncover medical insights that would otherwise remain obscure. READ: AI's Ethical Concerns Go Beyond Data Security and Quality The research is a collaboration between Duke University, Massachusetts General Hospital, and the International Centre for Diarrheal Disease Research, in Bangladesh.

These are patterns that even the most sophisticated scientist couldn't detect by eye,