A rapid microfluidic in VIVO bioassay for screening functional ingredients for improving gut health

Abstract

Provided herein are systems and methods for a rapid microfluidic in vivo bioassay for screening functional ingredients for improving gut health. An AI model is also described that enables the automated detection of leaky gut and health gut in C. elegans.

Description

TITLEA RAPID MICROFLUIDIC IN VIVO BIOASSAY FOR SCREENING FUNCTIONAL INGREDIENTS FOR IMPROVING GUT HEALTHBACKGROUND

[0001] The invention relates to high-throughput microfluidic screening of functional ingredients for their biological effect on gut health in an intact living microorganism. Specifically, three rapid in vivo assays that can identify ingredients that prevent leaky gut syndrome caused by aging, poor nutrition, and pathogenic infection of the gut.

[0002] A major determinant of gut health is the integrity of the intestinal epithelial barrier as it serves as a physical and functional barrier between the gut lumen and the underlying tissues [ref, review articles]. Disruption of this barrier or leaky gut can lead to the translocation of harmful microbial products, toxins, and antigens into the systemic circulation, triggering inflammation and immune responses. Numerous research studies have highlighted the significance of intestinal barrier dysfunction in the pathogenesis of various human-related disorders, including inflammatory bowel disease (IBD, PMID: 19855405), celiac disease, and irritable bowel syndrome (IBS), neurodegenerative disorders18-20and cancer. Thus, there is a significant need to identify ingredients and therapeutics that can reduce intestinal permeability, maintain gut barrier integrity and improve gut as well as systemic health.

[0003] A variety of functional ingredients and their combinations including prebiotics, probiotics, postbiotics, phytochemicals, botanical extracts, metabolites, pharmaceutical compounds and micronutrients have the potential to maintain and improve gut barrier integrity. The mechanisms through which ingredients improve intestinal barrier function are usually complex involving immunomodulation, anti-microbial activity and activation of stress resistance pathways. These mechanisms are usually identified using biological systems that are amenable to detailed investigations including intestinal cell culture, worms, flies and rodent models.

[0004] In vitro gut models based on intestinal cell monolayers are cost-effective and can achieve higher throughput. However, they lack the complexity of the in vivo environment, including the dynamic interplay between different cell types and physiological factors, limiting their ability to replicate the in vivo situation. Rodent models provide a closer representation of the intestinal environment, allowing the study of complex interactions between the gut microbiota, and theintestinal epithelium. However, rodent models have ethical considerations, and higher costs, limiting their scalability.

[0005] Current methods for measuring gut barrier integrity using rodent models are unsuited for high-throughput discovery screens of functional ingredients for treating leaky gut. 1) To detect age-associated leaky gut syndrome in mice, they must be aged till very late life (~21 months) and fed a high-fat diet to cause failure of gut barrier integrity. The need to mix age with obesity can cause confounding effects in the data from the screen. 2) Growing large numbers of mice in highly controlled conditions for nearly two years is challenging and requires a lot of space and energy resources. 3) To detect diet- or pathogen-induced leaky gut requires mice to be at least six weeks old, which is still not optimal for high-throughput screens. 4) The most common method for measuring changes in gut permeability requires a complex multi-step process involving a 4-6 hour fast, oral gavage of FITC-dextran, a blood draw from the tail 4 hours post-gavage, and finally, fluorescent spectroscopy to quantify the amount of FITC-dextran that has ‘leaked’ into the blood system. This series of steps limits how many conditions can be examined daily. 5) An alternative method involves sacrificing the mice at the appropriate age, removing the intestine, and sectioning it into slices on microscope slides. These slides are then subjected to immunohistochemistry with fluorescently labeled antibodies that bind to proteins in the tight junctions between intestinal epithelial cells. The antibody-labeled tight junctions can then be visualized with fluorescent microscopy to determine the degree of gut permeability. As this procedure involves killing the mice, it can’t be used to look at individuals over time.

[0006] In nematodes, conducting leaky-gut assays on standard agar plates is tedious and can lead to confounding data. Worms must be transferred to new plates manually which can induce physiological stress and artifacts. To avoid animal transfers, progeny-blocking drugs can be used, but these drugs can interact with the ingredients (e.g. probiotics) to be tested and alter their functional properties including safety and efficacy. In addition, monitoring the leakiness of the gut, involves picking worms and putting them on new substrates, which not only can compromise physiology and induce stress, but also makes the assay not high throughput.

[0007] The present invention attempts to solve these problems as well as others.SUMMARY OF THE INVENTION

[0008] Provided herein are systems and methods for a rapid microfluidic in vivo bioassay for screening functional ingredients for improving gut health.

[0009] The systems and methods are set forth in part in the description which follows, and in part will be obvious from the description, or can be learned by practice of the systems and methods. The advantages of the systems and methods will be realized and attained by means of the elements and combinations particularly pointed out in the appended claims. It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the systems and methods, as claimed.

[0010] Accordingly, it is an object of the invention not to encompass within the invention any previously known product, process of making the product, or method of using the product such that Applicants reserve the right and hereby disclose a disclaimer of any previously known product, process, or method. It is further noted that the invention does not intend to encompass within the scope of the invention any product, process, or making of the product or method of using the product, which does not meet the written description and enablement requirements of the USPTO (35 U.S.C. § 112, first paragraph) or the EPO (Article 83 of the EPC), such that Applicants reserve the right and hereby disclose a disclaimer of any previously described product, process of making the product, or method of using the product. It may be advantageous in the practice of the invention to be in compliance with Art. 53(c) EPC and Rule 28(b) and (c) EPC. All rights to explicitly disclaim any embodiments that are the subject of any granted patent(s) of applicant in the lineage of this application or in any other lineage or in any prior filed application of any third party is explicitly reserved. Nothing herein is to be construed as a promise.BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In the accompanying figures, like elements are identified by like reference numerals among the several preferred embodiments of the present invention.

[0012] Figs. 1A-1C are micrographs showing the scoring criteria for leaky gut assays. Fig. 1A shows worms with a healthy gut, where the non-absorbable erioglaucine dye is restricted to the lumen of the intestine. Fig. IB shows an animal with a moderate degree of gut leakiness, whereas gut health declines, the tight junctions between the intestinal epithelial cells begin to break down, allowing the dye to translocate out of the lumen and into some surrounding tissues. Fig. 1C shows the worm in the most severe cases of leaky gut, the gut barrier is so degraded that the dye can stain all the body's peripheral tissues.

[0013] Fig. 1 are circle graphs showing the incidence of age-associated leaky gut is reduced by probiotic treatment. As worms age, the tight junctions between intestinal epithelial cells breakdown, allowing the dye to leak into the surrounding tissues. Changing the bacterial diet of worms from E. coli OP50 to a probiotic strain belonging to the Lactobacillus genus results in a large increase in the number of worms with good gut health on day 16 of animal life. In comparison, a probiotic strain belonging to the Bacillus genus does not affect age-associated leaky gut significantly.

[0014] Fig. 2 are circle graphs showing the incidence of leaky caused by poor nutrition is reduced by probiotic treatment. Feeding worms a high-sugar diet (2% glucose) harms gut health, with -58% of worms having leaky gut syndrome by day 12 of animal life. However, treatment with probiotic strains belonging to the Lactobacillus and Bacillus genera significantly reduces the number of worms with leaky gut syndrome induced by poor nutrition at this age.

[0015] Fig. 3 are circle graphs showing the leaky gut induced by enteropathogenic infection is reduced by probiotic treatment. Infection of the gut by the enteropathogenic Pseudomonas aeruginosa strain PA14 increases gut leakiness by day 10 of animal life. The treatment with probiotic strains belonging to the Lactobacillus and Bacillus genera significantly reduces the number of worms with leaky gut syndrome induced by PAM infection at day 10 of animal life.

[0016] Figs. 5A-5C are photographs showing the distribution of blue dye in different classes of worms (Fig. 5A) dye leaked through the damaged intestinal barrier (leaky gut) and spread across the entire body, (Fig. 5B) dye is contained in the lumen by the intact intestinal barrier (healthy gut), and (Fig. 5C) censored worm examples due to added objects to the worm body, bursting or partial body in the image.

[0017] Fig. 6 is a schematic diagram of YOLO deep learning pipeline for gut health evaluation.

[0018] Fig. 7A is a confusion matrix resulting from the ML model for leaky gut. The background is the image segment absent with the worm object (FN-False negative, FP-False positive). The model is designed to remove censored objects from the inferencing step. Fig. 7B is a graph showing the comparison of model prediction against a human-curated dataset.

[0019] Figs. 8A-8C are graphs showing the accuracy and validation of the ML model. Fig. 8A- 8C show the comparison of the model prediction compared to the human-curated scores for notreatment control, L. rhamnosus strain (probiotic), and 2% glucose diet, respectively.

[0020] Figs. 9A-9D are graphs showing the distribution of the leakiness scores, (a) all leaky phenotypes (red phenotype) and all healthy phenotypes (blue curve). Leaky phenotype peaks at a leakiness score of 0.12 and the healthy phenotype peaks at a leakiness score of 0.84. Animal age,20 days, (b) - (d) distribution of the leakiness score for no treatment control, A. rhamnosus strain (probiotic), and 2% glucose diet respectively.DETAILED DESCRIPTION OF THE INVENTION

[0021] The foregoing and other features and advantages of the invention are apparent from the following detailed description of exemplary embodiments, read in conjunction with the accompanying drawings. The detailed description and drawings are merely illustrative of the invention rather than limiting, the scope of the invention being defined by the appended claims and equivalents thereof.

[0022] Embodiments of the invention will now be described with reference to the Figures, wherein like numerals reflect like elements throughout. The terminology used in the description presented herein is not intended to be interpreted in any limited or restrictive way, simply because it is being utilized in conjunction with detailed description of certain specific embodiments of the invention. Furthermore, embodiments of the invention may include several novel features, no single one of which is solely responsible for its desirable attributes or which is essential to practicing the invention described herein.

[0023] The use of the terms “a” and “an” and “the” and similar referents in the context of describing the invention are to be construed to cover both the singular and the plural, unless otherwise indicated herein or clearly contradicted by context. It will be further understood that the terms “comprises,” “comprising,” “includes,” and / or “including,” when used herein, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0024] Recitation of ranges of values herein are merely intended to serve as a shorthand method of referring individually to each separate value falling within the range, unless otherwise indicated herein, and each separate value is incorporated into the specification as if it were individually recited herein. The word “about,” when accompanying a numerical value, is to be construed as indicating a deviation of up to and inclusive of 10% from the stated numerical value. The use of any and all examples, or exemplary language (“e.g.” or “such as”) provided herein, is intended merely to better illuminate the invention and does not pose a limitation on the scope of the invention unless otherwise claimed. No language in the specification should be construed as indicating any nonclaimed element as essential to the practice of the invention.

[0025] References to “one embodiment,” “an embodiment,” “example embodiment,” “various embodiments,” etc., may indicate that the embodiment(s) of the invention so described may include a particular feature, structure, or characteristic, but not every embodiment necessarily includes the particular feature, structure, or characteristic. Further, repeated use of the phrase “in one embodiment,” or “in an exemplary embodiment,” do not necessarily refer to the same embodiment, although they may.

[0026] As used herein the term “method” refers to manners, means, techniques and procedures for accomplishing a given task including, but not limited to, those manners, means, techniques and procedures either known to, or readily developed from known manners, means, techniques and procedures by practitioners of the chemical, pharmacological, biological, biochemical and medical arts. Unless otherwise expressly stated, it is in no way intended that any method or aspect set forth herein be construed as requiring that its steps be performed in a specific order. Accordingly, where a method claim does not specifically state in the claims or descriptions that the steps are to be limited to a specific order, it is no way intended that an order be inferred, in any respect. This holds for any possible non-express basis for interpretation, including matters of logic with respect to arrangement of steps or operational flow, plain meaning derived from grammatical organization or punctuation, or the number or type of aspects described in the specification.

[0027] Description of the Embodiments

[0028] Generally speaking, a rapid microfluidic in vivo bioassay for screening functional ingredients for improving gut health comprises at least three complimentary microfluidic in vivo bioassays that identify changes in gut health caused by loss of gut barrier integrity in C. elegans. The three complimentary microfluidic in vivo assays use the microscopic nematode Caenorhabditis elegans as a preclinical model for leaky gut syndrome caused by aging, poor nutrition, and enteropathogenic infection. In one embodiment, each assay is conducted in a microfluidic device that minimizes reagent use and enables high-throughput screening.

[0029] In one embodiment, the microfluidic device allows whole-life husbandry of the nematodes, with capabilities to feed the worms with a variety of ingredients, and non-invasive monitoring of the leakiness of the gut. in the microfluidic device, mention a device where worms are housed for life, with the ability to add or remove ingredients and dyes (any soluble chemical, substance, cells).

[0030] The three microfluidic bioassays identify new functional ingredients that reduce leaky gut syndrome caused by these three phenomena. These in vivo assays are agnostic to the nature of thefunctional ingredient, allowing a vast range of materials including, but not limited to: pre-, pro-, postbiotics, metabolite, botanicals, proteins, soluble fibers, pharmaceutical compounds, vitamins, minerals, and more to be screened with much higher throughput than currently possible. This rapid microfluidic in vivo bioassay for screening functional ingredients for improving gut health comprises enables high-throughput screens at a scale that dramatically increases functional ingredient and therapeutic discovery for leaky gut syndrome.

[0031] The nematode C. elegans presents significant advantages compared to in vitro and rodent models for high throughput screening (HTS), of functional ingredients for gut health. First, aspects of safety, gastric tolerance, intestinal adhesion, and efficacy can all be adequately modeled in vivo with the worm in a single step, increasing confidence in the hits early on and reducing in vivo screening timelines from years to months. Second, their short reproductive cycle (~3 days) generates large populations (>10K) needed for HTS studies. These advantages underscore this invertebrate model's power as a screening tool to accelerate and de-risk the identification of functional ingredients for improving gut health.

[0032] Despite the significant advantages of C. elegans as a living biological system, technical challenges with current methods limit the ability to assess loss of gut barrier integrity. Observation of leakiness of the gut requires multi-day culture of adult animals. Current methods use agar plates to grow adult animals, and manually transfer them to new plates, otherwise progeny can confound the data. Approaches to eliminate progeny using progeny-blocking drugs are limiting as these drugs can interact with the ingredients (e g. probiotics) to be tested and alter their functional properties including safety and efficacy. Additionally, evaluating gut leakiness requires feeding the animals a non-adsorbable reagent, and imaging them at the desired time-points. The multi-day feeding and imaging requires transferring worms, which can introduce physiological stress and artifacts. These bottlenecks limit the screening throughput to identify novel functional ingredients that mitigate intestinal permeability of the C. elegans gut.

[0033] In the examples provided below, microfluidics are used to address the technical limitations of multi-day culture and imaging of C. elegans. Three complimentary microfluidic in vivo bioassays identify changes in gut health caused by loss of gut barrier integrity in C. elegans. These three assays use the microscopic nematode Caenorhabditis elegans as a preclinical model for leaky gut syndrome caused by aging, poor nutrition, and enteropathogenic infection. Each assay is conducted in a microfluidic device that minimizes reagent use and enables high-throughputscreening. The microfluidic device allows whole-life husbandry of the nematodes, with capabilities to feed the worms with a variety of ingredients, and non-invasive monitoring of the leakiness of the gut. These in vivo assays are agnostic to the nature of the functional ingredient, allowing a vast range of materials such as pre-, pro-, postbiotics, metabolite, botanicals, proteins, soluble fibers, pharmaceutical compounds, vitamins, minerals, and more to be screened with much higher throughput than currently possible. This new capability enables high-throughput screens at a scale that dramatically increases functional ingredient and therapeutic discovery for leaky gut syndrome that could be translated to improve human health and wellness.

[0034] This rapid microfluidic in vivo bioassay for screening functional ingredients for improving gut health comprises three microfluidic bioassays that identify functional ingredients or therapeutics for leaky gut syndrome caused by age, poor diet, or enteropathogenic infection without confounding factors.

[0035] The three assays use the nematode worm Caenorhabditis elegans, a microscopic worm capable of clonal reproduction with a short reproductive cycle of three days and a three-week lifespan. These biological features of the worm allow the invention to grow tens of thousands of worms in less space than a single mouse cage. The three assays are more resource efficient than mouse assays, providing much larger sample sizes for statistical analysis.

[0036] The microfluidic format allows (1) animal husbandry without the need for transferring worms daily, or introducing progeny-blocking drugs (2) non-invasive monitoring of gut-barrier integrity (3) gut integrity can be evaluated at multiple time points during the life-history of the animal (4) variety of gut permeating molecules (e.g. colorimetric dyes, fluorescent dyes, non- adsorbable molecules etc.) can be introduced at any given time point to assess degree of leakiness, without the need to transfer animals to new culture substrates (5) The microfluidic method is flexible to induce leaky gut by several routes including poor diet, infection, aging, gut irritants, intestinal stressors etc.

[0037] Using C. elegans instead of mice dramatically lowers the cost of screens as the worms need far fewer resources to grow large populations for experiments, which take less time due to the short lifespan of the worms.

[0038] The three assays a methodologically simpler than any of the mouse or C. elegans assays and so they take less time to generate data and allow more conditions to be run in parallel.

[0039] Examples

[0040] The following examples are put forth so as to provide those of ordinary skill in the art with a complete disclosure and description of how the compounds, compositions, articles, devices and / or methods claimed herein are made and evaluated and are intended to be purely exemplary of the invention and are not intended to limit the scope of what the inventors regard as their invention. However, those of skill in the art should, considering the present disclosure, appreciate that many changes can be made in the specific embodiments which are disclosed and still obtain a like or similar result without departing from the spirit and scope of the invention.

[0041] Efforts have been made to ensure accuracy with respect to numbers (e g., amounts, temperature, etc.), but some errors and deviations should be accounted for. Unless indicated otherwise, parts are parts by weight, temperature is in ° C. or is at ambient temperature, and pressure is at or near atmospheric.

[0042] Example 1

[0043] Materials and Methods

[0044] C. elegans Culture: To obtain a large age-synchronous population of N2 (wild-type) worms, five L4-stage larvae were placed onto a 10 cm nematode growth media (NGM) agar plate seeded with Escherichia coli strain OP50. The animals were incubated at 20°C for five days, which allowed the population to expand across two generations. On day 5, all the worms were gently washed off the plate using liquid NGM buffer, leaving behind F2 generation eggs embedded in the bacterial lawn. The plates were then left at 20°C for four additional hours of incubation to allow the eggs to hatch. The freshly hatched LI larvae were gently washed off using liquid NGM buffer. These age-synchronized LI larvae were then transferred to fresh plates seeded with OP50 and maintained for 48 hours at 20°C until they reached the L4 larval stage. Approximately sixty L4- stage worms were loaded into a proprietary microfluidic device, the Infinity Chip. After loading, the worms were switched to a 20 mg / mL diet of live OP50 bacteria resuspended in liquid NGM buffer. They were cultured on the chip for 24 hours at 20°C until they reached the first day of adulthood, day four of animal life. After 24 hours, the chips were washed with ~12 mL of NGM buffer to remove progeny, and the media was exchanged for the treatment condition. The animals were maintained on the chip by washing and replenishing the appropriate media every 24 hours until the imaging day.

[0045] Bacterial Culture: New OP50 and Pseudomonas aeruginosa strain PA14 plates were set up by streaking from frozen stocks. Single colonies of each strain were separately inoculated into25 mL of sterile LB media and incubated in a shaking incubator at 250 rpm for 18 hours at 37°C. After incubation, the bacterial cultures were transferred to pre-weighed sterile 50 mL Falcon tubes. The tubes were centrifuged at 2200 g to pellet the bacteria, and the supernatant was discarded. The bacterial pellets were washed with 25 mL of NGM buffer, followed by another round of centrifugation. The washing step was repeated twice with NGM buffer for each strain. The wet weight of the bacterial pellets was determined by weighing each tube and subtracting the original weight of the empty tube. Subsequently, the bacterial pellets were resuspended in liquid NGM buffer to obtain a final stock concentration of 40 mg / mL for each strain. The OP50 suspension was diluted to a final 20 mg / mL concentration using NGM buffer or the appropriate treatment condition. The PA14 suspension was diluted to a final concentration of 10 mg / mL for the pathogen-induced leaky gut assay. For the probiotic studies, each bacterial strain was cultured in the media, typically MRS broth, recommended by the source of each isolate. These were then prepared in the same way as the OP50.

[0046] Dye Preparation: To prepare the dye solution, 1 g of Erioglaucine disodium salt (Sigma- Aldrich) was dissolved in 20 mL of a 20 mg / mL OP50 suspension in liquid NGM buffer, resulting in a 5% (W / V) solution of the dye.

[0047] Age-Induced Leaky Gut Assay: For the age-induced leaky gut assay, worms were loaded into the chips as L4 larvae in NGM buffer with a 20 mg / mL OP50 suspension. The next day (day four of animal life), the chips were washed with NGM buffer, and the media was exchanged with 200 pL of a 20 mg / mL OP50 or the probiotic suspension. The worms were maintained on the chip with daily washing and media exchange until day 16 of animal life. On day 16, the worms were rinsed with NGM buffer and treated with 200 pL of a 5% Erioglaucine disodium salt dye solution. The animals were incubated with the dye for 3 hours. Subsequently, the chip was rinsed with 1 mL of NGM buffer and treated with 25 mM sodium azide to paralyze the worms for imaging. The chip was mounted on an Olympus 1X70 inverted microscope with an Imaging Source DMK 33UX252 camera. The images were captured using AmScope software. At least 30 animals were imaged per chip per condition to obtain 60 animals per condition.

[0048] High-Sugar Diet-Induced Leaky Gut Assay: To model leaky gut syndrome caused by poor nutrition, the worms were fed a high-sugar diet that causes a breakdown of gut barrier integrity by day 12 of animal life. For the diet-induced leaky gut assay, animals were loaded into the chips on day 3 of animal life with a 20 mg / mL OP50 suspension. On day 4, the chips werewashed with NGM buffer, and the media was exchanged with 200 pL of a 20 mg / mL OP50 or probiotic suspension supplemented with a 2% (W / V) glucose solution. The animals were maintained on the chip with daily washing and media exchange until day 12 of animal life. On day 12, the animals were rinsed, stained, and imaged using the same protocol as above.

[0049] Pathogen-Induced Leaky Gut Assay: For the pathogen-induced leaky gut assay, worms were loaded into the chips on day 3 of animal life with a 20 mg / mL OP50 suspension. On day 4 of animal life, each chip was washed with NGM buffer, and the media was exchanged with 200 pL of a 20 mg / mL OP50 suspension or probiotic strain supplemented with 10 mg / mL PA14. The animals were maintained on the chip with daily washing and media exchange until day 10 of animal life. On day 10, the animals were rinsed, stained, and imaged using the protocol above.

[0050] Scoring of Leaky Gut Phenotypes: The acquired images were qualitatively analyzed, categorizing the leaky gut phenotypes into three categories, healthy gut, moderately leaky, and severely leaky gut (see Figs. 1A-1C).

[0051] Figs. 1A-1C: Scoring criteria for leaky gut assays. Fig. 1A shows the worms with a healthy gut, the non-ab sorbable erioglaucine dye 100 is restricted to the lumen 102 of the intestine. Fig. IB shows an animal with a moderate degree of gut leakiness. As gut health declines, the tight junctions between the intestinal epithelial cells begin to break down, allowing the dye 100 to translocate out of the lumen and into some surrounding tissues 110. Fig. 1C shows the most severe cases of leaky gut, the gut barrier is so degraded that the dye can stain all the body's peripheral tissues 120.

[0052] Fig. 4: The incidence of age-associated leaky gut is reduced by probiotic treatment. As worms age, the tight junctions between intestinal epithelial cells break down, allowing the dye to leak into the surrounding tissues. Changing the bacterial diet of worms from E. coh OP50 to a probiotic strain belonging to the Lactobacillus genus results in a large increase in the number of worms with good gut health on day 16 of animal life. In comparison, a probiotic strain belonging to the Bacillus genus does not affect age-associated leaky gut significantly.

[0053] Fig. 5: The incidence of leaky caused by poor nutrition is reduced by probiotic treatment. Feeding worms a high-sugar diet (2% glucose) harms gut health, with -58% of worms having leaky gut syndrome by day 12 of animal life. However, treatment with probiotic strains belonging to the Lactobacillus and Bacillus genera significantly reduces the number of worms with leaky gut syndrome induced by poor nutrition at this age.

[0054] Fig. 6: Leaky gut induced by enteropathogenic infection is reduced by probiotic treatment. Infection of the gut by the enteropathogenic Pseudomonas aeruginosa strain PAM increases gut leakiness by day 10 of animal life. The treatment with probiotic strains belonging to the Lactobacillus and Bacillus genera significantly reduces the number of worms with leaky gut syndrome induced by PAM infection at day 10 of animal life.

[0055] Machine learning based scoring of leaky and healthy gut.

[0056] Currently, the scoring of leaky gut is carried out manually and subjective, severely limiting rapid in vivo screening of functional ingredients for gut health. In one embodiment, a machine learning model is designed to examine an image containing one or more worms to detect and classify the worms into two primary classes: healthy gut and leaky gut in one step. This method comprises automatic scoring to conduct high throughput screening of bioactives using the leaky gut as an endpoint and with minimal human bias in classifying the gut health in worms.

[0057] Training set composition

[0058] Imaging: Adult C. elegans (nematode) is imaged at high magnification (10X) with a color camera (0.711 microns per pixel). At this resolution, non-absorbable erioglaucine dye (blue dye) is visible in the intact intestinal lumen (healthy or no leak, Fig. 5A) and permeates into peripheral tissues for worms with a compromised gut barrier integrity (leaky gut, Fig 5B). The worms could be fed a standard diet or diet supplemented with the bioactive to evaluate the potential of the bioactive to mitigate leakiness in the worm gut.

[0059] Training set composition: In one embodiment, the training set comprises 2600 images where the images can contain one or more worms in a background of debris, pillars, bubbles, and extraneous objects. The worms in the images were scored manually for four classes: (i) healthy gut, (ii) moderately leaky gut, (iii) severe leaky gut, and (iv) censored. The severely and moderately leaky gut comprise the leaky phenotype where dye is spread in the peripheral tissues outside the lumen. Three censored classes may be present in the images: (i) partial worm, (ii) dead worm, and (iii) worm with bursting phenotype. A section of the worm body inside the image frame boundary is called a partial worm, which may be part of a severe or moderately leaked phenotype but is difficult to score without examining the rest of the worm body. A dead worm body absorbs a high concentration of dye across its body mass and may wrongly be scored for a leaky gut phenotype. An animal may also suffer from age or stress-induced vulval bursting, which also causes dye absorption throughout the body mass. These three additional phenotypes make up the"censored" category (Fig. 5C). The dataset was prepared for training by splitting it into training, testing, and validation sets, with a random distribution of image and annotation pairs at 50 %, 25 %, and 25%, respectively.

[0060] Model Architecture and Training: In one embodiment, the real-time single-stage object detection model architecture is used because it can detect and classify multiple objects in one step, making it computationally very efficient and allowing the model to be more specific. In other embodiments, other real-time single stage objection detection models may be used, such as YOLO, 3DCNN and the like. YOLO v3 is built on a deep convolutional neural network (CNN) that is composed of many layers of filters. The CNN is followed by several fully connected layers, which predict class probabilities and bounding box coordinates. YOLO v3 also uses a different loss function than previous versions. A 3D Convolutional Neural Network (3D CNN) as refers to neural network architectures with multiple layers that can learn hierarchical data representations. This architecture is often used to detect complex images as well as videos, such as medical images.

[0061] A few modifications were made and tailored towards efficiency and scale in the Randomization step shown in the schematic (Fig. 6). The modifications are listed below in A-D.

[0062] A. Because of the initially limited dataset, the hyperparameter is adjusted (Fig. 6) to regulate how fast the model learned to prevent overfitting.

[0063] B. A few transformations were disallowed, such as color, because they are crucial for the analysis and could cause the model not to converge correctly at hyperparameter adjustment (Fig 6)

[0064] C. Fine-tuned the model to adapt variations in image properties (background, illumination, etc.) generated from different systems. The model applies filters to the image, normalizing many factors that could cause an issue.

[0065] D. The model uses open-source frameworks and models, but specifics on what transformations are allowed remain hidden.

[0066] The gut health ML-based scoring model is a GPU-based pipeline that allows for a much more parallelized operation. It can be run on any platform supporting ONNX and scaled indefinitely based on the throughput needs.

[0067] Performance of the ML model for leaky gut: The confusion matrix (Fig. 7A) shows the performance of the ML model. The model achieved greater than 0.92 precision, greater than 0.85 recall, and an Fl score of about 0.88 for a healthy gut. The high background false positives showthat the model incorrectly detects background as healthy gut and thus overcounts healthy gut phenotype. A filter was applied and removed the background and censored objects from the inferencing output. The model is then run on a validation set. The model predicted about 98% of the worm counts accurately as leaky or healthy gut (Fig. 7B). The model prediction output was validated against age-induced, diet-induced, and pathogen-induced gut damages (Fig. 8A-8C). The prediction achieved a high degree of accuracy (96-99.9%).

[0068] Scoring system and visualization: Because the endpoint of the model is a sigmoid function, normalized confidence between 0 and 1 is obtained for each class, allowing the scoring of gut health in a more gradient way while only annotating for a binary outcome. The confidence score for all worms detected with leaky gut is modified to be 1 minus the original confidence score to better illustrate the worms' gut health. This transformation allows the identification of leaky gut phenotype with low scores, with 0.0 - 0.4 being leaky and a high score of 0.6 - 1.0 being the healthy gut and which is termed as the “leakiness score”. This definition was validated on 1000 annotated leaky and 1000 healthy gut images. A distinct peak (Fig. 9A) was found at a confidence score of 0.12 for the leaky and 0.84 for the healthy gut population. The detection confidence is equivalent to the probability score for the leakiness of the worm gut. The leakiness score distribution was tested and evaluated for age-induced, diet-induced, and pathogen-induced leaky gut (Fig. 9B-9D). The precision, recall, and Fl numbers are for the current training set and a precision score is >0.92 and a recall score > 0.85. Fl is a balance between the precisions score and the recall score, so generally remains at about 0.88. These numbers will get close to perfect with a much larger training set which we are currently working to build. In one embodiment, a minimum number detection accuracy is > 96 %.

[0069] Automated Classification of Gut Health:

[0070] In one embodiment, the method of a Gut Health Model (GHM) comprises automated classification of gut health using an Al model based on high-magnification images of C. elegans. In one embodiment, the high magnification images of C. elegans is stained with erioglaucine dye. In one embodiment the Al model is a YOLO architecture or real-time single-stage object detection model architecture.

[0071] Specific Adaptations for Gut Health Analysis:

[0072] In one embodiment, the method of a Gut Health Model (GHM) comprises modifying the YOLO architecture, including preventing overfitting and disallowing color transformations critical for the analysis. The specific adaptations focus on gut health and a unique dataset.

[0073] Application of YOLO for Gut Health:

[0074] In one embodiment, the method of a Gut Health Model (GHM) comprises applying the YOLO architecture to the specific problem of gut health detection in C. elegans and the applying adjustments to the YOLO architecture.

[0075] Scoring and Visualization Techniques:

[0076] In one embodiment, the method of a Gut Health Model (GHM) comprises using a sigmoid function to provide a normalized confidence score and converting the normalized confidence score for visualization. In one embodiment, the conversion of the normalized confidence scores of leaky gut is modified to 1 minus the original score.

[0077] High-Throughput Screening:

[0078] In one embodiment, the method of a Gut Health Model (GHM) comprises conducting high- throughput screening efficiently and economically. The GHM model addresses the limitations of manual scoring, such as low throughput and human bias.

[0079] Quantitative Analysis:

[0080] In one embodiment, the method of GHM comprises providing a gradient measure of gut health rather than a binary classification enhances the utility for various research and clinical applications.

[0081] An AI-Based System for Gut Health Classification:

[0082] In one embodiment, an AI-Based System for Gut Health Classification comprising an Al model configured to analyze high-magnification images of stained C. elegans to classify gut health into multiple categories, including healthy and leaky gut.

[0083] Modifications to YOLO Architecture:

[0084] In one embodiment, the GHM method comprises, specifically modifying the YOLO architecture for preventing overfitting, disallowing certain image transformations, and fine-tuning for gut health analysis.

[0085] Scoring and Visualization Method:

[0086] In one embodiment, a method for scoring gut health comprising using a sigmoid function to produce normalized confidence scores and visualizing the normalized confidence scores to represent gut health in a gradient manner.

[0087] High-Throughput Screening Capability:

[0088] In one embodiment, a system pipeline comprising utilizing the Al model for high- throughput screening of gut health in C. elegans and enabling large-scale analysis with reduced human bias.

[0089] Conclusion

[0090] The GHM model comprises a novel application of Al to gut health detection, specific adaptations for accuracy, and significant utility in high-throughput screening.

[0091] System

[0092] Generally speaking, the Al model or the GHM model is run on a processor-implemented computing device in which one or more aspects of the present disclosure may be implemented is shown. According to an embodiment, a processing system may generally comprise at least one processor, or processing unit or plurality of processors, memory, at least one input device and at least one output device, coupled together via a bus or group of buses. In certain embodiments, input device and output device could be the same device. An interface a can also be provided for coupling the processing system a to one or more peripheral devices, for example interface a could be a PCI card or PC card. At least one storage device which houses at least one database can also be provided. The memor can be any form of memory device, for example, volatile or non-volatile memory, solid state storage devices, magnetic devices, etc. The processor could comprise more than one distinct processing device, for example to handle different functions within the processing system. Input device receives input data and can comprise, for example, a keyboard, a pointer device such as a pen-like device or a mouse, audio receiving device for voice-controlled activation such as a microphone, data receiver or antenna such as a modem or wireless data adaptor, data acquisition card, etc. Input data could come from different sources, for example keyboard instructions in conjunction with data received via a network. Output device a produces or generates output data and can comprise, for example, a display device or monitor in which case output data is visual, a printer in which case output data is printed, a port for example a USB port, a peripheral component adaptor, a data transmitter or antenna such as a modem or wireless network adaptor, etc. Output data could be distinct and derived from different output devices, for example a visualdisplay on a monitor in conjunction with data transmitted to a network. A user could view data output, or an interpretation of the data output, on, for example, a monitor or using a printer. The storage device can be any form of data or information storage means, for example, volatile or nonvolatile memory, solid state storage devices, magnetic devices, etc.

[0093] In use, the processing system is adapted to allow data or information to be stored in and / or retrieved from, via wired or wireless communication means, at least one data storage structure (e.g. database). The interface may allow wired and / or wireless communication between the processing unit and peripheral components that may serve a specialized purpose. In general, the processor a can receive instructions as input data via input device and can display processed results or other output to a user by utilizing output device. More than one input device and / or output device can be provided. It should be appreciated that the processing system may be any form of terminal, server, specialized hardware, or the like.

[0094] It is to be appreciated that the processing system a may be a part of a networked communications system. Processing system a could connect to a network, for example the Internet or a WAN. Input data and output data could be communicated to other devices via the network. The transfer of information and / or data over the network can be achieved using wired communications means or wireless communications means. A server can facilitate the transfer of data between the network and one or more databases. A server and one or more databases provide an example of an information source.

[0095] Thus, the processing computing system environment may operate in a networked environment using logical connections to one or more remote computers. The remote computer may be a personal computer, a server, a router, a network PC, a peer device, or other common network node, and typically includes many or all of the elements described above.

[0096] It is to be further appreciated that the logical connections include a local area network (LAN) and a wide area network (WAN), but may also include other networks such as a personal area network (PAN). Such networking environments are commonplace in offices, enterprise- wide computer networks, intranets, and the Internet. For instance, when used in a LAN networking environment, the computing system environment is connected to the LAN through a network interface or adapter. When used in a WAN networking environment, the computing system environment typically includes a modem or other means for establishing communications over the WAN, such as the Internet. The modem, which may be internal or external, may be connected toa system bus via a user input interface, or via another appropriate mechanism. In a networked environment, program modules depicted relative to the computing system environment, or portions thereof, may be stored in a remote memory storage device. It is to be appreciated that the illustrated network connections described are exemplary and other means of establishing a communications link between multiple computers may be used.

[0097] This system intended to provide a brief, general description of an illustrative and / or suitable exemplary environment in which embodiments of the below described present invention may be implemented. This an example of a suitable environment and is not intended to suggest any limitation as to the structure, scope of use, or functionality of an embodiment of the present invention. A particular environment should not be interpreted as having any dependency or requirement relating to any one or combination of components illustrated in an exemplary operating environment. For example, in certain instances, one or more elements of an environment may be deemed not necessary and omitted. In other instances, one or more other elements may be deemed necessary and added.

[0098] Embodiments may be described in a general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform particular tasks or implement particular abstract data types. An embodiment may also be practiced in a distributed computing environment where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

[0099] The computer-executable program code may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational phases to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the code portions which execute on the computer or other programmable apparatus provide phases for implementing the functions / acts specified in the flowchart and / or block diagram block(s). Alternatively, computer program implemented phases or acts may be combined with operator or human implemented phases or acts in order to carry out an embodiment of the invention.

[0100] As the phrases are used herein, a processor may be “operable to” or “configured to” perform a certain function in a variety of ways, including, for example, by having one or more general-purpose circuits perform the function by executing particular computer-executable program code embodied in computer-readable medium, and / or by having one or more applicationspecific circuits perform the function.

[0101] The terms “program” or “software” are used herein in a generic sense to refer to any type of computer code or set of computer-executable instructions that can be employed to program a computer or other processor to implement various aspects of the present technology as discussed above. Additionally, it should be appreciated that according to one aspect of this embodiment, one or more computer programs that when executed perform methods of the present technology need not reside on a single computer or processor, but may be distributed in a modular fashion amongst a number of different computers or processors to implement various aspects of the present technology.

[0102] Any suitable transitory or non-transitory computer readable medium may be utilized. The computer readable medium may be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device. More specific examples of the computer readable medium include, but are not limited to, the following: an electrical connection having one or more wires; a tangible storage medium such as a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a compact disc read-only memory (CD-ROM), or other optical or magnetic storage device.

[0103] In the context of this document, a computer readable medium may be any medium that can contain, store, communicate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The computer usable program code may be transmitted using any appropriate medium, including but not limited to the Internet, wireline, optical fiber cable, radio frequency (RF) signals, or other mediums.

[0104] Computer-executable program code for carrying out operations of embodiments of the present invention may be written in an object oriented, scripted or unscripted programming language such as Java, Perl, Smalltalk, C++, or the like. However, the computer program code for carrying out operations of embodiments of the present invention may also be written inconventional procedural programming languages, such as the “C” programming language or similar programming languages.

[0105] Embodiments of the present invention are described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus(es), systems, and computer program products. It will be understood that each block of the flowchart illustrations and / or block diagrams, and / or combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-executable program code portions. These computer-executable program code portions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a particular machine, such that the code portions, which execute via the processor of the computer or other programmable data processing apparatus, create mechanisms for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0106] All publications and patent applications mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication or patent application was specifically and individually indicated to be incorporated by reference.

[0107] While the invention has been described in connection with various embodiments, it will be understood that the invention is capable of further modifications. This application is intended to cover any variations, uses or adaptations of the invention following, in general, the principles of the invention, and including such departures from the present disclosure as, within the known and customary practice within the art to which the invention pertains.

Claims

CLAIMSWhat is claimed is:

1. A method for rapid microfluidic in vivo bioassay for screening functional ingredients for improving gut health comprising:Conducting an age-induced leaky gut assay, a high sugar diet induced leaky gut assay, and a pathogen induced leaky gut assay in a microfluidic environment on C. elegans,' treating or feeding the C. elegans with a functional ingredient; and identifying changes in gut health caused by loss of gut barrier integrity in C. elegans in response to the functional ingredient.

2. The method of Claim 1, wherein the age-induced leaky gut assay comprises: maintaining C. elegans in the microfluidic environment with daily washing and media exchange until days 10-16 of life; treating the C. elegans with a salt dye solution for a first period of time at days 10- 16 of life and rinsing the C. elegans after the first period of time; and imaging the worms for a leaky gut phenotype.

3. The method of Claim 2, wherein the High-Sugar Diet-Induced Leaky Gut Assay comprises: maintaining C. elegans in the microfluidic environment with daily washing and media exchange until days 2-5 of life; exchanging the media with a glucose solution on days 3-6 of life; treating the C. elegans with a salt dye solution for a second period of time at days 10-16 of life and rinsing the C. elegans after the second period of time; and imaging the worms for the leaky gut phenotype.

4. The method of Claim 3, wherein the Pathogen-Induced Leaky Gut Assay comprises:maintaining C. elegans in the microfluidic environment with daily washing and media exchange until days 3-6 of life; exchanging the media with Pseudomonas aeruginosa on days 2-5 of life; treating the C. elegans with a salt dye solution for a third period of time at days 8- 12 of life and rinsing the C. elegans after the third period of time; and imaging the worms for the leaky gut phenotype.

5. The method of Claim 4, further comprising scoring of the leaky gut phenotypes into a healthy gut category, a moderately leaky category, or a severely leaky gut category.

6. The method of Claim 5, wherein the healthy gut category comprises the salt dye being restricted to the lumen of the intestine; the moderately leaky category comprises the salt dye translocate out of the lumen and into surrounding tissues of the intestine; and the severely leaky gut category comprises the salt dye staining all the body's peripheral tissues.

7. The method of Claim 6, further comprising reducing the incidence of age-associated leaky gut by probiotic treatment; changing the bacterial diet of C. elegans from E. coll to a probiotic strain belonging to the Lactobacillus genus or a probiotic strain belonging to Bacillus genus; and increasing the number of worms with the healthy gut category on days 13-18 of animal life with the C. elegans being fed Lactobacillus genus compared to the C. elegans being fed the Bacillus genus.

8. The method of Claim 7, comprising reducing the incidence of leaky caused by poor nutrition by probiotic treatment; feeding C. elegans with probiotic strains belonging to the Lactobacillus and Bacillus after a high-sugar diet; and the C. elegans fed with probiotic strains belonging to the Lactobacillus and Bacillus genera significantly reduces the numberof worms with leaky gut phenotype induced by the high sugar diet at days 10-14 of animal life.

9. The method of Claim 8, comprising reducing Leaky gut induced by enteropathogenic infection; feeding C. elegans with probiotic strains after infection of the gut by the enteropathogenic Pseudomonas aeruginosa strain; and the C. elegans fed with probiotic strains belonging to the Lactobacillus and Bacillus genera significantly reduces the number of C. elegans with leaky gut syndrome induced by Pseudomonas aeruginosa infection at days 8-12 of animal life.

10. The method of Claim 9, wherein the functional ingredient is selected from the group consisting of: pre-, pro-, postbiotics, metabolite, botanicals, proteins, soluble fibers, pharmaceutical compounds, vitamins, minerals, and combinations thereof.

11. The method of Claim 10, wherein the functional ingredient to treat leaky gut is identified when the functional ingredient reduces the incidence of age-associated leaky gut by the same or greater amount than the probiotic treatment of Lactobacillus genus.

12. The method of Claim 11, wherein the functional ingredient to treat leaky gut is identified when the functional ingredient reduces the incidence of leaky gut caused by poor nutrition by the same or greater amount than the probiotic treatment of Lactobacillus or Bacillus genus.

13. The method of Claim 12, wherein the functional ingredient to treat leaky gut is identified when the functional ingredient reduces the incidence of leaky gut induced by enteropathogenic infection by the same or greater amount than the probiotic treatment of Lactobacillus or Bacillus genus.

14. An Artificial Intelligence (Al) Based System for Gut Health Classification comprising, an Al model configured to analyze high-magnification images of stained C. elegans to classify gut health into a plurality of categories, including a healthy gut category and a leaky gut category.

15. The system of Claim 14, wherein the Al model comprises a real-time single-stage object detection model architecture and specifically modifying the real-time single-stage object detection model architecture for preventing overfitting, disallowing certain image transformations, and fine-tuning for gut health analysis.

16. The system of Claim 15, further comprising scoring gut health in C. elegans by using a sigmoid function to produce normalized confidence scores and visualizing the normalized confidence scores to represent gut health in a gradient manner.

17. The system of Claim 16, further comprising utilizing the Al model for high-throughput screening of gut health in C. elegans and enabling large-scale analysis with reduced human bias.

18. The system of Claim 17, wherein the Al model achieves a precision score greater than 0.92, a recall score greater than 0.85, and an Fl score of 0.88 for a healthy gut; the Al model predicted 98% of the C. elegans counts accurately as a leaky gut or a healthy gut; and the Al model prediction output achieved a degree of accuracy greater than 96%.

19. The system of Claim 18, wherein the Al model includes a normalized confidence between 0 and 1 for each class, the confidence score for all worms detected with leaky gut is 1 minus the original confidence score to illustrate the worms' gut health; and identifying a leaky gut phenotype with low scores, 0 - 0.4 being leaky and a high score of 0.6 - 1.0 being the healthy gut.

20. The system of Claim 19, wherein the Al model is trained on high-magnification images ofC. elegans stained with erioglaucine dye.

Images