WO2016038377A1

WO2016038377A1 - Biomarker

Info

Publication number: WO2016038377A1
Application number: PCT/GB2015/052622
Authority: WO
Inventors: James Covington; Ramesh Arasaradnam
Original assignee: The University Of Warwick
Priority date: 2014-09-10
Filing date: 2015-09-10
Publication date: 2016-03-17
Also published as: GB201416015D0

Abstract

A invention relates to a method for diagnosing a subject, or for providing a prognosis of the subject's condition. The method comprises analysing the concentration of a signature compound in a bodily sample from a test subject and comparing this concentration with a reference for the concentration of the signature compound in an individual who does not suffer from the disease being screen for. An increase in the concentration of the signature compound in the bodily sample from the test subject compared to the reference suggests that the subject is suffering from the disease being screen for, or has a pre-disposition thereto, or provides a negative prognosis of the subject's condition. The disease being screened for is coeliac disease or bile acid diarrhoea.

Description

Biomarker

The present invention relates to biomarkers, and particularly although not exclusively, to novel biological markers for diagnosing conditions where a symptom is diarrhoea. In particular, the invention relates to the use of these compounds as diagnostic and prognostic markers in assays for detecting bile acid diarrhoea and coeliac disease. The invention also relates to methods of determining the efficacy of treating these diseases with a therapeutic agent, and apparatus for carrying out the assays and methods. The assays are qualitative and/ or quantitative, and are adaptable to large-scale screening and clinical trials.

Chronic diarrhoea is a significant clinical problem estimated to affect up to 5% of the population. There are many causes for chronic diarrhoea but bile acid diarrhoea (BAD) is one of the commonest. Bile acids are essential for the emulsification and subsequent digestion of fat. More than 98% of bile acids produced are reabsorbed back in to circulation, with less than 2% lost in faeces. If this process of reabsorption is perturbed either through disease, surgical removal of a length of bowel or through defects in certain regulatory proteins, then, the excess bile that is not reabsorbed spills over into the colon resulting in symptoms of diarrhoea. The excess bile acids can be 'mopped up' or sequestered effectively using medication known as bile acid sequestrants.

Although common, BAD is under-diagnosed partly as it requires nuclear medicine imaging and ingestion of a radioactive capsule (Selenium 75 tagged to homo- chlorotauric acid - SeHCAT). The SeHCAT retention test involves a synthetically tagged isotope, which is swallowed and diluted within the bile acid circulation and thus able to track its movements. This is the accepted gold standard to diagnose BAD but the cost is prohibitive, i.e. approximately £210 ($320) per patient, and thus in some areas patients have been denied the opportunity to have this diagnosis made.

Another condition which may result in chronic diarrhoea is coeliac disease. This is a T- cell mediated gluten sensitive enteropathy, affecting approximately 1% of the UK population, although only 10-15% of patients with the condition are diagnosed. It can be clinically difficult to distinguish from diarrhoea predominant irritable bowel Syndrome (D-IBS); a non-inflammatory, multifactorial chronic condition affecting the GI tract. The gold standard for diagnosis of coeliac disease is histopathological examination of small bowel biopsies, following initial serological investigations on patients in whom coeliac disease is suspected. Serological screening tests have been developed over the years and those currently in use are Anti-gliadin antibodies, anti- endomysial and anti-tissue transglutaminase (TTG) antibodies with the latter two being the most accurate. Anti-endomysial tests showed a lower sensitivity than for dual (IgA and IgG) anti TTG antibodies (62 - 68% vs 90- 92%) but a higher specificity (80- 99% vs 81 - 83%). Combination testing of both endomysial and TTG antibodies has shown a slight increase in positive predictive value, negative predictive value and specificity, at the expense of sensitivity.

Both these serological tests however have had their accuracy questioned in young patients, the elderly and those with minimal mucosal damage. Furthermore their accuracy at monitoring response to a gluten free diet has also been debated. The value of these tests are further impaired in cases where the patients suffers from IgA deficiency and so the IgA antibodies that the tests would normally detect can be absent, leading to a false negative diagnosis.

The detection of specific patterns of volatile organic compounds (VOCs) in urine, breath, sweat and faeces has been a developing novel tool in recent years for the noninvasive detection of various disease states. The analysis of the VOCs pattern in patient's breath using GCMS (Gas Chromatography and Mass Spectrometry) has been shown to distinguish not just cancer from non-cancer patients but also various cancer subtypes including lung, breast, prostate and colorectal cancer. Furthermore analysis of VOCs in faeces has distinguished colorectal cancer from controls using Electronic nose (E-nose) technology. VOCs patterns in urine have been analysed by E-nose and Field Asymmetric Ion Mobility Studies (FAIMS) and these have been able to distinguish between not only Inflammatory Bowel Disease (IBD) and healthy control patients but between patients with Crohn's disease and ulcerative colitis (UC) and active disease from quiescent. Patients with significant gastrointestinal side effects following pelvic radiotherapy have also been identified in this way. VOCS have been found to be perturbed in many physiological and pathological states, including different diets and numerous disease states. The exact mechanism by which VOCs are generated is the subject of current research but their generation in the bowel is believed to be the result of dietary non-starch polysaccharides undergoing

fermentation. As such, they represent the complex interaction of colonic cells, human gut microflora and invading pathogens. The resultant products of fermentation, known as the 'fermentome' can exist in the gaseous phase and are present in exhaled air, sweat, urine and faeces. Their presence in sweat, exhaled air and urine is presumed possible due to the altered gut permeability afforded in certain gut diseases. The inventors believe that VOCs represent a bio-signature that reflects the sum of the multifactorial influences (genetics, environmental factors including diet and disease states) affecting an individual.

What is required is a reliable non-invasive marker to identify patients suffering from bile acid diarrhoea or coeliac disease. A diagnostic method to identify those patients with bile acid diarrhoea or coeliac disease would be of immense benefit to patients and would raise the possibility of early treatment and improved prognosis.

The inventors have now determined several biomarkers or so-called signature compounds as being indicative of bile acid diarrhoea or coeliac disease. Hence, in a first aspect, there is provided a method for diagnosing a subject, or for providing a prognosis of the subject's condition, the method comprising analysing the concentration of a signature compound in a bodily sample from a test subject and comparing this concentration with a reference for the concentration of the signature compound in an individual who does not suffer from the disease being screen for, wherein an increase in the concentration of the signature compound in the bodily sample from the test subject compared to the reference suggests that the subject is suffering from the disease being screen for, or has a pre-disposition thereto, or provides a negative prognosis of the subject's condition, wherein the disease being screened for is coeliac disease or bile acid diarrhoea.;.

In a second aspect, there is provided a method for determining the efficacy of treating a subject suffering from a disease with a therapeutic agent or specialised diet, the method comprising analysing the concentration of a signature compound in a bodily sample from a test subject and comparing this concentration with a reference for the concentration of the signature compound in an individual who does not suffer from the disease, wherein a difference in the concentration of the signature compound in the bodily sample compared to the reference is indicative of the efficacy of treating the test subject with the therapeutic agent, wherein the disease being screened for is coeliac disease or bile acid diarrhoea. In a third aspect, there is provided an apparatus for diagnosing a subject suffering from a disease, or for providing a prognosis of the subject's condition, the apparatus comprising:-

(i) means for determining the concentration of a signature compound in a sample from a test subject; and

(ii) a reference for the concentration of the signature compound in a sample from an individual who does not suffer from coeliac disease and/ or bile acid diarrhoea,

wherein the apparatus is used to identify an increase in the concentration of the signature compound in the sample from the test subject compared to the reference concentration, thereby suggesting that the test subject suffers from coeliac disease and/ or bile acid diarrhoea, or has a pre-disposition thereto, or providing a negative prognosis of the subject's condition, and the disease is coeliac disease or bile acid diarrhoea.

In a fourth aspect, the invention provides an apparatus for determining the efficacy of treating a subject suffering from disease with a therapeutic agent or a specialised diet, the apparatus comprising:-

(i) means for determining the concentration of a signature in a sample from a test subject; and

wherein the apparatus is used to identify a difference in the concentration of signature compound in the sample from the test subject compared to the reference concentration, the difference in concentration being indicative of the efficacy of treating the test subject with the therapeutic agent, and the disease is coeliac disease or bile acid diarrhoea.

According to a fifth aspect of the invention, there is provided a method of treating an individual suffering from a disease, said method comprising the steps of:

(i) determining the concentration of a signature compound in a sample from a test subject concentration, wherein an increase in the concentration of a signature compound in the bodily sample from the test subject compared to the concentration of signature compound in a sample from an individual who does not suffer from coeliac disease and/or bile acid diarrhoea, suggests that the test subject suffers from coeliac disease and/ or bile acid diarrhoea, or is pre-disposed thereto, or has a negative prognosis, and the disease is coeliac disease or bile acid diarrhoea; and

(ii) administering, to the test subject, a therapeutic agent or putting the test subject on a specialised diet, wherein the therapeutic agent or specialised diet prevent, reduce or delay progression of the disease.

An important feature of any useful biomarker used in disease diagnosis and prognosis is that it exhibits high sensitivity and specificity for a given disease. Firstly, as explained in the examples, the inventors have surprisingly demonstrated that a number of signature compounds are found in the gaseous phase of urine. Secondly, they have found that any of these compounds can serve as robust biomarkers for diseases such as bile acid diarrhoea (being surprisingly able to distinguish this disease from Ulcerative Colitis, a disease with similar symptoms but different causality) and coeliac disease (being surprisingly able to distinguish this disease from diarrhoea predominant Irritable bowel Syndrome, a disease with similar symptoms but different causality), and can therefore be used for the detection of these diseases, and disease prognosis. In addition, the inventors have shown that using such signature compounds as a biomarker for disease employs an assay which is simple, reproducible, non-invasive and inexpensive, and with minimal inconvenience to the patient.

Currently, bile acid diarrhoea is diagnosed using nuclear medicine imaging and ingestion of a radioactive capsule (SeHCAT) and coeliac disease is diagnosed using histopathological examination of small bowel biopsies. Advantageously, the methods and apparatus of the invention provide a non-invasive means for diagnosing these and other various diseases. The method according to the first aspect is useful for enabling a clinician to make decisions with regards to the best course of treatment for a subject who is currently or who may suffer from a selected disease. It is preferred that the method of the first aspect is useful for enabling a clinician to decide how to treat a subject who is currently suffering from a selected disease. In addition, the methods of the first and second aspects are useful for monitoring the efficacy of a putative treatment for a disease, for example if the disease is bile acid diarrhoea treatment may comprise administration of bile acid sequestrants, such as Cholestyramine or

Colestipol, where dosage is proportional to severity of bile acid diarrhoea and if the disease is coeliac disease the treatment may comprise implementation of a gluten free diet. Hence, the apparatus according to the third and fourth aspects are useful for providing a prognosis of the subject's condition, such that the clinician can carry out the treatment according to the fifth aspect. The apparatus of the third aspect may be used to monitor the efficacy of a putative treatment for the diarrhoea. The methods and apparatus are therefore very useful for guiding treatment regime for the clinician, and to monitor the efficacy of such a treatment regime. The clinician may use the apparatus of the invention in conjunction with existing diagnostic tests (e.g. SeHCAT and/ or histopathological examination of small bowel biopsies) to improve the accuracy of diagnosis.

Preferably, the signature compound is selected from a group of compounds consisting of: octatetraene; cyclooctatetraene; 1,3,5,7-cyclooctatetraene; 2,6-dimethyl-i,3,5,7- octatetraene; i,8-diphenyl-i,3,5,7-octatetraene; N-[(4-hydroxy)hydrocinnamoyl]- benzene-ethanamine; styrene; benzene; bicyclo[4.2.o]octa-i,3,5-triene; l-methylethyl hydroperoxide; l-methyl-i-phenylethyl hydroperoxide; 4-penten-2-ol; i-penten-4-ol; 4-methyl-4-penten-2-ol; l-pentene; 4-methyl-i-pentene; 3-methyl-i-penten; ethyl cyclopropane; i-ethyl-2-methylcyclopropane; propane; ethylenediamine; methyl- cyclopropane; tetramethyl oxirane; 3-ethyl-2,2-dimethyl oxirane; N-methyl ethanamine; N-methyltryptamine; isopropyl alcohol (2-propanol); i-amino-2- propanol; acetamide; Ν,Ν-dimethylacetamide; acetone; cyclopentane; pentane; and heptane .

Preferably, the signature compound comprises a 2-propanol group, for example isopropanol or i-amino-2-propanol.

In one embodiment, the disease being screened for is coeliac disease, and the signature compound is selected from a group of compounds consisting of: octatetraene;

cyclooctatetraene; 1,3,5,7-cyclooctatetraene; 2,6-dimethyl-i,3,5,7-octatetraene; 1,8- diphenyl-i,3,5,7-octatetraene; N-[(4-hydroxy)hydrocinnamoyl]-benzene-ethanamine; styrene; benzene; and bicyclo[4.2.o]octa-i,3,5-triene, preferably cyclooctatetraene, more preferably 1,3,5,7-cyclooctatetraene. Preferably, the method of the second aspect is for determining the efficacy of treating a subject suffering from coeliac disease with a specialised diet. Preferably, the specialised diet comprises a gluten free diet.

In an alternative embodiment, the disease being screened for is bile acid diarrhoea, and the signature compound is selected from a group of compounds consisting of: 1- methylethyl hydroperoxide; l-methyl-i-phenylethyl hydroperoxide; 4-penten-2-ol; 1- penten-4-ol; 4-methyl-4-penten-2-ol; l-pentene; 4-methyl-i-pentene; 3-methyl-i- penten; ethyl cyclopropane; i-ethyl-2-methylcyclopropane; propane; ethylenediamine; methyl-cyclopropane; tetramethyl oxirane; 3-ethyl-2,2-dimethyl oxirane; N-methyl ethanamine; N-methyltryptamine; isopropyl alcohol (2-propanol); i-amino-2- propanol; acetamide; N,N-dimethylacetamide; Ν,Ν-dimethylacetamide; acetone; cyclopentane; pentane; and heptane. Preferably, the method of the second aspect is for determining the efficacy of treating a subject suffering from bile acid diarrhoea with a therapeutic agent.

The methods, apparatus and uses may also comprise analysing the concentration of an analogue or a derivative of the signature compound. Examples of suitable analogues or derivatives of chemical groups which may be assayed include alcohols, ketones, aromatics, organic acids and gases (such as CO, C0₂, NO, N0₂, H₂S, S0₂, CH₄).

The subject may be any animal of veterinary interest, for instance, a cat, dog, horse etc. However, it is preferred that the subject is a mammal, such as a human, either male or female.

Preferably, a sample is taken from the subject, and the concentration of the signature compound in the bodily sample is then measured.

The signature compounds, which are detected, are known as volatile organic compounds (VOCs), which lead to a fermentation profile, and they may be detected in the bodily sample by a variety of techniques. In one embodiment, these compounds maybe detected within a liquid or semi-solid sample in which they are dissolved. In a preferred embodiment, however, the compounds are detected from gases or vapours. For example, as the signature compounds are VOCs, they may emanate from the sample, and may thus be detected in gaseous or vapour form.

The apparatus of the third or fourth aspect may comprise sample extraction means for obtaining the sample from the test subject. The sample extraction means may comprise a needle or syringe or the like. The apparatus may comprise a sample collection container for receiving the extracted sample, which may be liquid, gaseous or semisolid. Preferably the sample is any bodily sample into which the signature compound is secreted. For example, the sample may comprise urine, faeces, hair, sweat, saliva, blood or tears. The inventors believe that the VOCs are breakdown products of other compounds found within the blood. Blood samples may be assayed for the signature compound's levels immediately. Alternatively, the blood maybe stored at low temperatures, for example in a fridge or even frozen before the concentration of signature compound is determined. Measurement of the signature compound in the bodily sample maybe made on whole blood or processed blood.

The sample is preferably a urine sample. It is preferred that the concentration of the signature compound in the bodily sample is measured in vitro from a urine sample taken from the subject. Most preferably, the compound is detected from gases or vapours emanating from the urine sample. It will be appreciated that detection of the compound in the gas phase emitted from urine is most preferred.

It will also be appreciated that "fresh" bodily samples may be analysed immediately after they have been taken from a subject. Alternatively, the samples may be frozen and stored. The sample may then be de-frosted and analysed at a later date.

The difference in concentration of signature compound in the methods of the second aspect or the apparatus of the fourth aspect maybe an increase or a decrease compared to the reference. As described in the examples, the inventors monitored the

concentration of signature compounds in numerous patients who suffered from a given disease, and compared them to the concentration of these compounds in individuals who did not suffer from the disease (i.e. controls). They demonstrated that there was a statistically significant increase in the concentration of these compounds in the patients suffering from the disease. Indeed, the inventors found that the urine from subjects suffering from bile acid diarrhoea contained much higher quantities of signature compounds compared to the urine from subjects with Ulcerative Colitis and healthy individuals. Thus, preferably the difference in concentration of signature compound in the method of the second aspect or the apparatus of the fourth aspect is an increase compared to the reference.

It will be appreciated that the concentration of signature compound in patients suffering from a disease is highly dependent on a number of factors, for example how far the disease has progressed, and the age and gender of the subject. It will also be appreciated that the concentration of signature compound in individuals who do not suffer from the disease may fluctuate to some degree, but that on average over a given period of time, the concentration tends to be substantially constant. In addition, it should be appreciated that the concentration of signature compound in one group of individuals who suffer from a disease may be different to the concentration of that compound in another group of individuals who do not suffer from the disease.

However, it is possible to determine the average concentration of signature compound in individuals who do not suffer from bile acid diarrhoea, and this is referred to as the 'normal' concentration of signature compound. The normal concentration corresponds to the reference values discussed above in the first to fifth aspects. In one embodiment, the method of the invention preferably comprises determining the ratio of chemicals within the urine (i.e. use other components within it as a reference), and then compare these markers to the disease to show if they are elevated.

The signature compound is preferably a volatile organic compound (VOC), which leads to a fermentation profile, and it may be detected in or from the bodily sample by a variety of techniques. Thus, these compounds may be detected using a gas analyser.

Examples of suitable detector for detecting the signature compound preferably includes an electrochemical sensor, a semiconducting metal oxide sensor, a quartz crystal microbalance sensor, an optical dye sensor, a fluorescence sensor, a conducting polymer sensor, a composite polymer sensor, or optical spectrometry.

The inventors have demonstrated that the signature compounds can be reliably detected using electronic nose methodology, a Field Asymmetric Ion Mobility

Spectrometer (FAIMS), gas chromatography, mass spectrometry, GCMS or TOF.

Preferably, electronic nose methodology or FAIMS is used for the detection step.

The reference values may be obtained by assaying a statistically significant number of control samples (i.e. samples from subjects who do not suffer from the disease).

Accordingly, the reference (ii) according to the apparatus of the third and fourth aspects of the invention may be a control sample (for assaying).

The apparatus may comprise a positive control (preferably provided in a container), which corresponds to the signature compound. The apparatus may comprise a negative control (preferably provided in a container). In a preferred embodiment, the apparatus may comprise the reference, a positive control and a negative control. The apparatus may also comprise further controls, as necessary, such as "spike-in" controls to provide a reference for concentration, and further positive controls for each of the signature compounds, or an analogue or derivative thereof.

Accordingly, the inventors have realised that the difference in concentrations of signature compound between the normal (i.e. control) and increased levels, can be used as a physiological marker, suggestive of the presence of a disease in the test subject. It will be appreciated that if a subject has an increased concentration of one or more signature compounds which is considerably higher than the 'normal' concentration of that compound in the reference, control value, then they would be at a higher risk of having the disease, or a condition that was more advanced, than if the concentration of that compound was only marginally higher than the 'normal' concentration.

The inventors noted that the concentration of signature compounds referred to herein in the test individuals was statistically more than the reference concentration (as calculated using the method described in the Example). This may be referred to herein as the 'increased' concentration of the signature compound.

The skilled technician will appreciate how to measure the concentrations of the signature compound in a statistically significant number of control individuals, and the concentration of compound in the test subject, and then use these respective figures to determine whether the test subject has a statistically significant increase in the compound's concentration, and therefore infer whether that subject is suffering from the disease which has been screened for. In the method of the second aspect and the apparatus of the fourth aspect, the difference in the concentration of the signature compound in the bodily sample compared to the corresponding concentration in the reference is indicative of the efficacy of treating the subject's disease with the therapeutic agent or specialist diet, for example a bile acid sequesterant or a gluten free diet. The difference may be an increase or a decrease in the concentration of the signature compound in the bodily sample compared to the reference value. In embodiments where the concentration of the compound in the bodily sample is lower than the corresponding concentration in the reference, then this would indicate that the therapeutic agent or specialist diet is successfully treating the disorder in the test subject. Conversely, where the

concentration of the signature compound in the bodily sample is higher than the corresponding concentration in the reference, then this would indicate that the therapeutic agent or specialist diet is not successfully treating the disorder.

All features described herein (including any accompanying claims, abstract and drawings), and/ or all of the steps of any method or process so disclosed, may be combined with any of the above aspects in any combination, except combinations where at least some of such features and/ or steps are mutually exclusive.

For a better understanding of the invention, and to show how embodiments of the same may be carried into effect, reference will now be made, by way of example, to the accompanying Figures, in which: -

Figure l shows the raw Asymmetric Ion Mobility Studies (FAIMS) output for a coeliac patient urine sample;

Figure 2 shows a heat map of the FAIMS features identified as informative where each row corresponds to a given sample and each column corresponds to a given feature; Figure 3 is a scatter plot of tissue transglutaminase (TTG) serology vs classification probability for coeliac cases;

Figure 4 is a box-and-whisker plot of the classification probabilities by disease group generated by sparse logistic regression;

Figure 5 is a section of coeliac disease sample chromatogram showing a unique peak; Figure 6 is a section of a mass spectrum showing to unique gas chromatography (GC) peaks;

Figure 7(a) shows raw electronic nose results showing the sensor responses to a bile acid diarrhea (BAD) patient urine sample, and Figure 7(b) shows raw data from the FAIMS instrument to a BAD patient urine sample;

Figure 8 shows electronic nose average responses to different sample groups;

Figure 9(a) shows Linear Discriminant Analysis of AlphaMOS Fox 4000 results, and Figure 9(b) shows associated loadings plot for LDA (DF is discriminant function); Figure 10 shows Linear Discriminant Analysis of FAIMS data; and

Figure 11 shows a section of a BAD sample GC Chromatogram showing unique peaks.

Example 1 - Coeliac Disease

Materials and Methods

Subjects 47 patients were recruited prospectively for this study. The mean age was 48 years (SD 17) and there were 13 males. 27 patients had coeliac disease, confirmed histologically according to Marsh Criteria or according to HLA genotyping coupled with tTG serology. The coeliac patients were established on gluten free diets at the time of urine specimen collection. Some patients were established on long term (10 years or more) gluten free diets and some were more recent diagnoses. tTG serology was performed on all the patients, either at initial screening or for monitoring in the long term patients. 20 patients had D-IBS according to the ROME II criteria with negative tTG serology, normal TSH as well as colonoscopy. These patients were selected as they were on diets inclusive of gluten. The demographics of the subjects are shown in table 1.

Table 1: Demographic data of subjects

Study Design

This was a case control study where patients were recruited from dedicated

Gastroenterology outpatient clinics at University Hospital Coventry & Warwickshire, UK. Urine was then collected in standard universal sterilin specimen containers (Newport, UK) and frozen at -8o°C for subsequent batch analysis, within 2 hours of collection.

Analysis

Urine samples were thawed by carefully raising the sample temperature to 5°C in a controlled procedure (usually done overnight) and then divided into separate 5 mL aliquots for analysis in each of the instruments employed in this study. The samples were aliquoted whilst still at this temperature to minimise loss of the chemical signal. One of these was transferred into a 20 mL glass vial by pipette and heated to 60 °C to produce a reasonable headspace of volatiles. This headspace was extracted, mixed with a make-up flow of clean air at a ratio of 1:3, and run through a Lonestar Field

Asymmetric Ion Mobility Studies (FAIMS) (Owlstone Ltd.) using an attached ATLAS sampling unit and split flow box. The headspace of each sample was used to produce three full matrices of FAIMS data from the instrument, and blanks of clean, dry air were run both before and after each urine sample to ensure that the baseline response was returned. FAIMS is a process that separates and then measures the concentration of gases and vapours based on their different mobilities in high electric fields. In addition, another 5 mL aliquot was pipetted into a 10 mL glass vial and sealed with a crimp lid for analysis using a Bruker Scion SQ gas chromatograph - mass spectrometer (GC-MS) fitted with a Restek Rxi-624Sil MS fused silica GC column (length 20 m, 0.18 mm internal diameter, 1.0 μπι wall thickness) and a Combipal Autosampler (CTC, Switzerland). Due to the expected small concentrations of chemical components within the sample, the autosampler was improved by attaching a solid phase micro-extraction (SPME) pre-concentration fibre composed of poly-dimethylsiloxane (PDMS) of thickness 100 um. These sealed aliquots were individually heated to 6o°C for 5 minutes, before the SPME fibre was introduced into the vials for a further 10 minutes to absorb the volatile organic compounds being released into the headspace above the urine. The now-saturated fibre was then heated to 250°C at the GC injector port to introduce the desorbed volatiles into the machine. Samples were mixed with helium carrier gas when entering the column at a split ratio of 1:20 to maintain peak sharpness at the end detector. The GC oven followed a temperature programme for each sample in order to separate the constituent VOCs in terms of boiling point and molecular weight, by first holding at 50°C for 1 minute before increasing at a constant rate of 20°C /s up to a maximum of 280 °C. The separated compounds were detected by chromatography, then fragmented and analysed by the mass spectrometer. Alternate 5mL samples of de- ionised water were run through the system in between each urine sample, in order to verify that non of the VOCs identified were introduced from the external environment.

Statistical Methods

In order to assess the FAIMS system's ability to differentiate between coeliac disease and irritable bowel syndrome, the inventors performed a leave-one-out cross-validation (LOO-CV), using several machine learning classification algorithms. Similar statistical methods have been used in previous studies (Arasaradnam et al, 2013). LOO-CV is a technique for assessing the ability to make good predictions as to the disease class of an unseen sample. The method proceeds by training a classification algorithm on data from all-except-one of the samples. The algorithm is then used to predict the disease state of the held-out sample. Because the algorithm has no knowledge of the true disease state of this held-out sample, its prediction can be compared to the ground truth as a fair test of performance. This process was repeated in turn for each sample to obtain a fair test of predictive ability across the whole data set. The inventors repeated this procedure for each of the classification algorithms (Hastie et al, 2009).

Before performing the LOO-CV, the inventors applied some data pre-processing in order to better extract the signal from the data. The inventors applied a lD

(Daubechies) wavelet transformation to the data vector from each sample, using the R package 'wavethresh'. Wavelets are a common method of data reduction used for audio compression (Chui, 1992). They then removed all the wavelet coefficients whose variance across the data set is below a given threshold, on the basis that these will be dominated by noise. Finally, before training the classification algorithms, they used a Wilcoxon rank-sum test to find the most informative features as to disease state. The inventors emphasise that this final step is performed inside the LOO-CV loop, and only on the training data, so that it cannot bias the results. The variance threshold and the number of features kept from the Wilcoxon analyses are parameters that have been tuned by hand to a limited degree in this analysis.

The inventors considered three classification algorithms, all of which are known to give good performance for a wide range of tasks. It was important to consider several algorithms here, as some will typically be better suited to a given task than others. The inventors use the following machine learning classification algorithms (Murphy, 2012):

Sparse logistic regression: A version of logistic regression that imposes feature sparsity via an elasticnet prior. This has the effect of removing uninformative features from the analysis, thereby improving the quality of the analysis.

Random Forest classification: An ensemble of decision trees, which leads to highly flexible data modelling.

• Support Vector Machine: A kernel-based method for separating the data space - ι₅ - into separate disease subspaces.

Ethics

Scientific and ethical approval was obtained from local Research & Development Office as well as Warwickshire Ethics Committee ref: 09/H1211/38. Written informed consent was obtained from all patients who participated in the study.

Results

As mentioned above, the demographic data of the coeliac disease group and the D-IBS controls are described in Table 1. Details of the tTG titres and the Marsh classifications for the coeliac patients are shown in Table 2. It should be noted that two patients did not have their Marsh scores available, both were established on long term gluten free diets and had a tTG titre of <ikU/L at the time of urine collection. Table 2: Tissue Transglutamase (TTG) titres at time of specimen collection and Marsh scores at diagnosis

*HLADQ2+ A list of all drugs that the D-IBS and coeliac patients were taking at the time of urine collection can be seen in Table 3.

Table 3: Drugs being taken by coeliac and D-IBS patients at time of urine collection

Medication Coeliac D-IBS (n=20)

Disease

(n=27) Gastrointestinal Antispasmodics 2.1% (1/47) 6.4% (3/47) tract (Mebeverine,

Buscopan)

Laxatives 2.1% (1/47) 8.5% (4/47) (Fybogel,

Movicol,

Lactulose)

Anti-diarrhoea 2.1% (1/47) 4-3% (2/47) (Loperamide)

Bile acid 2.1% (1/47) 0% (0/47) sequestrants

(Ursodeoxycholic

acid)

5HT 4 agonist 0% (0/47) 4-3% (2/47) (Prucalopride)

Proton Pump 0% (0/47) 14.9% (7/47) Inhibitors

(omeprazole,

lansoprazole)

Anti-emetics 0% (0/47) 2.1% (1/47) (Domperidone)

Multivitamins 0% (0/47) 6.4% (3/47)

Others Iron 2.1% (1/47) 2.1% (1/47)

Antidepressants 11% (5/47) 13% (6/47) (SSRIs, TCAs)

Bisphosphonates 19% (9/47) 0% (0/47)

Calcium & 19% (9/47) 0% (0/47) Vitamin D

supplementation

Thyroxine 4-3% (2/47) 0% (0/47)

Antibiotics 2.1% (1/47) 0% (0/47)

(trimethoprim/

nitrofurantoin)

Opioids 4-3% (2/47) 4-3% (2/47)

Antihistamine 4-3% (2/47) 0% (0/47)

Hormone 6.4% (3/47) 0% (0/47) replacement

therapy/COCP

Warfarin 2.1% (1/47) 0% (0/47)

Antipsychotics 0% (0/47) 2.1% (1/47)

Pregabalin 2.1% (1/47) 0% (0/47)

Monteleukast 2.1% (1/47) 0% (0/47)

Cardiovascular Anti6.4% (3/47) 2.1% (1/47) hypertensives Statins 6.4% (3/47) 4-3% (2/47)

Diuretics 2.1% (1/47) 0% (0/47)

Aspirin 2.1% (1/47) 0% (0/47)

Diabetic Insulin 2.1% (1/47) 0% (0/47)

Oral 2.1% (1/47) 0% (0/47)

hypoglycaemics

FAIMS

The analysis of the FAIMS data for coeliac patients and controls was carried out using three different machine learning classifiers, as described above. Figure 1 shows a raw plot of the data created by FAIMS technique. As mobility of a chemical is not constant and is a function of applied electric field, the instrument scans through a range of different settings (which is described by the dispersion field in Figure 1), with the compensation voltage being a fixed DC voltage that compensates for the mobility of the molecule, allowing gas/vapour molecules with only that specific mobility to be measured.

The results are shown in Table 4 which gives the receiver operating characteristic (ROC) curve Area-Under-Curve (AUC) scores, sensitivities and specificities for the three classification algorithms. The values are computed using a leave-one-out cross- validation. The 95% confidence intervals are shown in brackets. The sensitivities and specificities are determined from the ROC curve, selecting in each case a threshold that gives good values for both. It can be seen that the best performance was obtained using sparse logistic regression, with a ROC curve AUC of 0.91 (0.83 - 0.99), Sensitivity of 0.85 (0.66 - 0.96), and Specificity of 0.85 (0.62 - 0.97).

Table 4: Results of the machine learning analysis

Figure 2 shows a heat map of the FAIMS features identified as informative where each row corresponds to a given sample and each column corresponds to a given feature. As can be seen, there is a clear difference in the data signatures between coeliac and D-IBS patients. This signature leads to the strong predictive performance of the machine learning algorithms.

Table 5 and Figure 3 show comparisons between the classification probabilities and (respectively) Marsh score, and TTG serology. The classification probabilities are the probability of a given patient having coeliac disease, as determined by the sparse logistic regression algorithm. The overall correlation of these points is 0.28. One outlying point with TTG>6o kU/L has been removed from the data. As can be seen, within this data set there are no strong relationships between the probability of having coeliac (as determined by sparse logistic regression) and either Marsh score or TTG serology. As mentioned above, two patients did not have their Marsh scores available, both were established on long term gluten free diets and had a tTG titre of <ikU/L at the time of urine collection. Table 5: Predicted probability of coeliac disease and Marsh scores at diagnosis

*HLADQ2+

Figure 4 shows the classification probabilities generated by sparse logistic regression, plotted by disease group. The boxes show the interquartile ranges. The whiskers show the data range, but are truncated to a maximum of twice the interquartile range.

GC-MS

The data from the GC-MS were analysed by observing the retention times of chromatogram peaks, and comparing the corresponding mass spectra to those from a known NIST library of chemical components. This comparison comprises a measure of both forward- and reverse- matching between observed and known spectra which produce a list, ranked by probability, of potential chemical compounds that could have caused each peak.

In order to discover the most likely VOCs that make up a urine headspace sample, the highest-probability matching compounds for peaks at the same GC retention times were tallied for all samples and the most common were suggested as the probable source. Only clear peaks above the 1.8 MCps (microporous co-ordination polymers) threshold were identified, to ensure that the signals were significantly above the noise floor of the instrument. We identified over 70 separate chemicals, but there was a high variation in individual sample composition, but a number of VOCs were found to be present in urine samples with a significant degree of certainty. Table 6 lists the GC peaks found in the majority of urine samples along with their retention times, associated mass spectra peaks, and highest probability NIST library 'hits'. Table 6: Mass Ion Peaks and NIST Identifications of GC Peaks

Notably, one of the compounds discovered using this method was observed at approximately 4.67 minutes in the chromatograms of the samples taken from coeliac disease patients, while being absent in those of D-IBS sufferers (Figures 5 and 6). The compound with the mass spectrum that is by far the most consistent with those observed here is 1, 3, 5, 7 cyclooctatetraene, as shown in Figure 5. A mass spectrum of a GC peak from one of the coeliac samples is shown in Figure 6, illustrating the mass ratios of the major components found in this region. The peak at 104 likely corresponds to cyclooctatetraene (CsHg), and the peaks at 78, 63, 51 and 40 likely correspond to ϋόΗό, C₅H₃, C₄H₃ and C₃H₃ respectively which are all common fragmentations seen to come from cyclooctatetraene. Other compounds with mass spectrum that are consistent with those observed here are N-[(4-hydroxy)hydrocinnamoyl]-benzene-ethanamine, styrene and bicyclo[4.2.o]octa-i,3,5-triene. Finally, the peak at 44 is a common base peak for many organic compounds, including cyclooctatetraene.

Discussion

The inventors have found evidence that FAIMS has potential applications as an alternative non-invasive test for the initial screening of patients suspected of having coeliac disease. This may be done via the detection of a unique gas phase bio-odorant fingerprint found in the urine of patients with coeliac disease. This expands on previous research which has shown that E-nose and FAIMS analysis can analyse and distinguish the VOCs patterns in urine of patients with UC, Crohn's disease, bile acid diarrhoea, IBS and healthy controls (15).

The FAIMS data for the coeliac patients showed tight clustering and high

reclassification accuracy, suggesting a discernable VOC profile. With suitable feature extraction, coeliac patients and IBS patients could be separated by FAIMS with a sensitivity and specificity of 85%. IBS tends to be diagnosed in patients with diarrhoea, constipation or abdominal discomfort for which no underlying cause can be

ascertained. Therefore, instead of a distinct VOC profile, there is likely to be large patient-to-patient variation, and this is reflected in the data found here.

Additionally, data given by the GC-MS has revealed a peak unique for those with coeliac disease - specifically mass spectra that indicate it is most likely due to the volatile compound cyclooctatetraene. Other compounds that the unique peak may correspond to include N-[(4-hydroxy)hydrocinnamoyl]-benzene-ethanamine, styrene and bicyclo[4.2.o]octa-i,3,5-triene. Previous studies have shown production of

cyclooctatetraene by various species of fungi for its inhibitory effect on the growth of other microbes (Stinson et al, 2003; Ting et al, 2011). There have also been a number of studies into volatiles produced from stool samples (Amann et al, 2011), without being linked to any particular disease. E-nose and FAIMS technology has been shown not only to distinguish UC from Crohn's disease but also to differentiate active disease from patients in remission (Arasaradnam et al, 2013). This could indicate a potential role for these technologies in the monitoring of compliance with a gluten free diet in coeliac patients as currently tTG antibodies have shown inconsistent results when used for this purpose (Vahedi et al, 2003; Dahle et al 2008). Analysis of the VOCs in urine could in the future represent a more effective and real time means of monitoring compliance by patients at home (with a portable device or specialised mobile phone application).

The unique chemical fingerprint produced by the different disease states shows the potential of this technology as an initial alternative screening test for coeliac disease. Furthermore it has the potential to aid in the further investigation of individuals with other GI disease in whom the diagnosis is not clear. VOCs are believed to be produced by colonic fermentation: the result of a complex interaction between the colonocyte cells, human faecal flora, mucosal integrity and invading pathogens (Arasaradnam et al, 2011). These thereafter pass into bodily fluids and as a result, VOCs found in urine, faeces and breath have huge potential as biomarkers to aid in the assessment of gastrointestinal diseases. Any changes found in the pattern of VOCs are reflective of changes and variations within the gastrointestinal environment. This suggests a possible role for gut microflora dysbiosis in the pathophysiology of coeliac disease which has been found in several studies including paediatric coeliac disease (Caminero et al, 2014; De Palma et al, 2010; Collado et al, 2009; Nadal et al, 2007).

GCMS data also identified a chemical that could be correlated to the coeliac disease state, with a high proportion of NIST library 'hits' suggesting 1, 3, 5, 7

cyclooctatetraene. In addition, identification of this chemical was made via the NIST library by forward and reverse matching scores between documented spectra and those found in the sample set.

This pilot study serves to demonstrate the potential of IMS technology (FAIMS) using only urine samples to differentiate coeliac disease from other overlap gastrointestinal conditions such as IBS. Its advantages include portability, rapid real time and cost effective diagnostic approach.

Example 2 - Bile Acid Diarrhoea

Materials and methods

Samples

All urine samples were analysed by Electronic nose and FAIMS and a subset analysed by GCMS. Urine was collected in a standard universal specimen container and immediately stored at -8o°C after collection for subsequent batch analysis. Before testing, they were then left to thaw overnight in a lab fridge at 4 °C and aliquoted into appropriate sample bottles (described below). The samples were then used for analysis using the electronic nose and FAIMS experimental methods. FAIMS measurements were undertaken over a 6 month period (tested in three batches) with a sub-group used for a single electronic nose test (due to instrument availability).

Subjects

A total of no patients were recruited for this study and consisted of adults aged 28 to 81 years. Patients were recruited from general Gastroenterology and inflammatory bowel disease clinics at University Hospital Coventry & Warwickshire, UK and

Rotherham General Hospital, UK. Demographic data and disease activity score index was collected from the patients. The study cohort included 3 groups: 23 patients with BAD, 42 patients with UC and 45 healthy controls. Bile acid diarrhoea was defined as those with a Se75 homo-chloro-tauric acid test of less than 15% retention at day seven (7d SeHCAT retention). A lower retention value suggests inability to reabsorb bile back into circulation thus resulting in bile acid diarrhoea. The UC patients were all in clinical remission (confirmed by clinical scores and inflammatory markers). Those with an uncertain diagnosis or inconclusive radiological or histological confirmation were excluded from the study. The demographics and clinical parameters of the subjects are shown in Table 7. Scientific and ethical approval was obtained from local Research & Development Department and Warwickshire Ethics Committee (ref: 09/H1211/38).

Written informed consent was obtained from all patients who participated in the study.

Patient Groups Bile acid Ulcerative Healthy

diarrhoea Colitis Controls

Number 23 42 45

Age 49 (14) 56 (15.8) 32(8)

BMI 24 (5) 28 (4.3) 25 (5)

7 d Se^HCAT 7 (1) n/a n/a

retention

5-Aminosalicylate n/a 33 (85%) n/a

acid ( )

Azathioprine ( ) n/a 7 (17%) n/a

Steroids ( ) n/a 7 (17%) n/a

Table 7: Demographic and Clinical Characteristics of Study Population Age and Body mass index (BMI) are mean values with standard deviation in brackets.

7 d Se^HCAT retention are mean retention values at day 7 with standard deviation in brackets (values≤ 15 are deemed abnormal). Test only performed in those suspected to have bile acid diarrhoea.

5-Aminoslicylate acid, Azathioprine and steroids are drugs used to treat inflammatory bowel disease (for UC patients), inducing and maintaining clinical remission. Figures are absolute numbers of patients, with percentages of the total number given in brackets.

Electronic Nose

The electronic nose was developed as an instrument to replicate the biological olfactory system and as an alternative to more sophisticated analytical equipment (such as GCMS). These instruments operate at room temperature, use air as the carrier gas and can give a real-time result. They comprise an array of differing chemical sensors, which are modulated in some way when exposed to a sample. Thus, when a complex sample is presented to the chemical sensor array, as each sensor is different, the response of each sensor to the sample is unique. The response of all the sensors can be brought together to create a smell 'fingerprint' of that sample. When a similar sample is presented again to the instrument, it will produce a similar sensor response profile and thus we are able to identify that sample. This identification process is normally achieved using some form pattern recognition technique. Consequently, we are able to present many different types of sample to the instrument, allow it to learn these smell fingerprints, and thus characterize/identify those samples. In this study a commercial electronic nose (Fox 4000, AlphaMOS, France) was used to analyse the chemical signature of the samples. This instrument comprises an array of 18 metal oxide gas sensors, whose resistance is modulated in the presence of a target gas/vapour. Experimentally, 5 mL of each urine sample were aliquoted into 10 mL sample bottles with a crimp lid, fitted with a septum. The Fox 4000 electronic nose is fitted with a HS100 autosampler, which allows up to 64 samples to be run in one batch. The autosampler moves each bottle into a preparation chamber, which heats the samples for 10 minutes to 60 °C and agitates the bottle. After 10 minutes a syringe takes 1 mL of headspace from the sample bottle and directly injects it into the electronic nose. The change in resistance of the sensors was measured from the injection time for 180 seconds at a sample rate of 1 Hz. The instrument was flushed with clean, dry air (flow rate of 500 mL/min) for 10 minutes after each exposure to ensure that the sensors had fully recovered. Each sample was tested three times. Here, a smaller set of samples were tested than with the FAIMS instrument (41 in total, 14 BAD, 7 Controls and 20 UC).

FAIMS (Field Asymmetric Ion Mobility Spectrometry)

For FAIMS analysis, again a commercial instrument was deployed (Lonestar, Owlstone, UK). Unlike the electronic nose, this system achieves separation of chemical

components on the basis of differences in ion mobility within a high electric field.

FAIMS is a fairly recent technology that allows gas molecules to be separated and analysed at atmospheric pressure and room temperature. Here a test sample is first ionised with a radiation source (Ni-63 in our case), resulting in a group of ions of various sizes and types. These are introduced between two conductive plates and an asynchronous waveform is used, where a high positive voltage is applied for a short time and a low negative voltage is applied for a longer time, but their magnitudes equal in terms of voltage ^χ time. The ionized molecules are subjected to these high electric fields and depending on their physical properties, move towards or away from one of the high voltage plate (or not affected at all) depending upon their mobilities. If ions touch either of the plates, their charge is lost and not detected as they exit the plates. Therefore, a compensation voltage is added that counteracts a specific level of mobility allowing those molecules to exit the plates with their charge and be detected. By scanning through a range of compensation voltages, a range molecules will different mobilities can be measured (Covington et al., Sensors, 2012, 12(10), 13002-18).

For FAIMS, 7 mL of urine was aliquoted into a standard 30mL Sterilin bottle (Newport, UK). The plastic lids were modified with the addition of push-fit fittings (for 3mm PTFE tubing), which allowed the bottle to be connected to the FAIMS instrument. The sterilin bottles were heated to 6o°C ± 0.1 for 30 minutes before each experiment. The FAIMS instrument was set up in a pressurised configuration with a flow rate of 2L/ min. The dispersion field was stepped through 51 equal settings between o and 100% (the dispersion field in the ratio of the high electric field to low electric field) and for each dispersion field the compensation voltage stepped was between +6V and -6V in 512 steps. Both positive and negative scans were used (electric fields applied first with a high positive potential and then with a high negative potential), where each scan produced 26,112 data points. Statistical Methods

Exploratory data analysis for the electronic nose was performed using Principal Component Analysis (PCA) and both the electronic nose and FAIMS using Linear Discriminant Analysis (LDA). These exploratory techniques are extensively used for these types of experiment. Their purpose is to allow the simple interpretation of complex data to determine if differences in groups of samples can be seen. For the electronic nose analysis, the raw data was extracted using Alphasoft (AlphaMOS

V12.36) and analysed in Multisens Analyzer (JLM Innovations, Germany).

FAIMS data was processed in a custom Lab VIEW program (Ver 2012, National Instruments, USA). For analysis both the positive and negative ion matrices for each scan were concatenated and joined to make a single 52,224 element array. These were then wavelet transformed using a Daubechies D4 wavelet. Variables in the resulting array, suitable for discrimination, were then identified. For each variable, the class scatter (ΣσΟ² and the between class scatter: (σ_μ)²/ (ΣσΟ², were calculated and then thresholds set to identify variables for analysis.

the standard deviation of the dimension in question within the class i, and σ_μ was the standard deviation of the means of the dimension under test between classes). These were then used as the input to a LDA algorithm.

This approach gave a two dimensional input parameter space (within class scatter and between class scatter) to control the separation algorithm. This space was explored by incrementing through threshold values of these two parameters and selecting variables that were below this threshold. For each threshold increment, one sample was removed from the dataset and re-classification was attempted based on the analysis of the remaining samples. Classification employed a K-Nearest-Neighbour (KNN) routine. This exploration identified groups of common variables in the parameter space where re-classification exceeded that which would be expected from random re-classifi cation (three standard deviations from the mean). Variables set in this robust region were used for further analysis.

Gas Chromatograph /Mass Spectrometry

A subset of the samples (10 from each group; BAD, UC and controls) were analyzed by GCMS to evaluate if there were any key chemical markers for bile acid diarrhoea. Here analysis was undertaken with a Bruker Scion SQ GCMS system, fitted with a Restek Rxi-624Sil MS fused silica GC column (length 20 m, 0.18 mm internal diameter, 1.0 μπι wall thickness) and a Combipal Autosampler (CTC, Switzerland). Due to the expected small concentrations of chemical components within the sample, the autosampler was enhanced with an ITEX2 pre-concentrator (CTC, Switzerland). 5 mL of urine sample were aliquoted into 10 mL glass vials and the lid crimped. Samples were heated to 6o°C and the headspace pulled through the ITEX a total of 15 times per sample over a time period of 3 minutes. After pre-concentration the sample was desorbed into the GCMS by heating the ITEX up to 250°C and injecting into the fused silica column. The injector was kept at a constant temperature of 250°C, sending samples in the column at a split ratio of 1:20 to maintain peak sharpness at the end detector. The GC then underwent a temperature program in order to separate the samples' constituent VOCs in terms of boiling point and molecular weight, holding at 50°C for 1 minute before increasing at a constant rate of 20°C/s up to a maximum of 28o°C. The separated species were detected by the chromatograph, then fragmented and analysed by the mass spectrometer.

Results

Electronic Nose, FAIMS and GCMS results

Sex distribution was broadly equal with a similar BMI within the three groups. Figure 7(a) shows a typical response of the electronic nose sensor array to a urine sample and Figure 7(b) shows a typical FAIMS 'plume' for a positive ion scan. Intensity is in arbitrary units of ion count. The change in resistance was used as the feature for data processing. Figure 8 shows a radar plot of the change in sensor resistances to different samples (sensors averaged over complete dataset).

Initial electronic nose analysis was undertaken using PCA (PCA being a non-classified technique). Results from PCA showed no clear trend, but when the samples are re- analysed using LDA (a pre-classified technique), shown in Figure 9(a), the groups are clearly separated. Figure 9(b) shows the associated loadings for this plot, showing that the analysis employs a spectrum of different sensors. Test sets were removed and reclassified (using an n-i algorithm and a K-nearest neighbour reclassification routine based on LDA weights). Accuracy of reclassification was 85% for the three groups (taken together due to the small sample size). The results of LDA on the FAIMS data for patients with BAD, Ulcerative Colitis and controls are shown in Figure 10. Accuracy of reclassification of the elements of the test sets varied between the different sample groups, with controls being 82%, Ulcerative Colitis being 79% and BAM 83%. However, re-classifying based on BAM and none BAM results is a reclassification above 90%. This indicates a significant difference in the spectra associated with disease groups, but the optimum set of variables are yet to be identified.

The data from the GCMS were analysed by comparing the retention times (from the gas chromatography) and Molecular mass (from the mass spectrometry) observed by the instrument with those from a known NIST library of chemical compounds (NIST 2012). While individual sample variation was high, some overall trends in concentration ratios of the constituent gases were observed which separated the BAD samples from the UC and controls. Most notably, two peaks were found within the BAD samples that were not noticeably present in any other sample groups. These were observed at 1.71 minutes and 2.05 minutes in BAD sample chromatograms (as shown in Figure 11), and are consistent with NIST library entries for 2-propanol and acetamide, respectively. It is possible that these compounds relate to products of fermentation rather than effect of drugs.

Discussion

This study, for the first time, demonstrates the utility of novel non-invasive and inexpensive technologies for use in a common clinical condition of chronic diarrhoea. Specifically, its ability to separate those with the less common form of diarrhoea associated with inflammation (ulcerative colitis) and the more common form due to bile acid diarrhoea. This distinction is important to make for two reasons: (1) the clinical management is very different for both these conditions, and (2) therapeutic efficacy that is offered is more effective in the latter condition especially as newer therapies (bile acid sequestrants) are becoming available suggesting a greater number of people are likely to gain benefit if the condition can be diagnosed.

The VOC/gas signature profiles are different between those with bile acid diarrhoea, ulcerative colitis (type of inflammatory bowel disease) and healthy individuals being detected using two distinct types of technologies namely electronic nose and ion mobility spectroscopy - FAIMS technology. The uniqueness of this study is the specific use of non-invasive tests which is the first to demonstrate the use of volatile organic compounds detected by electronic nose and FAIMS technology in urine of patients with bile acid diarrhoea. The changes in gas profile in patients with BAD compared with Ulcerative Colitis and healthy controls confirms the inventors' a priori hypothesis that gut dysbiosis in those with BAD results in a chemical fingerprint that can be detected (altered fermentation profile). VOCs and other vapours are produced as a result of colonic fermentation following a complex interaction between the colonocyte, human faecal flora, and mucosal integrity and invading pathogens (Arasaradnam et al., Med. Hypotheses, 2009, 73(5), 753-756). They are emitted from bodily fluids and as a result, vapours emitted from urine, faeces and breath may include biomarkers of use in the assessment of gastrointestinal disease. Therefore, changes in the gas profile are reflective of the variation of gut microbiota and shed light onto their causative role in pathological states. It is plausible that the biodiversity of gut microflora, which cleave bile acids, may be altered in those with bile acid diarrhoea resulting in changes in the gas profiles of these patients - an indirect representation of the complex pathological process involved in the disease state.

These data show that it is possible to distinguish diarrhoea due to excess bile acids compared to those with inflammatory conditions. Confirmation was noted by GCMS where 2-propanol and acetamide were found to be prominent only in patients with BAD suggesting that these compounds can be used to distinguish BAD from other disease groups. It is noteworthy that these compounds are not breakdown products of drugs but rather may reflect an altered fermentome profile which is disease-specific. Conclusions

Current diagnostic methods to diagnose those with BAD require support from nuclear medicine - Se75HCAT study which is expensive and not widely available. The utility of a portable, inexpensive electronic nose that can make a rapid diagnosis in real time will be a paradigm shift in the management of patients with BAD. In this study 110 patients with BAD, Ulcerative Colitis and healthy controls have been analysed by the electronic nose and FAIMS technology. Results indicate differences in chemical signatures from these groups, with a re-classification robustness test exceeding 80% in most cases.

Summary

Bile acid diarrhoea (BAD) is common and requires expensive imaging to diagnose. The products of fermentation - volatile organic compounds (VOCs), lead to a fermentation profile which can be measured from urine. The inventors propose to track the resultant VOCs and/or gases that emanate from urine using gas analysis tools, specifically an AlphaMOS Fox 4000 electronic nose and an Owlstone Lonestar Field Asymmetric Ion Mobility Spectrometer (FAIMS) instruments to identify BAD. A total of 110 patients were recruited; 23 with BAD, 42 with ulcerative colitis (UC) and 45 controls. Patients with BAD also received standard imaging (Se75HCAT) for confirmation. Urine samples were collected and the headspace analysed using the electronic nose, FAIMS instrument and a subset by gas chromatography, mass spectrometry (GCMS). Linear Discriminant Analysis (LDA) was used to explore both the electronic nose and FAIMS data. LDA showed statistical differences between the different disease groups, with reclassification success rates (using an n-i approach) at typically 85%. GCMS results confirmed these results and showed that patients with BAD had two additional chemical compounds in the urine headspace either not present or in much reduced quantities in the UC or control samples. This work will lead to a new tool to diagnose BAD, which is cheaper, quicker and easier that current methods.

References

Vahedi K, Mascart F, Mary Y,et al. (2003) Reliability of antitransglutaminase antibodies as predictors of gluten-free diet compliance in adult celiac disease. Am J Gastroenterol. 98(5):i079-87.

Dahle C, Hagman A, Ignatova S, et al. (2008) Antibodies against deamidated gliadin peptides identify adult coeliac disease patients negative for antibodies against endomysium and tissue transglutaminase. Aliment Pharmacol Ther. 32(2):254-6o.

Arasaradnam RP, Ouaret N, Thomas MG, et al. (2013) A novel tool for noninvasive diagnosis and tracking of patients with inflammatory bowel disease. Inflamm Bowel Dis. Apr;i9(5):999-1003. Arasaradnam R, Quraishi N, Kyrou I, et al. (2011) Insights into 'Fermentonomics':

Evaluation of volatile organic compounds (VOCs) in human disease using an Electronic 'e' Nose. J Med Eng Technol. Feb;35(2):87-9i. Epub 2011 Jan 4.

Hastie, T., Tibshirani, R., Friedman, J., Hastie, T., Friedman, J., & Tibshirani, R.

(2009). The elements of statistical learning (Vol. 2, No. 1). New York: Springer. Chui, Charles K. (1992). An Introduction to Wavelets. San Diego: Academic Press.

Murphy, K. P. (2012). Machine learning: a probabilistic perspective. MIT press. Stinson M, Ezra D, Hess WM, et al. (2003) An endophytic Gliocladium sp. of Eucryphia cordifolia producing selective volatile antimicrobial compounds. Plant Science

Oct; 165(4): 913-22.

Ting ASY, Mah SW, Tee CS. (2011) Detection of potential volatile inhibitory compounds produced by endobacteria with biocontrol properties towards Fusarium oxysporum f. sp. cubense race 4. World J Microbiol Biotechnol Feb;27(2):229-35.

Amann A, Smith D. Volatile Biomarker: Non-Invasive Diagnosis in Physiology and Medicine. Chapter 22: Volatile Organic Compounds Found in Urine and Stool: 411. Elsevier 2013.

Caminero A, Herran AR, Nistal E, et al. (2014) Diversity of the cultivable human gut microbiome involved in gluten metabolism: Isolation of microorganisms with potential interest for coeliac disease. FEMS Microbiol Ecol. Feb 6. [Epub ahead of print]

De Palma G, Nadal I, Medina M, et al. (2010) Intestinal dysbiosis and reduced immunoglobulin-coated bacteria associated with coeliac disease in children. BMC Microbiol. Feb 24510:63. Collado MC, Donat E, Ribes-Koninckx C, et al. (2009) Specific duodenal and faecal bacterial groups associated with paediatric coeliac disease. J Clin Pathol.

Mar;62(3):204-9.

Nadal I, Donat E, Ribes-Koninckx C, et al. (2007) Imbalance in the composition of the duodenal microbiota of children with coeliac disease. J Med Microbiol. Dec;56(Pt 12): 1669-74.

Claims

1. A method for diagnosing a subject, or for providing a prognosis of the subject's condition, the method comprising analysing the concentration of a signature compound in a bodily sample from a test subject and comparing this concentration with a reference for the concentration of the signature compound in an individual who does not suffer from the disease being screen for, wherein an increase in the concentration of the signature compound in the bodily sample from the test subject compared to the reference suggests that the subject is suffering from the disease being screen for, or has a pre-disposition thereto, or provides a negative prognosis of the subject's condition, wherein the disease being screened for is coeliac disease or bile acid diarrhoea.

2. A method for determining the efficacy of treating a subject suffering from a disease with a therapeutic agent or specialised diet, the method comprising analysing the concentration of a signature compound in a bodily sample from a test subject and comparing this concentration with a reference for the concentration of the signature compound in an individual who does not suffer from the disease, wherein a difference in the concentration of the signature compound in the bodily sample compared to the reference is indicative of the efficacy of treating the test subject with the therapeutic agent, wherein the disease being screened for is coeliac disease or bile acid diarrhoea.

3. A method according to either claim 1 or 2, wherein the signature compound is selected from a group of compounds consisting of: octatetraene; cyclooctatetraene; 1,3,5,7-cyclooctatetraene; 2,6-dimethyl-i,3,5,7-octatetraene; i,8-diphenyl-i,3,5,7- octatetraene; N-[(4-hydroxy)hydrocinnamoyl]-benzene-ethanamine; styrene; benzene; bicyclo[4.2.o]octa-i,3,5-triene; l-methylethyl hydroperoxide; l-methyl-i-phenylethyl hydroperoxide; 4-penten-2-ol; i-penten-4-ol; 4-methyl-4-penten-2-ol; l-pentene; 4- methyl-i-pentene; 3-methyl-i-penten; ethyl cyclopropane; i-ethyl-2- methylcyclopropane; propane; ethylenediamine; methyl-cyclopropane; tetramethyl oxirane; 3-ethyl-2,2-dimethyl oxirane; N-methyl ethanamine; N-methyltryptamine; isopropyl alcohol (2-propanol); i-amino-2-propanol; acetamide; N,N- dimethylacetamide; acetone; cyclopentane; pentane; and heptane.

4. A method according to any preceding claim, wherein the disease being screened for is coeliac disease, and the signature compound is selected from a group of compounds consisting of: octatetraene; cyclooctatetraene; 1,3,5,7-cyclooctatetraene; 2,6-dimethyl-i,3,5,7-octatetraene; i,8-diphenyl-i,3,5,7-octatetraene; N-[(4- hydroxy)hydrocinnamoyl]-benzene-ethanamine; styrene; benzene; and

bicyclo[4.2.o]octa-i,3,5-triene. 5. A method according to claim 4, wherein the signature compound is

cyclooctatetraene, more preferably 1,3,

5,7-cyclooctatetraene.

6. A method according to any one of claims 1 to 3, wherein the disease being screened for is bile acid diarrhoea, and the signature compound is selected from a group of compounds consisting of: l-methylethyl hydroperoxide; l-methyl-i- phenylethyl hydroperoxide; 4-penten-2-ol; i-penten-4-ol; 4-methyl-4-penten-2-ol; 1- pentene; 4-methyl-i-pentene; 3-methyl-i-penten; ethyl cyclopropane; i-ethyl-2- methylcyclopropane; propane; ethylenediamine; methyl-cyclopropane; tetramethyl oxirane; 3-ethyl-2,2-dimethyl oxirane; N-methyl ethanamine; N-methyltryptamine; isopropyl alcohol (2-propanol); i-amino-2-propanol; acetamide; N,N- dimethylacetamide; Ν,Ν-dimethylacetamide; acetone; cyclopentane; pentane; and heptane .

7. A method according to any preceding claim, wherein the method also comprises analysing the concentration of an analogue or a derivative of the signature compound.

8. A method according to any preceding claim, wherein the sample is any bodily sample into which the signature compound is secreted.

9. A method according to any preceding claim, wherein the sample is a urine sample.

10. A method according to claim 9, wherein the concentration of the signature compound in the bodily sample is measured in vitro from a urine sample taken from the subject.

11. A method according to either of claims 9 or 10, wherein the compound is detected from gases or vapours emanating from the urine sample.

12. A method according to any preceding claim, wherein the signature compound is detected by a gas analyser.

13. An apparatus for diagnosing a subject suffering from a disease, or for providing a prognosis of the subject's condition, the apparatus comprising:-

14. An apparatus for determining the efficacy of treating a subject suffering from disease with a therapeutic agent or a specialised diet, the apparatus comprising: -

wherein the apparatus is used to identify a difference in the concentration of signature compound in the sample from the test subject compared to the reference concentration, the difference in concentration being indicative of the efficacy of treating the test subject with the therapeutic agent, and the disease is s coeliac disease or bile acid diarrhoea.

15. An apparatus according to either claim 13 or claim 14, wherein the apparatus is for carrying out the method according to any one of claims 1-12.