Feasibility of integrating canine olfaction with chemical and microbial profiling of urine to detect lethal prostate cancer

Abstract

Prostate cancer is the second leading cause of cancer death in men in the developed world. A more sensitive and specific detection strategy for lethal prostate cancer beyond serum prostate specific antigen (PSA) population screening is urgently needed. Diagnosis by canine olfaction, using dogs trained to detect cancer by smell, has been shown to be both specific and sensitive. While dogs themselves are impractical as scalable diagnostic sensors, machine olfaction for cancer detection is testable. However, studies bridging the divide between clinical diagnostic techniques, artificial intelligence, and molecular analysis remains difficult due to the significant divide between these disciplines. We tested the clinical feasibility of a cross-disciplinary, integrative approach to early prostate cancer biosensing in urine using trained canine olfaction, volatile organic compound (VOC) analysis by gas chromatography-mass spectroscopy (GC-MS) artificial neural network (ANN)-assisted examination, and microbial profiling in a double-blinded pilot study. Two dogs were trained to detect Gleason 9 prostate cancer in urine collected from biopsy-confirmed patients. Biopsy-negative controls were used to assess canine specificity as prostate cancer biodetectors. Urine samples were simultaneously analyzed for their VOC content in headspace via GC-MS and urinary microbiota content via 16S rDNA Illumina sequencing. In addition, the dogs' diagnoses were used to train an ANN to detect significant peaks in the GC-MS data. The canine olfaction system was 71% sensitive and between 70-76% specific at detecting Gleason 9 prostate cancer. We have also confirmed VOC differences by GC-MS and microbiota differences by 16S rDNA sequencing between cancer positive and biopsy-negative controls. Furthermore, the trained ANN identified regions of interest in the GC-MS data, informed by the canine diagnoses. Methodology and feasibility are established to inform larger-scale studies using canine olfaction, urinary VOCs, and urinary microbiota profiling to develop machine olfaction diagnostic tools. Scalable multi-disciplinary tools may then be compared to PSA screening for earlier, non-invasive, more specific and sensitive detection of clinically aggressive prostate cancers in urine samples.

Fig 1. Study schema of workflow for the analysis of urine samples.

Urine samples from subjects diagnosed with Gleason 9 prostate cancer or biopsy-negative controls were collected and aliquots from each subject were sent for analysis by canine olfaction to Medical Detection Dogs (MDD) in the UK, GC-MS by Massachusetts Institute of Technology (MIT) and University of Texas at El Paso (UTEP) in the US, and microbiota profiling analysis by Johns Hopkins University (JHU) in the US. *Two control samples were reserved as extras for the trial if needed.

Fig 2. Study schema for canine olfaction trial.

(A) The two dogs, Florin and Midas, selected to participate in the trial. (B) Image of the presentation pots. (C) Test pots placed into the metal arm attached to the carousel. (D) Comparison of indications to biopsy-negative control and cancer samples in double blind trial. This table shows that out of the 21 control samples, Florin produced 5 false positive indications resulting in 76.2% specificity versus Midas’ 6 false positive indications resulting in 70% specificity. Both dogs correctly indicated to 5 out of 7 target samples giving 71.4 sensitivity.

Fig 3. Analysis of VOCs in patient urine samples.

(A) Study schema for VOC analysis. (B) Heat map of significantly increased or decreased VOCs by Wilcoxon rank-sum test (p <0.05) in cancer versus biopsy-negative control samples. Shown on x-axis are the CAS Registry numbers of the seven significant VOCs (p<0.05) showing elevating or reducing quantity in prostate cancer patients. The correlation between VOCs and patients ranges from low (black) to high (white). (C) Compounds significantly elevated or decreased in cancer versus biopsy-negative control samples. (D) The Receiver Operating Characteristic (ROC) curve for VOC prostate cancer logistic model and verified in 34 patients.

Fig 4. Analysis of microbiota in patient urine samples.

(A) Unsupervised clustering (log transformed) of 16S rDNA Illumina sequencing results from urine pellet samples by the top 25 species. The dendrogram was based on hierarchical clustering of the Euclidean distance between samples in the combined cancer and biopsy-negative control samples. (B) Beta-diversity (Bray-Curtis) of each urine bacterial profile, analyzed by cancer (yellow) or biopsy-negative control (blue). (C) Differential abundance of select species of bacteria in cancer and biopsy-negative control samples. Mean percent sequence abundances are given for the samples positive for the indicated species from the cancer and biopsy-negative control groups. MW = Mann-Whitney U test.

Fig 5. Network skeletonization of neural net mapping of GC-MS to canine-positive indicated and canine-negative indicated urine samples.

The network is depicted as a system of excitatory (red) and inhibitory connection weights (blue). Starting from the output node representing a canine-indicated positive (TP) canine diagnosis of prostate cancer, less significant weights are stripped away to reveal critical connections to the most dominant GC-MS peaks contributing to the canine cancer diagnosis. The top figure shows the net with all weights present, while the bottom figure reveals the peak near 13.139 minutes as positively correlated (i.e., red connection) with canine-positive indication of prostate cancer.

Fig 6. Auto-associative filtering methodology.

An auto-associative net was trained to reconstruct the GC-MS spectra of all the canine-negative indicated samples. Inputting the spectra of canine-positive indicated spectra, the net generated the nearest canine-negative indicated spectrum at its output. Subtraction of the output from the input spectrum revealed anomalous features possibly associated with the canine indication of cancer. In the example shown, both elute excesses (peaks) and deficiencies (troughs) are indicated in the difference spectrum. In short, this network acts as a database lookup table that supplies the closest matching canine-negative indicated spectrum to one that is applied, if need be producing synthetic data representing a potential canine-negative spectrum.

Fig 7. Auto-associative filtering reveals the most dominant GC-MS features contributing to canine-positive indication of prostate cancer from urine samples.

Anomalies fall into two groups: those showing an overabundance of elutes (JHBUI-0887, JHBUI-1028, and AWP-5734) and those revealing depletions of elutes (AWP-9307 and AWP-6373). The peak near 13.2 minutes in the first three of these plots corresponds to that resolved at 13.139 minutes via network skeletonization.