The goal of the project proposed is to develop a gas chromatography and differential mobility spectrometry (GC/DMS) molecular identification library for volatile organic compounds (VOCs) using a deep neural network approach. Vox Biomedical scientists will test the hypothesis that a novel, multi-task neural network architecture can predict characteristics of an previously unseen analyte from its GC/DMS spectrum. Vox Biomedical is in the process of commercializing the GC/DMS based microAnalyzer instrument, developed at DRAPER, for detecting the presence of psychoactive drugs and disease through exhaled breath analysis. While drug detection consists of measuring the concentrations in the exhaled breath of compounds whose identity is well known (such as psychoactive opioids and cannabinoids), exhaled breath disease detection is focused on characterization of a particular diseaseâs exhaled volatile organic compound signature. Volatile organic compounds (VOCs) are byproducts of cellular metabolism that travel from cells throughout the body to the lungs, where they are efficiently exhaled in the breath. VOCs have become of interest as biomarkers of metabolic diseases such as cancer, kidney disease and diabetes. The current generation of exhaled breath VOC based disease detection methods rely on gas chromatography and mass spectrometry (GC/MS), which, while highly sensitive, is a complex analytical modality that is expensive, slow, and must be operated by skilled professionals. The microAnalyzer instrumentâs inherent portability, ease of use, and ability to obtain results at the point-of- measurements make it an ideal instrument for breath-based disease detection. However, the currently a GC/DMS peak can only be identified through characterization of a chemical standard or by performing confirmatory GC/MS analysis using a similar sample. This makes biomarker discovery a resource and time intensive process. The creation of a VOC chemical identity library, as would result from successful completion of the proposed project, will allow the identity of samples introduced to the microAnalyzer instrument to be predicted without the need for confirmatory standard characterization or GC/MS work. This will make biomarker discovery for disease a less resource intensive process expediting the discovery and confirmation of biomarkers for early-stage disease detection, ultimately saving lives.
Public Health Relevance Statement: Project Narrative This project is focused on creating a molecular identification library that can be used with fieldable instruments for exhaled breath analysis. The proposed work will enable the constituents of an exhaled breath sample to be identified without referencing a standard. Such capabilities will enable breath-based biomarker discovery for diseases such as cancer, liver disease, and invasive infection.
Project Terms: Breath Tests; breath analysis; Malignant Neoplasms; Cancers; Malignant Tumor; malignancy; neoplasm/cancer; Cannabinoids; Cells; Cell Body; Analytical Chemistry; Analytic Chemistry; Gas Chromatography; vapor phase chromatography; Classification; Systematics; Communicable Diseases; Infectious Disease Pathway; Infectious Diseases; Infectious Disorder; Diabetes Mellitus; diabetes; Disease; Disorder; Environment; Goals; Grant; Infection; Ions; Kidney Diseases; Nephropathy; Renal Disease; kidney disorder; renal disorder; Learning; Libraries; Liver diseases; Hepatic Disorder; hepatic disease; hepatopathy; liver disorder; Lung; Lung Respiratory System; pulmonary; Mass Fragmentography; GC MS; GCMS; Gas-Liquid-Mass Spectrometry Chromatography; Mass Fragmentographies; Mass-Gas Chromatography Spectrometry; Mass-Gas Chromatography Spectrum Analysis; ion trap mass spectrometry; mass fragmentometry; Metabolic Diseases; Metabolic Disorder; Thesaurismosis; metabolism disorder; Metabolism; Intermediary Metabolism; Metabolic Processes; Methods; Molecular Structure; Macromolecular Structure; Psychotropic Drugs; Psychoactive Agents; Psychoactive Compound; Psychoactive Drugs; Psychopharmaceuticals; Resources; Research Resources; Signal Transduction; Cell Communication and Signaling; Cell Signaling; Intracellular Communication and Signaling; Signal Transduction Systems; Signaling; biological signal transduction; Spectrum Analysis; Spectroscopy; Spectrum Analyses; Testing; Time; Travel; Work; Ultrafine; Generations; Measures; early cancer detection; screening cancer patients; Screening for cancer; Clinical; Chemicals; Training; Opiates; Opioid; Measurement; instrument; Stereoisomer; Machine Learning; machine based learning; Spectrometry; Dimensions; Complex; Exhalation; Exhaling; Respiratory Expiration; Source; Techniques; Benchmarking; Best Practice Analysis; benchmark; interest; Performance; success; biomedical scientist; skills; novel; Modality; Modeling; Sampling; Neural Network Simulation; Connectionist Models; Neural Network Models; Perceptrons; Property; portability; NMR Spectroscopy; NMR Spectrometer; nuclear magnetic resonance spectroscopy; chemical standard; Data; Detection; Molecular Analysis; National Institute of Drug Abuse; NIDA; National Institute on Drug Abuse; Characteristics; Molecular; Process; Development; developmental; drug detection; drug testing; multi-task; multitask; volatile organic chemical; volatile organic compound; commercialization; multi-modality; multimodality; bio-markers; biologic marker; biomarker; Biological Markers; Linear Algebra; signal processing; Data Analytics; early biomarkers; early detection markers; early detection biomarkers; biomarker discovery; experiment; experimental research; experiments; experimental study; Injections; deep learning based neural network; deep learning neural network; deep neural net; deep neural network; neural net architecture; neural network architecture; detection procedure; detection technique; detection met
