Ovarian cancer detection from metabolomic liquid chromatography/mass spectrometry data by support vector machines

A critical appraisal of the role of metabolomics in breast cancer research and diagnostics

Breast cancer (BC) remains the most prevalent cancer among women worldwide, despite significant advancements in its prevention and treatment. The escalating incidence of BC globally necessitates continued research into novel diagnostic and therapeutic strategies. Metabolomics, a burgeoning field, offers a comprehensive analysis of all metabolites within a cell, tissue, system, or organism, providing crucial insights into the dynamic changes occurring during cancer development and progression. This review focuses on the metabolic alterations associated with BC, highlighting the potential of metabolomics in identifying biomarkers for early detection, diagnosis, treatment and prognosis. Metabolomics studies have revealed distinct metabolic signatures in BC, including alterations in lipid metabolism, amino acid metabolism, and energy metabolism. These metabolic changes not only support the rapid proliferation of cancer cells but also influence the tumour microenvironment and therapeutic response. Furthermore, metabolomics holds great promise in personalized medicine, facilitating the development of tailored treatment strategies based on an individual's metabolic profile. By providing a holistic view of the metabolic changes in BC, metabolomics has the potential to revolutionize our understanding of the disease and improve patient outcomes.

Toward Automatic Inference of Glycan Linkages Using MSn and Machine Learning─Proof of Concept Using Sialic Acid Linkages

Glycosidic linkages in oligosaccharides play essential roles in determining their chemical properties and biological activities. MSn has been widely used to infer glycosidic linkages but requires a substantial amount of starting material, which limits its application. In addition, there is a lack of rigorous research on what MSn protocols are proper for characterizing glycosidic linkages. In this work, to deliver high-quality experimental data and analysis results, we propose a machine learning-based framework to establish appropriate MSn protocols and build effective data analysis methods. We demonstrate the proof-of-principle by applying our approach to elucidate sialic acid linkages (α2'-3' and α2'-6') in a set of sialyllactose standards and NIST sialic acid-containing N-glycans as well as identify several protocol configurations for producing high-quality experimental data. Our companion data analysis method achieves nearly 100% accuracy in classifying α2'-3' vs α2'-6' using MS5, MS4, MS3, or even MS2 spectra alone. The ability to determine glycosidic linkages using MS2 or MS3 is significant as it requires substantially less sample, enabling linkage analysis for quantity-limited natural glycans and synthesized materials, as well as shortens the overall experimental time. MS2 is also more amenable than MS3/4/5 to automation when coupled to direct infusion or LC-MS. Additionally, our method can predict the ratio of α2'-3' and α2'-6' in a mixture with 8.6% RMSE (root-mean-square error) across data sets using MS5 spectra. We anticipate that our framework will be generally applicable to analysis of other glycosidic linkages.

Construction of the XGBoost model for early lung cancer prediction based on metabolic indices

BACKGROUND

Lung cancer is a malignant tumour, and early diagnosis has been shown to improve the survival rate of lung cancer patients. In this study, we assessed the use of plasma metabolites as biomarkers for lung cancer diagnosis. In this work, we used a novel interdisciplinary mechanism, applied for the first time to lung cancer, to detect biomarkers for early lung cancer diagnosis by combining metabolomics and machine learning approaches.

RESULTS

In total, 478 lung cancer patients and 370 subjects with benign lung nodules were enrolled from a hospital in Dalian, Liaoning Province. We selected 47 serum amino acid and carnitine indicators from targeted metabolomics studies using LC‒MS/MS and age and sex demographic indicators of the subjects. After screening by a stepwise regression algorithm, 16 metrics were included. The XGBoost model in the machine learning algorithm showed superior predictive power (AUC = 0.81, accuracy = 75.29%, sensitivity = 74%), with the metabolic biomarkers ornithine and palmitoylcarnitine being potential biomarkers to screen for lung cancer. The machine learning model XGBoost is proposed as an tool for early lung cancer prediction. This study provides strong support for the feasibility of blood-based screening for metabolites and provide a safer, faster and more accurate tool for early diagnosis of lung cancer.

CONCLUSIONS

This study proposes an interdisciplinary approach combining metabolomics with a machine learning model (XGBoost) to predict early the occurrence of lung cancer. The metabolic biomarkers ornithine and palmitoylcarnitine showed significant power for early lung cancer diagnosis.

Applications of machine learning in metabolomics: Disease modeling and classification

Metabolomics research has recently gained popularity because it enables the study of biological traits at the biochemical level and, as a result, can directly reveal what occurs in a cell or a tissue based on health or disease status, complementing other omics such as genomics and transcriptomics. Like other high-throughput biological experiments, metabolomics produces vast volumes of complex data. The application of machine learning (ML) to analyze data, recognize patterns, and build models is expanding across multiple fields. In the same way, ML methods are utilized for the classification, regression, or clustering of highly complex metabolomic data. This review discusses how disease modeling and diagnosis can be enhanced via deep and comprehensive metabolomic profiling using ML. We discuss the general layout of a metabolic workflow and the fundamental ML techniques used to analyze metabolomic data, including support vector machines (SVM), decision trees, random forests (RF), neural networks (NN), and deep learning (DL). Finally, we present the advantages and disadvantages of various ML methods and provide suggestions for different metabolic data analysis scenarios.

Metabolomics by NMR Combined with Machine Learning to Predict Neoadjuvant Chemotherapy Response for Breast Cancer

Simple Summary

Neoadjuvant chemotherapy (NACT) is offered to breast cancer (BC) patients to downstage the disease. However, some patients may not respond to NACT, being resistant. We used the serum metabolic profile by Nuclear Magnetic Resonance (NMR) combined with disease characteristics to differentiate between sensitive and resistant BC patients. We obtained accuracy above 80% for the response prediction and showcased how NMR can substantially enhance the prediction of response to NACT.

Abstract

Neoadjuvant chemotherapy (NACT) is offered to patients with operable or inoperable breast cancer (BC) to downstage the disease. Clinical responses to NACT may vary depending on a few known clinical and biological features, but the diversity of responses to NACT is not fully understood. In this study, 80 women had their metabolite profiles of pre-treatment sera analyzed for potential NACT response biomarker candidates in combination with immunohistochemical parameters using Nuclear Magnetic Resonance (NMR). Sixty-four percent of the patients were resistant to chemotherapy. NMR, hormonal receptors (HR), human epidermal growth factor receptor 2 (HER2), and the nuclear protein Ki67 were combined through machine learning (ML) to predict the response to NACT. Metabolites such as leucine, formate, valine, and proline, along with hormone receptor status, were discriminants of response to NACT. The glyoxylate and dicarboxylate metabolism was found to be involved in the resistance to NACT. We obtained an accuracy in excess of 80% for the prediction of response to NACT combining metabolomic and tumor profile data. Our results suggest that NMR data can substantially enhance the prediction of response to NACT when used in combination with already known response prediction factors.

Metabolic detection of malignant brain gliomas through plasma lipidomic analysis and support vector machine-based machine learning

Background

Most malignant brain gliomas (MBGs) are associated with dismal outcomes, mainly due to their late diagnosis. Current diagnostic methods for MBGs are based on imaging and histological examination, which limits their early detection. Here, we aimed to identify reliable plasma lipid biomarkers for non-invasive diagnosis for MBGs.

Methods

Untargeted lipidomic analysis was firstly performed using a discovery cohort (n=107). The data were processed by a support vector machine (SVM)-based discriminating model to retrieve a panel of candidate biomarkers. Then, a targeted quantification method was developed, and the SVM-based diagnostic model was constructed using a training cohort (n=750) and tested using a test cohort (n=225). Finally, the performance of the diagnostic model was further evaluated in an independent validation cohort (n=920) enrolled from multiple medical centers.

Findings

A panel of 11 plasma lipids was identified as candidate biomarkers with an accuracy of 0.999. The diagnostic model developed achieved a high performance in distinguishing MBGs patients from normal controls with an area under the receiver-operating characteristic curve (AUC) of 0.9877 and 0.9869 in the training and test cohorts, respectively. In the validation cohort, the 11 lipid panel still achieved an accuracy of 0.9641 and an AUC of 0.9866.

Interpretation

The present study demonstrates the applicability and robustness of utilizing a machine learning algorithm to analyze lipidomic data for efficient and reliable biomarker screening. The 11 lipid biomarkers show great potential for the non-invasive diagnosis of MBGs with high throughput.

Funding

A full list of funding bodies that contributed to this study can be found in the Acknowledgments section.

Current and Emerging Methods for Ovarian Cancer Screening and Diagnostics: A Comprehensive Review

With a 5-year survival rate of less than 50%, ovarian high-grade serous carcinoma (HGSC) is one of the most highly aggressive gynecological malignancies affecting women today. The high mortality rate of HGSC is largely attributable to delays in diagnosis, as most patients remain undiagnosed until the late stages of -disease. There are currently no recommended screening tests for ovarian cancer and there thus remains an urgent need for new diagnostic methods, particularly those that can detect the disease at early stages when clinical intervention remains effective. While diagnostics for ovarian cancer share many of the same technical hurdles as for other cancer types, the low prevalence of the disease in the general population, coupled with a notable lack of sensitive and specific biomarkers, have made the development of a clinically useful screening strategy particularly challenging. Here, we present a detailed review of the overall landscape of ovarian cancer diagnostics, with emphasis on emerging methods that employ novel protein, genetic, epigenetic and imaging-based biomarkers and/or advanced diagnostic technologies for the noninvasive detection of HGSC, particularly in women at high risk due to germline mutations such as BRCA1/2. Lastly, we discuss the translational potential of these approaches for achieving a clinically implementable solution for screening and diagnostics of early-stage ovarian cancer as a means of ultimately improving patient outcomes in both the general and high-risk populations.

Relevance, redundancy, and complementarity trade-off (RRCT): A principled, generic, robust feature-selection tool

We present a new heuristic feature-selection (FS) algorithm that integrates in a principled algorithmic framework the three key FS components: relevance, redundancy, and complementarity. Thus, we call it relevance, redundancy, and complementarity trade-off (RRCT). The association strength between each feature and the response and between feature pairs is quantified via an information theoretic transformation of rank correlation coefficients, and the feature complementarity is quantified using partial correlation coefficients. We empirically benchmark the performance of RRCT against 19 FS algorithms across four synthetic and eight real-world datasets in indicative challenging settings evaluating the following: (1) matching the true feature set and (2) out-of-sample performance in binary and multi-class classification problems when presenting selected features into a random forest. RRCT is very competitive in both tasks, and we tentatively make suggestions on the generalizability and application of the best-performing FS algorithms across settings where they may operate effectively.

The role of bile acids in carcinogenesis

Bile acids are soluble derivatives of cholesterol produced in the liver that subsequently undergo bacterial transformation yielding a diverse array of metabolites. The bulk of bile acid synthesis takes place in the liver yielding primary bile acids; however, other tissues have also the capacity to generate bile acids (e.g. ovaries). Hepatic bile acids are then transported to bile and are subsequently released into the intestines. In the large intestine, a fraction of primary bile acids is converted to secondary bile acids by gut bacteria. The majority of the intestinal bile acids undergo reuptake and return to the liver. A small fraction of secondary and primary bile acids remains in the circulation and exert receptor-mediated and pure chemical effects (e.g. acidic bile in oesophageal cancer) on cancer cells. In this review, we assess how changes to bile acid biosynthesis, bile acid flux and local bile acid concentration modulate the behavior of different cancers. Here, we present in-depth the involvement of bile acids in oesophageal, gastric, hepatocellular, pancreatic, colorectal, breast, prostate, ovarian cancer. Previous studies often used bile acids in supraphysiological concentration, sometimes in concentrations 1000 times higher than the highest reported tissue or serum concentrations likely eliciting unspecific effects, a practice that we advocate against in this review. Furthermore, we show that, although bile acids were classically considered as pro-carcinogenic agents (e.g. oesophageal cancer), the dogma that switch, as lower concentrations of bile acids that correspond to their serum or tissue reference concentration possess anticancer activity in a subset of cancers. Differences in the response of cancers to bile acids lie in the differential expression of bile acid receptors between cancers (e.g. FXR vs. TGR5). UDCA, a bile acid that is sold as a generic medication against cholestasis or biliary surge, and its conjugates were identified with almost purely anticancer features suggesting a possibility for drug repurposing. Taken together, bile acids were considered as tumor inducers or tumor promoter molecules; nevertheless, in certain cancers, like breast cancer, bile acids in their reference concentrations may act as tumor suppressors suggesting a Janus-faced nature of bile acids in carcinogenesis.

Biomarker selection and a prospective metabolite-based machine learning diagnostic for lyme disease

We provide a pipeline for data preprocessing, biomarker selection, and classification of liquid chromatography–mass spectrometry (LCMS) serum samples to generate a prospective diagnostic test for Lyme disease. We utilize tools of machine learning (ML), e.g., sparse support vector machines (SSVM), iterative feature removal (IFR), and k-fold feature ranking to select several biomarkers and build a discriminant model for Lyme disease. We report a 98.13% test balanced success rate (BSR) of our model based on a sequestered test set of LCMS serum samples. The methodology employed is general and can be readily adapted to other LCMS, or metabolomics, data sets.

Detection of Schizophrenia Cases From Healthy Controls With Combination of Neurocognitive and Electrophysiological Features

BACKGROUND

The search for a method that utilizes biomarkers to identify patients with schizophrenia from healthy individuals has occupied researchers for decades. However, no single indicator can be employed to achieve the good in clinical practice. We aim to develop a comprehensive machine learning pipeline based on neurocognitive and electrophysiological combined features for distinguishing schizophrenia patients from healthy people.

METHODS

In the present study, 69 patients with schizophrenia and 50 healthy controls participated. Neurocognitive (contains seven specific domains of cognition) and electrophysiological [prepulse inhibition, electroencephalography (EEG) power spectrum, detrended fluctuation analysis, and fractal dimension (FD)] features were collected, all these features were taken together to generate the identification models of schizophrenia by applying logistics, random forest, and extreme gradient boosting algorithm. The classification capabilities of these models were also evaluated.

RESULTS

Both the neurocognitive and electrophysiological feature sets showed a good classification effect with the highest accuracy greater than 85% and AUC greater than 90%. Specifically, the performances of the combined neurocognitive and electrophysiological feature sets achieved the highest accuracy of 93.28% and AUC of 97.91%. The extreme gradient boosting algorithm as a whole presented more stably and precisely in classification efficiency.

CONCLUSION

The highest classification accuracy of 93.28% by combination of neurocognitive and electrophysiological features shows that both measurements are appropriate indicators to be used in discriminating schizophrenia patients and healthy individuals. Also, among three algorithms, extreme gradient boosting had better classified performances than logistics and random forest algorithms.

Screening of important metabolites and KRAS genotypes in colon cancer using secondary ion mass spectrometry

Time-of-flight secondary ion mass spectrometry (TOF-SIMS) is an imaging-based analytical technique that can characterize the surfaces of biomaterials. We used TOF-SIMS to identify important metabolites and oncogenic KRAS mutation expressed in human colorectal cancer (CRC). We obtained 540 TOF-SIMS spectra from 180 tissue samples by scanning cryo-sections and selected discriminatory molecules using the support vector machine (SVM) algorithm. Each TOF-SIMS spectrum contained nearly 860,000 ion profiles and hundreds of spectra were analyzed; therefore, reducing the dimensionality of the original data was necessary. We performed principal component analysis after preprocessing the spectral data, and the principal components (20) of each spectrum were used as the inputs of the SVM algorithm using the R package. The performance of the algorithm was evaluated using the receiver operating characteristic (ROC) area under the curve (AUC) (0.9297). Spectral peaks (m/z) corresponding to discriminatory molecules used to classify normal and tumor samples were selected according to p-value and were assigned to arginine, α-tocopherol, and fragments of glycerophosphocholine. Pathway analysis using these discriminatory molecules showed that they were involved in gastrointestinal disease and organismal abnormalities. In addition, spectra were classified according to the expression of KRAS somatic mutation, with 0.9921 AUC. Taken together, TOF-SIMS efficiently and simultaneously screened metabolite biomarkers and performed KRAS genotyping. In addition, a machine learning algorithm was provided as a diagnostic tool applied to spectral data acquired from clinical samples prepared as frozen tissue slides, which are commonly used in a variety of biomedical tests.

Distinguishing Alzheimer's Disease Patients and Biochemical Phenotype Analysis Using a Novel Serum Profiling Platform: Potential Involvement of the VWF/ADAMTS13 Axis

It is important to develop minimally invasive biomarker platforms to help in the identification and monitoring of patients with Alzheimer's disease (AD). Assisting in the understanding of biochemical mechanisms as well as identifying potential novel biomarkers and therapeutic targets would be an added benefit of such platforms. This study utilizes a simplified and novel serum profiling platform, using mass spectrometry (MS), to help distinguish AD patient groups (mild and moderate) and controls, as well as to aid in understanding of biochemical phenotypes and possible disease development. A comparison of discriminating sera mass peaks between AD patients and control individuals was performed using leave one [serum sample] out cross validation (LOOCV) combined with a novel peak classification valuation (PCV) procedure. LOOCV/PCV was able to distinguish significant sera mass peak differences between a group of mild AD patients and control individuals with a p value of 10^-13. This value became non-significant (p = 0.09) when the same sera samples were randomly allocated between the two groups and reanalyzed by LOOCV/PCV. This is indicative of physiological group differences in the original true-pathology binary group comparison. Similarities and differences between AD patients and traumatic brain injury (TBI) patients were also discernable using this novel LOOCV/PCV platform. MS/MS peptide analysis was performed on serum mass peaks comparing mild AD patients with control individuals. Bioinformatics analysis suggested that cell pathways/biochemical phenotypes affected in AD include those involving neuronal cell death, vasculature, neurogenesis, and AD/dementia/amyloidosis. Inflammation, autoimmunity, autophagy, and blood-brain barrier pathways also appear to be relevant to AD. An impaired VWF/ADAMTS13 vasculature axis with connections to F8 (factor VIII) and LRP1 and NOTCH1 was indicated and is proposed to be important in AD development.

Predictive Modeling for Metabolomics Data

In recent years, mass spectrometry (MS)-based metabolomics has been extensively applied to characterize biochemical mechanisms, and study physiological processes and phenotypic changes associated with disease. Metabolomics has also been important for identifying biomarkers of interest suitable for clinical diagnosis. For the purpose of predictive modeling, in this chapter, we will review various supervised learning algorithms such as random forest (RF), support vector machine (SVM), and partial least squares-discriminant analysis (PLS-DA). In addition, we will also review feature selection methods for identifying the best combination of metabolites for an accurate predictive model. We conclude with best practices for reproducibility by including internal and external replication, reporting metrics to assess performance, and providing guidelines to avoid overfitting and to deal with imbalanced classes. An analysis of an example data will illustrate the use of different machine learning methods and performance metrics.

Biomarker discovery by feature ranking: Evaluation on a case study of embryonal tumors

The task of biomarker discovery is best translated to the machine learning task of feature ranking. Namely, the goal of biomarker discovery is to identify a set of potentially viable targets for addressing a given biological status. This is aligned with the definition of feature ranking and its goal - to produce a list of features ordered by their importance for the target concept. This differs from the task of feature selection (typically used for biomarker discovery) in that it catches viable biomarkers that have redundant or overlapping information with often highly important biomarkers, while with feature selection this is not the case. We propose to use a methodology for evaluating feature rankings to assess the quality of a given feature ranking and to discover the best cut-off point. We demonstrate the effectiveness of the proposed methodology on 10 datasets containing data about embryonal tumors. We evaluate two most commonly used feature ranking algorithms (Random forests and RReliefF) and using the evaluation methodology identifies a set of viable biomarkers that have been confirmed to be related to cancer.

Early lung cancer diagnostic biomarker discovery by machine learning methods

•

Early diagnosis could improve lung cancer survival rate.

•

The availability of blood-based screening could increase lung cancer patient uptake.

•

An interdisciplinary mechanism combines metabolomics and machine learning methods.

•

Metabolic biomarkers could be potential screening biomarkers for early detection of lung cancer.

•

Naïve Bayes is recommended as an exploitable tool for early lung tumor prediction.

Early diagnosis has been proved to improve survival rate of lung cancer patients. The availability of blood-based screening could increase early lung cancer patient uptake. Our present study attempted to discover Chinese patients’ plasma metabolites as diagnostic biomarkers for lung cancer. In this work, we use a pioneering interdisciplinary mechanism, which is firstly applied to lung cancer, to detect early lung cancer diagnostic biomarkers by combining metabolomics and machine learning methods. We collected total 110 lung cancer patients and 43 healthy individuals in our study. Levels of 61 plasma metabolites were from targeted metabolomic study using LC-MS/MS. A specific combination of six metabolic biomarkers note-worthily enabling the discrimination between stage I lung cancer patients and healthy individuals (AUC = 0.989, Sensitivity = 98.1%, Specificity = 100.0%). And the top 5 relative importance metabolic biomarkers developed by FCBF algorithm also could be potential screening biomarkers for early detection of lung cancer. Naïve Bayes is recommended as an exploitable tool for early lung tumor prediction. This research will provide strong support for the feasibility of blood-based screening, and bring a more accurate, quick and integrated application tool for early lung cancer diagnostic. The proposed interdisciplinary method could be adapted to other cancer beyond lung cancer.

Emerging Role of Metabolomics in Ovarian Cancer Diagnosis

Ovarian cancer is considered a silent killer due to the lack of clear symptoms and efficient diagnostic tools that often lead to late diagnoses. Over recent years, the impelling need for proficient biomarkers has led researchers to consider metabolomics, an emerging omics science that deals with analyses of the entire set of small-molecules (≤1.5 kDa) present in biological systems. Metabolomics profiles, as a mirror of tumor-host interactions, have been found to be useful for the analysis and identification of specific cancer phenotypes. Cancer may cause significant metabolic alterations to sustain its growth, and metabolomics may highlight this, making it possible to detect cancer in an early phase of development. In the last decade, metabolomics has been widely applied to identify different metabolic signatures to improve ovarian cancer diagnosis. The aim of this review is to update the current status of the metabolomics research for the discovery of new diagnostic metabolomic biomarkers for ovarian cancer. The most promising metabolic alterations are discussed in view of their potential biological implications, underlying the issues that limit their effective clinical translation into ovarian cancer diagnostic tools.

Distinguishing patients with idiopathic epilepsy from solitary cysticercus granuloma epilepsy and biochemical phenotype assessment using a serum biomolecule profiling platform

A major source of epilepsy is Neurocysticercosis (NCC), caused by Taenia solium infection. Solitary cysticercus granuloma (SCG), a sub-group of NCC induced epilepsy, is the most common form of NCC in India. Current diagnostic criteria for SCG epilepsy require brain imaging which may not be available in communities where the disease is endemic. Identification of serum changes and potential biomolecules that could distinguish SCG epilepsy from idiopathic generalized epilepsy (IE), without the initial need for imaging, could assist in disease identification, understanding, and treatment. The objective here was to investigate, using mass spectrometry (MS), sera biomolecule differences between patients with SCG epilepsy or IE to help distinguish these disorders based on physiological differences, to understand underlying phenotypes and mechanisms, and to lay ground work for future therapeutic and biomarker analyses. Sera were obtained from patients with SCG or IE (N = 29 each group). Serum mass peak profiling was performed with electrospray ionization (ESI) MS, and mass peak area means in the two groups were compared using leave one [serum sample] out cross validation (LOOCV). Serum LOOCV analysis identified significant differences between SCG and IE patient groups (p = 10-20), which became non-significant (p = 0.074) when the samples were randomly allocated to the groups and reanalyzed. Tandem MS/MS peptide analysis of serum mass peaks from SCG or IE patients was performed to help identify potential peptide/protein biochemical and phenotypic changes involving these two forms of epilepsy. Bioinformatic analysis of these peptide/protein changes suggested neurological, inflammatory, seizure, blood brain barrier, cognition, ion channel, cell death, and behavior related biochemical systems were being altered in these disease states. This study provides groundwork for aiding in distinguishing SCG and IE patients in minimally invasive, lower-cost manners, for improving understanding of underlying epilepsy mechanisms, and for further identifying discriminatory biomarkers and potential therapeutic targets.

Artificial Intelligence to Decode Cancer Mechanism: Beyond Patient Stratification for Precision Oncology

The multitude of multi-omics data generated cost-effectively using advanced high-throughput technologies has imposed challenging domain for research in Artificial Intelligence (AI). Data curation poses a significant challenge as different parameters, instruments, and sample preparations approaches are employed for generating these big data sets. AI could reduce the fuzziness and randomness in data handling and build a platform for the data ecosystem, and thus serve as the primary choice for data mining and big data analysis to make informed decisions. However, AI implication remains intricate for researchers/clinicians lacking specific training in computational tools and informatics. Cancer is a major cause of death worldwide, accounting for an estimated 9.6 million deaths in 2018. Certain cancers, such as pancreatic and gastric cancers, are detected only after they have reached their advanced stages with frequent relapses. Cancer is one of the most complex diseases affecting a range of organs with diverse disease progression mechanisms and the effectors ranging from gene-epigenetics to a wide array of metabolites. Hence a comprehensive study, including genomics, epi-genomics, transcriptomics, proteomics, and metabolomics, along with the medical/mass-spectrometry imaging, patient clinical history, treatments provided, genetics, and disease endemicity, is essential. Cancer Moonshot℠ Research Initiatives by NIH National Cancer Institute aims to collect as much information as possible from different regions of the world and make a cancer data repository. AI could play an immense role in (a) analysis of complex and heterogeneous data sets (multi-omics and/or inter-omics), (b) data integration to provide a holistic disease molecular mechanism, (c) identification of diagnostic and prognostic markers, and (d) monitor patient's response to drugs/treatments and recovery. AI enables precision disease management well beyond the prevalent disease stratification patterns, such as differential expression and supervised classification. This review highlights critical advances and challenges in omics data analysis, dealing with data variability from lab-to-lab, and data integration. We also describe methods used in data mining and AI methods to obtain robust results for precision medicine from "big" data. In the future, AI could be expanded to achieve ground-breaking progress in disease management.

Serum discrimination and phenotype assessment of coronary artery disease patents with and without type 2 diabetes prior to coronary artery bypass graft surgery

Diabetes Mellitus (DM) accelerates coronary artery disease (CAD) and atherosclerosis, the causes of most heart attacks. The biomolecules involved in these inter-related disease processes are not well understood. This study analyzes biomolecules in the sera of patients with CAD, with and without type (T) 2DM, who are about to undergo coronary artery bypass graft (CABG) surgery. The goal is to develop methodology to help identify and monitor CAD patients with and without T2DM, in order to better understand these phenotypes and to glean relationships through analysis of serum biomolecules. Aorta, fat, muscle, and vein tissues from CAD T2DM patients display diabetic-related histologic changes (e.g., lipid accumulation, fibrosis, loss of cellularity) when compared to non-diabetic CAD patients. The patient discriminatory methodology utilized is serum biomolecule mass profiling. This mass spectrometry (MS) approach is able to distinguish the sera of a group of CAD patients from controls (p value 10⁻¹⁵), with the CAD group containing both T2DM and non-diabetic patients. This result indicates the T2DM phenotype does not interfere appreciably with the CAD determination versus control individuals. Sera from a group of T2DM CAD patients however are distinguishable from non-T2DM CAD patients (p value 10⁻⁸), indicating it may be possible to examine the T2DM phenotype within the CAD disease state with this MS methodology. The same serum samples used in the CAD T2DM versus non-T2DM binary group comparison were subjected to MS/MS peptide structure analysis to help identify potential biochemical and phenotypic changes associated with CAD and T2DM. Such peptide/protein identifications could lead to improved understanding of underlying mechanisms, additional biomarkers for discriminating and monitoring these disease conditions, and potential therapeutic targets. Bioinformatics/systems biology analysis of the peptide/protein changes associated with CAD and T2DM suggested cell pathways/systems affected include atherosclerosis, DM, fibrosis, lipogenesis, loss of cellularity (apoptosis), and inflammation.

Distinguishing and Biochemical Phenotype Analysis of Epilepsy Patients Using a Novel Serum Profiling Platform

Diagnosis of non-symptomatic epilepsy includes a history of two or more seizures and brain imaging to rule out structural changes like trauma, tumor, infection. Such analysis can be problematic. It is important to develop capabilities to help identify non-symptomatic epilepsy in order to better monitor and understand the condition. This understanding could lead to improved diagnostics and therapeutics. Serum mass peak profiling was performed using electrospray ionization mass spectrometry (ESI-MS). A comparison of sera mass peaks between epilepsy and control groups was performed via leave one [serum sample] out cross-validation (LOOCV). MS/MS peptide analysis was performed on serum mass peaks to compare epilepsy patient and control groups. LOOCV identified significant differences between the epilepsy patient group and control group (p = 10⁻²²). This value became non-significant (p = 0.10) when the samples were randomly allocated between the groups and reanalyzed by LOOCV. LOOCV was thus able to distinguish a non-symptomatic epilepsy patient group from a control group based on physiological differences and underlying phenotype. MS/MS was able to identify potential peptide/protein changes involved in this epilepsy versus control comparison, with 70% of the top 100 proteins indicating overall neurologic function. Specifically, peptide/protein sera changes suggested neuro-inflammatory, seizure, ion-channel, synapse, and autoimmune pathways changing between epilepsy patients and controls.

Dysregulation of amino acids and lipids metabolism in schizophrenia with violence

BACKGROUND

Many studies have related biochemical characteristics to violence and have reported schizophrenia could elevated the risk of violent behaviour. However, the metabolic characteristics of schizophrenia patients with violence (V.SC) are unclear.

METHODS

To explore the metabolic characteristics of schizophrenia with violence and to identify potential biomarkers, untargeted metabolomics was performed by using gas chromatography time-of-flight mass spectrometry to analyse the plasma metabolites of fifty-three V.SC and twenty-four schizophrenia patients without violence (NV.SC). Multivariate and univariate analyses were performed to identify differential metabolites and biomarkers. Violence was assessed by the MacArthur Violence Assessment Study method. Psychiatric symptoms were assessed by the Positive and Negative Syndrome Scale.

RESULTS

Multivariate analysis was unable to distinguish V.SC from NV.SC. Glycerolipid metabolism and phenylalanine, tyrosine and tryptophan biosynthesis were the differential metabolic pathways between V.SC and NV.SC. We confirmed ten metabolites and five metabolites as metabolic biomarkers of V.SC by random forest and support vector machine analysis, respectively. The biomarker panel, including the ratio of L-asparagine to L-aspartic acid, vanillylmandelic acid and glutaric acid, yielded an area under the receiver operating characteristic curve of 0.808.

CONCLUSIONS

This study gives a holistic view of the metabolic phenotype of schizophrenia with violence which is characterized by the dysregulation of lipids and amino acids. These results might provide information for the aetiological understanding and management of violence in schizophrenia; however, this is a preliminary metabolomics study about schizophrenia with violence, which needs to be repeated in future studies.

Machine Learning Approach for Predicting Past Environmental Exposures From Molecular Profiling of Post-Exposure Human Serum Samples

OBJECTIVE

To develop an approach for a retrospective analysis of post-exposure serum samples using diverse molecular profiles.

METHODS

The 236 molecular profiles from 800 de-identified human serum samples from the Department of Defense Serum Repository were classified as smokers or non-smokers based on direct measurement of serum cotinine levels. A machine-learning pipeline was used to classify smokers and non-smokers from their molecular profiles.

RESULTS

The refined supervised support vector machines with recursive feature elimination predicted smokers and non-smokers with 78% accuracy on the independent held-out set. Several of the identified classifiers of smoking status have previously been reported and four additional miRNAs were validated with experimental tobacco smoke exposure in mice, supporting the computational approach.

CONCLUSIONS

We developed and validated a pipeline that shows retrospective analysis of post-exposure serum samples can identify environmental exposures.

Deep Metabolomics of a High-Grade Serous Ovarian Cancer Triple-Knockout Mouse Model

High-grade serous carcinoma (HGSC) is the most common and deadliest ovarian cancer (OC) type, accounting for 70-80% of OC deaths. This high mortality is largely due to late diagnosis. Early detection is thus crucial to reduce mortality, yet the tumor pathogenesis of HGSC remains poorly understood, making early detection exceedingly difficult. Faithfully and reliably representing the clinical nature of human HGSC, a recently developed triple-knockout (TKO) mouse model offers a unique opportunity to examine the entire disease spectrum of HGSC. Metabolic alterations were investigated by applying ultra-performance liquid chromatography-mass spectrometry (UPLC-MS) to serum samples collected from these mice at premalignant, early, and advanced stages of HGSC. This comprehensive analysis revealed a panel of 29 serum metabolites that distinguished mice with HGSC from controls and mice with uterine tumors with over 95% accuracy. Meanwhile, our panel could further distinguish early-stage HGSC from controls with 100% accuracy and from advanced-stage HGSC with over 90% accuracy. Important identified metabolites included phospholipids, sphingomyelins, sterols, N-acyltaurine, oligopeptides, bilirubin, 2(3)-hydroxysebacic acids, uridine, N-acetylneuraminic acid, and pyrazine derivatives. Overall, our study provides insights into dysregulated metabolism associated with HGSC development and progression, and serves as a useful guide toward early detection.

Distinguishing and phenotype monitoring of traumatic brain injury and post-concussion syndrome including chronic migraine in serum of Iraq and Afghanistan war veterans

Traumatic Brain Injury (TBI) and persistent post-concussion syndrome (PCS) including chronic migraine (CM) are major health issues for civilians and the military. It is important to understand underlying biochemical mechanisms of these conditions, and be able to monitor them in an accurate and minimally invasive manner. This study describes the initial use of a novel serum analytical platform to help distinguish TBI patients, including those with post-traumatic headache (PTH), and to help identify phenotypes at play in these disorders. The hypothesis is that physiological responses to disease states like TBI and PTH and related bodily stresses are reflected in biomolecules in the blood in disease-specific manner. Leave one out (serum sample) cross validations (LOOCV) and sample randomizations were utilized to distinguished serum samples from the following TBI patient groups: TBI +PTSD + CM + severe depression (TBI "most affected" group) vs healthy controls, TBI "most affected" vs TBI, TBI vs controls, TBI + CM vs controls, and TBI + CM vs TBI. Inter-group discriminatory p values were ≤ 10-10, and sample group randomizations resulted in p non-significant values. Peptide/protein identifications of discriminatory mass peaks from the TBI "most affected" vs controls and from the TBI plus vs TBI minus CM groups yielded information of the cellular/molecular effects of these disorders (immune responses, amyloidosis/Alzheimer's disease/dementia, neuronal development). More specific biochemical disease effects appear to involve blood brain barrier, depression, migraine headache, autoimmunity, and autophagy pathways. This study demonstrated the ability for the first time of a novel, accurate, biomarker platform to monitor these conditions in serum, and help identify biochemical relationships leading to better understanding of these disorders and to potential therapeutic approaches.

Machine Learning in Untargeted Metabolomics Experiments

Machine learning is a form of artificial intelligence (AI) that provides computers with the ability to learn generally without being explicitly programmed. Machine learning refers to the ability of computer programs to adapt when exposed to new data. Here we examine the use of machine learning for use with untargeted metabolomics data, when it is appropriate to use, and questions it can answer. We provide an example workflow for training and testing a simple binary classifier, a multiclass classifier and a support vector machine using the Waikato Environment for Knowledge Analysis (Weka), a toolkit for machine learning. This workflow should provide a framework for greater integration of machine learning with metabolomics study.

Distinguishing neurocysticercosis epilepsy from epilepsy of unknown etiology using a minimal serum mass profiling platform

Neurocysticercosis is associated with epilepsy in pig-raising communities with poor sanitation. Current internationally recognized diagnostic guidelines for neurocysticercosis rely on brain imaging, a technology that is frequently not available or not accessible in areas endemic for neurocysticercosis. Minimally invasive and low-cost aids for diagnosing neurocysticercosis epilepsy could improve treatment of neurocysticercosis. The goal of this study was to test the extent to which patients with neurocysticercosis epilepsy, epilepsy of unknown etiology, idiopathic headaches and among different types of neurocysticercosis lesions could be distinguished from each other based on serum mass profiling. For this, we collected sera from patients with neurocysticercosis-associated epilepsy, epilepsy of unknown etiology, recovered neurocysticercosis, and idiopathic headaches then performed binary group comparisons among them using electrospray ionization mass spectrometry. A leave one [serum sample] out cross validation procedure was employed to analyze spectral data. Sera from neurocysticercosis patients was distinguished from epilepsy of unknown etiology patients with a p-value of 10^-28. This distinction was lost when samples were randomized to either group (p-value = 0.22). Similarly, binary comparisons of patients with neurocysticercosis who has different types of lesions showed that different forms of this disease were also distinguishable from one another. These results suggest neurocysticercosis epilepsy can be distinguished from epilepsy of unknown etiology based on biomolecular differences in sera detected by mass profiling.

Classifying osteosarcoma patients using machine learning approaches

Metabolomic data analysis presents a unique opportunity to advance our understanding of osteosarcoma, a common bone malignancy for which genomic and proteomic studies have enjoyed limited success. One of the major goals of metabolomic studies is to classify osteosarcoma in early stages, which is required for metastasectomy treatment. In this paper we subject our metabolomic data on osteosarcoma patients collected by the SJTU team to three classification methods: logistic regression, support vector machine (SVM) and random forest (RF). The performances are evaluated and compared using receiver operating characteristic curves. All three classifiers are successful in distinguishing between healthy control and tumor cases, with random forest outperforming the other two for cross-validation in training set (accuracy rate for logistic regression, support vector machine and random forest are 88%, 90% and 97% respectively). Random forest achieved overall accuracy rate of 95% with 0.99 AUC on testing set.

Critical review of reporting of the data analysis step in metabolomics

INTRODUCTION

We present the first study to critically appraise the quality of reporting of the data analysis step in metabolomics studies since the publication of minimum reporting guidelines in 2007.

OBJECTIVES

The aim of this study was to assess the standard of reporting of the data analysis step in metabolomics biomarker discovery studies and to investigate whether the level of detail supplied allows basic understanding of the steps employed and/or reuse of the protocol. For the purposes of this review we define the data analysis step to include the data pretreatment step and the actual data analysis step, which covers algorithm selection, univariate analysis and multivariate analysis.

METHOD

We reviewed the literature to identify metabolomic studies of biomarker discovery that were published between January 2008 and December 2014. Studies were examined for completeness in reporting the various steps of the data pretreatment phase and data analysis phase and also for clarity of the workflow of these sections.

RESULTS

We analysed 27 papers, published anytime in 2008 until the end of 2014 in the area or biomarker discovery in serum metabolomics. The results of this review showed that the data analysis step in metabolomics biomarker discovery studies is plagued by unclear and incomplete reporting. Major omissions and lack of logical flow render the data analysis' workflows in these studies impossible to follow and therefore replicate or even imitate.

CONCLUSIONS

While we await the holy grail of computational reproducibility in data analysis to become standard, we propose that, at a minimum, the data analysis section of metabolomics studies should be readable and interpretable without omissions such that a data analysis workflow diagram could be extrapolated from the study and therefore the data analysis protocol could be reused by the reader. That inconsistent and patchy reporting obfuscates reproducibility is a given. However even basic understanding and reuses of protocols are hampered by the low level of detail supplied in the data analysis sections of the studies that we reviewed.

Circulating metabolite profiles to predict overall survival in advanced non-small cell lung cancer patients receiving first-line chemotherapy

OBJECTIVES

The prognosis for advanced-stage non-small cell lung cancer (NSCLC) is usually poor. However, survival may be variable and difficult to predict. In the current study, we aimed to identify circulating metabolites as potential predictive biomarkers for overall survival of advanced-stage (III/IV) NSCLC patients treated with first-line platinum-based chemotherapy.

MATERIALS AND METHODS

Using two-stage study design, we performed global metabolomic profiling in blood of 220 advanced-stage NSCLC patients, including 110 with poor survival and 110 with good survival. Metabolomic profiling was conducted using Metabolon platform. The association of each metabolite with survival was assessed by Cox proportional hazard regression model with adjustment for covariates.

RESULTS AND CONCLUSION

We found levels of 4 metabolites, caffeine, paraxanthine, stachydrine, and methyl glucopyranoside (alpha+beta), differed significantly between NSCLC patients with poor and good survival in both discovery and validation phases (P<0.05). Interestingly, majority of the identified metabolites are involved in caffeine metabolism, and 2 metabolites are related to coffee intake. In fact, caffeine metabolism pathway was the only significant pathway identified which significantly differed between NSCLC patients with poor and good survival (P=1.48E-07) in the pathway analysis. We also found 4 metabolites whose levels were significantly associated with good survival in both discovery and validation phases. Strong cumulative effects on overall survival were observed for these 4 metabolites. In conclusion, we identified a panel of metabolites including metabolites in caffeine metabolism pathway that may predict survival outcome in advanced-stage NSCLC patients. The identified small metabolites may be useful biomarker candidates to help identify patients who may benefit from platinum-based chemotherapy.

Open source machine-learning algorithms for the prediction of optimal cancer drug therapies

Precision medicine is a rapidly growing area of modern medical science and open source machine-learning codes promise to be a critical component for the successful development of standardized and automated analysis of patient data. One important goal of precision cancer medicine is the accurate prediction of optimal drug therapies from the genomic profiles of individual patient tumors. We introduce here an open source software platform that employs a highly versatile support vector machine (SVM) algorithm combined with a standard recursive feature elimination (RFE) approach to predict personalized drug responses from gene expression profiles. Drug specific models were built using gene expression and drug response data from the National Cancer Institute panel of 60 human cancer cell lines (NCI-60). The models are highly accurate in predicting the drug responsiveness of a variety of cancer cell lines including those comprising the recent NCI-DREAM Challenge. We demonstrate that predictive accuracy is optimized when the learning dataset utilizes all probe-set expression values from a diversity of cancer cell types without pre-filtering for genes generally considered to be “drivers” of cancer onset/progression. Application of our models to publically available ovarian cancer (OC) patient gene expression datasets generated predictions consistent with observed responses previously reported in the literature. By making our algorithm “open source”, we hope to facilitate its testing in a variety of cancer types and contexts leading to community-driven improvements and refinements in subsequent applications.

Serum Monitoring and Phenotype Identification of Stage I Non-Small Cell Lung Cancer Patients

A stage I non-small cell lung cancer (NSCLC) serum profiling platform is presented which is highly efficient and accurate. Test sensitivity (0.95) for stage I NSCLC is the highest reported so far. Test metrics are reported for discriminating stage I adenocarcinoma vs squamous cell carcinoma subtypes. Blinded analysis identified 23 out of 24 stage I NSCLC and control serum samples. Group-discriminating mass peaks were targeted for tandem mass spectrometry peptide/protein identification, and yielded a lung cancer phenotype. Bioinformatic analysis revealed a novel lymphocyte adhesion pathway involved with early-stage lung cancer.

Evaluation of Classifier Performance for Multiclass Phenotype Discrimination in Untargeted Metabolomics

Statistical classification is a critical component of utilizing metabolomics data for examining the molecular determinants of phenotypes. Despite this, a comprehensive and rigorous evaluation of the accuracy of classification techniques for phenotype discrimination given metabolomics data has not been conducted. We conducted such an evaluation using both simulated and real metabolomics datasets, comparing Partial Least Squares-Discriminant Analysis (PLS-DA), Sparse PLS-DA, Random Forests, Support Vector Machines (SVM), Artificial Neural Network, k-Nearest Neighbors (k-NN), and Naïve Bayes classification techniques for discrimination. We evaluated the techniques on simulated data generated to mimic global untargeted metabolomics data by incorporating realistic block-wise correlation and partial correlation structures for mimicking the correlations and metabolite clustering generated by biological processes. Over the simulation studies, covariance structures, means, and effect sizes were stochastically varied to provide consistent estimates of classifier performance over a wide range of possible scenarios. The effects of the presence of non-normal error distributions, the introduction of biological and technical outliers, unbalanced phenotype allocation, missing values due to abundances below a limit of detection, and the effect of prior-significance filtering (dimension reduction) were evaluated via simulation. In each simulation, classifier parameters, such as the number of hidden nodes in a Neural Network, were optimized by cross-validation to minimize the probability of detecting spurious results due to poorly tuned classifiers. Classifier performance was then evaluated using real metabolomics datasets of varying sample medium, sample size, and experimental design. We report that in the most realistic simulation studies that incorporated non-normal error distributions, unbalanced phenotype allocation, outliers, missing values, and dimension reduction, classifier performance (least to greatest error) was ranked as follows: SVM, Random Forest, Naïve Bayes, sPLS-DA, Neural Networks, PLS-DA and k-NN classifiers. When non-normal error distributions were introduced, the performance of PLS-DA and k-NN classifiers deteriorated further relative to the remaining techniques. Over the real datasets, a trend of better performance of SVM and Random Forest classifier performance was observed.

Biomarker analysis of American toad (Anaxyrus americanus) and grey tree frog (Hyla versicolor) tadpoles following exposure to atrazine

The objective of the current study was to use a biomarker-based approach to investigate the influence of atrazine exposure on American toad (Anaxyrus americanus) and grey tree frog (Hyla versicolor) tadpoles. Atrazine is one of the most frequently detected herbicides in environmental matrices throughout the United States. In surface waters, it has been found at concentrations from 0.04-2859μg/L and thus presents a likely exposure scenario for non-target species such as amphibians. Studies have examined the effect of atrazine on the metamorphic parameters of amphibians, however, the data are often contradictory. Gosner stage 22-24 tadpoles were exposed to 0 (control), 10, 50, 250 or 1250μg/L of atrazine for 48h. Endogenous polar metabolites were extracted and analyzed using gas chromatography coupled with mass spectrometry. Statistical analyses of the acquired spectra with machine learning classification models demonstrated identifiable changes in the metabolomic profiles between exposed and control tadpoles. Support vector machine models with recursive feature elimination created a more efficient, non-parametric data analysis and increased interpretability of metabolomic profiles. Biochemical fluxes observed in the exposed groups of both A. americanus and H. versicolor displayed perturbations in a number of classes of biological macromolecules including fatty acids, amino acids, purine nucleosides, pyrimidines, and mono- and di-saccharides. Metabolomic pathway analyses are consistent with findings of other studies demonstrating disruption of amino acid and energy metabolism from atrazine exposure to non-target species.

Metabolomics of biomarker discovery in ovarian cancer: a systematic review of the current literature

INTRODUCTION

Metabolomics is the emerging member of "omics" sciences advancing the understanding, diagnosis and treatment of many cancers, including ovarian cancer (OC).

OBJECTIVES

To systematically identify the metabolomic abnormalities in OC detection, and the dominant metabolic pathways associated with the observed alterations.

METHODS

An electronic literature search was performed, up to and including January 15th 2016, for studies evaluating the metabolomic profile of patients with OC compared to controls. QUADOMICS tool was used to assess the quality of the twenty-three studies included in this systematic review.

RESULTS

Biological samples utilized for metabolomic analysis include: serum/plasma (n = 13), urine (n = 4), cyst fluid (n = 3), tissue (n = 2) and ascitic fluid (n = 1). Metabolites related to cellular respiration, carbohydrate, lipid, protein and nucleotide metabolism were significantly altered in OC. Increased levels of tricarboxylic acid cycle intermediates and altered metabolites of the glycolytic pathway pointed to perturbations in cellular respiration. Alterations in lipid metabolism included enhanced fatty acid oxidation, abnormal levels of glycerolipids, sphingolipids and free fatty acids with common elevations of palmitate, oleate, and myristate. Increased levels of glutamine, glycine, cysteine and threonine were commonly reported while enhanced degradations of tryptophan, histidine and phenylalanine were found. N-acetylaspartate, a brain amino acid, was found elevated in primary and metastatic OC tissue and ovarian cyst fluid. Further, elevated levels of ketone bodies including 3-hydroxybutyrate were commonly reported. Increased levels of nucleotide metabolites and tocopherols were consistent through out the studies.

CONCLUSION

Metabolomics presents significant new opportunities for diagnostic biomarker development, elucidating previously unknown mechanisms of OC pathogenesis.

Serum metabolomic profiling facilitates the non-invasive identification of metabolic biomarkers associated with the onset and progression of non-small cell lung cancer

Lung cancer (LC) is responsible for most cancer deaths. One of the main factors contributing to the lethality of this disease is the fact that a large proportion of patients are diagnosed at advanced stages when a clinical intervention is unlikely to succeed. In this study, we evaluated the potential of metabolomics by 1H-NMR to facilitate the identification of accurate and reliable biomarkers to support the early diagnosis and prognosis of non-small cell lung cancer (NSCLC).We found that the metabolic profile of NSCLC patients, compared with healthy individuals, is characterized by statistically significant changes in the concentration of 18 metabolites representing different amino acids, organic acids and alcohols, as well as different lipids and molecules involved in lipid metabolism. Furthermore, the analysis of the differences between the metabolic profiles of NSCLC patients at different stages of the disease revealed the existence of 17 metabolites involved in metabolic changes associated with disease progression.Our results underscore the potential of metabolomics profiling to uncover pathophysiological mechanisms that could be useful to objectively discriminate NSCLC patients from healthy individuals, as well as between different stages of the disease.

Highly-accurate metabolomic detection of early-stage ovarian cancer

High performance mass spectrometry was employed to interrogate the serum metabolome of early-stage ovarian cancer (OC) patients and age-matched control women. The resulting spectral features were used to establish a linear support vector machine (SVM) model of sixteen diagnostic metabolites that are able to identify early-stage OC with 100% accuracy in our patient cohort. The results provide evidence for the importance of lipid and fatty acid metabolism in OC and serve as the foundation of a clinically significant diagnostic test.

Metabolic profiling of epithelial ovarian cancer cell lines: evaluation of harvesting protocols for profiling using NMR spectroscopy

BACKGROUND

Metabolic profiling represents a novel technology for analyzing tumor cells. Epithelial ovarian carcinoma has a low survival rate due to the development of aggressive and chemotherapy-resistant cells. A tailored and reliable protocol is presented for profiling of chemoresistant cells using the cell line SKOV3 and a multiresistant subline SKOV3R.

RESULTS

Harvesting protocols with cold methanol or MilliQ freeze/thaw cycles were compared. Increased reproducibility using MilliQ was evidenced. Importantly, both approaches resulted in similar profiles. Compared with parental SKOV3, the SKOV3R cells showed a significantly different profile.

CONCLUSION

The MilliQ protocol is preferred owing to higher reproducibility and increased sample preparation options. The resulting metabolic profiles summarize metabolic alterations in chemoresistant cells consistent with a progressed and aggressive phenotype.

Discriminating patients with early-stage pancreatic cancer or chronic pancreatitis using serum electrospray mass profiling

Blood tests are needed to aid in the early detection of pancreatic ductal adenocarcinoma (PDAC), and monitoring pancreatitis development into malignancy especially in high risk patients. This study exhibits efforts and progress toward developing such blood tests, using electrospray-mass spectrometry (MS) serum profiling to distinguish patients with early-stage PDAC or pancreatitis from each other and from controls. Identification of significant serum mass peak differences between these individuals was performed using t tests and "leave one out" cross validation. Serum mass peak distributions of control individuals were distinguished from those of patients with chronic pancreatitis or early-stage PDAC with P values <10(-15), and patients with chronic pancreatitis were distinguished from those of patients with early-stage PDAC with a P value <10(-12). Sera from 12 out of 12 patients with PDAC stages I, IIA and IIB were blindly validated from controls. Tandem MS/MS identified a cancer phenotype with elements of PDAC involved in early-stage PDAC/control discrimination. These studies indicate electrospray-MS mass profiling can detect serum changes in patients with pancreatitis or early-stage pancreatic cancer. Such technology has the potential to aid in early detection of pancreatic cancer, biomarker development, and in monitoring development of pancreatitis into PDAC.

Current state-of-the-art of nontargeted metabolomics based on liquid chromatography-mass spectrometry with special emphasis in clinical applications

Metabolomics, as a part of systems biology, has been widely applied in different fields of life science by studying the endogenous metabolites. The development and applications of liquid chromatography (LC) coupled with high resolution mass spectrometry (MS) greatly improve the achievable data quality in non-targeted metabolic profiling. However, there are still some emerging challenges to be covered in LC-MS based metabolomics. Here, recent approaches about sample collection and preparation, instrumental analysis, and data handling of LC-MS based metabolomics are summarized, especially in the analysis of clinical samples. Emphasis is put on the improvement of analytical techniques including the combination of different LC columns, isotope coded derivatization methods, pseudo-targeted LC-MS method, new data analysis algorithms and structural identification of important metabolites.

Metabolomics reveals the sex-specific effects of the SORT1 low-density lipoprotein cholesterol locus in healthy young adults

Metabolite profiles of individuals possessing either the cardiovascular risk or protective variants of the low-density lipoprotein cholesterol (LDL-C) associated 1p13.3 locus of the SORT1 gene (rs646776) were analyzed. Serum metabolites and lipids were assessed using LC-MS-based metabolomics in a healthy young population (n = 138: 95 males, 43 females). Although no significant differences were observed in the combined cohort, divergent sex effects were identified. Females carrying the protective allele showed increased phosphatidylcholines, very long chain fatty acids (>C20), and unsaturated fatty acids. Unsaturated fatty acids are considered to be protective against cardiovascular disease. In contrast, males carrying the protective allele exhibited decreased long-chain fatty acids (≤C20) and sphingomyelins, which is similarly considered to decrease cardiovascular disease risk. No significant changes in clinically assessed lipids such as LDL-C, high-density lipoprotein (HDL-C), total cholesterol, or triglycerides were observed in females, whereas only LDL-C was significantly changed in males. This indicates that, apart from reducing LDL-C, other mechanisms may contribute to the protective effect of the SORT1 locus. Thus, the analysis of metabolic biomarkers might reveal early disease development that may be overlooked by relying on standard clinical parameters.

Feasibility of detecting prostate cancer by ultraperformance liquid chromatography-mass spectrometry serum metabolomics

Prostate cancer (PCa) is the second leading cause of cancer-related mortality in men. The prevalent diagnosis method is based on the serum prostate-specific antigen (PSA) screening test, which suffers from low specificity, overdiagnosis, and overtreatment. In this work, untargeted metabolomic profiling of age-matched serum samples from prostate cancer patients and healthy individuals was performed using ultraperformance liquid chromatography coupled to high-resolution tandem mass spectrometry (UPLC-MS/MS) and machine learning methods. A metabolite-based in vitro diagnostic multivariate index assay (IVDMIA) was developed to predict the presence of PCa in serum samples with high classification sensitivity, specificity, and accuracy. A panel of 40 metabolic spectral features was found to be differential with 92.1% sensitivity, 94.3% specificity, and 93.0% accuracy. The performance of the IVDMIA was higher than the prevalent PSA test. Within the discriminant panel, 31 metabolites were identified by MS and MS/MS, with 10 further confirmed chromatographically by standards. Numerous discriminant metabolites were mapped in the steroid hormone biosynthesis pathway. The identification of fatty acids, amino acids, lysophospholipids, and bile acids provided further insights into the metabolic alterations associated with the disease. With additional work, the results presented here show great potential toward implementation in clinical settings.

Distinguishing patients with stage I lung cancer versus control individuals using serum mass profiling

Serum mass profiling can discern physiological changes associated with specific disease states and their progression. Sera (86 total) from control individuals and patients with stage I nonsmall cell lung cancer or benign small pulmonary nodules were discriminated retrospectively by serum changes discerned by mass profiling. Control individuals were distinguished from patients with Stage I lung cancer or benign nodules with test sensitivities of 89% and 83%. Lung cancer patients versus those with benign nodules were distinguished with 80% sensitivity. This study exhibits progress toward a minimally-invasive aid in early detection of lung cancer and monitoring small pulmonary nodules for malignancy.

Mass profiling of serum to distinguish mice with pancreatic cancer induced by a transgenic Kras mutation

Mass spectrometry (MS) has the unique ability to profile, in an easily accessible body tissue (peripheral blood/serum,) the sizes and relative amounts of a wide variety of biomolecules in a single platform setting. Using electrospray ionization (ESI)-MS, we distinguished individual serum from wild-type control mice from serum of mice containing an oncogenic Kras mutation, which leads to development of pancreatic ductal adenocarcinoma (PDAC) similar to that observed in humans. Identification of differences in significant ESI-MS sera mass peaks between Kras-activated mice and control mice was performed using t tests and a "nested leave one out" cross-validation procedure. Peak distributions in serum of control mice from mice with Kras-mutant-dependent PDAC were distinguished from those of pancreatic intraepithelial neoplasia (PanIN) lesions (p = 0.00024). In addition, Kras mutant mice with PDAC were distinguished from Kras mutant mice with PanIN alone (p = 0.0057). Test specificity, a measure of the false positives, was greater for the control vs. Kras mutated mice, and the test sensitivity, a measure of false negatives, was greater for the PDAC vs. PanIN containing mice. Receiver-operating characteristic (ROC) curve discriminatory values were 0.85 for both comparisons. These studies indicate ESI-MS serum mass profiling can detect physiological changes associated with pancreatic cancer initiation and development in a GEM (genetic engineered mouse) model that mimics pancreatic cancer development in humans. Such technology has the potential to aid in early detection of pancreatic cancer and in developing therapeutic drug interventions.