Sparse representation approaches for the classification of high-dimensional biological data

Background

High-throughput genomic and proteomic data have important applications in medicine including prevention, diagnosis, treatment, and prognosis of diseases, and molecular biology, for example pathway identification. Many of such applications can be formulated to classification and dimension reduction problems in machine learning. There are computationally challenging issues with regards to accurately classifying such data, and which due to dimensionality, noise and redundancy, to name a few. The principle of sparse representation has been applied to analyzing high-dimensional biological data within the frameworks of clustering, classification, and dimension reduction approaches. However, the existing sparse representation methods are inefficient. The kernel extensions are not well addressed either. Moreover, the sparse representation techniques have not been comprehensively studied yet in bioinformatics.

Results

In this paper, a Bayesian treatment is presented on sparse representations. Various sparse coding and dictionary learning models are discussed. We propose fast parallel active-set optimization algorithm for each model. Kernel versions are devised based on their dimension-free property. These models are applied for classifying high-dimensional biological data.

Conclusions

In our experiment, we compared our models with other methods on both accuracy and computing time. It is shown that our models can achieve satisfactory accuracy, and their performance are very efficient.

     

Characterizing biomarkers in osteosarcoma metastasis based on an ego-network

Objectives

To characterize biomarkers that underlie osteosarcoma (OS) metastasis based on an ego-network.

Results

From the microarray data, we obtained 13,326 genes. By combining PPI data and microarray data, 10,520 shared genes were found and constructed into ego-networks. 17 significant ego-networks were identified with p < 0.05. In the pathway enrichment analysis, seven ego-networks were identified with the most significant pathway.

Conclusions

These significant ego-modules were potential biomarkers that reveal the potential mechanisms in OS metastasis, which may contribute to understanding cancer prognoses and providing new perspectives in the treatment of cancer.

     

A lost opportunity for science: journals promote data sharing in metabolomics but do not enforce it

Introduction

Data sharing is being increasingly required by journals and has been heralded as a solution to the ‘replication crisis’.

Objectives

(i) Review data sharing policies of journals publishing the most metabolomics papers associated with open data and (ii) compare these journals’ policies to those that publish the most metabolomics papers.

Methods

A PubMed search was used to identify metabolomics papers. Metabolomics data repositories were manually searched for linked publications.

Results

Journals that support data sharing are not necessarily those with the most papers associated to open metabolomics data.

Conclusion

Further efforts are required to improve data sharing in metabolomics.

     

Does centrifugation matter? Centrifugal force and spinning time alter the plasma metabolome

Background

Centrifugation is an indispensable procedure for plasma sample preparation, but applied conditions can vary between labs.

Aim

Determine whether routinely used plasma centrifugation protocols (1500×g 10 min; 3000×g 5 min) influence non-targeted metabolomic analyses.

Methods

Nuclear magnetic resonance spectroscopy (NMR) and High Resolution Mass Spectrometry (HRMS) data were evaluated with sparse partial least squares discriminant analyses and compared with cell count measurements.

Results

Besides significant differences in platelet count, we identified substantial alterations in NMR and HRMS data related to the different centrifugation protocols.

Conclusion

Already minor differences in plasma centrifugation can significantly influence metabolomic patterns and potentially bias metabolomics studies.

     

An improved sparse representation model with structural information for Multicolour Fluorescence <Emphasis Type="Italic">In-Situ</Emphasis> Hybridization (M-FISH) image classification

Background

Multicolour Fluorescence In-Situ Hybridization (M-FISH) images are employed for detecting chromosomal abnormalities such as chromosomal translocations, deletions, duplication and inversions. This technique uses mixed colours of fluorochromes to paint the whole chromosomes for rapid detection of chromosome rearrangements. The M-FISH data sets used in our research are obtained from microscopic scanning of a metaphase cell labelled with five different fluorochromes and a DAPI staining. The reliability of the technique lies in accurate classification of chromosomes (24 classes for male and 23 classes for female) from M-FISH images. However, due to imaging noise, mis-alignment between multiple channels and many other imaging problems, there is always a classification error, leading to wrong detection of chromosomal abnormalities. Therefore, how to accurately classify different types of chromosomes from M-FISH images becomes a challenging problem.

Methods

This paper presents a novel sparse representation model considering structural information for the classification of M-FISH images. In our previous work a sparse representation based classification model was proposed. This model employed only individual pixel information for the classification. With the structural information of neighbouring pixels as well as the information of themselves simultaneously, the novel approach extended the previous one to the regional case. Based on Orthogonal Matching Pursuit (OMP), we developed simultaneous OMP algorithm (SOMP) to derive an efficient solution of the improved sparse representation model by incorporating the structural information.

Results

The p-value of two models shows that the newly proposed model incorporating the structural information is significantly superior to our previous one. In addition, we evaluated the effect of several parameters, such as sparsity level, neighbourhood size, and training sample size, on the of the classification accuracy.

Conclusions

The comparison with our previously used sparse model demonstrates that the improved sparse representation model is more effective than the previous one on the classification of the chromosome abnormalities.

     

Pathway-based analyses

Background

New technologies for acquisition of genomic data, while offering unprecedented opportunities for genetic discovery, also impose severe burdens of interpretation andpenalties for multiple testing.

Methods

The Pathway-based Analyses Group of the Genetic Analysis Workshop 19 (GAW19) sought reduction of multiple-testing burden through various approaches to aggregation of highdimensional data in pathways informed by prior biological knowledge.

Results

Experimental methods testedincluded the use of "synthetic pathways" (random sets of genes) to estimate power and false-positive error rate of methods applied to simulated data; data reduction via independent components analysis, single-nucleotide polymorphism (SNP)-SNP interaction, and use of gene sets to estimate genetic similarity; and general assessment of the efficacy of prior biological knowledge to reduce the dimensionality of complex genomic data.

Conclusions

The work of this group explored several promising approaches to managing high-dimensional data, with the caveat that these methods are necessarily constrained by the quality of external bioinformatic annotation.

     

Metabolomic profiling of maternal hair suggests rapid development of intrahepatic cholestasis of pregnancy

Introduction

Intrahepatic cholestasis of pregnancy (ICP) is a common maternal liver disease; development can result in devastating consequences, including sudden fetal death and stillbirth. Currently, recognition of ICP only occurs following onset of clinical symptoms.

Objective

Investigate the maternal hair metabolome for predictive biomarkers of ICP.

Methods

The maternal hair metabolome (gestational age of sampling between 17 and 41 weeks) of 38 Chinese women with ICP and 46 pregnant controls was analysed using gas chromatography–mass spectrometry.

Results

Of 105 metabolites detected in hair, none were significantly associated with ICP.

Conclusion

Hair samples represent accumulative environmental exposure over time. Samples collected at the onset of ICP did not reveal any metabolic shifts, suggesting rapid development of the disease.

     

Identification of a urine metabolite constellation characteristic for kidney allograft rejection

Introduction

Allograft rejection is still an important complication after kidney transplantation. Currently, monitoring of these patients mostly relies on the measurement of serum creatinine and clinical evaluation. The gold standard for diagnosing allograft rejection, i.e. performing a renal biopsy is invasive and expensive. So far no adequate biomarkers are available for routine use.

Objectives

We aimed to develop a urine metabolite constellation that is characteristic for acute renal allograft rejection.

Methods

NMR-Spectroscopy was applied to a training cohort of transplant recipients with and without acute rejection.

Results

We obtained a metabolite constellation of four metabolites that shows promising performance to detect renal allograft rejection in the cohorts used (AUC of 0.72 and 0.74, respectively).

Conclusion

A metabolite constellation was defined with the potential for further development of an in-vitro diagnostic test that can support physicians in their clinical assessment of a kidney transplant patient.

     

Optimization of fecal sample preparation for untargeted LC-HRMS based metabolomics

Introduction

Collecting feces is easy. It offers direct outcome to endogenous and microbial metabolites.

Objectives

In a context of lack of consensus about fecal sample preparation, especially in animal species, we developed a robust protocol allowing untargeted LC-HRMS fingerprinting.

Methods

The conditions of extraction (quantity, preparation, solvents, dilutions) were investigated in bovine feces.

Results

A rapid and simple protocol involving feces extraction with methanol (1/3, M/V) followed by centrifugation and a step filtration (10 kDa) was developed.

Conclusion

The workflow generated repeatable and informative fingerprints for robust metabolome characterization.

     

Applications of metabolomics in the study and management of preeclampsia: a review of the literature

Introduction

Preeclampsia represents a major public health burden worldwide, but predictive and diagnostic biomarkers are lacking. Metabolomics is emerging as a valuable approach to generating novel biomarkers whilst increasing the mechanistic understanding of this complex condition.

Objectives

To summarize the published literature on the use of metabolomics as a tool to study preeclampsia.

Methods

PubMed and Web of Science were searched for articles that performed metabolomic profiling of human biosamples using either Mass-spectrometry or Nuclear Magnetic Resonance based approaches and which included preeclampsia as a primary endpoint.

Results

Twenty-eight studies investigating the metabolome of preeclampsia in a variety of biospecimens were identified. Individual metabolite and metabolite profiles were reported to have discriminatory ability to distinguish preeclamptic from normal pregnancies, both prior to and post diagnosis. Lipids and carnitines were among the most commonly reported metabolites. Further work and validation studies are required to demonstrate the utility of such metabolites as preeclampsia biomarkers.

Conclusion

Metabolomic-based biomarkers of preeclampsia have yet to be integrated into routine clinical practice. However, metabolomic profiling is becoming increasingly popular in the study of preeclampsia and is likely to be a valuable tool to better understand the pathophysiology of this disorder and to better classify its subtypes, particularly when integrated with other omic data.

     

Metabolomics approach for predicting response to neoadjuvant chemotherapy for colorectal cancer

Introduction

Colorectal cancer (CRC) is a clinically heterogeneous disease, which necessitates a variety of treatments and leads to different outcomes. Only some CRC patients will benefit from neoadjuvant chemotherapy (NACT).

Objectives

An accurate prediction of response to NACT in CRC patients would greatly facilitate optimal personalized management, which could improve their long-term survival and clinical outcomes.

Methods

In this study, plasma metabolite profiling was performed to identify potential biomarker candidates that can predict response to NACT for CRC. Metabolic profiles of plasma from non-response (n?=?30) and response (n?=?27) patients to NACT were studied using UHPLC–quadruple time-of-flight)/mass spectrometry analyses and statistical analysis methods.

Results

The concentrations of nine metabolites were significantly different when comparing response to NACT. The area under the receiver operating characteristic curve value of the potential biomarkers was up to 0.83 discriminating the non-response and response group to NACT, superior to the clinical parameters (carcinoembryonic antigen and carbohydrate antigen 199).

Conclusion

These results show promise for larger studies that could result in more personalized treatment protocols for CRC patients.

     

Advantages of Amplifluor-like SNP markers over KASP in plant genotyping

Background

KASP (KBioscience Competitive Allele Specific PCR) and Amplifluor (Amplification with fluorescence) SNP markers are two prominent technologies based upon a shared identical Allele-specific PCR platform.

Methods

Amplifluor-like SNP and KASP analysis was carried out using published and own design of Universal probes (UPs) and Gene-specific primers (GSPs).

Results

Advantages of the Amplifluor-like system over KASP include the significantly lower costs and much greater flexibility in the adjustment and development of ‘self-designed’ dual fluorescently-labelled UPs and regular GSPs. The presented results include optimisation of ‘tail’ length in UPs and GSPs, protocol adjustment, and the use of various fluorophores in different qPCR instruments. The compatibility of the KASP Master-mix in both original and Amplifluor-like systems has been demonstrated in the presented results, proving their similar principles. Results of SNP scoring with rare alleles in addition to more frequently occurring alleles are shown.

Conclusions

The Amplifluor-like system produces SNP genotyping results with a level of sensitivity and accuracy comparable to KASP but at a significantly cheaper cost and with much greater flexibility for UPs with self-designed GSPs.

     

Prospects for developing an accurate diagnostic biomarker panel for low prevalence cancers

Background

Early detection screening of asymptomatic populations for low prevalence cancers requires a highly specific test in order to limit the cost and anxiety produced by falsely positive identifications. Most solid cancers are a heterogeneous collection of diseases as they develop from various combinations of genetic lesions and epigenetic modifications. Therefore, it is unlikely that a single test will discriminate all cases of any particular cancer type. We propose a novel, intuitive biomarker panel design that accommodates disease heterogeneity by allowing for diverse biomarker selection that increases diagnostic accuracy.

Methods

Using characteristics of nine pancreatic ductal adenocarcinoma (PDAC) biomarkers measured in human sera, we modeled the behavior of biomarker panels consisting of a sum of indicator variables representing a subset of biomarkers within a larger biomarker data set. We then chose a cutoff for the sum to force specificity to be high and delineated the number of biomarkers required for adequate sensitivity of PDAC in our panel design.

Results

The model shows that a panel consisting of 40 non-correlated biomarkers characterized individually by 32% sensitivity at 95% specificity would require any 7 biomarkers to be above their respective thresholds and would result in a panel specificity and sensitivity of 99% each.

Conclusions

A highly accurate blood-based diagnostic panel can be developed from a reasonable number of individual serum biomarkers that are relatively weak classifiers when used singly. A panel constructed as described is advantageous in that a high level of specificity can be forced, accomplishing a prerequisite for screening asymptomatic populations for low-prevalence cancers.

     

Serum metabolomic study for detecting biomarkers of non-traumatic osteonecrosis of the femoral head

Introduction

Non-traumatic osteonecrosis of the femoral head (NTONFH) is a progressive disease, always leading to hip dysfunction if no early intervention was applied. The difficulty for early diagnosis of NTONFH is due to the slight symptoms at early stages as well as the high cost for screening patients by using magnetic resonance imaging.

Objective

The aim was to detect biomarkers of early-stage NTONFH, which was beneficial to the exploration of a cost-effective approach for the early diagnose of the disease.

Methods

Metabolomic approaches were employed in this study to detect biomarkers of early-stage NTONFH (22 patients, 23 controls), based on the platform of ultra-performance liquid chromatography tandem quadrupole time-of-flight mass spectrometry (UPLC-QTOF-MS) and the uses of multivariate statistic analysis, putative metabolite identification, metabolic pathway analysis and biomarker analysis.

Results

In total, 33 serum metabolites were found altered between NTONFH group and control group. In addition, glycerophospholipid metabolism and pyruvate metabolism were highly associated with the disease.

Conclusion

The combination of LysoPC (18:3), l-tyrosine and l-leucine proved to have a high diagnostic value for early-stage NTONFH. Our findings may contribute to the protocol for early diagnosis of NTONFH and further elucidate the underlying mechanisms of the disease.

     

Group-wise ANOVA simultaneous component analysis for designed <Emphasis Type="Italic">omics</Emphasis> experiments

Introduction

Modern omics experiments pertain not only to the measurement of many variables but also follow complex experimental designs where many factors are manipulated at the same time. This data can be conveniently analyzed using multivariate tools like ANOVA-simultaneous component analysis (ASCA) which allows interpretation of the variation induced by the different factors in a principal component analysis fashion. However, while in general only a subset of the measured variables may be related to the problem studied, all variables contribute to the final model and this may hamper interpretation.

Objectives

We introduce here a sparse implementation of ASCA termed group-wise ANOVA-simultaneous component analysis (GASCA) with the aim of obtaining models that are easier to interpret.

Methods

GASCA is based on the concept of group-wise sparsity introduced in group-wise principal components analysis where structure to impose sparsity is defined in terms of groups of correlated variables found in the correlation matrices calculated from the effect matrices.

Results

The GASCA model, containing only selected subsets of the original variables, is easier to interpret and describes relevant biological processes.

Conclusions

GASCA is applicable to any kind of omics data obtained through designed experiments such as, but not limited to, metabolomic, proteomic and gene expression data.

     

Metabolomic profiling in follicular fluid of patients with infertility-related deep endometriosis

Introduction

Endometriosis is an estrogen-dependent gynecological disease that causes infertility, and potential metabolomic biomarkers related to ovarian endometriosis and poor outcomes after assisted reproductive treatments are still lacking.

Objectives

The present study analyzed the metabolomic profiling of follicular fluid samples from 40 patients undergoing in vitro fertilization.

Methods

The follicular fluid samples were classified as controls (n = 22) and endometriosis patients (n = 18). The samples were submitted to Bligh and Dyer protocol followed by metabolomics analysis by ultra-performance liquid chromatography mass spectrometry. Clinical data was assessed by Students’ T-test and metabolomics data was analyzed by multivariate statistics by MetaboAnalyst 3.0 to obtain intrinsic characteristics that allowed for groups discrimination. The Receiver Operating Characteristic curve was carried out for the proposed biomarkers, aiming to determine their specificity and sensitivity, as a set and individually.

Results

From the metabolomic analysis, 20 ion masses were selected as potential biomarkers from principal component analysis, which showed that all biomarkers were more abundant in the endometriosis group when compared to controls. Tentative attribution was performed by lipid maps database, demonstrating that these potential biomarkers correspond to fatty acids, carnitines, monoacylglycerols, lysophosphatidic acids, lysophosphatidylglycerols, diacylglycerols, lysophosphatidylcholines, phosphatidylserine, lysophosphatidylinositols and Phosphatidic Acid.

Conclusion

The use of mass spectrometry-based metabolomics allowed for the identification of effective biomarkers for ovarian endometriosis, which may contribute for a better comprehension of the disease and how it affects the ovary, as well as assisting in the development of accessory tools for endometriosis diagnosis and infertility management.

     

<Emphasis Type="Italic">massPix</Emphasis>: an R package for annotation and interpretation of mass spectrometry imaging data for lipidomics

Introduction

Mass spectrometry imaging (MSI) experiments result in complex multi-dimensional datasets, which require specialist data analysis tools.

Objectives

We have developed massPix—an R package for analysing and interpreting data from MSI of lipids in tissue.

Methods

massPix produces single ion images, performs multivariate statistics and provides putative lipid annotations based on accurate mass matching against generated lipid libraries.

Results

Classification of tissue regions with high spectral similarly can be carried out by principal components analysis (PCA) or k-means clustering.

Conclusion

massPix is an open-source tool for the analysis and statistical interpretation of MSI data, and is particularly useful for lipidomics applications.

     

Predicting ovarian cancer recurrence by plasma metabolic profiles before and after surgery

Background

Previous metabolomic studies have revealed that plasma metabolic signatures may predict epithelial ovarian cancer (EOC) recurrence. However, few studies have performed metabolic profiling of pre- and post-operative specimens to investigate EOC prognostic biomarkers.

Objective

The aims of our study were to compare the predictive performance of pre- and post-operative specimens and to create a better model for recurrence by combining biomarkers from both metabolic signatures.

Methods

Thirty-five paired plasma samples were collected from 35 EOC patients before and after surgery. The patients were followed-up until December, 2016 to obtain recurrence information. Metabolomics using rapid resolution liquid chromatography–mass spectrometry was performed to identify metabolic signatures related to EOC recurrence. The support vector machine model was employed to predict EOC recurrence using identified biomarkers.

Results

Global metabolomic profiles distinguished recurrent from non-recurrent EOC using both pre- and post-operative plasma. Ten common significant biomarkers, hydroxyphenyllactic acid, uric acid, creatinine, lysine, 3-(3,5-diiodo-4-hydroxyphenyl) lactate, phosphohydroxypyruvic acid, carnitine, coproporphyrinogen, l-beta-aspartyl-l-glutamic acid and 24,25-hydroxyvitamin D3, were identified as predictive biomarkers for EOC recurrence. The area under the receiver operating characteristic (AUC) values in pre- and post-operative plasma were 0.815 and 0.909, respectively; the AUC value after combining the two sets reached 0.964.

Conclusion

Plasma metabolomic analysis could be used to predict EOC recurrence. While post-operative biomarkers have a predictive advantage over pre-operative biomarkers, combining pre- and post-operative biomarkers showed the best predictive performance and has great potential for predicting recurrent EOC.

     

A systematic review of metabolomics biomarkers for Bisphenol A exposure

Introduction

Bisphenol A (BPA), 2,2-bis(4-hydroxyphenyl) propane, a common industrial chemical which has extremely huge production worldwide, is ubiquitous in the environment. Human have high risk of exposing to BPA and the health problems caused by BPA exposure have aroused public concern. However, the biomarkers for BPA exposure are lacking. As a rapidly developing subject, metabolomics has accumulated a large amount of valuable data in various fields. The secondary application of published metabolomics data could be a very promising field for generating novel biomarkers whilst further understanding of toxicity mechanisms.

Objectives

To summarize the published literature on the use of metabolomics as a tool to study BPA exposure and provide a systematic perspectives of current research on biomarkers screening of BPA exposure.

Methods

We conducted a systematic search of MEDLINE (PubMed) up to the end of June 25, 2017 with the key term combinations of ‘metabolomics’, ‘metabonomics’, ‘mass spectrometry’, ‘nuclear magnetic spectroscopy’, ‘metabolic profiling’ and ‘amino acid profile’ combined with ‘BPA exposure’. Additional articles were identified through searching the reference lists from included studies.

Results

This systematic review included 15 articles. Intermediates of glycolysis, Krebs cycle, β oxidation of long chain fatty acids, pentose phosphate pathway, nucleoside metabolism, branched chain amino acid metabolism, aromatic amino acids metabolism, sulfur-containing amino acids metabolism were significantly changed after BPA exposure, suggesting BPA had a highly complex toxic effects on organism which was consistent with existing studies. The biomarkers most consistently associated with BPA exposure were lactate and choline.

Conclusion

Existing metabolomics studies of BPA exposure present heterogeneous findings regarding metabolite profile characteristics. We need more evidence from target metabolomics and epidemiological studies to further examine the reliability of these biomarkers which link to low, environmentally relevant, exposure of BPA in human body.