A stable iterative method for refining discriminative gene clusters

Background

Microarray technology is often used to identify the genes that are differentially expressed between two biological conditions. On the other hand, since microarray datasets contain a small number of samples and a large number of genes, it is usually desirable to identify small gene subsets with distinct pattern between sample classes. Such gene subsets are highly discriminative in phenotype classification because of their tightly coupling features. Unfortunately, such identified classifiers usually tend to have poor generalization properties on the test samples due to overfitting problem.

Results

We propose a novel approach combining both supervised learning with unsupervised learning techniques to generate increasingly discriminative gene clusters in an iterative manner. Our experiments on both simulated and real datasets show that our method can produce a series of robust gene clusters with good classification performance compared with existing approaches.

Conclusion

This backward approach for refining a series of highly discriminative gene clusters for classification purpose proves to be very consistent and stable when applied to various types of training samples.

     

Metabolites predict cardiovascular disease events in persons living with HIV: a pilot case–control study

Introduction

Persons living with HIV (PLWH) are at higher risk for cardiovascular disease (CVD) events than uninfected persons. Current risk-stratification methods to define PLWH at highest risk for CVD events are lacking.

Methods

Using tandem flow injection mass spectrometry, we quantified plasma levels of 60 metabolites in 24 matched pairs of PLWH [1:1 with and without known coronary artery disease (CAD)]. Metabolite levels were reduced to interpretable factors using principal components analysis.

Results

Factors derived from short-chain dicarboxylacylcarnitines (SCDA) (p?=?0.08) and glutamine/valine (p?=?0.003) were elevated in CAD cases compared to controls.

Conclusion

SCDAs and glutamine/valine may be valuable markers of cardiovascular risk among persons living with HIV in the future, pending validation in larger cohorts.

     

Gastric cancers of Western European and African patients show different patterns of genomic instability

Background

Infection with H. pylori is important in the etiology of gastric cancer. Gastric cancer is infrequent in Africa, despite high frequencies of H. pylori infection, referred to as the African enigma. Variation in environmental and host factors influencing gastric cancer risk between different populations have been reported but little is known about the biological differences between gastric cancers from different geographic locations. We aim to study genomic instability patterns of gastric cancers obtained from patients from United Kingdom (UK) and South Africa (SA), in an attempt to support the African enigma hypothesis at the biological level.

Methods

DNA was isolated from 67 gastric adenocarcinomas, 33 UK patients, 9 Caucasian SA patients and 25 native SA patients. Microsatellite instability and chromosomal instability were analyzed by PCR and microarray comparative genomic hybridization, respectively. Data was analyzed by supervised univariate and multivariate analyses as well as unsupervised hierarchical cluster analysis.

Results

Tumors from Caucasian and native SA patients showed significantly more microsatellite instable tumors (p < 0.05). For the microsatellite stable tumors, geographical origin of the patients correlated with cluster membership, derived from unsupervised hierarchical cluster analysis (p = 0.001). Several chromosomal alterations showed significantly different frequencies in tumors from UK patients and native SA patients, but not between UK and Caucasian SA patients and between native and Caucasian SA patients.

Conclusions

Gastric cancers from SA and UK patients show differences in genetic instability patterns, indicating possible different biological mechanisms in patients from different geographical origin. This is of future clinical relevance for stratification of gastric cancer therapy.

     

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.

     

Iridoid and phenylethanoid/phenylpropanoid metabolite profiles of <Emphasis Type="Italic">Scrophularia</Emphasis> and <Emphasis Type="Italic">Verbascum</Emphasis> species used medicinally in North America

Introduction

Botanicals containing iridoid and phenylethanoid/phenylpropanoid glycosides are used worldwide for the treatment of inflammatory musculoskeletal conditions that are primary causes of human years lived with disability, such as arthritis and lower back pain.

Objectives

We report the analysis of candidate anti-inflammatory metabolites of several endemic Scrophularia species and Verbascum thapsus used medicinally by peoples of North America.

Methods

Leaves, stems, and roots were analyzed by ultra-performance liquid chromatography-mass spectrometry (UPLC-MS) and partial least squares-discriminant analysis (PLS-DA) was performed in MetaboAnalyst 3.0 after processing the datasets in Progenesis QI.

Results

Comparison of the datasets revealed significant and differential accumulation of iridoid and phenylethanoid/phenylpropanoid glycosides in the tissues of the endemic Scrophularia species and Verbascum thapsus.

Conclusions

Our investigation identified several species of pharmacological interest as good sources for harpagoside and other important anti-inflammatory metabolites.

     

Our local experience with the surgical treatment of ampullary cancer

Background

The aim of this study is to report the outcome after surgical treatment of 32 patients with ampullary cancers from 1990 to 1999.

Methods

Twenty-one of them underwent pancreaticoduodenectomy and 9 local excision of the ampullary lesion. The remaining 2 patients underwent palliative surgery.

Results

When the final histological diagnosis was compared with the preoperative histological finding on biopsy, accurate diagnosis was preoperatively established in 24 patients. The hospital morbidity was 18.8% as 9 complications occurred in 6 patients. Following local excision of the ampullary cancer, the survival rate at 3 and 5 years was 77.7% and 33.3% respectively. Among the patients that underwent Whipple's procedure, the 3-year survival rate was 76.2% and the 5-year survival rate 62%.

Conclusion

In this series, local resection was a safe option in patients with significant co-morbidity or small ampullary tumors less than 2 cm in size, and was associated with satisfactory long-term survival rates.

     

Normalization and integration of large-scale metabolomics data using support vector regression

Introduction

Untargeted metabolomics studies for biomarker discovery often have hundreds to thousands of human samples. Data acquisition of large-scale samples has to be divided into several batches and may span from months to as long as several years. The signal drift of metabolites during data acquisition (intra- and inter-batch) is unavoidable and is a major confounding factor for large-scale metabolomics studies.

Objectives

We aim to develop a data normalization method to reduce unwanted variations and integrate multiple batches in large-scale metabolomics studies prior to statistical analyses.

Methods

We developed a machine learning algorithm-based method, support vector regression (SVR), for large-scale metabolomics data normalization and integration. An R package named MetNormalizer was developed and provided for data processing using SVR normalization.

Results

After SVR normalization, the portion of metabolite ion peaks with relative standard deviations (RSDs) less than 30 % increased to more than 90 % of the total peaks, which is much better than other common normalization methods. The reduction of unwanted analytical variations helps to improve the performance of multivariate statistical analyses, both unsupervised and supervised, in terms of classification and prediction accuracy so that subtle metabolic changes in epidemiological studies can be detected.

Conclusion

SVR normalization can effectively remove the unwanted intra- and inter-batch variations, and is much better than other common normalization methods.

     

Urinary metabolic profiling of asymptomatic acute intermittent porphyria using a rule-mining-based algorithm

Introduction

Metabolomic profiling combines Nuclear Magnetic Resonance spectroscopy with supervised statistical analysis that might allow to better understanding the mechanisms of a disease.

Objectives

In this study, the urinary metabolic profiling of individuals with porphyrias was performed to predict different types of disease, and to propose new pathophysiological hypotheses.

Methods

Urine ¹H-NMR spectra of 73 patients with asymptomatic acute intermittent porphyria (aAIP) and familial or sporadic porphyria cutanea tarda (f/sPCT) were compared using a supervised rule-mining algorithm. NMR spectrum buckets bins, corresponding to rules, were extracted and a logistic regression was trained.

Results

Our rule-mining algorithm generated results were consistent with those obtained using partial least square discriminant analysis (PLS-DA) and the predictive performance of the model was significant. Buckets that were identified by the algorithm corresponded to metabolites involved in glycolysis and energy-conversion pathways, notably acetate, citrate, and pyruvate, which were found in higher concentrations in the urines of aAIP compared with PCT patients. Metabolic profiling did not discriminate sPCT from fPCT patients.

Conclusion

These results suggest that metabolic reprogramming occurs in aAIP individuals, even in the absence of overt symptoms, and supports the relationship that occur between heme synthesis and mitochondrial energetic metabolism.

     

Discrimination of pancreatic cancer and pancreatitis by LC-MS metabolomics

Introduction

Pancreatic ductal adenocarcinoma (PDAC) is the fifth most common cause of cancer-related death in Europe with a 5-year survival rate of <5%. Chronic pancreatitis (CP) is a risk factor for PDAC development, but in the majority of cases malignancy is discovered too late for curative treatment. There is at present no reliable diagnostic marker for PDAC available.

Objectives

The aim of the study was to identify single blood-based metabolites or a panel of metabolites discriminating PDAC and CP using liquid chromatography-mass spectrometry (LC-MS).

Methods

A discovery cohort comprising PDAC (n?=?44) and CP (n?=?23) samples was analyzed by LC-MS followed by univariate (Student’s t test) and multivariate (orthogonal partial least squares-discriminant analysis (OPLS-DA)) statistics. Discriminative metabolite features were subject to raw data examination and identification to ensure high feature quality. Their discriminatory power was then confirmed in an independent validation cohort including PDAC (n?=?20) and CP (n?=?31) samples.

Results

Glycocholic acid, N-palmitoyl glutamic acid and hexanoylcarnitine were identified as single markers discriminating PDAC and CP by univariate analysis. OPLS-DA resulted in a panel of five metabolites including the aforementioned three metabolites as well as phenylacetylglutamine (PAGN) and chenodeoxyglycocholate.

Conclusion

Using LC-MS-based metabolomics we identified three single metabolites and a five-metabolite panel discriminating PDAC and CP in two independent cohorts. Although further study is needed in larger cohorts, the metabolites identified are potentially of use in PDAC diagnostics.

     

<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.

     

Identification of cancer subtypes from single-cell RNA-seq data using a consensus clustering method

Background

Human cancers are complex ecosystems composed of cells with distinct molecular signatures. Such intratumoral heterogeneity poses a major challenge to cancer diagnosis and treatment. Recent advancements of single-cell techniques such as scRNA-seq have brought unprecedented insights into cellular heterogeneity. Subsequently, a challenging computational problem is to cluster high dimensional noisy datasets with substantially fewer cells than the number of genes.

Methods

In this paper, we introduced a consensus clustering framework conCluster, for cancer subtype identification from single-cell RNA-seq data. Using an ensemble strategy, conCluster fuses multiple basic partitions to consensus clusters.

Results

Applied to real cancer scRNA-seq datasets, conCluster can more accurately detect cancer subtypes than the widely used scRNA-seq clustering methods. Further, we conducted co-expression network analysis for the identified melanoma subtypes.

Conclusions

Our analysis demonstrates that these subtypes exhibit distinct gene co-expression networks and significant gene sets with different functional enrichment.

     

An unsupervised machine learning method for assessing quality of tandem mass spectra

Background

In a single proteomic project, tandem mass spectrometers can produce hundreds of millions of tandem mass spectra. However, majority of tandem mass spectra are of poor quality, it wastes time to search them for peptides. Therefore, the quality assessment (before database search) is very useful in the pipeline of protein identification via tandem mass spectra, especially on the reduction of searching time and the decrease of false identifications. Most existing methods for quality assessment are supervised machine learning methods based on a number of features which describe the quality of tandem mass spectra. These methods need the training datasets with knowing the quality of all spectra, which are usually unavailable for the new datasets.

Results

This study proposes an unsupervised machine learning method for quality assessment of tandem mass spectra without any training dataset. This proposed method estimates the conditional probabilities of spectra being high quality from the quality assessments based on individual features. The probabilities are estimated through a constraint optimization problem. An efficient algorithm is developed to solve the constraint optimization problem and is proved to be convergent. Experimental results on two datasets illustrate that if we search only tandem spectra with the high quality determined by the proposed method, we can save about 56 % and 62% of database searching time while losing only a small amount of high-quality spectra.

Conclusions

Results indicate that the proposed method has a good performance for the quality assessment of tandem mass spectra and the way we estimate the conditional probabilities is effective.

     

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.

     

A novel approach to minimize false discovery rate in genome-wide data analysis

Background

High-throughput technologies, such as DNA microarray, have significantly advanced biological and biomedical research by enabling researchers to carry out genome-wide screens. One critical task in analyzing genome-wide datasets is to control the false discovery rate (FDR) so that the proportion of false positive features among those called significant is restrained. Recently a number of FDR control methods have been proposed and widely practiced, such as the Benjamini-Hochberg approach, the Storey approach and Significant Analysis of Microarrays (SAM).

Methods

This paper presents a straight-forward yet powerful FDR control method termed miFDR, which aims to minimize FDR when calling a fixed number of significant features. We theoretically proved that the strategy used by miFDR is able to find the optimal number of significant features when the desired FDR is fixed.

Results

We compared miFDR with the BH approach, the Storey approach and SAM on both simulated datasets and public DNA microarray datasets. The results demonstrated that miFDR outperforms others by identifying more significant features under the same FDR cut-offs. Literature search showed that many genes called only by miFDR are indeed relevant to the underlying biology of interest.

Conclusions

FDR has been widely applied to analyzing high-throughput datasets allowed for rapid discoveries. Under the same FDR threshold, miFDR is capable to identify more significant features than its competitors at a compatible level of complexity. Therefore, it can potentially generate great impacts on biological and biomedical research.

Availability

If interested, please contact the authors for getting miFDR.

     

Deep learning for DNase I hypersensitive sites identification

Background

The DNase I hypersensitive sites (DHSs) are associated with the cis-regulatory DNA elements. An efficient method of identifying DHSs can enhance the understanding on the accessibility of chromatin. Despite a multitude of resources available on line including experimental datasets and computational tools, the complex language of DHSs remains incompletely understood.

Methods

Here, we address this challenge using an approach based on a state-of-the-art machine learning method. We present a novel convolutional neural network (CNN) which combined Inception like networks with a gating mechanism for the response of multiple patterns and longterm association in DNA sequences to predict multi-scale DHSs in Arabidopsis, rice and Homo sapiens.

Results

Our method obtains 0.961 area under curve (AUC) on Arabidopsis, 0.969 AUC on rice and 0.918 AUC on Homo sapiens.

Conclusions

Our method provides an efficient and accurate way to identify multi-scale DHSs sequences by deep learning.

     

Microarray-based analysis and clinical validation identify ubiquitin-conjugating enzyme E2E1 (<Emphasis Type="Italic">UBE2E1</Emphasis>) as a prognostic factor in acute myeloid leukemia

Background

Previous research suggested that single gene expression might be correlated with acute myeloid leukemia (AML) survival. Therefore, we conducted a systematical analysis for AML prognostic gene expressions.

Methods

We performed a microarray-based analysis for correlations between gene expression and adult AML overall survival (OS) using datasets GSE12417 and GSE8970. Positive findings were validated in an independent cohort of 50 newly diagnosed, non-acute promyelocytic leukemia (APL) AML patients by quantitative RT-PCR and survival analysis.

Results

Microarray-based analysis suggested that expression of eight genes was each associated with 1-year and 3-year AML OS in both GSE12417 and GSE8970 datasets (p?<?0.05). Next, we validated our findings in an independent cohort of AML samples collected in our hospital. We found that ubiquitin-conjugating enzyme E2E1 (UBE2E1) expression was adversely correlated with AML survival (p?=?0.04). Multivariable analysis showed that UBE2E1 ^high patients had a significant shorter OS and shorter progression-free survival after adjusting other known prognostic factors (p?=?0.03). At last, we found that UBE2E1 expression was negatively correlated with patients’ response to induction chemotherapy (p?<?0.05).

Conclusions

In summary, we demonstrated that UBE2E1 expression was a novel prognostic factor in adult, non-APL AML patients.

     

Prognostic significance of microvascular invasion in tumor stage for hepatocellular carcinoma

Background

The presence of microvascular invasion (McVI) in hepatocellular carcinoma (HCC) has been proposed as a cause of recurrence and poor survival, although this has not been officially emphasized in staging systems. Thus, we conducted a retrospective study to investigate the prognostic importance of McVI in tumor staging in patients with HCC who underwent hepatic resection.

Methods

A retrospective analysis was performed of patients who underwent hepatic resection for HCC at our center from 1994 to 2012. Patients with HCC were classified into four groups based on the presence of McVI and extent of gross vascular invasion (VI).

Results

The 5-year overall and recurrence-free survival rates of 676 patients were 63.3 and 42.6%, respectively. There was no difference in tumor recurrence or survival rate between patients with HCC and McVI without gross VI and those with gross VI confined to segmental/sectional branches. Multivariate analysis revealed that the extent of VI based on the presence of McVI and gross VI was independently associated with tumor recurrence and overall survival.

Conclusions

McVI was revealed to be an important risk factor similar to gross VI confined to a segmental/sectional branch in patients with HCC who underwent hepatic resection. This finding should be considered when estimating the stage for prognosis.