Differentiation of multiple types of pancreatico-biliary tumors by molecular analysis of clinical specimens

Efficient cross-validation traversals in feature subset selection

Sparse and robust classification models have the potential for revealing common predictive patterns that not only allow for categorizing objects into classes but also for generating mechanistic hypotheses. Identifying a small and informative subset of features is their main ingredient. However, the exponential search space of feature subsets and the heuristic nature of selection algorithms limit the coverage of these analyses, even for low-dimensional datasets. We present methods for reducing the computational complexity of feature selection criteria allowing for higher efficiency and coverage of screenings. We achieve this by reducing the preparation costs of high-dimensional subsets [Formula: see text] to those of one-dimensional ones [Formula: see text]. Our methods are based on a tight interaction between a parallelizable cross-validation traversal strategy and distance-based classification algorithms and can be used with any product distance or kernel. We evaluate the traversal strategy exemplarily in exhaustive feature subset selection experiments (perfect coverage). Its runtime, fitness landscape, and predictive performance are analyzed on publicly available datasets. Even in low-dimensional settings, we achieve approximately a 15-fold increase in exhaustively generating distance matrices for feature combinations bringing a new level of evaluations into reach.

A perceptually optimised bivariate visualisation scheme for high-dimensional fold-change data

Visualising data as diagrams using visual attributes such as colour, shape, size, and orientation is challenging. In particular, large data sets demand graphical display as an essential step in the analysis. In order to achieve comprehension often different attributes need to be displayed simultaneously. In this work a comprehensible bivariate, perceptually optimised visualisation scheme for high-dimensional data is proposed and evaluated. It can be used to show fold changes together with confidence values within a single diagram. The visualisation scheme consists of two parts: a uniform, symmetric, two-sided colour scale and a patch grid representation. Evaluation of uniformity and symmetry of the two-sided colour scale was performed in comparison to a standard RGB scale by twenty-five observers. Furthermore, the readability of the generated map was validated and compared to a bivariate heat map scheme.

Combined microRNA and mRNA microfluidic TaqMan array cards for the diagnosis of malignancy of multiple types of pancreatico-biliary tumors in fine-needle aspiration material

Pancreatic ductal adenocarcinoma (PDAC) continues to carry the lowest survival rates among all solid tumors. A marked resistance against available therapies, late clinical presentation and insufficient means for early diagnosis contribute to the dismal prognosis. Novel biomarkers are thus required to aid treatment decisions and improve patient outcomes.

We describe here a multi-omics molecular platform that allows for the first time to simultaneously analyze miRNA and mRNA expression patterns from minimal amounts of biopsy material on a single microfluidic TaqMan Array card. Expression profiles were generated from 113 prospectively collected fine needle aspiration biopsies (FNAB) from patients undergoing surgery for suspect masses in the pancreas. Molecular classifiers were constructed using support vector machines, and rigorously evaluated for diagnostic performance using 10×10fold cross validation. The final combined miRNA/mRNA classifier demonstrated a sensitivity of 91.7%, a specificity of 94.5%, and an overall diagnostic accuracy of 93.0% for the differentiation between PDAC and benign pancreatic masses, clearly outperfoming miRNA-only classifiers. The classification algorithm also performed very well in the diagnosis of other types of solid tumors (acinar cell carcinomas, ampullary cancer and distal bile duct carcinomas), but was less suited for the diagnostic analysis of cystic lesions.

We thus demonstrate that simultaneous analysis of miRNA and mRNA biomarkers from FNAB samples using multi-omics TaqMan Array cards is suitable to differentiate suspect solid pancreatic masses with high precision.

A multistep high-content screening approach to identify novel functionally relevant target genes in pancreatic cancer

In order to foster the systematic identification of novel genes with important functional roles in pancreatic cancer, we have devised a multi-stage screening strategy to provide a rational basis for the selection of highly relevant novel candidate genes based on the results of functional high-content analyses. The workflow comprised three consecutive stages: 1) serial gene expression profiling analyses of primary human pancreatic tissues as well as a number of in vivo and in vitro models of tumor-relevant characteristics in order to identify genes with conspicuous expression patterns; 2) use of ‘reverse transfection array’ technology for large-scale parallelized functional analyses of potential candidate genes in cell-based assays; and 3) selection of individual candidate genes for further in-depth examination of their cellular roles. A total of 14 genes, among them 8 from “druggable” gene families, were classified as high priority candidates for individual functional characterization. As an example to demonstrate the validity of the approach, comprehensive functional data on candidate gene ADRBK1/GRK2, which has previously not been implicated in pancreatic cancer, is presented.

[Will molecular diagnostics become established in pancreatic pathology?]

Genetic alterations of solid and cystic tumors of the pancreas have been increasingly more characterized over the last few years. Pancreatic ductal adenocarcinoma (PDAC) carries numerous point mutations and, to a lesser extent, deletions and amplifications of genes that are associated with at least 13 tumor relevant signalling pathways and processes. Besides the four common driver mutations in the KRAS, p53, CDKN2a and SMAD4 genes there are a number of low frequency driver mutations. The classification of PDAC subtypes has benefited from recent analyses of transcriptional profiles that revealed a classical KRAS driven and a KRAS independent quasi-mesenchymal subtype. The analyses of mRNA and miRNA expression profiles of fine needle aspirates serve as a basis for reliable preoperative diagnosis of pancreatic masses.The four most common cystic pancreatic tumors bear tumor-specific genetic alterations, such as GNAS mutations in intraductal papillary mucinous neoplasms, β-catenin mutations in solid pseudopapillary neoplasms and VHL mutations or loss of heterozygosity in serous cystadenoma. Recovery of DNA from aspirates of cyst fluids enables an improved preoperative management of cystic pancreatic tumors by mutational analysis. In addition to the analysis of DNA there are promising approaches in distinguishing benign and premalignant/malignant cystic tumors by evaluating miRNA profiles.In recent years much progress has been made in molecular genetic characterization and preoperative evaluation of pancreatic tumors. Hopefully these results will contribute to prognostic and therapeutic stratification of PDAC and to a reliable preoperative diagnostics of benign cystic pancreatic tumors in the future.