Improving counterfactual reasoning with kernelised dynamic mixing models.

Simulation-based approaches to disease progression allow us to make counterfactual predictions about the effects of an untried series of treatment choices. However, building accurate simulators of disease progression is challenging, limiting the utility of these approaches for real world treatment planning. In this work, we present a novel simulation-based reinforcement learning approach that mixes between models and kernel-based approaches to make its forward predictions. On two real world tasks, managing sepsis and treating HIV, we demonstrate that our approach both learns state-of-the-art treatment policies and can make accurate forward predictions about the effects of treatments on unseen patients.

Gene expression analysis of biopsy samples reveals critical limitations of transcriptome-based molecular classifications of hepatocellular carcinoma.

Molecular classification of hepatocellular carcinomas (HCC) could guide patient stratification for personalized therapies targeting subclass-specific cancer 'driver pathways'. Currently, there are several transcriptome-based molecular classifications of HCC with different subclass numbers, ranging from two to six. They were established using resected tumours that introduce a selection bias towards patients without liver cirrhosis and with early stage HCCs. We generated and analyzed gene expression data from paired HCC and non-cancerous liver tissue biopsies from 60 patients as well as five normal liver samples. Unbiased consensus clustering of HCC biopsy profiles identified 3 robust classes. Class membership correlated with survival, tumour size and with Edmondson and Barcelona Clinical Liver Cancer (BCLC) stage. When focusing only on the gene expression of the HCC biopsies, we could validate previously reported classifications of HCC based on expression patterns of signature genes. However, the subclass-specific gene expression patterns were no longer preserved when the fold-change relative to the normal tissue was used. The majority of genes believed to be subclass-specific turned out to be cancer-related genes differentially regulated in all HCC patients, with quantitative rather than qualitative differences between the molecular subclasses. With the exception of a subset of samples with a definitive ß-catenin gene signature, biological pathway analysis could not identify class-specific pathways reflecting the activation of distinct oncogenic programs. In conclusion, we have found that gene expression profiling of HCC biopsies has limited potential to direct therapies that target specific driver pathways, but can identify subgroups of patients with different prognosis.

Quantitative proteomics and phosphoproteomics on serial tumor biopsies from a sorafenib-treated HCC patient.

Compensatory signaling pathways in tumors confer resistance to targeted therapy, but the pathways and their mechanisms of activation remain largely unknown. We describe a procedure for quantitative proteomics and phosphoproteomics on snap-frozen biopsies of hepatocellular carcinoma (HCC) and matched nontumor liver tissue. We applied this procedure to monitor signaling pathways in serial biopsies taken from an HCC patient before and during treatment with the multikinase inhibitor sorafenib. At diagnosis, the patient had an advanced HCC. At the time of the second biopsy, abdominal imaging revealed progressive disease despite sorafenib treatment. Sorafenib was confirmed to inhibit MAPK signaling in the tumor, as measured by reduced ribosomal protein S6 kinase phosphorylation. Hierarchical clustering and enrichment analysis revealed pathways broadly implicated in tumor progression and resistance, such as epithelial-to-mesenchymal transition and cell adhesion pathways. Thus, we describe a protocol for quantitative analysis of oncogenic pathways in HCC biopsies and obtained first insights into the effect of sorafenib in vivo. This protocol will allow elucidation of mechanisms of resistance and enable precision medicine.

Malaria haplotype frequency estimation.

We present a Bayesian approach for estimating the relative frequencies of multi-single nucleotide polymorphism (SNP) haplotypes in populations of the malaria parasite Plasmodium falciparum by using microarray SNP data from human blood samples. Each sample comes from a malaria patient and contains one or several parasite clones that may genetically differ. Samples containing multiple parasite clones with different genetic markers pose a special challenge. The situation is comparable with a polyploid organism. The data from each blood sample indicates whether the parasites in the blood carry a mutant or a wildtype allele at various selected genomic positions. If both mutant and wildtype alleles are detected at a given position in a multiply infected sample, the data indicates the presence of both alleles, but the ratio is unknown. Thus, the data only partially reveals which specific combinations of genetic markers (i.e. haplotypes across the examined SNPs) occur in distinct parasite clones. In addition, SNP data may contain errors at non-negligible rates. We use a multinomial mixture model with partially missing observations to represent this data and a Markov chain Monte Carlo method to estimate the haplotype frequencies in a population. Our approach addresses both challenges, multiple infections and data errors.

Probabilistic inference of viral quasispecies subject to recombination.

RNA viruses exist in their hosts as populations of different but related strains. The virus population, often called quasispecies, is shaped by a combination of genetic change and natural selection. Genetic change is due to both point mutations and recombination events. We present a jumping hidden Markov model that describes the generation of viral quasispecies and a method to infer its parameters from next-generation sequencing data. The model introduces position-specific probability tables over the sequence alphabet to explain the diversity that can be found in the population at each site. Recombination events are indicated by a change of state, allowing a single observed read to originate from multiple sequences. We present a specific implementation of the expectation maximization (EM) algorithm to find maximum a posteriori estimates of the model parameters and a method to estimate the distribution of viral strains in the quasispecies. The model is validated on simulated data, showing the advantage of explicitly taking the recombination process into account, and applied to reads obtained from a clinical HIV sample.

A seven-marker signature and clinical outcome in malignant melanoma: a large-scale tissue-microarray study with two independent patient cohorts.

BACKGROUND: Current staging methods such as tumor thickness, ulceration and invasion of the sentinel node are known to be prognostic parameters in patients with malignant melanoma (MM). However, predictive molecular marker profiles for risk stratification and therapy optimization are not yet available for routine clinical assessment. METHODS AND FINDINGS: Using tissue microarrays, we retrospectively analyzed samples from 364 patients with primary MM. We investigated a panel of 70 immunohistochemical (IHC) antibodies for cell cycle, apoptosis, DNA mismatch repair, differentiation, proliferation, cell adhesion, signaling and metabolism. A marker selection procedure based on univariate Cox regression and multiple testing correction was employed to correlate the IHC expression data with the clinical follow-up (overall and recurrence-free survival). The model was thoroughly evaluated with two different cross validation experiments, a permutation test and a multivariate Cox regression analysis. In addition, the predictive power of the identified marker signature was validated on a second independent external test cohort (n=225). A signature of seven biomarkers (Bax, Bcl-X, PTEN, COX-2, loss of ß-Catenin, loss of MTAP, and presence of CD20 positive B-lymphocytes) was found to be an independent negative predictor for overall and recurrence-free survival in patients with MM. The seven-marker signature could also predict a high risk of disease recurrence in patients with localized primary MM stage pT1-2 (tumor thickness ≤2.00 mm). In particular, three of these markers (MTAP, COX-2, Bcl-X) were shown to offer direct therapeutic implications. CONCLUSIONS: The seven-marker signature might serve as a prognostic tool enabling physicians to selectively triage, at the time of diagnosis, the subset of high recurrence risk stage I-II patients for adjuvant therapy. Selective treatment of those patients that are more likely to develop distant metastatic disease could potentially lower the burden of untreatable metastatic melanoma and revolutionize the therapeutic management of MM.

Interferon-induced gene expression is a stronger predictor of treatment response than IL28B genotype in patients with hepatitis C.

BACKGROUND & AIMS: The host immune response during the chronic phase of hepatitis C virus infection varies among individuals; some patients have a no interferon (IFN) response in the liver, whereas others have full activation of IFN-stimulated genes (ISGs). Preactivation of this endogenous IFN system is associated with nonresponse to pegylated IFN-α (pegIFN-α) and ribavirin. Genome-wide association studies have associated allelic variants near the IL28B (IFNλ3) gene with treatment response. We investigated whether IL28B genotype determines the constitutive expression of ISGs in the liver and compared the abilities of ISG levels and IL28B genotype to predict treatment outcome. METHODS: We genotyped 109 patients with chronic hepatitis C for IL28B allelic variants and quantified the hepatic expression of ISGs and of IL28B. Decision tree ensembles, in the form of a random forest classifier, were used to calculate the relative predictive power of these different variables in a multivariate analysis. RESULTS: The minor IL28B allele was significantly associated with increased expression of ISG. However, stratification of the patients according to treatment response revealed increased ISG expression in nonresponders, irrespective of IL28B genotype. Multivariate analysis of ISG expression, IL28B genotype, and several other factors associated with response to therapy identified ISG expression as the best predictor of treatment response. CONCLUSIONS: IL28B genotype and hepatic expression of ISGs are independent predictors of response to treatment with pegIFN-α and ribavirin in patients with chronic hepatitis C. The most accurate prediction of response was obtained with a 4-gene classifier comprising IFI27, ISG15, RSAD2, and HTATIP2.

Infinite mixture-of-experts model for sparse survival regression with application to breast cancer.

BACKGROUND: We present an infinite mixture-of-experts model to find an unknown number of sub-groups within a given patient cohort based on survival analysis. The effect of patient features on survival is modeled using the Cox's proportionality hazards model which yields a non-standard regression component. The model is able to find key explanatory factors (chosen from main effects and higher-order interactions) for each sub-group by enforcing sparsity on the regression coefficients via the Bayesian Group-Lasso. RESULTS: Simulated examples justify the need of such an elaborate framework for identifying sub-groups along with their key characteristics versus other simpler models. When applied to a breast-cancer dataset consisting of survival times and protein expression levels of patients, it results in identifying two distinct sub-groups with different survival patterns (low-risk and high-risk) along with the respective sets of compound markers. CONCLUSIONS: The unified framework presented here, combining elements of cluster and feature detection for survival analysis, is clearly a powerful tool for analyzing survival patterns within a patient group. The model also demonstrates the feasibility of analyzing complex interactions which can contribute to definition of novel prognostic compound markers.

Detection of urothelial bladder cancer cells in voided urine can be improved by a combination of cytology and standardized microsatellite analysis.

PURPOSE: To evaluate molecular and immunohistochemical markers to develop a molecular grading of urothelial bladder cancer and to test these markers in voided urine samples. EXPERIMENTAL DESIGN: 255 consecutive biopsies from primary bladder cancer patients were evaluated on a tissue microarray. The clinical parameters gender, age, adjacent carcinoma in situ, and multifocality were collected. UroVysion fluorescence in situ hybridization (FISH) was done. Expression of cytokeratin 20, MIB1, and TP53 was analyzed by immunohistochemistry. Fibroblast growth factor receptor 3 (FGFR3) status was studied by SNaPshot mutation detection. Results were correlated with clinical outcome by Cox regression analysis. To assess the predictive power of different predictor subsets to detect high grade and tumor invasion, logistic regression models were learned. Additionally, voided urine samples of 119 patients were investigated. After cytologic examination, urine samples were matched with their biopsies and analyzed for loss of heterozygosity (LOH), FGFR3 mutation, polysomy, and p16 deletion using UroVysion FISH. Receiver operator characteristic curves for various predictor subsets were plotted. RESULTS: In biopsies, high grade and solid growth pattern were independent prognostic factors for overall survival. A model consisting of UroVysion FISH and FGFR3 status (FISH + FGFR3) predicted high grade significantly better compared with a recently proposed molecular grade (MIB1 + FGFR3). In voided urine, the combination of cytology with LOH analysis (CYTO + LOH) reached the highest diagnostic accuracy for the detection of bladder cancer cells and performed better than cytology alone (sensitivity of 88.2% and specificity of 97.1%). CONCLUSIONS: The combination of cytology with LOH analysis could reduce unpleasant cystoscopies for bladder cancer patients.

NovoHMM: a hidden Markov model for de novo peptide sequencing.

De novo sequencing of peptides poses one of the most challenging tasks in data analysis for proteome research. In this paper, a generative hidden Markov model (HMM) of mass spectra for de novo peptide sequencing which constitutes a novel view on how to solve this problem in a Bayesian framework is proposed. Further extensions of the model structure to a graphical model and a factorial HMM to substantially improve the peptide identification results are demonstrated. Inference with the graphical model for de novo peptide sequencing estimates posterior probabilities for amino acids rather than scores for single symbols in the sequence. Our model outperforms state-of-the-art methods for de novo peptide sequencing on a large test set of spectra.

Stability-based validation of clustering solutions.

Data clustering describes a set of frequently employed techniques in exploratory data analysis to extract "natural" group structure in data. Such groupings need to be validated to separate the signal in the data from spurious structure. In this context, finding an appropriate number of clusters is a particularly important model selection question. We introduce a measure of cluster stability to assess the validity of a cluster model. This stability measure quantifies the reproducibility of clustering solutions on a second sample, and it can be interpreted as a classification risk with regard to class labels produced by a clustering algorithm. The preferred number of clusters is determined by minimizing this classification risk as a function of the number of clusters. Convincing results are achieved on simulated as well as gene expression data sets. Comparisons to other methods demonstrate the competitive performance of our method and its suitability as a general validation tool for clustering solutions in real-world problems.

Bayesian class discovery in microarray datasets.

A novel approach to class discovery in gene expression datasets is presented. In the context of clinical diagnosis, the central goal of class discovery algorithms is to simultaneously find putative (sub-)types of diseases and to identify informative subsets of genes with disease-type specific expression profile. Contrary to many other approaches in the literature, the method presented implements a wrapper strategy for feature selection, in the sense that the features are directly selected by optimizing the discriminative power of the used partitioning algorithm. The usual combinatorial problems associated with wrapper approaches are overcome by a Bayesian inference mechanism. On the technical side, we present an efficient optimization algorithm with guaranteed local convergence property. The only free parameter of the optimization method is selected by a resampling-based stability analysis. Experiments with Leukemia and Lymphoma datasets demonstrate that our method is able to correctly infer partitions and corresponding subsets of genes which both are relevant in a biological sense. Moreover, the frequently observed problem of ambiguities caused by different but equally high-scoring partitions is successfully overcome by the model selection method proposed.