Computational Analysis Identifies Novel Biomarkers for High-Risk Bladder Cancer Patients.

In the case of bladder cancer, carcinoma in situ (CIS) is known to have poor diagnosis. However, there are not enough studies that examine the biomarkers relevant to CIS development. Omics experiments generate data with tens of thousands of descriptive variables, e.g., gene expression levels. Often, many of these descriptive variables are identified as somehow relevant, resulting in hundreds or thousands of relevant variables for building models or for further data analysis. We analyze one such dataset describing patients with bladder cancer, mostly non-muscle-invasive (NMIBC), and propose a novel approach to feature selection. This approach returns high-quality features for prediction and yet allows interpretability as well as a certain level of insight into the analyzed data. As a result, we obtain a small set of seven of the most-useful biomarkers for diagnostics. They can also be used to build tests that avoid the costly and time-consuming existing methods. We summarize the current biological knowledge of the chosen biomarkers and contrast it with our findings.

Identification of Candidate Therapeutic Genes for More Precise Treatment of Esophageal Squamous Cell Carcinoma and Adenocarcinoma.

The standard therapy administered to patients with advanced esophageal cancer remains uniform, despite its two main histological subtypes, namely esophageal squamous cell carcinoma (SCC) and esophageal adenocarcinoma (AC), are being increasingly considered to be different. The identification of potential drug target genes between SCC and AC is crucial for more effective treatment of these diseases, given the high toxicity of chemotherapy and resistance to administered medications. Herein we attempted to identify and rank differentially expressed genes (DEGs) in SCC vs. AC using ensemble feature selection methods. RNA-seq data from The Cancer Genome Atlas and the Fudan-Taizhou Institute of Health Sciences (China). Six feature filters algorithms were used to identify DEGs. We built robust predictive models for histological subtypes with the random forest (RF) classification algorithm. Pathway analysis also be performed to investigate the functional role of genes. 294 informative DEGs (87 of them are newly discovered) have been identified. The areas under receiver operator curve (AUC) were higher than 99.5% for all feature selection (FS) methods. Nine genes (i.e., ERBB3, ATP7B, ABCC3, GALNT14, CLDN18, GUCY2C, FGFR4, KCNQ5, and CACNA1B) may play a key role in the development of more directed anticancer therapy for SCC and AC patients. The first four of them are drug targets for chemotherapy and immunotherapy of esophageal cancer and involved in pharmacokinetics and pharmacodynamics pathways. Research identified novel DEGs in SCC and AC, and detected four potential drug targeted genes (ERBB3, ATP7B, ABCC3, and GALNT14) and five drug-related genes.

Osteopontin-A Potential Biomarker for IgA Nephropathy: Machine Learning Application.

Many potential biomarkers in nephrology have been studied, but few are currently used in clinical practice. One is osteopontin (OPN). We compared urinary OPN concentrations in 80 participants: 67 patients with various biopsy-proven glomerulopathies (GNs)-immunoglobulin A nephropathy (IgAN, 29), membranous nephropathy (MN, 20) and lupus nephritis (LN, 18) and 13 with no GN. Follow-up included 48 participants. Machine learning was used to correlate OPN with other factors to classify patients by GN type. The resulting algorithm had an accuracy of 87% in differentiating IgAN from other GNs using urinary OPN levels only. A lesser effect for discriminating MN and LN was observed. However, the lower number of patients and the phenotypic heterogeneity of MN and LN might have affected those results. OPN was significantly higher in IgAN at baseline than in other GNs and therefore might be useful for identifying patients with IgAN. That observation did not apply to either patients with IgAN at follow-up or to patients with other GNs. OPN seems to be a valuable biomarker and should be validated in future studies. Machine learning is a powerful tool that, compared with traditional statistical methods, can be also applied to smaller datasets.

NR3C1 Glucocorticoid Receptor Gene Polymorphisms Are Associated with Membranous and IgA Nephropathies.

Glomerular diseases (GNs) are responsible for approximately 20% of chronic kidney diseases. Glucocorticoid receptor gene (NR3C1) single nucleotide polymorphisms (SNPs) are implicated in differences in predisposition to autoimmunity and steroid sensitivity. The aim of this study was to evaluate the frequency of the NR3C1 SNPs-rs6198, rs41423247 and rs17209237-in 72 IgA nephropathy (IgAN) and 38 membranous nephropathy (MN) patients compared to 175 healthy controls and to correlate the effectiveness of treatment in IgAN and MN groups defined as a reduction of proteinuria <1 g/24 h after 12 months of treatment. Real-time polymerase chain reactions and SNP array-based typing were used. We found significant rs41423247 association with MN (p = 0.026); a significant association of rs17209237 with eGFR reduction after follow-up period in all patients with GNs (p = 0.021) and with the degree of proteinuria after 1 year of therapy in all patients with a glomerulopathy (p = 0.013) and IgAN (p = 0.021); and in the same groups treated with steroids (p = 0.021; p = 0.012). We also observed the association between rs41423247 and IgAN histopathologic findings (p = 0.012). In conclusion, our results indicate that NR3C1 polymorphisms may influence treatment susceptibility and clinical outcome in IgAN and MN.

Prediction of Alternative Drug-Induced Liver Injury Classifications Using Molecular Descriptors, Gene Expression Perturbation, and Toxicology Reports.

Motivation: Drug-induced liver injury (DILI) is one of the primary problems in drug development. Early prediction of DILI, based on the chemical properties of substances and experiments performed on cell lines, would bring a significant reduction in the cost of clinical trials and faster development of drugs. The current study aims to build predictive models of risk of DILI for chemical compounds using multiple sources of information. Methods: Using several supervised machine learning algorithms, we built predictive models for several alternative splits of compounds between DILI and non-DILI classes. To this end, we used chemical properties of the given compounds, their effects on gene expression levels in six human cell lines treated with them, as well as their toxicological profiles. First, we identified the most informative variables in all data sets. Then, these variables were used to build machine learning models. Finally, composite models were built with the Super Learner approach. All modeling was performed using multiple repeats of cross-validation for unbiased and precise estimates of performance. Results: With one exception, gene expression profiles of human cell lines were non-informative and resulted in random models. Toxicological reports were not useful for prediction of DILI. The best results were obtained for models discerning between harmless compounds and those for which any level of DILI was observed (AUC = 0.75). These models were built with Random Forest algorithm that used molecular descriptors.

Robust Data Integration Method for Classification of Biomedical Data.

We present a protocol for integrating two types of biological data - clinical and molecular - for more effective classification of patients with cancer. The proposed approach is a hybrid between early and late data integration strategy. In this hybrid protocol, the set of informative clinical features is extended by the classification results based on molecular data sets. The results are then treated as new synthetic variables. The hybrid protocol was applied to METABRIC breast cancer samples and TCGA urothelial bladder carcinoma samples. Various data types were used for clinical endpoint prediction: clinical data, gene expression, somatic copy number aberrations, RNA-Seq, methylation, and reverse phase protein array. The performance of the hybrid data integration was evaluated with a repeated cross validation procedure and compared with other methods of data integration: early integration and late integration via super learning. The hybrid method gave similar results to those obtained by the best of the tested variants of super learning. What is more, the hybrid method allowed for further sensitivity analysis and recursive feature elimination, which led to compact predictive models for cancer clinical endpoints. For breast cancer, the final model consists of eight clinical variables and two synthetic features obtained from molecular data. For urothelial bladder carcinoma, only two clinical features and one synthetic variable were necessary to build the best predictive model. We have shown that the inclusion of the synthetic variables based on the RNA expression levels and copy number alterations can lead to improved quality of prognostic tests. Thus, it should be considered for inclusion in wider medical practice.

Integration of human cell lines gene expression and chemical properties of drugs for Drug Induced Liver Injury prediction.

MOTIVATION: Drug-induced liver injury (DILI) is one of the primary problems in drug development. Early prediction of DILI can bring a significant reduction in the cost of clinical trials. In this work we examined whether occurrence of DILI can be predicted using gene expression profile in cancer cell lines and chemical properties of drugs. METHODS: We used gene expression profiles from 13 human cell lines, as well as molecular properties of drugs to build Machine Learning models of DILI. To this end, we have used a robust cross-validated protocol based on feature selection and Random Forest algorithm. In this protocol we first identify the most informative variables and then use them to build predictive models. The models are first built using data from single cell lines, and chemical properties. Then they are integrated using Super Learner method with several underlying methods for integration. The entire modelling process is performed using nested cross-validation. RESULTS: We have obtained weakly predictive ML models when using either molecular descriptors, or some individual cell lines (AUC ∈(0.55-0.61)). Models obtained with the Super Learner approach have a significantly improved accuracy (AUC=0.73), which allows to divide substances in two categories: low-risk and high-risk.

Sensitivity analysis based on the random forest machine learning algorithm identifies candidate genes for regulation of innate and adaptive immune response of chicken.

Two categories of immune responses-innate and adaptive immunity-have both polygenic backgrounds and a significant environmental component. The goal of the reported study was to define candidate genes and mutations for the immune traits of interest in chickens using machine learning-based sensitivity analysis for single-nucleotide polymorphisms (SNPs) located in candidate genes defined in quantitative trait loci regions. Here the adaptive immunity is represented by the specific antibody response toward keyhole limpet hemocyanin (KLH), whereas the innate immunity was represented by natural antibodies toward lipopolysaccharide (LPS) and lipoteichoic acid (LTA). The analysis consisted of 3 basic steps: an identification of candidate SNPs via feature selection, an optimisation of the feature set using recursive feature elimination, and finally a gene-level sensitivity analysis for final selection of models. The predictive model based on 5 genes (MAPK8IP3 CRLF3, UNC13D, ILR9, and PRCKB) explains 14.9% of variance for KLH adaptive response. The models obtained for LTA and LPS use more genes and have lower predictive power, explaining respectively 7.8 and 4.5% of total variance. In comparison, the linear models built on genes identified by a standard statistical analysis explain 1.5, 0.5, and 0.3% of variance for KLH, LTA, and LPS response, respectively. The present study shows that machine learning methods applied to systems with a complex interaction network can discover phenotype-genotype associations with much higher sensitivity than traditional statistical models. It adds contribution to evidence suggesting a role of MAPK8IP3 in the adaptive immune response. It also indicates that CRLF3 is involved in this process as well. Both findings need additional verification.

The need for standardisation in life science research - an approach to excellence and trust.

Today, academic researchers benefit from the changes driven by digital technologies and the enormous growth of knowledge and data, on globalisation, enlargement of the scientific community, and the linkage between different scientific communities and the society. To fully benefit from this development, however, information needs to be shared openly and transparently. Digitalisation plays a major role here because it permeates all areas of business, science and society and is one of the key drivers for innovation and international cooperation. To address the resulting opportunities, the EU promotes the development and use of collaborative ways to produce and share knowledge and data as early as possible in the research process, but also to appropriately secure results with the European strategy for Open Science (OS). It is now widely recognised that making research results more accessible to all societal actors contributes to more effective and efficient science; it also serves as a boost for innovation in the public and private sectors. However  for research data to be findable, accessible, interoperable and reusable the use of standards is essential. At the metadata level, considerable efforts in standardisation have already been made (e.g. Data Management Plan and FAIR Principle etc.), whereas in context with the raw data these fundamental efforts are still fragmented and in some cases completely missing. The CHARME consortium, funded by the European Cooperation in Science and Technology (COST) Agency, has identified needs and gaps in the field of standardisation in the life sciences and also discussed potential hurdles for implementation of standards in current practice. Here, the authors suggest four measures in response to current challenges to ensure a high quality of life science research data and their re-usability for research and innovation.

Parallel Implementation of a Sequential Markov Chain in Monte Carlo Simulations of Physical Systems with Pairwise Interactions.

In molecular simulations performed by Markov Chain Monte Carlo (typically employing the Metropolis criterion), each state of a system is obtained by a small random modification of the previous state. Therefore, the process consists of an immense number of small, quick to calculate steps, which are inherently sequential and hence considered to be very hard to parallelise. Here, we present a novel protocol for efficient calculation of multiple sequential steps in parallel. To this end, we first precompute in parallel energy components of all states achievable in a sequence of steps. Then we select a single path through all achievable states, which is identical with the path obtained with the sequential algorithm. As an example, we carried out simulations of the TIP5P water model with the new protocol and compared results with those obtained using the standard Metropolis Monte Carlo scheme. The implementation on the Titan X (Pascal) graphic processor (GPU) architectures allows for a 30-fold speedup in comparison with a simulation on a single core of a multicore CPU. The protocol is general and not limited to the GPU; it can also be used on multicore CPU when the longest possible length of the single simulation is required.

Integration of multiple types of genetic markers for neuroblastoma may contribute to improved prediction of the overall survival.

BACKGROUND: Modern experimental techniques deliver data sets containing profiles of tens of thousands of potential molecular and genetic markers that can be used to improve medical diagnostics. Previous studies performed with three different experimental methods for the same set of neuroblastoma patients create opportunity to examine whether augmenting gene expression profiles with information on copy number variation can lead to improved predictions of patients survival. We propose methodology based on comprehensive cross-validation protocol, that includes feature selection within cross-validation loop and classification using machine learning. We also test dependence of results on the feature selection process using four different feature selection methods. RESULTS: The models utilising features selected based on information entropy are slightly, but significantly, better than those using features obtained with t-test. The synergy between data on genetic variation and gene expression is possible, but not confirmed. A slight, but statistically significant, increase of the predictive power of machine learning models has been observed for models built on combined data sets. It was found while using both out of bag estimate and in cross-validation performed on a single set of variables. However, the improvement was smaller and non-significant when models were built within full cross-validation procedure that included feature selection within cross-validation loop. Good correlation between performance of the models in the internal and external cross-validation was observed, confirming the robustness of the proposed protocol and results. CONCLUSIONS: We have developed a protocol for building predictive machine learning models. The protocol can provide robust estimates of the model performance on unseen data. It is particularly well-suited for small data sets. We have applied this protocol to develop prognostic models for neuroblastoma, using data on copy number variation and gene expression. We have shown that combining these two sources of information may increase the quality of the models. Nevertheless, the increase is small and larger samples are required to reduce noise and bias arising due to overfitting. REVIEWERS: This article was reviewed by Lan Hu, Tim Beissbarth and Dimitar Vassilev.

DiSCaMB: a software library for aspherical atom model X-ray scattering factor calculations with CPUs and GPUs.

It has been recently established that the accuracy of structural parameters from X-ray refinement of crystal structures can be improved by using a bank of aspherical pseudoatoms instead of the classical spherical model of atomic form factors. This comes, however, at the cost of increased complexity of the underlying calculations. In order to facilitate the adoption of this more advanced electron density model by the broader community of crystallographers, a new software implementation called DiSCaMB, 'densities in structural chemistry and molecular biology', has been developed. It addresses the challenge of providing for high performance on modern computing architectures. With parallelization options for both multi-core processors and graphics processing units (using CUDA), the library features calculation of X-ray scattering factors and their derivatives with respect to structural parameters, gives access to intermediate steps of the scattering factor calculations (thus allowing for experimentation with modifications of the underlying electron density model), and provides tools for basic structural crystallographic operations. Permissively (MIT) licensed, DiSCaMB is an open-source C++ library that can be embedded in both academic and commercial tools for X-ray structure refinement.

Amino acid properties conserved in molecular evolution.

That amino acid properties are responsible for the way protein molecules evolve is natural and is also reasonably well supported both by the structure of the genetic code and, to a large extent, by the experimental measures of the amino acid similarity. Nevertheless, there remains a significant gap between observed similarity matrices and their reconstructions from amino acid properties. Therefore, we introduce a simple theoretical model of amino acid similarity matrices, which allows splitting the matrix into two parts - one that depends only on mutabilities of amino acids and another that depends on pairwise similarities between them. Then the new synthetic amino acid properties are derived from the pairwise similarities and used to reconstruct similarity matrices covering a wide range of information entropies. Our model allows us to explain up to 94% of the variability in the BLOSUM family of the amino acids similarity matrices in terms of amino acid properties. The new properties derived from amino acid similarity matrices correlate highly with properties known to be important for molecular evolution such as hydrophobicity, size, shape and charge of amino acids. This result closes the gap in our understanding of the influence of amino acids on evolution at the molecular level. The methods were applied to the single family of similarity matrices used often in general sequence homology searches, but it is general and can be used also for more specific matrices. The new synthetic properties can be used in analyzes of protein sequences in various biological applications.

Active enhancer positions can be accurately predicted from chromatin marks and collective sequence motif data.

BACKGROUND: Transcriptional regulation in multi-cellular organisms is a complex process involving multiple modular regulatory elements for each gene. Building whole-genome models of transcriptional networks requires mapping all relevant enhancers and then linking them to target genes. Previous methods of enhancer identification based either on sequence information or on epigenetic marks have different limitations stemming from incompleteness of each of these datasets taken separately. RESULTS: In this work we present a new approach for discovery of regulatory elements based on the combination of sequence motifs and epigenetic marks measured with ChIP-Seq. Our method uses supervised learning approaches to train a model describing the dependence of enhancer activity on sequence features and histone marks. Our results indicate that using combination of features provides superior results to previous approaches based on either one of the datasets. While histone modifications remain the dominant feature for accurate predictions, the models based on sequence motifs have advantages in their general applicability to different tissues. Additionally, we assess the relevance of different sequence motifs in prediction accuracy showing that even tissue-specific enhancer activity depends on multiple motifs. CONCLUSIONS: Based on our results, we conclude that it is worthwhile to include sequence motif data into computational approaches to active enhancer prediction and also that classifiers trained on a specific set of enhancers can generalize with significant accuracy beyond the training set.

A Rough Set-Based Model of HIV-1 Reverse Transcriptase Resistome.

Reverse transcriptase (RT) is a viral enzyme crucial for HIV-1 replication. Currently, 12 drugs are targeted against the RT. The low fidelity of the RT-mediated transcription leads to the quick accumulation of drug-resistance mutations. The sequence-resistance relationship remains only partially understood. Using publicly available data collected from over 15 years of HIV proteome research, we have created a general and predictive rule-based model of HIV-1 resistance to eight RT inhibitors. Our rough set-based model considers changes in the physicochemical properties of a mutated sequence as compared to the wild-type strain. Thanks to the application of the Monte Carlo feature selection method, the model takes into account only the properties that significantly contribute to the resistance phenomenon. The obtained results show that drug-resistance is determined in more complex way than believed. We confirmed the importance of many resistance-associated sites, found some sites to be less relevant than formerly postulated and-more importantly-identified several previously neglected sites as potentially relevant. By mapping some of the newly discovered sites on the 3D structure of the RT, we were able to suggest possible molecular-mechanisms of drug-resistance. Importantly, our model has the ability to generalize predictions to the previously unseen cases. The study is an example of how computational biology methods can increase our understanding of the HIV-1 resistome.

Hydration free energy of a Model Lennard-Jones solute particle: microscopic Monte Carlo simulation studies, and interpretation based on mesoscopic models.

In this study, the hydration of a model Lennard-Jones solute particle and the analytical approximations of the free energy of hydration as functions of solute microscopic parameters are analyzed. The control parameters of the solute particle are the charge, the Lennard-Jones diameter, and also the potential well depth. The obtained multivariate free energy functions of hydration were parametrized based on Metropolis Monte Carlo simulations in the extended NpT ensemble, and interpreted based on mesoscopic solvation models proposed by Gallicchio and Levy [J. Comput. Chem. 25, 479 (2004)], and Wagoner and Baker [Proc. Natl. Acad. Sci. U.S.A. 103, 8331 (2006)]. Regarding the charge and the solute diameter, the dependence of the free energy on these parameters is in qualitative agreement with former studies. The role of the third parameter, the potential well depth not previously considered, appeared to be significant for sufficiently precise bivariate solvation free energy fits. The free energy fits for cations and neutral solute particles were merged, resulting in a compact manifold of the free energy of solvation. The free energy of hydration for anions forms two separate manifolds, which most likely results from an abrupt change of the coordination number when changing the size of the anion particle.

Efficacy of 2-halogen substituted D-glucose analogs in blocking glycolysis and killing "hypoxic tumor cells".

PURPOSE: Since 2-deoxy-D-glucose (2-DG) is currently in phase I clinical trials to selectively target slow-growing hypoxic tumor cells, 2-halogenated D-glucose analogs were synthesized for improved activity. Given the fact that 2-DG competes with D-glucose for binding to hexokinase, in silico modeling of molecular interactions between hexokinase I and these new analogs was used to determine whether binding energies correlate with biological effects, i.e. inhibition of glycolysis and subsequent toxicity in hypoxic tumor cells. METHODS AND RESULTS: Using a QSAR-like approach along with a flexible docking strategy, it was determined that the binding affinities of the analogs to hexokinase I decrease as a function of increasing halogen size as follows: 2-fluoro-2-deoxy-D-glucose (2-FG) > 2-chloro-2-deoxy-D-glucose (2-CG) > 2-bromo-2-deoxy-D-glucose (2-BG). Furthermore, D-glucose was found to have the highest affinity followed by 2-FG and 2-DG, respectively. Similarly, flow cytometry and trypan blue exclusion assays showed that the efficacy of the halogenated analogs in preferentially inhibiting growth and killing hypoxic vs. aerobic cells increases as a function of their relative binding affinities. These results correlate with the inhibition of glycolysis as measured by lactate inhibition, i.e. ID50 1 mM for 2-FG, 6 mM for 2-CG and > 6 mM for 2-BG. Moreover, 2-FG was found to be more potent than 2-DG for both glycolytic inhibition and cytotoxicity. CONCLUSIONS: Overall, our in vitro results suggest that 2-FG is more potent than 2-DG in killing hypoxic tumor cells, and therefore may be more clinically effective when combined with standard chemotherapeutic protocols.

Anti-HIV-1 activity of 3-deaza-adenosine analogs. Inhibition of S-adenosylhomocysteine hydrolase and nucleotide congeners.

Eight adenosine analogs, 3-deaza-adenosine (DZA), 3-deaza-(+/-)aristeromycin (DZAri), 2',3'-dideoxy-adenosine (ddAdo), 2',3'-dideoxy-3-deaza-adenosine (ddDZA), 2',3'-dideoxy-3-deaza-(+/-)aristeromycin (ddDZAri), 3-deaza-5'-(+/-)noraristeromycin (DZNAri), 3-deaza-neplanocin A (DZNep), and neplanocin A (NepA), were tested as inhibitors of human placenta S-adenosylhomocysteine (AdoHcy) hydrolase. The order of potency for the inhibition of human placental AdoHcy hydrolase was: DZNep approximately NepA >> DZAri approximately DZNAri > DZA >> ddAdo approximately ddDZA approximately ddDZAri. These same analogs were examined for their anti-HIV-1 activities measured by the reduction in p24 antigen produced by 3'-azido-3'-deoxythymidine (AZT)-sensitive HIV-1 isolates, A012 and A018, in phytohemagglutinin-stimulated peripheral blood mononuclear (PBMCs) cells. Interestingly, DZNAri and the 2',3'-dideoxy 3-deaza-nucleosides (ddAdo, ddDZAri, and ddDZA) were only marginal inhibitors of p24 antigen production in HIV-1 infected PBMC. DZNAri is unique because it is the only DZA analog with a deleted methylene group that precludes anabolic phosphorylation. In contrast, the other analogs were potent inhibitors of p24 antigen production by both HIV-1 isolates. Thus it was postulated that these nucleoside analogs could exert their antiviral effect via a combination of anabolically generated nucleotides (with the exception of DZNAri), which could inhibit reverse transcriptase or other viral enzymes, and the inhibition of viral or cellular methylation reactions. Additionally, QSAR-like models based on the molecular mechanics (MM) were developed to predict the order of potency of eight adenosine analogs for the inhibition of human AdoHcy hydrolase. In view of the potent antiviral activities of the DZA analogs, this approach provides a promising tool for designing and screening of more potent AdoHcy hydrolase inhibitors and antiviral agents.