publications

OBJECTIVE To develop and validate a novel, machine learning–derived model to predict the risk of heart failure (HF) among patients with type 2 diabetes mellitus (T2DM). RESEARCH DESIGN AND METHODS Using data from 8,756 patients free at baseline of HF, with \textless10% missing data, and enrolled in the Action to Control Cardiovascular Risk in Diabetes (ACCORD) trial, we used random survival forest (RSF) methods, a nonparametric decision tree machine learning approach, to identify predictors of incident HF. The RSF model was externally validated in a cohort of individuals with T2DM using the Antihypertensive and Lipid-Lowering Treatment to Prevent Heart Attack Trial (ALLHAT). RESULTS Over a median follow-up of 4.9 years, 319 patients (3.6%) developed incident HF. The RSF models demonstrated better discrimination than the best performing Cox-based method (C-index 0.77 [95% CI 0.75–0.80] vs. 0.73 [0.70–0.76] respectively) and had acceptable calibration (Hosmer-Lemeshow statistic \chi2 = 9.63, P = 0.29) in the internal validation data set. From the identified predictors, an integer-based risk score for 5-year HF incidence was created: the WATCH-DM (Weight [BMI], Age, hyperTension, Creatinine, HDL-C, Diabetes control [fasting plasma glucose], QRS Duration, MI, and CABG) risk score. Each 1-unit increment in the risk score was associated with a 24% higher relative risk of HF within 5 years. The cumulative 5-year incidence of HF increased in a graded fashion from 1.1% in quintile 1 (WATCH-DM score ≤7) to 17.4% in quintile 5 (WATCH-DM score ≥14). In the external validation cohort, the RSF-based risk prediction model and the WATCH-DM risk score performed well with good discrimination (C-index = 0.74 and 0.70, respectively), acceptable calibration (P ≥0.20 for both), and broad risk stratification (5-year HF risk range from 2.5 to 18.7% across quintiles 1–5). CONCLUSIONS We developed and validated a novel, machine learning–derived risk score that integrates readily available clinical, laboratory, and electrocardiographic variables to predict the risk of HF among outpatients with T2DM.

Aim To identify distinct phenotypic subgroups in a highly‐dimensional, mixed‐data cohort of individuals with heart failure (HF) with preserved ejection fraction (HFpEF) using unsupervised clustering analysis. Methods and results The study included all Treatment of Preserved Cardiac Function Heart Failure with an Aldosterone Antagonist (TOPCAT) participants from the Americas (n = 1767). In the subset of participants with available echocardiographic data (derivation cohort, n = 654), we characterized three mutually exclusive phenogroups of HFpEF participants using penalized finite mixture model‐based clustering analysis on 61 mixed‐data phenotypic variables. Phenogroup 1 had higher burden of co‐morbidities, natriuretic peptides, and abnormalities in left ventricular structure and function; phenogroup 2 had lower prevalence of cardiovascular and non‐cardiac co‐morbidities but higher burden of diastolic dysfunction; and phenogroup 3 had lower natriuretic peptide levels, intermediate co‐morbidity burden, and the most favourable diastolic function profile. In adjusted Cox models, participants in phenogroup 1 (vs. phenogroup 3) had significantly higher risk for all adverse clinical events including the primary composite endpoint, all‐cause mortality, and HF hospitalization. Phenogroup 2 (vs. phenogroup 3) was significantly associated with higher risk of HF hospitalization but a lower risk of atherosclerotic event (myocardial infarction, stroke, or cardiovascular death), and comparable risk of mortality. Similar patterns of association were also observed in the non‐echocardiographic TOPCAT cohort (internal validation cohort, n = 1113) and an external cohort of patients with HFpEF [Phosphodiesterase‐5 Inhibition to Improve Clinical Status and Exercise Capacity in Heart Failure with Preserved Ejection Fraction (RELAX) trial cohort, n = 198], with the highest risk of adverse outcome noted in phenogroup 1 participants. Conclusions Machine learning‐based cluster analysis can identify phenogroups of patients with HFpEF with distinct clinical characteristics and long‐term outcomes.

Membrane drug transporters contribute to the disposition of many drugs. In human liver, drug transport is controlled by two main superfamilies of transporters, the solute carrier transporters (SLC) and the ATP Binding Cassette transporters (ABC). Altered expression of these transporters due to drug-drug interactions can contribute to differences in drug exposure and possibly effect. In this study, we determined the effect of rifampin on gene expression of hundreds of membrane transporters along with all clinically relevant drug transporters.

The introduction of next-generation sequencing technologies has radically changed the way we view structural genetic events. Microhomology-mediated break-induced replication (MMBIR) is just one of the many mechanisms that can cause genomic destabilization that may lead to cancer. Although the mechanism for MMBIR remains unclear, it has been shown that MMBIR is typically associated with template-switching events. Currently, to our knowledge, there is no existing bioinformatics tool to detect these template-switching events. We have developed MMBIRFinder, a method that detects template-switching events associated with MMBIR from whole-genome sequenced data. MMBIRFinder uses a half-read alignment approach to identify potential regions of interest. Clustering of these potential regions helps narrow the search space to regions with strong evidence. Subsequent local alignments identify the templateswitching events with single-nucleotide accuracy. Using simulated data, MMBIRFinder identified 83% of the MMBIR regions within a 5 nucleotide tolerance. Using real data, MMBIRFinder identified 16 MMBIR regions on a normal breast tissue data sample and 51 MMBIR regions on a triple-negative breast cancer tumor sample resulting in detection of 37 novel template-switching events. Finally, we identified template-switching events residing in the promoter region of 7 genes that have been implicated in breast cancer. The program is freely available for download at https://github.com/msegar/MMBIRFinder.

Emerging results indicate that cancer stem-like cells contribute to chemoresistance and poor clinical outcomes in many cancers, including ovarian cancer (OC). As epigenetic regulators play a major role in the control of normal stem cell differentiation, epigenetics may offer a useful arena to develop strategies to target cancer stem-like cells. Epigenetic aberrations, especially DNA methylation, silence tumor suppressor and differentiation-associated genes that regulate the survival of ovarian cancer stem-like cell (OCSC). In this study, we tested the hypothesis that DNA hypomethylating agents may be able to reset OCSC towards a differentiated phenotype, by evaluating the effects of the new DNA methytransferase inhibitor SGI-110 on OCSC phenotype, as defined by expression of the cancer stem-like marker aldehyde dehydrogenase (ALDH). We demonstrated that ALDH+ OC cells possess multiple stem cell characteristics, were highly chemoresistant, and were enriched in xenografts residual after platinum therapy. Low dose SGI-110 reduced the stem-like properties of ALDH+ cells, including their tumor initiating capacity, resensitized these OCSCs to platinum, and induced re-expression of differentiation-associated genes. Maintenance treatment with SGI-110 after carboplatin inhibited OCSC growth, causing global tumor hypomethylation and decreased tumor progression. Our work offers preclinical evidence that epigenome-targeting strategies have the potential to delay tumor progression by re-programming residual cancer stem-like cells. Further, the results suggest that SGI-110 might be administered in combination with platinum to prevent the development of recurrent and chemoresistant ovarian cancer.

BACKGROUND: In mass spectrometry-based proteomics, the statistical significance of a peptide-spectrum or protein-spectrum match is an important indicator of the correctness of the peptide or protein identification. In bottom-up mass spectrometry, probabilistic models, such as the generating function method, have been successfully applied to compute the statistical significance of peptide-spectrum matches for short peptides containing no post-translational modifications. As top-down mass spectrometry, which often identifies intact proteins with post-translational modifications, becomes available in many laboratories, the estimation of statistical significance of top-down protein identification results has come into great demand.\backslashn\backslashnRESULTS: In this paper, we study an extended generating function method for accurately computing the statistical significance of protein-spectrum matches with post-translational modifications. Experiments show that the extended generating function method achieves high accuracy in computing spectral probabilities and false discovery rates.\backslashn\backslashnCONCLUSIONS: The extended generating function method is a non-trivial extension of the generating function method for bottom-up mass spectrometry. It can be used to choose the correct protein-spectrum match from several candidate protein-spectrum matches for a spectrum, as well as separate correct protein-spectrum matches from incorrect ones identified from a large number of tandem mass spectra.