A5081059721- Sleep and Wakefulness Research
- Sleep and related disorders
- Computational Drug Discovery Methods
- Circadian rhythm and melatonin
- EEG and Brain-Computer Interfaces
- Analytical Chemistry and Chromatography
- Metabolomics and Mass Spectrometry Studies
- Machine Learning in Materials Science
- Statistical Methods in Clinical Trials
- Statistical Methods and Inference
- Statistical Methods and Bayesian Inference
- Reliability and Agreement in Measurement
- Restless Legs Syndrome Research
- Advanced Statistical Methods and Models
- Gene expression and cancer classification
- Blind Source Separation Techniques
- Protein Structure and Dynamics
- Advanced Data Processing Techniques
- Machine Learning in Bioinformatics
- Neural dynamics and brain function
- Monoclonal and Polyclonal Antibodies Research
- Biosimilars and Bioanalytical Methods
- Molecular spectroscopy and chirality
- Neuroscience and Neural Engineering
- Microbial Natural Products and Biosynthesis
Merck & Co., Inc., Rahway, NJ, USA (United States)
2016-2025
Decision Sciences (United States)
2016-2025
Zimmer Biomet (United States)
2019
United States Military Academy
2004-2017
University of Wisconsin–Madison
2005
Saint-Petersburg State Agrarian University
1986-1987
A new classification and regression tool, Random Forest, is introduced investigated for predicting a compound's quantitative or categorical biological activity based on description of the molecular structure. Forest an ensemble unpruned trees created by using bootstrap samples training data random feature selection in tree induction. Prediction made aggregating (majority vote averaging) predictions ensemble. We built predictive models six cheminformatics sets. Our analysis demonstrates that...
Neural networks were widely used for quantitative structure-activity relationships (QSAR) in the 1990s. Because of various practical issues (e.g., slow on large problems, difficult to train, prone overfitting, etc.), they superseded by more robust methods like support vector machine (SVM) and random forest (RF), which arose early 2000s. The last 10 years has witnessed a revival neural learning community thanks new preventing efficient training algorithms, advancements computer hardware. In...
Deep neural networks (DNNs) are complex computational models that have found great success in many artificial intelligence applications, such as computer vision1,2 and natural language processing.3,4 In the past four years, DNNs also generated promising results for quantitative structure-activity relationship (QSAR) tasks.5,6 Previous work showed can routinely make better predictions than traditional methods, random forests, on a diverse collection of QSAR data sets. It was multitask DNN...
Protein redesign and engineering has become an important task in pharmaceutical research development. Recent advances technology have enabled efficient protein by mimicking natural evolutionary mutation, selection, amplification steps the laboratory environment. For any given protein, number of possible mutations is astronomical. It impractical to synthesize all sequences or even investigate functionally interesting variants. Recently, there been increased interest using machine learning...
A classification and regression tool, J. H. Friedman's Stochastic Gradient Boosting (SGB), is applied to predicting a compound's quantitative or categorical biological activity based on description of the molecular structure. procedure for building sequence models, instance trees (as in this paper), whose outputs are combined form predicted quantity, either an estimate activity, class label which molecule belongs. In particular, SGB builds model stage-wise manner by fitting each tree...
Abstract Orexin neuropeptides regulate sleep/wake through orexin receptors (OX 1 R, OX 2 R); R is the predominant mediator of arousal promotion. The potential for single antagonism to effectively promote sleep has yet be demonstrated in humans. MK-1064 an R-single antagonist. Preclinically, promotes and increases both rapid eye movement (REM) non-REM (NREM) rats at occupancies higher than range observed dual receptor antagonists. Similar antagonists, NREM REM dogs without inducing cataplexy....
Abstract Background Computational and microarray-based experimental approaches were used to generate a comprehensive transcript index for the human genome. Oligonucleotide probes designed from approximately 50,000 known predicted sequences genome survey transcription diverse set of 60 tissues cell lines using ink-jet microarrays. Further, expression activity over at least six conditions was more generally assessed genomic tiling arrays consisting tiled through repeat-masked version sequence...
Previous studies of the differences between patients with insomnia and good sleepers regard to quantitative electroencephalographic measures have mostly utilized small samples consequently had limited ability account for potentially important confounding factors age, sex part night. We conducted a power spectral analysis using large database sleep recordings evaluate (N = 803) 811), while simultaneously accounting these their interaction. Comparisons as function age night were made cohorts...
The quantitative structure–activity relationship (QSAR) regression model is a commonly used technique for predicting the biological activities of compounds using their molecular descriptors. Besides accurate activity estimation, obtaining prediction uncertainty metric like interval highly desirable. Quantifying an active research area in statistical and machine learning (ML), but implementation QSAR remains challenging. However, most ML algorithms with high predictive performance require...
Current methods of measuring disease progression neurodegenerative disorders, including Parkinson's (PD), largely rely on composite clinical rating scales, which are prone to subjective biases and lack the sensitivity detect signals in a timely manner. Digital health technology (DHT)-derived measures offer potential solutions provide objective, precise, sensitive that address these limitations. However, complexity DHT datasets derive numerous digital features were not previously possible...
In drug discovery, the reliability of compound screening based on manual assessments is compromised by potential bias, while existing methods lack robust risk control measures. To address these challenges, we introduced conformal selection as an enhanced approach to optimize process with balanced risks and benefits. Leveraging inference, our constructs p-values for each candidate molecule quantify statistical evidence selection. The final molecules determined comparing against thresholds...
Eastern Cooperative Oncology Group performance status (ECOG PS) is a key confounder in comparative effectiveness research, predicting treatment and survival, but often incomplete electronic health records (EHRs). Imputation on the basis of classification metrics alone may introduce differences survival between patients with known imputed ECOG PS, complicating research. We developed an approach to impute PS so that those are indistinguishable their reducing potential biases introduced by...
Suvorexant, an orexin receptor antagonist, improves sleep in healthy subjects (HS) and patients with insomnia. We compared the electroencephalographic (EEG) power spectral density (PSD) profile of suvorexant placebo using data from a phase 2 trial also suvorexant's PSD profiles other insomnia treatments 3 HS studies Phase trial—randomized, double-blind, two-period (4 w per period) crossover. studies—randomized, Sleep laboratories. Insomnia (n = 229) or 124). trial—suvorexant 10 mg, 20 40 80...
Objective:To evaluate the performance of 2 automated systems, Morpheus and Somnolyzer24X7, with various levels human review/editing, in scoring polysomnographic (PSG) recordings from a clinical trial using zolpidem model transient insomnia.
With the growing commonality of multi‐omics datasets, there is now increasing evidence that integrated omics profiles lead to more efficient discovery clinically actionable biomarkers enable better disease outcome prediction and patient stratification. Several methods exist perform host phenotype from cross‐sectional, single‐omics data modalities but decentralized frameworks jointly analyze multiple time‐dependent highlight integrative dynamic impact repeatedly measured are currently...
Abstract Study Objectives To examine the duration and frequency of wake bouts underlying wakefulness-after-sleep-onset (WASO) reduction with suvorexant. Methods We analyzed polysomnogram recordings from clinical trials involving 1518 insomnia patients receiving suvorexant (40/30, 20/15 mg) or placebo to determine following: (1) number of, time spent in, long short (2) association between sleep quality bout characteristics. also compared characteristics in versus zolpidem healthy subjects...
Abstract The orexin receptor antagonist suvorexant was previously reported to significantly improve total sleep time (TST), by 28 min per night versus placebo after 4 weeks, in a laboratory polysomnography (PSG) study of patients with Alzheimer's disease and insomnia. included an exploratory evaluation consumer‐grade wearable “watch” device for assessing that we report on here. Participants who met diagnostic criteria both probable dementia insomnia were randomized 10–20 mg ( N = 142) or...
Accurate diagnosis of Alzheimer disease (AD) involving less invasive molecular procedures and at reasonable cost is an unmet medical need. We identified a serum miRNA signature for AD that than measure in cerebrospinal fluid. From the Oxford Project to Investigate Memory Aging (OPTIMA) study, 96 samples were profiled by multiplex (>500 analytes) microRNA (miRNA) reverse transcription quantitative PCR analysis, including 51 controls, 32 from patients with AD, 13 mild cognitive impairment...
Quantitative structure–activity relationship (QSAR) is a very commonly used technique for predicting the biological activity of molecule using information contained in molecular descriptors. The large number compounds and descriptors sparseness pose important challenges to traditional statistical methods machine learning (ML) algorithms (such as random forest (RF)) this field. Recently, Bayesian Additive Regression Trees (BART), flexible nonparametric regression approach, has been...
To evaluate cyclic alternating pattern (CAP) in a phase advance model of transient insomnia and the effects gaboxadol zolpidem. A randomized, double-blind, cross-over study which habitual sleep time was advanced by 4 h. 6 research laboratories US 55 healthy subjects (18–57 y) Gaboxadol 15 mg (GBX), zolpidem 10 (ZOL), placebo (PBO). Routine polysomnographic (PSG) measures, CAP, spectral power density, self-reported measures The produced significant changes CAP parameters. Both GBX ZOL...