This is probably the most popular design of experiments (DOE) book. It is unquestionably the leading DOE book in industry. So I am excepting it from the usual disdain I show for the  fth edition (5E) of any book, even though it follows the fourth edition (4E) by only four years. See Grice (2000) for a report on the 4E. Very likely this book bears little resemblance to the  rst edition way back in the 1970s. The author has taken particular care with this latest edition to reorganize the book to be consistent with modern DOE practice rather than classical DOE presentation. The primary change has been to move the chapters on regression modeling and response surface methods forward in the book. In the 4E these were the last two chapters in the book. In the 5E they follow the chapters on factorial and fractional factorial designs. Three chapters on “other designs” now close out the book. This certainly gives the book a better  ow for industry short courses. Perhaps these will simply be referenced as arcane methods in the sixth edition! Other production values in the book also continue to improve. There are many high-quality graphical displays. There is much use of printouts from Minitab and Design-Expert. A student version of Design-Export comes with the book. There is also an instructor’s CD-ROM with supplemental material to make the book suitable for more advanced courses. There is the now-essential Web site that has more information to help students and instructors. Perhaps if I were teaching DOE for master’s-level statisticians, the recent book by Dean and Voss (1999), reviewed by Amidan (2000), would be my choice. However, for most other audiences this is the complete DOE book. Industrial statisticians should get a copy of the new version and ensure its exposure to the relevant people in their organization.

Introduction to the Practice of Statistics

The number of bike-sharing services worldwide has grown over 1800% from 2014 to 2018. Accurate flow prediction of bike-sharing systems is critical for increasing user satisfaction, improving the efficiency, and planning new stations. Current flow prediction methods leave out important contextual features. In this paper, we propose a context-aware framework to predict bike flows for both existing stations and new stations. The model incorporates spatiotemporal, network, and environment contexts in a synergistic manner. The proposed model is evaluated on a bike-sharing system in New York City (NYC). Our model reduced error rate by 9% and root mean squared logarithmic error by 8% compared with the state-of-the-art neural network based method using context features. We also extend our model to a clustered bike flow prediction model, which is the focus of most of the current literature. Our model outperformed the state-of-the-art clustered model by 23% and 25% under anomalous situations in error rate and root mean squared logarithmic error respectively.

Context Aware Flow Prediction of Bike Sharing Systems

Prediction of bicycle counter data using regression

Representing an important cause of long–term disability, term neonatal hypoxic-ischemic encephalopathy (HIE) urgently needs further research aimed at repurposing existing drug as well as developing new therapeutics. Since various experimental in vitro and in vivo models of HIE have been developed with distinct characteristics, it becomes important to select the appropriate preclinical screening cascade for testing the efficacy of novel pharmacological treatments. As therapeutic hypothermia is already a routine therapy for neonatal encephalopathy, it is essential that hypothermia be administered to the experimental model selected to allow translational testing of novel or repurposed drugs on top of the standard of care. Moreover, a translational approach requires that therapeutic interventions must be initiated after the induction of the insult, and the time window for intervention should be evaluated to translate to real world clinical practice. Hippocampal organotypic slice cultures, in particular, are an invaluable intermediate between simpler cell lines and in vivo models, as they largely maintain structural complexity of the original tissue and can be subjected to transient oxygen–glucose deprivation (OGD) and subsequent reoxygenation to simulate ischemic neuronal injury and reperfusion. Progressing to in vivo models, generally, rodent (mouse and rat) models could offer more flexibility and be more cost-effective for testing the efficacy of pharmacological agents with a dose–response approach. Large animal models, including piglets, sheep, and non-human primates, may be utilized as a third step for more focused and accurate translational studies, including also pharmacokinetic and safety pharmacology assessments. Thus, a preclinical proof of concept of efficacy of an emerging pharmacological treatment should be obtained firstly in vitro, including organotypic models, and, subsequently, in at least two different animal models, also in combination with hypothermia, before initiating clinical trials.

https://www.mdpi.com/2227-9059/10/5/937/pdf?version=1650444419

Experimental Models for Testing the Efficacy of Pharmacological Treatments for Neonatal Hypoxic-Ischemic Encephalopathy

Public bike-sharing (PBS) systems have expanded to major cities around the world in efforts to mitigate air pollution, traffic congestion and traffic accidents. Users can pickup and drop-off bicycl...

Predicting Demand for a Bike-Sharing System with Station Activity Based on Random Forest

In Vitro Oxygen Glucose Deprivation Model of Ischemic Stroke: A Proteomics-Driven Systems Biological Perspective

This thesis looks at how machine learning algorithms might be used to predict bike-share traffic. We determine the accuracies of estimators such as decision trees, random forests and boosted decision trees. The effect of factors such as weather, geographic location, time of day, day of week etc on the number of bikes at a bike-share station are also investigated. Finally, we outline how a web-based prediction system that uses the estimators mentioned in this thesis could look like.

Predicting bike-share usage patterns with machine learning

Lacunar infarction (LACI), a subtype of acute ischemic stroke, has poor mid- to long-term prognosis due to recurrent vascular events or incident dementia which is difficult to predict using existing clinical data. Herein, we aim to discover blood-based biomarkers for LACI as a complementary prognostic tool. Convalescent plasma was collected from forty-five patients following a non-disabling LACI along with seventeen matched control subjects. The patients were followed up prospectively for up to five years to record an occurrence of adverse outcome and grouped accordingly (i.e., LACI-no adverse outcome, LACI-recurrent vascular event, and LACI-cognitive decline without any recurrence of vascular events). Medium-sized extracellular vesicles (MEVs), isolated from the pooled plasma of four groups, were analyzed by stable isotope labeling and 2D-LC-MS/MS. Out of 573 (FDR < 1%) quantified proteins, 146 showed significant changes in at least one LACI group when compared to matched healthy control. A systems analysis revealed that major elements (~85%) of the MEV proteome are different from the proteome of small-sized extracellular vesicles obtained from the same pooled plasma. The altered MEV proteins in LACI patients are mostly reduced in abundance. The majority of the shortlisted MEV proteins are not linked to commonly studied biological processes such as coagulation, fibrinolysis, or inflammation. Instead, they are linked to oxygen-glucose deprivation, endo-lysosomal trafficking, glucose transport, and iron homeostasis. The dataset is provided as a web-based data resource to facilitate meta-analysis, data integration, and targeted large-scale validation.

/pdf/quantitative-proteomics-of-medium-sized-extracellular-128fiain.pdf

Quantitative Proteomics of Medium-Sized Extracellular Vesicle-Enriched Plasma of Lacunar Infarction for the Discovery of Prognostic Biomarkers

Vasopressin controls renal water excretion through actions to regulate aquaporin-2 (AQP2) trafficking, transcription and degradation. These actions are in part dependent on vasopressin-induced phosphorylation changes in collecting duct cells. Although most efforts have focused on phosphorylation of AQP2 itself, phosphoproteomic studies have identified many vasopressin-regulated phosphorylation sites in proteins other than AQP2. The goal of this bioinformatics-based review is to create a compendium of vasopressin-regulated phosphorylation sites with focus on those that are seen in both native rat inner medullary collecting ducts and cultured collecting duct cells from mouse (mpkCCD), arguing that these sites are the best candidates for roles in AQP2 regulation. This analysis identified 51 vasopressin-regulated phosphorylation sites in 45 proteins. We provide resource web pages at https://esbl.nhlbi.nih.gov/Databases/AVP-Phos/ and https://esbl.nhlbi.nih.gov/AVP-Network/, listing the phosphorylation sites and describing annotated functions of each of the vasopressin-targeted phosphoproteins. Among these sites are 23 consensus protein kinase A (PKA) sites that are increased in response to vasopressin, consistent with a central role for PKA in vasopressin signaling. The remaining sites are predicted to be phosphorylated by other kinases, most notably ERK1/2 which accounts for decreased phosphorylation at sites with a X-p(S/T)-P-X motif. Additional protein kinases that undergo vasopressin-induced changes in phosphorylation are Camkk2, Cdk18, Erbb3, Mink1 and Src, which also may be activated directly or indirectly by PKA. The regulated phosphoproteins are mapped to processes that hypothetically can account for vasopressin-mediated control of AQP2 trafficking, cytoskeletal alterations, and Aqp2 gene expression, providing grist for future studies.

Data Resource: Vasopressin-Regulated Protein Phosphorylation Sites in Collecting Duct.

The advent of modern quantitative protein mass spectrometry techniques around the turn of the 21st century has contributed to a revolution in biology referred to as "systems biology". These methods allow identification and quantification of thousands of proteins in a biological specimen, as well as detection and quantification of post-translational protein modifications including phosphorylation. Here, we discuss these methodologies and show how they can be applied to understand the effects of the peptide hormone vasopressin to regulate the molecular water channel aquaporin-2 (AQP2). The emerging picture provides a detailed framework for understanding the molecular mechanisms involved in water balance disorders. Abstract figure legend Various quantitative protein mass spectrometry have been used to study the mechanisms of vasopressin induced AQP2 protein expression. SILAC is a technology using isotopes (C-13 and N-15) to label arginine and lysine in cell culture that allows mass spectrometry to distinguish control and treatment samples. The quantification is done by measuring the relative intensity of the light and heavy peptides that corresponded to the relative abundance of the parent protein in the samples. Dynamic SILAC is designed to quantify protein half-lives and translation rates by switching normal media to heavy isotopes containing media and trace the changes of intensity in the light and heavy peptides. TMT is a set of isotopic tags with the same molecular weight that can label peptides directly. The advantages of the TMT technology is multiplexing and can be applied to any sample types without pre-incubation with heavy isotope culture media. Multiplexing of TMT quantification is essential for study time-responsive phosphoproteomics. This article is protected by copyright. All rights reserved.

Arnab Kumar Datta

Papers

In Vitro Oxygen Glucose Deprivation Model of Ischemic Stroke: A Proteomics-Driven Systems Biological Perspective

Predicting bike-share usage patterns with machine learning

Quantitative Proteomics of Medium-Sized Extracellular Vesicle-Enriched Plasma of Lacunar Infarction for the Discovery of Prognostic Biomarkers

Data Resource: Vasopressin-Regulated Protein Phosphorylation Sites in Collecting Duct.

Proteomics and AQP2 regulation.