Efficient prediction of drug–drug interaction using deep learning models

A drug–drug interaction or drug synergy is extensively utilised for cancer treatment. However, prediction of drug–drug interaction is defined as an ill‐posed problem, because manual testing is only implementable on small group of drugs. Predicting the drug–drug interaction score has been a popular research topic recently. Recently many machine learning models have proposed in the literature to predict the drug–drug interaction score efficiently. However, these models suffer from the over‐fitting issue. Therefore, these models are not so‐effective for predicting the drug–drug interaction score. In this work, an integrated convolutional mixture density recurrent neural network is proposed and implemented. The proposed model integrates convolutional neural networks, recurrent neural networks and mixture density networks. Extensive comparative analysis reveals that the proposed model significantly outperforms the competitive models.Inspec keywords: cancer, learning (artificial intelligence), drugs, recurrent neural nets, convolutional neural nets, drug delivery systemsOther keywords: drug synergy, drug–drug interaction score, drug–drug interaction prediction, deep learning, cancer treatment, machine learning, convolutional mixture density recurrent neural network     

Electricity consumption in G7 countries: A panel cointegration analysis of residential demand elasticities

This article applies recently developed panel unit root and panel cointegration techniques to estimate the long-run and short-run income and price elasticities for residential demand for electricity in G7 countries. The panel results indicate that in the long-run residential demand for electricity is price elastic and income inelastic. The study concludes that from an environmental perspective there is potential to use pricing policies in the G7 countries to curtail residential electricity demand, and thus curb carbon emissions, in the long run.     

下一代翅片式铜管热交换器的设计思考

世界范围内,电器要达到越来越高的能效标准指标。为此,本文阐述了在实验性的盘管结构中的若干革新,这些革新可以缩小HVAC/R用品中风扇和电机的尺寸,并能帮助OEM厂商节约原料成本。     

Rheological study of polypropylene copolymer/polyolefinic elastomer blends

Blends of polypropylene copolymer (PP‐cp) and a polyolefinic elastomer (POE) were prepared by a melt‐blending process at 210°C and 60 rpm using a counterrotating twin‐screw extruder. The POE content was varied up to 25%. The shear viscosity over a wide range of shear rate was measured. All blend compositions showed well‐defined zero shear viscosity and shear thinning behavior. The melt viscosity values were between those of the principal components in all cases. Rheology of blends shows different behavior up to concentrations of POE corresponding to the tough–brittle transition. The linear viscoelastic properties (G′, G″, η*, η′, η″) were used to check the miscibility of the two components in the melt state. All blend compositions showed a good degree of miscibility over the range of POE concentrations studied. © 2002 Wiley Periodicals, Inc. J Appl Polym Sci 84: 665–671, 2002; DOI 10.1002/app.10376     

Ion-exchange kinetics and thermal decomposition characteristics of Fe2+-exchanged alginic acid membrane for the formation of iron oxide nanoparticles

The ion-exchange kinetics of Fe²⁺ cations in aqueous solution with H⁺ from alginic acid have been analyzed in this study as a function of contact time lengths using inductively coupled plasma-atomic emission spectrometry analysis. The kinetic parameters have been evaluated using pseudo 1st or 2nd order models, and a consistent ion-exchange mechanism is suggested. Furthermore, an insight into the calcination of Fe²⁺ ion-exchanged alginic acid process has been obtained by using simultaneous thermo-gravimetric analysis coupled with differential scanning calorimetry and high temperature X-ray diffraction.     

Superparamagnetic Behavior of Zinc-Substituted Nickel Ferrite Nanoparticles and its Effect on Mossbauer and Magnetic Parameters

Zinc-substituted nickel ferrite (Ni _1?x Zn _x Fe ₂ O ₄ with x = 0.0, 0.2, 0.4, 0.6, 0.8, and 1.0) nanoparticles were synthesized by solgel auto-combustion technique at low temperature and characterized by using X-ray diffraction, scanning electron microscopy, pulse field hysteresis loop technique, and Mossbauer spectroscopy. X-ray diffraction studies confirmed the formation of single-phase spinel structure of the prepared ferrite samples with average crystallite size of 30 nm, very close to that of the critical size for nanoparticles exhibiting superparamagnetism. Scanning electron micrographs of the ferrite samples showed uniform spherical morphology of nanograins with homogenous microstructure. Further investigations on magnetic properties by pulse field hysteresis loop technique and Mossbauer spectroscopy indicated the presence of superparamagnetic phases in the ferrite samples attributed to occupation of octahedral [B] sites by zinc ions in these Ni–Zn samples and also to the nanometer sizes of the ferrite particles. Magnetic behavior of the Ni–Zn ferrite system is in agreement, initially, with Neel’s two-sublattice collinear model and then with the Yafet–Kittel model for samples with higher zinc content (x ≥ 0.4). Value of hyperfine splitting is found to decrease with increase in zinc content and is attributed to the reduction in particle size giving rise to superparamagnetism. Other Mossbauer parameters like quadrupole splitting and the isomer shift are within the reported range for those of ferrites with spinel structure.     

Effects of spray modeling on heat and mass transfer in air–water spray systems in parallel flow

The heat and mass transfer equations for a co-flow water spray in air were solved for different combinations of drop diameter category and velocity sub-class, and compared with experimental data. For uniform drop velocities, the number of categories was increased to 10, 50, 100 and 200, as against 5 in an earlier study. Best predictions were obtained with 100 categories. For 5 categories, 10, 20 and 40 velocity sub-classes within each category were introduced, and predictions were slightly better than with a single velocity. Results with 100 categories–1 velocity and 10 categories–10 velocity sub-classes were similar; the latter matched experiments mostly within ± 15% as against ± 30% in an earlier study.     

A Novel Mechanism of Embrittlement Affecting the Impact Reliability of Tin-Based Lead-Free Solder Joints

This work addresses a new mode of brittle failure that occurs in the bulk of tin-based lead-free solder joints, unlike the typical brittle failures that occur in the interfacial intermetallics. Brittle failures in the joint bulk result from the low-temperature ductile-to-brittle transition in the fracture behavior of β-tin. The bulk embrittlement of these joints is discussed by referring to the results of impact tests performed on both solder joints and bulk solder specimens. The mechanism of bulk embrittlement is largely explained based on the results of a fractography study performed on the bulk joint failures using scanning electron microscopy.     

Parallel asynchronous variational integrators

This paper presents a scalable parallel variational time integration algorithm for nonlinear elastodynamics with the distinguishing feature of allowing each element in the mesh to have a possibly different time step. Furthermore, the algorithm is obtained from a discrete variational principle, and hence it is termed parallel asynchronous variational integrator (PAVI). The underlying variational structure grants it outstanding conservation properties. Based on a domain decomposition strategy, PAVI combines a careful scheduling of computations with fully asynchronous communications to provide a very efficient methodology for finite element models with even mild distributions of time step sizes. Numerical tests are shown to illustrate PAVI's performance on both slow and fast networks, showing scalability properties similar to the best parallel explicit synchronous algorithms, with lower execution time. Finally, a numerical example in which PAVI needs ≈100 times less computing than an explicit synchronous algorithm is shown. Copyright © 2006 John Wiley & Sons, Ltd.     

Solid-state sensors for in-line monitoring of NO2 in automobile exhaust emission

Three types of planar solid-state sensors for measuring NO₂ in a gas mixture has been designed and tested in the laboratory under controlled atmosphere between 573–723 K. The concentration of NO₂ in the gas mixture was in the range of 0–500 ppm with the balance gas consisting of air. The three types of NO₂ gas sensors that have been tested in this investigation can be schematically represented as follows:Pt, NO₂ + air, NaNO₃ + Ba(NO₃)₂ | NASICON disk | Porous YSZ disk | NO₂ + air, Pt (I)Pt, NO₂ + air, NaNO₃ + Ba(NO₃)₂ | NASICON disk | YSZ thin film | NO₂ + air, Pt (II)Pt, NO₂ + air, Pt | YSZ disk | Au – Pd, NO₂ + air, Pt (III)In sensor (I) the two solid electrolyte disks were attached by diffusion bonding at elevated temperature whereas in sensor (II) the (8 mol% Y₂O₃–ZrO₂) YSZ thin film was deposited on (Na₃Zr₂Si₂PO₁₂) NASICON disk by radio frequency (RF) magnetron sputtering technique. The measured open circuit electromotive force (Emf) of each sensor was found to attain stable value at all the concentrations of NO₂ in the gas mixture and also varied linearly as a function of the logarithm of the partial pressure of NO₂ in the gas mixture. The time required to reach 90% of the stable emf at a fixed concentration of NO₂ and at a constant temperature was found to be 30–40 min for sensor (I) and approximately 2–3 min for sensor (II) and (III).