Topic Review
Physiologically Based Pharmacokinetic Modeling of Nanoparticle Biodistribution
Cancer treatment and pharmaceutical development require targeted treatment and less toxic therapeutic intervention to achieve real progress against this disease. In this scenario, nanomedicine emerged as a reliable tool to improve drug pharmacokinetics and to translate to the clinical biologics based on large molecules. However, the ability of body to recognize foreign objects together with carrier transport heterogeneity derived from the combination of particle physical and chemical properties, payload and surface modification, make the designing of effective carriers very difficult. In this scenario, physiologically based pharmacokinetic modeling can help to design the particles and eventually predict their ability to reach the target and treat the tumor. This effort is performed by scientists with specific expertise and skills and familiarity with artificial intelligence tools such as advanced software that are not usually in the “cords” of traditional medical or material researchers. 
  • 501
  • 04 Nov 2022
Topic Review
NNetEn Entropy
NNetEn is the first entropy measure that is based on artificial intelligence methods. The method modifies the structure of the LogNNet classification model so that the classification accuracy of the MNIST-10 digits dataset indicates the degree of complexity of a given time series. The calculation results of the proposed model are similar to those of existing methods, while the model structure is completely different and provides considerable advantages.
  • 577
  • 19 Jun 2023
Topic Review
Molecular Dynamics Simulations for DNAs
DNA carries the genetic information required for the synthesis of RNA and proteins and plays an important role in many processes of biological development. Understanding the three-dimensional (3D) structures and dynamics of DNA is crucial for understanding their biological functions and guiding the development of novel materials. Molecular dynamics (MD) simulations can generally reproduce the behavior of DNAs in a computer, providing detailed structural and dynamical insights that enhancing our comprehension of relevant experimental data. MD simulations using classical force fields such as AMBER and CHARMM have provided highly detailed and flexible descriptions of DNA dynamics, including structural transformations, stability of non-canonical conformations, salt ion cohesion effects, twist-stretch coupling of stress, flexibility under methylation modifications, and interactions with other macromolecules. It is always fascinating to obtain microscopic insights into DNA dynamics through MD simulations. However, the innumerable degrees of freedom, interconnected in complex ways, can make it practically impossible to detect DNA dynamics on biologically relevant time scales and length scales using currently available computer hardware
  • 254
  • 28 Jun 2023
Topic Review
ML-Based Detection Approaches of Coal Workers’ Pneumoconiosis
Computer-aided diagnostic (CAD) systems can assist radiologists in detecting coal workers’ pneumoconiosis (CWP) in their chest X-rays. Early diagnosis of the CWP can significantly improve workers’ survival rate.  The feature extraction and detection approaches of computer-based analysis in CWP using chest X-ray radiographs (CXR) can be summarised into three categories: classical methods including computer and international labor organization (ILO) classification-based detection; traditional machine learning methods; and CNN methods.
  • 438
  • 10 Jun 2022
Topic Review
MG-RAST
MG-RAST is an open-source web application server that suggests automatic phylogenetic and functional analysis of metagenomes. It is also one of the biggest repositories for metagenomic data. The name is an abbreviation of Metagenomic Rapid Annotations using Subsystems Technology. The pipeline automatically produces functional assignments to the sequences that belong to the metagenome by performing sequence comparisons to databases in both nucleotide and amino-acid levels. The applications supplies phylogenetic and functional assignments of the metagenome being analysed, as well as tools for comparing different metagenomes. It also provides a RESTful API for programmatic access. The server was created and maintained by Argonne National Laboratory from the University of Chicago. In December 29 of 2016, the system had analyzed 60 terabase-pairs of data from more than 150,000 data sets. Among the analyzed data sets, more than 23,000 are available to the public. Currently, the computational resources are provided by the DOE Magellan cloud at Argonne National Laboratory, Amazon EC2 Web services, and a number of traditional clusters.
  • 481
  • 10 Oct 2022
Topic Review
Machine Learning-Based for Depressive Syndrome
The current polythetic and operational criteria for major depression inevitably contribute to the heterogeneity of depressive syndromes. The heterogeneity of depressive syndrome has been criticized using the concept of language game in Wittgensteinian philosophy. Moreover, “a symptom- or endophenotype-based approach, rather than a diagnosis-based approach, has been proposed” as the “next-generation treatment for mental disorders” by Thomas Insel. Understanding the heterogeneity renders promise for personalized medicine to treat cases of depressive syndrome, in terms of both defining symptom clusters and selecting antidepressants. Machine learning algorithms have emerged as a tool for personalized medicine by handling clinical big data that can be used as predictors for subtype classification and treatment outcome prediction. The large clinical cohort data from the Sequenced Treatment Alternatives to Relieve Depression (STAR*D), Combining Medications to Enhance Depression Outcome (CO-MED), and the German Research Network on Depression (GRND) have recently began to be acknowledged as useful sources for machine learning-based depression research with regard to cost effectiveness and generalizability. In addition, noninvasive biological tools such as functional and resting state magnetic resonance imaging techniques are widely combined with machine learning methods to detect intrinsic endophenotypes of depression.
  • 476
  • 24 Sep 2021
Topic Review
Machine Learning for Process Monitoring
In the last few decades, hot-melt extrusion (HME) has emerged as a rapidly growing technology in the pharmaceutical industry, due to its various advantages over other fabrication routes for drug delivery systems. After the introduction of the ‘quality by design’ (QbD) approach by the Food and Drug Administration (FDA), many research studies have focused on implementing process analytical technology (PAT), including near-infrared (NIR), Raman, and UV–Vis, coupled with various machine learning algorithms, to monitor and control the HME process in real time. This review gives a comprehensive overview of the application of machine learning algorithms for HME processes, with a focus on pharmaceutical HME applications. The main current challenges in the application of machine learning algorithms for pharmaceutical processes are discussed, with potential future directions for the industry.
  • 543
  • 17 Sep 2021
Topic Review
LncRNA-Protein Interactions
LncRNA can act as gene regulators, and like other epigenetic mechanisms are involved in numerous biological processes. They achieve their regulatory function with their ability to interact with a wide range of biological molecules, such as other nucleic acids and proteins. These lncRNA-protein interactions (LPI) are involved in many biological pathways including development and disease. A variety of computational LPI predictors exist, each applying different strategies to achieve their goals, and are dependent on a few biological databases containing subsets of experimentally validated LPI. Most modern lncRNA-protein interaction (LPI) prediction algorithms use machine learning approaches, where algorithms are trained on large datasets with attributes of interest.
  • 1.3K
  • 05 Jul 2021
Topic Review
Lattice Boltzmann Method
Biofilm growth and evolution are very complex interactions among physicochemical and biological processes. Mathematical models are critical to modern biotechnology—both in research and in the engineering practice. Thus, many models of biofilms have been developed to include various biofilm reactor modules. However, considerable challenges exist in modelling microbial processes where mesoscopic dynamics of nutrient transport must be coupled with microscopic bacteria growth and their elementary biochemical reactions at reactive or enzymatic interfaces, in addition to the microbiological and/or ecological aspects of the “micro” organisms involved in biofilms. Lattice Boltzmann Method (LBM) treats flows in terms of fictive parcels of particles which reside on a mesh and conduct translation according to collision steps entailing overall fluid-like behavior. The goal of this review is to discuss and identify the opportunities of applying different LBM-based models to specific areas of biofilm research as well as unique challenges that LBM-based models must overcome.
  • 601
  • 19 Jul 2021
Topic Review
Kinases/Protein Phosphatases in Signaling Pathways Activation
Optimizing physical training regimens to increase muscle aerobic capacity requires an understanding of the internal processes that occur during exercise that initiate subsequent adaptation. During exercise, muscle cells undergo a series of metabolic events that trigger downstream signaling pathways and induce the expression of many genes in working muscle fibers. There are a number of studies that show the dependence of changes in the activity of AMP-activated protein kinase (AMPK), one of the mediators of cellular signaling pathways, on the duration and intensity of single exercises. The activity of various AMPK isoforms can change in different directions, increasing for some isoforms and decreasing for others, depending on the intensity and duration of the load.
  • 220
  • 11 Jul 2023
  • Page
  • of
  • 5