System science and engineering ; Vol. 12
215 s. : il.
- Conspectus
- Lékařské vědy. Lékařství
- NML Fields
- lékařská informatika
BACKGROUND AND OBJECTIVE: In silico prediction of drug-target interactions (DTI) could provide valuable information and speed-up the process of drug repositioning - finding novel usage for existing drugs. In our work, we focus on machine learning algorithms supporting drug-centric repositioning approach, which aims to find novel usage for existing or abandoned drugs. We aim at proposing a per-drug ranking-based method, which reflects the needs of drug-centric repositioning research better than conventional drug-target prediction approaches. METHODS: We propose Bayesian Ranking Prediction of Drug-Target Interactions (BRDTI). The method is based on Bayesian Personalized Ranking matrix factorization (BPR) which has been shown to be an excellent approach for various preference learning tasks, however, it has not been used for DTI prediction previously. In order to successfully deal with DTI challenges, we extended BPR by proposing: (i) the incorporation of target bias, (ii) a technique to handle new drugs and (iii) content alignment to take structural similarities of drugs and targets into account. RESULTS: Evaluation on five benchmark datasets shows that BRDTI outperforms several state-of-the-art approaches in terms of per-drug nDCG and AUC. BRDTI results w.r.t. nDCG are 0.929, 0.953, 0.948, 0.897 and 0.690 for G-Protein Coupled Receptors (GPCR), Ion Channels (IC), Nuclear Receptors (NR), Enzymes (E) and Kinase (K) datasets respectively. Additionally, BRDTI significantly outperformed other methods (BLM-NII, WNN-GIP, NetLapRLS and CMF) w.r.t. nDCG in 17 out of 20 cases. Furthermore, BRDTI was also shown to be able to predict novel drug-target interactions not contained in the original datasets. The average recall at top-10 predicted targets for each drug was 0.762, 0.560, 1.000 and 0.404 for GPCR, IC, NR, and E datasets respectively. CONCLUSIONS: Based on the evaluation, we can conclude that BRDTI is an appropriate choice for researchers looking for an in silico DTI prediction technique to be used in drug-centric repositioning scenarios. BRDTI Software and supplementary materials are available online at www.ksi.mff.cuni.cz/∼peska/BRDTI.
- MeSH
- Algorithms MeSH
- Bayes Theorem * MeSH
- Datasets as Topic MeSH
- Pharmacology * MeSH
- Humans MeSH
- Drug Repositioning MeSH
- Machine Learning MeSH
- Check Tag
- Humans MeSH
- Publication type
- Journal Article MeSH
PrankWeb is an online resource providing an interface to P2Rank, a state-of-the-art method for ligand binding site prediction. P2Rank is a template-free machine learning method based on the prediction of local chemical neighborhood ligandability centered on points placed on a solvent-accessible protein surface. Points with a high ligandability score are then clustered to form the resulting ligand binding sites. In addition, PrankWeb provides a web interface enabling users to easily carry out the prediction and visually inspect the predicted binding sites via an integrated sequence-structure view. Moreover, PrankWeb can determine sequence conservation for the input molecule and use this in both the prediction and result visualization steps. Alongside its online visualization options, PrankWeb also offers the possibility of exporting the results as a PyMOL script for offline visualization. The web frontend communicates with the server side via a REST API. In high-throughput scenarios, therefore, users can utilize the server API directly, bypassing the need for a web-based frontend or installation of the P2Rank application. PrankWeb is available at http://prankweb.cz/, while the web application source code and the P2Rank method can be accessed at https://github.com/jendelel/PrankWebApp and https://github.com/rdk/p2rank, respectively.
- MeSH
- Benchmarking MeSH
- Datasets as Topic MeSH
- Protein Interaction Domains and Motifs MeSH
- Internet MeSH
- Protein Conformation, alpha-Helical MeSH
- Protein Conformation, beta-Strand MeSH
- Humans MeSH
- Ligands MeSH
- Proteins chemistry metabolism MeSH
- Amino Acid Sequence MeSH
- Software * MeSH
- Machine Learning * MeSH
- Thermodynamics MeSH
- Protein Binding MeSH
- Binding Sites MeSH
- Check Tag
- Humans MeSH
- Publication type
- Journal Article MeSH
- Research Support, Non-U.S. Gov't MeSH
INTRODUCTION: Artificial intelligence through machine learning uses algorithms and prior learnings to make predictions. Recently, there has been interest to include more artificial intelligence in pharmacovigilance of products already in the market and pharmaceuticals in development. OBJECTIVE: The aim of this study was to identify and describe the uses of artificial intelligence in pharmacovigilance through a systematic literature review. METHODS: Embase and MEDLINE database searches were conducted for articles published from January 1, 2015 to July 9, 2021 using search terms such as 'pharmacovigilance,' 'patient safety,' 'artificial intelligence,' and 'machine learning' in the title or abstract. Scientific articles that contained information on the use of artificial intelligence in all modalities of patient safety or pharmacovigilance were reviewed and synthesized using a pre-specified data extraction template. Articles with incomplete information and letters to editor, notes, and commentaries were excluded. RESULTS: Sixty-six articles were identified for evaluation. Most relevant articles on artificial intelligence focused on machine learning, and it was used in patient safety in the identification of adverse drug events (ADEs) and adverse drug reactions (ADRs) (57.6%), processing safety reports (21.2%), extraction of drug-drug interactions (7.6%), identification of populations at high risk for drug toxicity or guidance for personalized care (7.6%), prediction of side effects (3.0%), simulation of clinical trials (1.5%), and integration of prediction uncertainties into diagnostic classifiers to increase patient safety (1.5%). Artificial intelligence has been used to identify safety signals through automated processes and training with machine learning models; however, the findings may not be generalizable given that there were different types of data included in each source. CONCLUSION: Artificial intelligence allows for the processing and analysis of large amounts of data and can be applied to various disease states. The automation and machine learning models can optimize pharmacovigilance processes and provide a more efficient way to analyze information relevant to safety, although more research is needed to identify if this optimization has an impact on the quality of safety analyses. It is expected that its use will increase in the near future, particularly with its role in the prediction of side effects and ADRs.
Current studies of gene × air pollution interaction typically seek to identify unknown heritability of common complex illnesses arising from variability in the host's susceptibility to environmental pollutants of interest. Accordingly, a single component generalized linear models are often used to model the risk posed by an environmental exposure variable of interest in relation to a priori determined DNA variants. However, reducing the phenotypic heterogeneity may further optimize such approach, primarily represented by the modeled DNA variants. Here, we reduce phenotypic heterogeneity of asthma severity, and also identify single nucleotide polymorphisms (SNP) associated with phenotype subgroups. Specifically, we first apply an unsupervised learning algorithm method and a non-parametric regression to find a biclustering structure of children according to their allergy and asthma severity. We then identify a set of SNPs most closely correlated with each sub-group. We subsequently fit a logistic regression model for each group against the healthy controls using benzo[a]pyrene (B[a]P) as a representative airborne carcinogen. Application of such approach in a case-control data set shows that SNP clustering may help to partly explain heterogeneity in children's asthma susceptibility in relation to ambient B[a]P concentration with greater efficiency.
- MeSH
- Algorithms MeSH
- Benzo(a)pyrene toxicity MeSH
- Asthma chemically induced genetics MeSH
- Child MeSH
- Genetic Predisposition to Disease * MeSH
- Gene-Environment Interaction MeSH
- Polymorphism, Single Nucleotide MeSH
- Air Pollutants toxicity MeSH
- Humans MeSH
- Multifactorial Inheritance * MeSH
- Statistics as Topic MeSH
- Unsupervised Machine Learning MeSH
- Case-Control Studies MeSH
- Environmental Exposure adverse effects MeSH
- Air Pollution adverse effects MeSH
- Check Tag
- Child MeSH
- Humans MeSH
- Male MeSH
- Female MeSH
- Publication type
- Journal Article MeSH
- Research Support, Non-U.S. Gov't MeSH
Viruses have been classified as non-living because they require a cellular host to support their replicative processes. Empirical investigations have significantly advanced our understanding of the many strategies employed by viruses to usurp and divert host regulatory and metabolic processes to drive the synthesis and release of infectious particles. The recent emergence of SARS-CoV-2 has permitted us to evaluate and discuss a potentially novel classification of viruses as living entities. The ability of SARS CoV-2 to engender comprehensive regulatory control of integrative cellular processes is strongly suggestive of an inherently dynamic informational registry that is programmatically encoded by linear ssRNA sequences responding to distinct evolutionary constraints. Responses to positive evolutionary constraints have resulted in a single-stranded RNA viral genome that occupies a threedimensional space defined by conserved base-paring resulting from a complex pattern of both secondary and tertiary structures. Additionally, regulatory control of virus-mediated infectious processes relies on extensive protein-protein interactions that drive conformational matching and shape recognition events to provide a functional link between complementary viral and host nucleic acid and protein domains. We also recognize that the seamless integration of complex replicative processes is highly dependent on the precise temporal matching of complementary nucleotide sequences and their corresponding structural and non-structural viral proteins. Interestingly, the deployment of concerted transcriptional and translational activities within targeted cellular domains may be modeled by artificial intelligence (AI) strategies that are inherently fluid, self-correcting, and adaptive at accommodating temporal changes in host defense mechanisms. An in-depth understanding of multiple self-correcting AIassociated viral processes will most certainly lead to novel therapeutic development platforms, notably the design of efficacious neuropharmacological agents to treat chronic CNS syndromes associated with long-COVID. In summary, it appears that viruses, notably SARS-CoV-2, are very much alive due to acquired genetic advantages that are intimately entrained to existential host processes via evolutionarily constrained AI-associated learning paradigms.
- MeSH
- COVID-19 * complications MeSH
- Genomics MeSH
- Humans MeSH
- SARS-CoV-2 genetics MeSH
- Machine Learning MeSH
- Artificial Intelligence MeSH
- Viruses * MeSH
- Check Tag
- Humans MeSH
- Publication type
- Journal Article MeSH
- MeSH
- Drug Industry instrumentation MeSH
- Humans MeSH
- Artificial Intelligence * trends MeSH
- Drug Development trends MeSH
- Check Tag
- Humans MeSH
- Publication type
- Newspaper Article MeSH
- News MeSH
Analyses of user experience in the electronic entertainment industry currently rely on self-reporting methods, such as surveys, ratings, focus group interviews, etc. We argue that self-reporting alone carries inherent problems-mainly the misinterpretation and temporal delay during longer experiments-and therefore, should not be used as a sole metric. To tackle this problem, we propose the possibility of modeling consumer experience using psychophysiological measures and demonstrate how such models can be trained using machine learning methods. We use a machine learning approach to model user experience using real-time data produced by the autonomic nervous system and involuntary psychophysiological responses. Multiple psychophysiological measures, such as heart rate, electrodermal activity, and respiratory activity, have been used in combination with self-reporting to prepare training sets for machine learning algorithms. The training data was collected from 31 participants during hour-long experiment sessions, where they played multiple video-games. Afterwards, we trained and compared the results of four different machine learning models, out of which the best one produced ∼96% accuracy. The results suggest that psychophysiological measures can indeed be used to assess the enjoyment of digital entertainment consumers.
- MeSH
- Algorithms MeSH
- Autonomic Nervous System physiology MeSH
- Adult MeSH
- Galvanic Skin Response physiology MeSH
- Humans MeSH
- Young Adult MeSH
- Psychophysiology methods MeSH
- Heart Rate physiology MeSH
- Machine Learning MeSH
- Video Games psychology MeSH
- Check Tag
- Adult MeSH
- Humans MeSH
- Young Adult MeSH
- Male MeSH
- Female MeSH
- Publication type
- Journal Article MeSH
Východiska: Problémy spojené s farmakologickým výzkumem u dětí, jsou hlavně v nedostatku informací o bezpečnosti a účinnosti podávaných léčiv (Salas et al., 2016). Děti se mohou lišit od dospělých ve fyziologii a patofyziologii nemoci, což zase může vést k rozdílu ve farmakodynamickém a farmakokinetickém profilu léčiva (Caldwell et al., 2004; Kearns et al., 2003). Nevhodné dávkování léků dětem, může způsobovat poruchy růstu a jiné zdravotní komplikace.Cíl: Cílem práce bylo identifikovat komplikace spojené s podáváním léků u dětí. Design studie byla zvolena přehledová studie.Metody: Do přehledové studie byly zahrnuty jen plné texty odborných článků publikované v anglickém jazyce v letech 2011 až 2020. Tyto články prezentovaly výsledky studií, které se vztahují k problematice podávání léků dětem, zaměřující se na komplikace, interakce a nežádoucí účinky, které mohou působit na dětský organismus a následně jej poškodit. Zdrojem dat byly zahraniční odborné licencované elektronické databáze ScienceDirect, CINAHL, PubMed, Google Scholar. Z původních 89 studií bylo vyřazeno 82 studií a do přehledu finální fáze bylo využito 7 studií.Výsledky: Z výsledků přehledové studie je zřejmé, že podávání léků dětem má svá specifika. Je nutné myslet na interakce mezi jednotlivými léčivy a možnost poškození dětského organismu. Sledovat u dětí možné alergické reakce na léčivo. Vyvarovat se podávání některých léků současně z důvodů poškození ledvin a jiných orgánů u dětí. Z přehledu je také patrné, že podávání léků není jen záležitostí zdravotnických pracovníků, ale také rodičů, kteří léky dětem podávají velmi často.Závěr: Přehledová studie prezentuje nejčastější komplikace, které mohou vzniknout při podávání léků u dětí. Které lékové interakce jsou pro dětský organismus nevhodné. Jaké mohou vzniknout nejčastější alergické reakce na léčivo. Všechny tyto komplikace mohou vést k postižení dětského pacienta a mnohdy i nenávratně. Je nutný další výzkum, který bude zaměřený na sledování nežádoucích účinků léčiv na dětský organismus.
Background: Problems connected with children pharmacological research arise from lack of information about the safety and effectiveness of administered medications (Salas et al., 2016). Children vary from adults in physiology and pathophysiology of illnesses, which can lead to differences in the pharmacodynamic and pharmacokinetic profile of the medication (Caldwell et al., 2004; Kearns et al., 2003). Inappropriate dosage of medications to children can cause growth problems and other health complications.Aim: The goal of the study was to identify complications connected with administering medications to children. The study was designed as an overview study.Methods: In the overview study, only full texts of technical articles in English were included which were published in the years 2011-2020. These texts presented results of studies related to issues connected with administering medications to children which were focused on complications, interactions, and side effects, which can affect child's organism and damage it. The source of data was foreign technical licensed electronic databases ScienceDirect, CINAHL, PubMed, Google Scholar. From the initial 89 studies, 82 were excluded and 7 studies were used in the final survey.Results: From the overview study results, it is evident that administering medications to children has its limitations. It is necessary to keep on mind interactions between medications and the possibility of causing damage to child's organism. It is necessary to watch for allergic reactions to medication, and also to avoid administering certain combinations of medications due to the possibility of damaging children's kidneys and other organs. From the survey, it is also apparent that administering medications is not only a matter of healthcare professionals but also of parents, who often give medications to their children.Conclusion: The overview study confirms the most common complications which can occur while administering medications to children. It says what medications interactions are inappropriate for child's organism and what allergic reactions are the most common. All these complications can lead to damaging a child patient, often irreversibly. Further research is necessary that will be focused on monitoring side effects of medications on child's organism.
- MeSH
- Financing, Organized MeSH
- Voice physiology MeSH
- Internet MeSH
- Humans MeSH
- Computer Communication Networks instrumentation trends utilization MeSH
- Signal Processing, Computer-Assisted MeSH
- Persons with Disabilities MeSH
- Aged MeSH
- Speech Recognition Software trends utilization MeSH
- Telephone instrumentation trends utilization MeSH
- Telecommunications instrumentation trends MeSH
- Information Storage and Retrieval methods utilization MeSH
- User-Computer Interface MeSH
- Check Tag
- Humans MeSH
- Aged MeSH
