A Novel Deep Learning Model for Drug-drug Interactions.

INTRODUCTION: Drug-drug interactions (DDIs) can lead to adverse events and compromised treatment efficacy that emphasize the need for accurate prediction and understanding of these interactions. METHODS: In this paper, we propose a novel approach for DDI prediction using two separate message-passing neural network (MPNN) models, each focused on one drug in a pair. By capturing the unique characteristics of each drug and their interactions, the proposed method aims to improve the accuracy of DDI prediction. The outputs of the individual MPNN models combine to integrate the information from both drugs and their molecular features. Evaluating the proposed method on a comprehensive dataset, we demonstrate its superior performance with an accuracy of 0.90, an area under the curve (AUC) of 0.99, and an F1-score of 0.80. These results highlight the effectiveness of the proposed approach in accurately identifying potential drugdrug interactions. RESULTS: The use of two separate MPNN models offers a flexible framework for capturing drug characteristics and interactions, contributing to our understanding of DDIs. The findings of this study have significant implications for patient safety and personalized medicine, with the potential to optimize treatment outcomes by preventing adverse events. CONCLUSION: Further research and validation on larger datasets and real-world scenarios are necessary to explore the generalizability and practicality of this approach.

Antibiotic hyper-resistance in a class I aminoacyl-tRNA synthetase with altered active site signature motif.

Antibiotics target key biological processes that include protein synthesis. Bacteria respond by developing resistance, which increases rapidly due to antibiotics overuse. Mupirocin, a clinically used natural antibiotic, inhibits isoleucyl-tRNA synthetase (IleRS), an enzyme that links isoleucine to its tRNAIle for protein synthesis. Two IleRSs, mupirocin-sensitive IleRS1 and resistant IleRS2, coexist in bacteria. The latter may also be found in resistant Staphylococcus aureus clinical isolates. Here, we describe the structural basis of mupirocin resistance and unravel a mechanism of hyper-resistance evolved by some IleRS2 proteins. We surprisingly find that an up to 103-fold increase in resistance originates from alteration of the HIGH motif, a signature motif of the class I aminoacyl-tRNA synthetases to which IleRSs belong. The structural analysis demonstrates how an altered HIGH motif could be adopted in IleRS2 but not IleRS1, providing insight into an elegant mechanism for coevolution of the key catalytic motif and associated antibiotic resistance.

Comprehensive Review on Drug-target Interaction Prediction - Latest Developments and Overview.

Drug-target interactions (DTIs) are an important part of the drug development process. When the drug (a chemical molecule) binds to a target (proteins or nucleic acids), it modulates the biological behavior/function of the target, returning it to its normal state. Predicting DTIs plays a vital role in the drug discovery (DD) process as it has the potential to enhance efficiency and reduce costs. However, DTI prediction poses significant challenges and expenses due to the time-consuming and costly nature of experimental assays. As a result, researchers have increased their efforts to identify the association between medications and targets in the hopes of speeding up drug development and shortening the time to market. This paper provides a detailed discussion of the initial stage in drug discovery, namely drug-target interactions. It focuses on exploring the application of machine learning methods within this step. Additionally, we aim to conduct a comprehensive review of relevant papers and databases utilized in this field. Drug target interaction prediction covers a wide range of applications: drug discovery, prediction of adverse effects and drug repositioning. The prediction of drugtarget interactions can be categorized into three main computational methods: docking simulation approaches, ligand-based methods, and machine-learning techniques.

Automating Drug Discovery using Machine Learning.

Drug discovery and development have been sped up because of the advances in computational science. In both industry and academics, artificial intelligence (AI) has been widely used. Machine learning (ML), an important component of AI, has been used in a variety of domains, including data production and analytics. One area that stands to gain significantly from this achievement of machine learning is drug discovery. The process of bringing a new drug to market is complicated and time-consuming. Traditional drug research takes a long time, costs a lot of money, and has a high failure rate. Scientists test millions of compounds, but only a small number make it to preclinical or clinical testing. It is crucial to embrace innovation, especially automated technologies, to lessen the complexity involved in drug research and avoid the high cost and lengthy process of bringing a medicine to the market. A rapidly developing field, a branch of artificial intelligence called machine learning (ML), is being used by numerous pharmaceutical businesses. Automating repetitive data processing and analysis processes can be achieved by incorporating ML methods into the drug development process. ML techniques can be used at numerous stages of the drug discovery process. In this study, we will discuss the steps of drug discovery and methods of machine learning that can be applied in these steps, as well as give an overview of each of the research works in this field.

Perspectives on tolerability and reasonableness.

Judgements on tolerability and reasonableness are central to the optimisation of protection. There are currently several international developments regarding these key considerations which will contribute to the review and evolution of the system of radiological protection. The IRPA15 International Congress brought together the principal issues currently under discussion, and the outcome of these discussions is presented.

Application of machine learning in screening for congenital heart diseases using fetal echocardiography.

There is a growing body of literature supporting the utilization of machine learning (ML) to improve diagnosis and prognosis tools of cardiovascular disease. The current study was to investigate the impact that the ML framework may have on the sensitivity of predicting the presence or absence of congenital heart disease (CHD) using fetal echocardiography. A comprehensive fetal echocardiogram including 2D cardiac chamber quantification, valvar assessments, assessment of great vessel morphology, and Doppler-derived blood flow interrogation was recorded. The postnatal echocardiogram was used to ascertain the diagnosis of CHD. A random forest (RF) algorithm with a nested tenfold cross-validation was used to train models for assessing the presence of CHD. The study population was derived from a database of 3910 singleton fetuses with maternal age of 28.8 ± 5.2 years and gestational age at the time of fetal echocardiography of 22.0 weeks (IQR 21-24). The proportion of CHD was 14.1% for the studied cohort confirmed by post-natal echocardiograms. Our proposed RF-based framework provided a sensitivity of 0.85, a specificity of 0.88, a positive predictive value of 0.55 and a negative predictive value of 0.97 to detect the CHD with the mean of mean ROC curves of 0.94 and the mean of mean PR curves of 0.84. Additionally, six first features, including cardiac axis, peak velocity of blood flow across the pulmonic valve, cardiothoracic ratio, pulmonary valvar annulus diameter, right ventricular end-diastolic diameter, and aortic valvar annulus diameter, are essential features that play crucial roles in adding more predictive values to the model in detecting patients with CHD. ML using RF can provide increased sensitivity in prenatal CHD screening with very good performance. The incorporation of ML algorithms into fetal echocardiography may further standardize the assessment for CHD.

From a policy perspective: what is at stake?

This paper does not necessarily reflect the views of the International Commission on Radiological Protection.What is at stake? It was one of the most frequently asked questions in a series of fora with concerned parties on the rehabilitation of living conditions in the aftermath of the accident at Fukushima Daiichi nuclear power plant. It was obvious that radioactive contamination was the source of the problem, and people were at a loss over how to cope with the situation. Various measures were taken under such circumstances, including detailed radiation monitoring, a decontamination programme to reduce the level of radiation in the living environment, and activities related to communication about radiation risk. Nevertheless, this question was asked repeatedly. Measures against radiation exposure were certainly necessary, but it is a reality that they were not enough to solve the difficulties experienced by people in the affected areas. This article presents the author's personal view of the underlying reasons for this, and discusses the way to facilitate recovery after a nuclear accident.

[Gastric adenocarcinoma with enteroblastic differentiation and elevated serum alpha fetoprotein].

Objective: To study the proportion and clinicopathological characteristics of gastric adenocarcinoma with enteroblastic differentiation (GAED) in gastric cancers showing an elevated serum alpha fetoprotein(AFP). Methods: A total of 724 resected gastric adenocarcinomas were collected from 2008 to 2018 at the 904 Hospital of Joint Service Support Force, and cases with pre-operative serum AFP>10 µg/L were screened. From the cases with elevated serum AFP, GAED cases were further evaluated based on morphology. Then the clincopathological features and immunohistochemical phenotypes of GAED were reviewed. In addition, the amplification of HER2 gene was detected with fluorescence in situ hybridization(FISH). When overall survival (OS) and progression-free survival (PFS) of GAED were analyzed, 289 cases ordinary gastric adenocarcinoma with normal serum AFP were employed as a control. Results: The percentage of GAED was 44% (11/25) in gastric cancers with elevated serum AFP. GAED was histologically tubular or papillary with clear cytoplasm, and some GAED cases showed cystadenoid structure similar to embryo sac (5 cases), homogeneous eosinophilic granules (4 cases) and intragland ulareosinophilic material (6 cases). All 11 GAED cases had lymph node metastasis. Liver metastasis and vascular thrombus were observed in 2 cases and 5 cases respectively. GAED was immunohistochemically positive for CDX2 (11/11), CD10 (8/11) and MUC2(3/11), which were intestinal epithelium differentiation markers. Meanwhile, primitive markers SALL4 (8/11), GPC3 (7/11) and AFP (5/11) were also expressed in GAED, and HER2 gene amplification was found in 3 cases (3/11) of GAED. Lastly, the PFS of GAED were significantly shorter than that of the control group (P=0.02), while OS was not statistically different between these two groups (P=0.99). Conclusions: Patients with GAED usually have a higher rate of elevated serum AFP in gastric adenocarcinoma, and the cancer exhibites features of both intestinal and primitive differentiation. As GAED is highly invasive, the prognosis of GAED may be poor. For GAED, the diagnosis of well-differentiated or moderately-differentiated adenocarcinoma should be avoided, because this diagnosis leads to underestimated malignant potential.

Pharmacist-Led Intervention to Enhance Medication Adherence in Patients With Acute Coronary Syndrome in Vietnam: A Randomized Controlled Trial.

Background: Patient adherence to cardioprotective medications improves outcomes of acute coronary syndrome (ACS), but few adherence-enhancing interventions have been tested in low-income and middle-income countries. Objectives: We aimed to assess whether a pharmacist-led intervention enhances medication adherence in patients with ACS and reduces mortality and hospital readmission. Methods: We conducted a randomized controlled trial in Vietnam. Patients with ACS were recruited, randomized to the intervention or usual care prior to discharge, and followed 3 months after discharge. Intervention patients received educational and behavioral interventions by a pharmacist. Primary outcome was the proportion of adherent patients 1 month after discharge. Adherence was a combined measure of self-reported adherence (the 8-item Morisky Medication Adherence Scale) and obtaining repeat prescriptions on time. Secondary outcomes were (1) the proportion of patients adherent to medication; (2) rates of mortality and hospital readmission; and (3) change in quality of life from baseline assessed with the European Quality of Life Questionnaire - 5 Dimensions - 3 Levels at 3 months after discharge. Logistic regression was used to analyze data. Registration: ClinicalTrials.gov (NCT02787941). Results: Overall, 166 patients (87 control, 79 intervention) were included (mean age 61.2 years, 73% male). In the analysis excluding patients from the intervention group who did not receive the intervention and excluding all patients who withdrew, were lost to follow-up, died or were readmitted to hospital, a greater proportion of patients were adherent in the intervention compared with the control at 1 month (90.0% vs. 76.5%; adjusted OR = 2.77; 95% CI, 1.01-7.62) and at 3 months after discharge (90.2% vs. 77.0%; adjusted OR = 3.68; 95% CI, 1.14-11.88). There was no significant difference in median change of EQ-5D-3L index values between intervention and control [0.000 (0.000; 0.275) vs. 0.234 (0.000; 0.379); p = 0.081]. Rates of mortality, readmission, or both were 0.8, 10.3, or 11.1%, respectively; with no significant differences between the 2 groups. Conclusion: Pharmacist-led interventions increased patient adherence to medication regimens by over 13% in the first 3 months after ACS hospital discharge, but not quality of life, mortality and readmission. These results are promising but should be tested in other settings prior to broader dissemination.

The mandate and work of ICRP Committee 1 on radiation effects.

The aim of the International Commission on Radiological Protection (ICRP) is to protect humans against cancer and other diseases and effects associated with exposure to ionising radiation, and also to protect the environment, without unduly limiting the beneficial use of ionising radiation. As of the second half of 2017, four committees are contributing to the overall mission of ICRP, including Committee 1 (Radiation Effects). The role of Committee 1 includes consideration of the risks and mechanisms of induction of cancer and heritable disease; discussion of the risks, severity, and mechanisms of induction of tissue/organ damage and developmental defects; and review of the effects of ionising radiation on non-human biota at population level. This paper gives an overview of the recent activities of Committee 1, and discusses the focus of its active task groups.

Large marine protected areas represent biodiversity now and under climate change.

Large marine protected areas (>30,000 km2) have a high profile in marine conservation, yet their contribution to conservation is contested. Assessing the overlap of large marine protected areas with 14,172 species, we found large marine protected areas cover 4.4% of the ocean and at least some portion of the range of 83.3% of the species assessed. Of all species within large marine protected areas, 26.9% had at least 10% of their range represented, and this was projected to increase to 40.1% in 2100. Cumulative impacts were significantly higher within large marine protected areas than outside, refuting the critique that they only occur in pristine areas. We recommend future large marine protected areas be sited based on systematic conservation planning practices where possible and include areas beyond national jurisdiction, and provide five key recommendations to improve the long-term representation of all species to meet critical global policy goals (e.g., Convention on Biological Diversity's Aichi Targets).

A report from the 2013 international symposium: the evaluation of the effects of low-dose radiation exposure in the life span study of atomic bomb survivors and other similar studies.

The RERF International Low-Dose Symposium was held on 5-6 December 2013 at the RERF campus in Hiroshima, Japan, to discuss the issues facing the Life Span Study (LSS) and other low-dose studies. Topics included the current status of low-dose risk detection, strategies for low-dose epidemiological and statistical research, methods to improve communication between epidemiologists and biologists, and the current status of radiological studies and tools. Key points made by the participants included the necessity of pooling materials over multiple studies to gain greater insight where data from single studies are insufficient; generating models that reflect epidemiological, statistical, and biological principles simultaneously; understanding confounders and effect modifiers in the current data; and taking into consideration less studied factors such as the impact of dose rate. It is the hope of all participants that this symposium be used as a trigger for further studies, especially those using pooled data, in order to reach a greater understanding of the health effects of low-dose radiation.

Critical research needs for managing coral reef marine protected areas: perspectives of academics and managers.

Marine protected areas (MPAs) are a primary policy instrument for managing and protecting coral reefs. Successful MPAs ultimately depend on knowledge-based decision making, where scientific research is integrated into management actions. Fourteen coral reef MPA managers and sixteen academics from eleven research, state and federal government institutions each outlined at least five pertinent research needs for improving the management of MPAs situated in Australian coral reefs. From this list of 173 key questions, we asked members of each group to rank questions in order of urgency, redundancy and importance, which allowed us to explore the extent of perceptional mismatch and overlap among the two groups. Our results suggest the mismatch among MPA managers and academics is small, with no significant difference among the groups in terms of their respective research interests, or the type of questions they pose. However, managers prioritised spatial management and monitoring as research themes, whilst academics identified climate change, resilience, spatial management, fishing and connectivity as the most important topics. Ranking of the posed questions by the two groups was also similar, although managers were less confident about the achievability of the posed research questions and whether questions represented a knowledge gap. We conclude that improved collaboration and knowledge transfer among management and academic groups can be used to achieve similar objectives and enhance the knowledge-based management of MPAs.

Development of a web-based CT dose calculator: WAZA-ARI.

A web-based computed tomography (CT) dose calculation system (WAZA-ARI) is being developed based on the modern techniques for the radiation transport simulation and for software implementation. Dose coefficients were calculated in a voxel-type Japanese adult male phantom (JM phantom), using the Particle and Heavy Ion Transport code System. In the Monte Carlo simulation, the phantom was irradiated with a 5-mm-thick, fan-shaped photon beam rotating in a plane normal to the body axis. The dose coefficients were integrated into the system, which runs as Java servlets within Apache Tomcat. Output of WAZA-ARI for GE LightSpeed 16 was compared with the dose values calculated similarly using MIRD and ICRP Adult Male phantoms. There are some differences due to the phantom configuration, demonstrating the significance of the dose calculation with appropriate phantoms. While the dose coefficients are currently available only for limited CT scanner models and scanning options, WAZA-ARI will be a useful tool in clinical practice when development is finalised.

Estimation of the number of CT procedures based on a nationwide survey in Japan.

In 2007, a nationwide survey was conducted to determine the frequency of CT procedures in Japan in order to compare the current use of CT among developed countries. The frequency of adult and pediatric CT scans was estimated using a model based on the results of the survey. Survey questionnaires were sent to 2,266 CT facilities: 1,068 government hospitals and 1,198 other hospitals and non-hospital medical centers. The questionnaire requested information including the number of beds, outpatients per day, type of CT scanner, various body regions scanned, and the number of scans performed. The results of the study indicate that the number of CT procedures was closely correlated with the number of hospital beds. The authors estimate that approximately 20.5 million procedures were performed in 2005 and 21.2 million in 2006. The number of pediatric CT procedures was calculated by multiplying the total number of CT procedures by the estimated fraction of pediatric (0-15 y) CT procedures. Annual pediatric CT procedures were estimated to have been approximately 580,000 in 2005 and 600,000 in 2006. The present study indicates that the number of procedures per thousand of population, 166 for total CT and 32-34 for pediatric CT, is lower in Japan than in the U.S.

Improvement of cardio-ankle vascular index by glimepiride in type 2 diabetic patients.

AIMS: Glimepiride, a third generation sulfonylurea (SU), is known to have extrapancreatic effects, but its vascular effect is unclear. We investigated the efficacy of glimepiride in improving arterial stiffness assessed by cardio-ankle vascular index (CAVI) in type 2 diabetic patients, compared with glibenclamide, a conventional SU. METHODS: Forty type 2 diabetic patients were randomly assigned to two groups. One group was administered glimepiride 1.5 mg/day, and the other group was administered glibenclamide 1.25 mg/day for 6 months. RESULTS: No significant difference in hypoglycaemic effect was observed between two groups. CAVI significantly decreased only in glimepiride group (9.4 ± 1.4→8.9 ± 0.8, p < 0.05). Decrease in CAVI was greater in glimepiride group than in glibenclamide group (-0.50 ± 0.98 vs. -0.04 ± 0.57, p = 0.048). Urinary 8-hydroxy-2'-deoxyguanosine (8-OHdG) decreased in glimepiride group and increased in glibenclamide group, and the changes were significantly different between groups (-1.5 ± 3.5 vs. + 1.8 ± 3.6, p = 0.009); whereas serum lipoprotein lipase mass increased in glibenclamide group and decreased in glibenclamide group, and the changes tended to be different between groups (+ 2.1 ± 19.1 vs. -7.4 ± 19.2, p = 0.096). Change in urinary 8-OHdG was a significant independent predictor for change in CAVI in all subjects. CONCLUSIONS: These results suggest that glimepiride improves CAVI compared with glibenclamide. Reduced oxidative stress and improved insulin resistance may contribute to the improvement of CAVI by glimerpiride.

Implication of replicative stress-related stem cell ageing in radiation-induced murine leukaemia.

BACKGROUND: The essential aetiology of radiation-induced acute myeloid leukaemia (AML) in mice is the downregulation of the transcription factor PU.1. The causative mutation of the PU.1-endocing Sfpi1 gene consists mostly of C:G to T:A transitions at a CpG site and is likely to be of spontaneous origin. To work out a mechanism underlying the association between radiation exposure and the AML induction, we have hypothesised that replicative stress after irradiation accelerates the ageing of haematopoietic stem cells (HSCs), and the ageing-related decline in DNA repair could affect the spontaneous mutation rates. METHODS: Mathematical model analysis was conducted to examine whether and to what extent the cell kinetics of HSCs can be modified after irradiation. The haematopoietic differentiation process is expressed as a mathematical model and the cell-kinetics parameters were estimated by fitting the simulation result to the assay data. RESULTS: The analysis revealed that HSCs cycle vigourously for more than a few months after irradiation. The estimated number of cell divisions per surviving HSC in 3 Gy-exposed mice reached as high as ten times that of the unexposed. INTERPRETATION: The mitotic load after 3 Gy irradiation seems to be heavy enough to accelerate the ageing of HSCs and the hypothesis reasonably explains the leukaemogenic process.

Intracellular ABC transporter A3 confers multidrug resistance in leukemia cells by lysosomal drug sequestration.

Multidrug resistance (MDR) seriously limits the efficacy of chemotherapy in patients with cancer and leukemia. Active transport across membranes is essential for such cellular drug resistance, largely provided by ATP-binding cassette (ABC) transport proteins. Intracellular drug sequestration contributes to MDR; however, a genuine intracellular ABC transport protein with MDR function has not yet been identified. Analyzing the intrinsic drug efflux capacity of leukemic stem cells, we found the ABC transporter A3 (ABCA3) to be expressed consistently in acute myeloid leukemia (AML) samples. Greater expression of ABCA3 is associated with unfavorable treatment outcome, and in vitro, elevated expression induces resistance toward a broad spectrum of cytostatic agents. ABCA3 remains localized within the limiting membranes of lysosomes and multivesicular bodies, in which cytostatics are efficiently sequestered. In addition to AML, we also detected ABCA3 in a panel of lymphohematopoietic tissues and transformed cell lines. In conclusion, we identified subcellular drug sequestration mediated by the genuinely intracellular ABCA3 as being a clinically relevant mechanism of intrinsic MDR.

Systematic review of the diagnostic accuracy of 201Tl single photon emission computed tomography in the detection of recurrent glioma.

OBJECTIVE: To determine the diagnostic accuracy of 201Tl SPECT in the detection of tumour recurrence in patients with previous radiotherapy for supratentorial glioma. METHODS: The databases of PubMed and Embase were searched for relevant studies. Two reviewers independently selected and extracted data on study characteristics, quality and accuracy of studies. Studies were included if they comprised at least six eligible patients who underwent 201Tl SPECT (index test) and in whom (histo)pathological confirmation (reference test) of the suspected brain lesion was obtained. Because of the methodological and statistical heterogeneity of the included studies, a quantitative meta-analysis was not performed. Instead, for every individual study, the sensitivity, specificity and diagnostic odds ratio of 201Tl SPECT was calculated. RESULTS: Eight studies met the inclusion criteria. Only one was considered of high methodological quality. Methodological limitations referred most notably to blinding and patient selection. The diagnostic odds ratio was greater than 1 in all studies included, with a broad range (2-351), and relatively wide 95% confidence intervals. The sensitivity of 201Tl SPECT ranged from 0.43 to 1.00, and the specificity from 0.25 to 1.00. CONCLUSION: 201Tl SPECT seems a valuable method in the detection of tumour recurrence in patients treated with radiotherapy for supratentorial glioma. However, the evidence is not very robust because of the low quality and high heterogeneity of the studies included. Future studies are warranted to further explore the diagnostic potential of 201Tl SPECT, and to determine optimum thresholds for the detection of glioma recurrence.