BioAct-Het: A Heterogeneous Siamese Neural Network for Bioactivity Prediction Using Novel Bioactivity Representation.

Drug failure during experimental procedures due to low bioactivity presents a significant challenge. To mitigate this risk and enhance compound bioactivities, predicting bioactivity classes during lead optimization is essential. The existing studies on structure-activity relationships have highlighted the connection between the chemical structures of compounds and their bioactivity. However, these studies often overlook the intricate relationship between drugs and bioactivity, which encompasses multiple factors beyond the chemical structure alone. To address this issue, we propose the BioAct-Het model, employing a heterogeneous siamese neural network to model the complex relationship between drugs and bioactivity classes, bringing them into a unified latent space. In particular, we introduce a novel representation for the bioactivity classes, called Bio-Prof, and enhance the original bioactivity data sets to tackle data scarcity. These innovative approaches resulted in our model outperforming the previous ones. The evaluation of BioAct-Het is conducted through three distinct strategies: association-based, bioactivity class-based, and compound-based. The association-based strategy utilizes supervised learning classification, while the bioactivity class-based strategy adopts a retrospective study evaluation approach. On the other hand, the compound-based strategy demonstrates similarities to the concept of meta-learning. Furthermore, the model's effectiveness in addressing real-world problems is analyzed through a case study on the application of vancomycin and oseltamivir for COVID-19 treatment as well as molnupiravir's potential efficacy in treating COVID-19 patients. The data and code underlying this article are available on https://github.com/CBRC-lab/BioAct-Het. However, data sets were derived from sources in the public domain.

Association of Disease-Modifying Therapies with COVID-19 Susceptibility and Severity in Patients with Multiple Sclerosis: A Systematic Review and Network Meta-Analysis.

Background: We conducted this study to assess the effect of disease-modifying therapies (DMTs) on coronavirus disease (COVID-19) susceptibility and severity in people with multiple sclerosis (MS). Methods: Available studies from PubMed, Scopus, EMBASE, Web of Science, and gray literature, including reference lists and conference abstracts, were searched from December 1, 2019, to July 26, 2021. We included cross-sectional, case-control, and cohort studies assessing the association of DMTs with risk of contracting COVID-19 or its outcomes in MS patients on univariate or multivariate regression analyses. We conducted a network meta-analysis (NMA) to compare the risk of COVID-19 and developing severe infection across DMTs. Results: Out of the initial 3893 records and 1883 conference abstracts, a total of 10 studies were included. Pairwise comparisons showed that none of the DMTs meaningfully affect the risk of acquiring infection. There was significant total heterogeneity and inconsistency across this NMA. In comparison with no DMT, dimethyl fumarate (0.62 (0.42, 0.93)), fingolimod (0.55 (0.32, 0.94)), natalizumab (0.50 (0.31, 0.81)), and interferon (0.42 (0.22, 0.79)) were associated with a decreased risk of severe COVID-19; but, rituximab was observed to increase the risk (1.94 (1.20, 3.12)). Compared to rituximab or ocrelizumab, all DMTs were associated with a decreased risk. Pairwise comparisons showed no differences across other DMTs. Interferon and rituximab were associated with the lowest and highest risks of severe COVID-19. Conclusion: Our study showed an increased risk of severe COVID-19 in patients on rituximab and ocrelizumab. No association with COVID-19 severity across other DMTs was observed.

Tricuspid Annular Plane Systolic Excursion (TAPSE) Measurement by Emergency Medicine Residents in Patients Suspected of Pulmonary Emboli.

OBJECTIVES: We aimed to evaluate the ability of emergency medicine (EM) residents to measure tricuspid annular plane systolic excursion (TAPSE) by M-Mode ultrasound. METHODS: Four EM residents with prior focused cardiac ultrasound (FOCUS) experience participated in 10 hours of hands-on training and then performed TAPSE measurements in adult patients at high risk of having pulmonary emboli (PE) between December 2020 and April 2021. Patients underwent bedside echocardiography by cardiology residents, and a CT pulmonary angiogram (CTPA) was performed to confirm the diagnosis. The agreement between EM and cardiology residents was assessed by intraclass correlation coefficient (ICC). RESULTS: Sixty-six patients were included (mean age = 58.7 ± 16.7 years), of which 28 patients (42.8%) had positive CTPA. The mean TAPSE, measured by EM residents was 16.36 ± 1.59 mm in the PE positive group and 21.68 ± 2.87 mm in the PE negative group (P-value = <.0001). The mean ± SD TAPSE, measured by cardiology residents, was 17.7 ± 1.98 mm in the PE group and 22.5 ± 3.6 mm in the PE negative group (P-value = <.0001). There was significant agreement between EM and cardiology residents in terms of measuring TAPSE (ICC = 0.91, 95% confidence interval [CI] = 0.80-0.95). The receiver operating characteristic (ROC) curves of TAPSE for diagnosing PE revealed that TAPSE, measured by EM residents, had a high level of accuracy (area under the ROC curve [AUC] = 0.93, 95% CI, 0.878-0.99). CONCLUSIONS: EM residents can perform M-Mode TAPSE measurement in suspected PE cases after 10 hours of hands-on training. TAPSE measurement should be added to routine FOCUS protocols, especially when there is suspicion of PE.

Students' medical ethics rounds: a combinatorial program for medical ethics education.

It has long been a common goal for both medical educators and ethicists to develop effective methods or programs for medical ethics education. The current lecture-based courses of medical ethics programs in medical schools are demonstrated as insufficient models for training "good doctors''. In this study, we introduce an innovative program for medical ethics education in an extra-curricular student-based design named Students' Medical Ethics Rounds (SMER). In SMER, a combination of educational methods, including theater-based case presentation, large group discussion, expert opinions, role playing and role modeling were employed. The pretest-posttest experimental design was used to assess the impact of interventions on the participants' knowledge and attitude regarding selected ethical topics. A total of 335 students participated in this study and 86.57% of them filled the pretest and posttest forms. We observed significant improvements in the knowledge (P < 0.0500) and attitude (P < 0.0001) of participants. Interestingly, 89.8% of participants declared that their confidence regarding how to deal with the ethical problems outlined in the sessions was increased. All of the applied educational methods were reported as helpful. We found that SMER might be an effective method of teaching medical ethics. We highly recommend the investigation of the advantages of SMER in larger studies and interdisciplinary settings.