Search

Abstract Background Deep learning-based drug-target affinity (DTA) prediction methods have shown impressive performance, despite a high number of training parameters relative to the available data. Previous studies have highlighted the presence of dataset bias by suggesting that models trained solely on protein or ligand structures may perform similarly to those trained on complex structures. However, these studies did not propose solutions and focused solely on analyzing complex structure-based models. Even when ligands are excluded, protein-only models trained on complex structures still incorporate some ligand information at the binding sites. Therefore, it is unclear whether binding affinity can be accurately predicted using only compound or protein features due to potential dataset bias. In this study, we expanded our analysis to comprehensive databases and investigated dataset bias through compound and protein feature-based methods using multilayer perceptron models. We assessed the impact of this bias on current prediction models and proposed the binding affinity similarity explorer (BASE) web service, which provides bias-reduced datasets. Results By analyzing eight binding affinity databases using multilayer perceptron models, we confirmed a bias where the compound-protein binding affinity can be accurately predicted using compound features alone. This bias arises because most compounds show consistent binding affinities due to high sequence or functional similarity among their target proteins. Our Uniform Manifold Approximation and Projection analysis based on compound fingerprints further revealed that low and high variation compounds do not exhibit significant structural differences. This suggests that the primary factor driving the consistent binding affinities is protein similarity rather than compound structure. We addressed this bias by creating datasets with progressively reduced protein similarity between the training and test sets, observing significant changes in model performance. We developed the BASE web service to allow researchers to download and utilize these datasets. Feature importance analysis revealed that previous models heavily relied on protein features. However, using bias-reduced datasets increased the importance of compound and interaction features, enabling a more balanced extraction of key features. Conclusions We propose the BASE web service, providing both the affinity prediction results of existing models and bias-reduced datasets. These resources contribute to the development of generalized and robust predictive models, enhancing the accuracy and reliability of DTA predictions in the drug discovery process. BASE is freely available online at https://synbi2024.kaist.ac.kr/base .

Virtual reality is a novel technology that provides users with an immersive experience in 3D virtual environments. The use of virtual reality is expanding in the medical and nursing settings to support treatment and promote wellness. Nursing has primarily used virtual reality for nursing education, but nurses might incorporate this technology into clinical practice to enhance treatment experience of patients and caregivers. Thus, it is important for nurses to understand what virtual reality and its features are, how this technology has been used in the health care field, and what future efforts are needed in practice and research for this technology to benefit nursing. In this article, we provide a brief orientation to virtual reality, describe the current application of this technology in multiple clinical scenarios, and present implications for future clinical practice and research in nursing.

Abstract Background Oncometabolites, often generated as a result of a gene mutation, show pro-oncogenic function when abnormally accumulated in cancer cells. Identification of such mutation-associated metabolites will facilitate developing treatment strategies for cancers, but is challenging due to the large number of metabolites in a cell and the presence of multiple genes associated with cancer development. Results Here we report the development of a computational workflow that predicts metabolite-gene-pathway sets. Metabolite-gene-pathway sets present metabolites and metabolic pathways significantly associated with specific somatic mutations in cancers. The computational workflow uses both cancer patient-specific genome-scale metabolic models (GEMs) and mutation data to generate metabolite-gene-pathway sets. A GEM is a computational model that predicts reaction fluxes at a genome scale and can be constructed in a cell-specific manner by using omics data. The computational workflow is first validated by comparing the resulting metabolite-gene pairs with multi-omics data (i.e., mutation data, RNA-seq data, and metabolome data) from acute myeloid leukemia and renal cell carcinoma samples collected in this study. The computational workflow is further validated by evaluating the metabolite-gene-pathway sets predicted for 18 cancer types, by using RNA-seq data publicly available, in comparison with the reported studies. Therapeutic potential of the resulting metabolite-gene-pathway sets is also discussed. Conclusions Validation of the metabolite-gene-pathway set-predicting computational workflow indicates that a decent number of metabolites and metabolic pathways appear to be significantly associated with specific somatic mutations. The computational workflow and the resulting metabolite-gene-pathway sets will help identify novel oncometabolites and also suggest cancer treatment strategies.

Abstract Background Acute myeloid leukemia (AML) is characterized by clonal heterogeneity, leading to frequent relapses and drug resistance despite intensive clinical therapy. Although AML's clonal architecture has been addressed in many studies, practical monitoring of dynamic changes in those subclones during relapse and treatment is still understudied. Method Fifteen longitudinal bone marrow (BM) samples were collected from three relapsed and refractory (R/R) AML patients. Using droplet digital polymerase chain reaction (ddPCR), the frequencies of patient's leukemic variants were assessed in seven cell populations that were isolated from each BM sample based on cellular phenotypes. By quantifying mutant clones at the diagnosis, remission, and relapse stages, the distribution of AML subclones was sequentially monitored. Results Minimal residual (MR) leukemic subclones exhibit heterogeneous distribution among BM cell populations, including mature leukocyte populations. During AML progression, these subclones undergo active phenotypic transitions and repopulate into distinct cell population regardless of normal hematopoiesis hierarchic order. Of these, MR subclones in progenitor populations of patient BM predominantly carry MR leukemic properties, leading to more robust expansion and stubborn persistence than those in mature populations. Moreover, a minor subset of MR leukemic subclones could be sustained at an extremely low frequency without clonal expansion during relapse. Conclusions In this study, we observed treatment persistent MR leukemic subclones and their phenotypic changes during the treatment process of R/R AML patients. This underscores the importance of preemptive inhibition of clonal promiscuity in R/R AML, proposing a practical method for monitoring AML MR subclones.

Abstract Background Therapy-related myeloid neoplasm (T-MN) rarely occurs among cancer survivors, and was characterized by poor prognosis. T-MN has germline predisposition in a considerable proportion. Here, clinical characteristics and germline/somatic variant profiles in T-MN patients were investigated, and the findings were compared with those of previous studies. Methods A review of medical records, cytogenetic study, targeted sequencing by next-generation sequencing, and survival analysis were performed on 53 patients with T-MN at a single institution in Korea. Results The patients were relatively younger compared to T-MN patients in other studies. Our T-MN patients showed a high frequency of complex karyotypes, −5/del(5q), and −7/del(7q), which was similar to the Japanese study group but higher than the Australian study group. The most common primary disease was non-Hodgkin lymphoma, followed by breast cancer. The detailed distributions of primary diseases were different across study groups. Seven patients (13.2%) harbored deleterious presumed/potential germline variants in cancer predisposition genes (CPG) such as BRIP1, CEBPA, DDX41, FANCM, NBN, NF1, and RUNX1. In the somatic variant profile, TP53 was the most frequently mutated gene, which was consistent with the previous studies about T-MN. However, the somatic variant frequency in our study group was lower than in other studies. Adverse factors for overall survival were male sex, older age, history of previous radiotherapy, previous longer cytotoxic therapy, and −5/del(5q). Conclusion The findings of our study corroborate important information about T-MN patients. As well as a considerable predisposition to CPG, the clinical characteristics and somatic variant profile showed distinctive patterns. Germline variant testing should be recommended for T-MN patients. If the T-MN patients harbor pathogenic germline variants, the family members for stem cell donation should be screened for carrier status through germline variant testing to avoid donor-derived myeloid neoplasm. For the prediction of the prognosis in T-MN patients, sex, age, past treatment history, and cytogenetic findings can be considered.

OBJECTIVES: To evaluate an interactive electronic Cancer Survivorship Patient Engagement Toolkit (CaS-PET) using a single-group pre-/post-test design. SAMPLE & SETTING: 30 cancer survivors with a mean age of 56.5 years (SD = 13.6) were recruited from the University of Maryland Medical Center in Baltimore. METHODS & VARIABLES: CaS-PET was designed to deliver survivorship care plans (SCPs) with multifactorial support and comprised of SCPs, biweekly follow-up using patient portal e-messages, and online resources. Outcomes included healthrelated quality of life, symptom burden, impact of cancer, fear of recurrence, physical activities, dietary behavior, patient--provider communication, adherence to treatment, and e-health literacy. RESULTS: At three months, there was a significant improvement in quality of life, physical symptom burden, and total symptom burden. IMPLICATIONS FOR NURSING: Findings suggest an excellent potential for using CaS-PET for survivors who are in transition from treatment to survivorship. [ABSTRACT FROM AUTHOR]