Search

Abstract Background As studies analyzing the networks and relational structures of research topics in academic fields emerge, studies that apply methods of network and relationship analysis, such as social network analysis (SNA), are drawing more attention. The purpose of this study is to explore the interaction of medical education subjects in the framework of complex systems theory using SNA and to analyze the trends in medical education. Methods The authors extracted keywords using Medical Subject Headings terms from 9,379 research articles (162,866 keywords) published in 1963–2015 in PubMed. They generated an occurrence frequency matrix, calculated relatedness using Weighted Jaccard Similarity, and analyzed and visualized the networks with Gephi software. Results Newly emerging topics by period units were identified as historical trends, and 20 global-level topic clusters were obtained through network analysis. A time-series analysis led to the definition of five historical periods: the waking phase (1963–1975), the birth phase (1976–1990), the growth phase (1991–1996), the maturity phase (1997–2005), and the expansion phase (2006–2015). Conclusions The study analyzed the trends in medical education research using SNA and analyzed their meaning using complex systems theory. During the 53-year period studied, medical education research has been subdivided and has expanded, improved, and changed along with shifts in society’s needs. By analyzing the trends in medical education using the conceptual framework of complex systems theory, the research team determined that medical education is forming a sense of the voluntary order within the field of medicine by interacting with social studies, philosophy, etc., and establishing legitimacy and originality.

Abstract Background Metabolic pathway prediction is one possible approach to address the problem in system biology of reconstructing an organism’s metabolic network from its genome sequence. Recently there have been developments in machine learning-based pathway prediction methods that conclude that machine learning-based approaches are similar in performance to the most used method, PathoLogic which is a rule-based method. One issue is that previous studies evaluated PathoLogic without taxonomic pruning which decreases its performance. Results In this study, we update the evaluation results from previous studies to demonstrate that PathoLogic with taxonomic pruning outperforms previous machine learning-based approaches and that further improvements in performance need to be made for them to be competitive. Furthermore, we introduce mlXGPR, a XGBoost-based metabolic pathway prediction method based on the multi-label classification pathway prediction framework introduced from mlLGPR. We also improve on this multi-label framework by utilizing correlations between labels using classifier chains. We propose a ranking method that determines the order of the chain so that lower performing classifiers are placed later in the chain to utilize the correlations between labels more. We evaluate mlXGPR with and without classifier chains on single-organism and multi-organism benchmarks. Our results indicate that mlXGPR outperform other previous pathway prediction methods including PathoLogic with taxonomic pruning in terms of hamming loss, precision and F1 score on single organism benchmarks. Conclusions The results from our study indicate that the performance of machine learning-based pathway prediction methods can be substantially improved and can even outperform PathoLogic with taxonomic pruning.

In the realm of large language models (LLMs), extending the context window for long text processing is crucial for enhancing performance. This paper introduces SBA-RoPE (Segmented Base Adjustment for Rotary Position Embeddings), a novel approach designed to efficiently extend the context window by segmentally adjusting the base of rotary position embeddings (RoPE). Unlike existing methods, such as Position Interpolation (PI), NTK, and YaRN, SBA-RoPE modifies the base of RoPE across different dimensions, optimizing the encoding of positional information for extended sequences. Through experiments on the Pythia model, we demonstrate the effectiveness of SBA-RoPE in extending context windows, particularly for texts exceeding the original training lengths. We fine-tuned the Pythia-2.8B model on the PG-19 dataset and conducted passkey retrieval and perplexity (PPL) experiments on the Proof-pile dataset to evaluate model performance. Results show that SBA-RoPE maintains or improves model performance when extending the context window, especially on longer text sequences. Compared to other methods, SBA-RoPE exhibits superior or comparable performance across various lengths and tasks, highlighting its potential as an effective technique for context window extension in LLMs.

Abstract The purpose of this study is to apply a machine learning approach to predict whether patients with burning mouth syndrome (BMS) respond to the initial approach and clonazepam therapy based on clinical data. Among the patients with the primary type of BMS who visited the clinic from 2006 to 2015, those treated with the initial approach of detailed explanation regarding home care instruction and use of oral topical lubricants, or who were prescribed clonazepam for a minimum of 1 month were included in this study. The clinical data and treatment outcomes were collected from medical records. Extreme Gradient-Boosted Decision Trees was used for machine learning algorithms to construct prediction models. Accuracy of the prediction models was evaluated and feature importance calculated. The accuracy of the prediction models for the initial approach and clonazepam therapy was 67.6% and 67.4%, respectively. Aggravating factors and psychological distress were important features in the prediction model for the initial approach, and intensity of symptoms before administration was the important feature in the prediction model for clonazepam therapy. In conclusion, the analysis of treatment outcomes in patients with BMS using a machine learning approach showed meaningful results of clinical applicability.

Early diagnosis of lung cancer to increase the survival rate, which is currently at a low range of mid-30%, remains a critical need. Despite this, multi-omics data have rarely been applied to non-small-cell lung cancer (NSCLC) diagnosis. We developed a multi-omics data-affinitive artificial intelligence algorithm based on the graph convolutional network that integrates mRNA expression, DNA methylation, and DNA sequencing data. This NSCLC prediction model achieved a 93.7% macro F1-score, indicating that values for false positives and negatives were substantially low, which is desirable for accurate classification. Gene ontology enrichment and pathway analysis of features revealed that two major subtypes of NSCLC, lung adenocarcinoma and lung squamous cell carcinoma, have both specific and common GO biological processes. Numerous biomarkers (i.e., microRNA, long non-coding RNA, differentially methylated regions) were newly identified, whereas some biomarkers were consistent with previous findings in NSCLC (e.g., SPRR1B). Thus, using multi-omics data integration, we developed a promising cancer prediction algorithm.

We present here COOBoostR, a computational method designed for the putative prediction of the tissue- or cell-of-origin of various cancer types. COOBoostR leverages regional somatic mutation density information and chromatin mark features to be applied to an extreme gradient boosting-based machine-learning algorithm. COOBoostR ranks chromatin marks from various tissue and cell types, which best explain the somatic mutation density landscape of any sample of interest. A specific tissue or cell type matching the chromatin mark feature with highest explanatory power is designated as a potential tissue- or cell-of-origin. Through integrating either ChIP-seq based chromatin data, along with regional somatic mutation density data derived from normal cells/tissue, precancerous lesions, and cancer types, we show that COOBoostR outperforms existing random forest-based methods in prediction speed, with comparable or better tissue or cell-of-origin prediction performance (prediction accuracy—normal cells/tissue: 76.99%, precancerous lesions: 95.65%, cancer cells: 89.39%). In addition, our results suggest a dynamic somatic mutation accumulation at the normal tissue or cell stage which could be intertwined with the changes in open chromatin marks and enhancer sites. These results further represent chromatin marks shaping the somatic mutation landscape at the early stage of mutation accumulation, possibly even before the initiation of precancerous lesions or neoplasia.

Abstract Analysis of compound–protein interactions (CPIs) has become a crucial prerequisite for drug discovery and drug repositioning. In vitro experiments are commonly used in identifying CPIs, but it is not feasible to discover the molecular and proteomic space only through experimental approaches. Machine learning’s advances in predicting CPIs have made significant contributions to drug discovery. Deep neural networks (DNNs), which have recently been applied to predict CPIs, performed better than other shallow classifiers. However, such techniques commonly require a considerable volume of dense data for each training target. Although the number of publicly available CPI data has grown rapidly, public data is still sparse and has a large number of measurement errors. In this paper, we propose a novel method, Multi-channel PINN, to fully utilize sparse data in terms of representation learning. With representation learning, Multi-channel PINN can utilize three approaches of DNNs which are a classifier, a feature extractor, and an end-to-end learner. Multi-channel PINN can be fed with both low and high levels of representations and incorporates each of them by utilizing all approaches within a single model. To fully utilize sparse public data, we additionally explore the potential of transferring representations from training tasks to test tasks. As a proof of concept, Multi-channel PINN was evaluated on fifteen combinations of feature pairs to investigate how they affect the performance in terms of highest performance, initial performance, and convergence speed. The experimental results obtained indicate that the multi-channel models using protein features performed better than single-channel models or multi-channel models using compound features. Therefore, Multi-channel PINN can be advantageous when used with appropriate representations. Additionally, we pretrained models on a training task then finetuned them on a test task to figure out whether Multi-channel PINN can capture general representations for compounds and proteins. We found that there were significant differences in performance between pretrained models and non-pretrained models.

Primary liver tissue cancer types are renowned to display a consistent increase in global disease burden and mortality, thus needing more effective diagnostics and treatments. Yet, integrative research efforts to identify cell-of-origin for these cancers by utilizing human specimen data were poorly established. To this end, we analyzed previously published whole-genome sequencing data for 384 tumor and progenitor tissues along with 423 publicly available normal tissue epigenomic features and single cell RNA-seq data from human livers to assess correlation patterns and extended this information to conduct in-silico prediction of the cell-of-origin for primary liver cancer subtypes. Despite mixed histological features, the cell-of-origin for mixed hepatocellular carcinoma/intrahepatic cholangiocarcinoma subtype was predominantly predicted to be hepatocytic origin. Individual sample-level predictions also revealed hepatocytes as one of the major predicted cell-of-origin for intrahepatic cholangiocarcinoma, thus implying trans-differentiation process during cancer progression. Additional analyses on the whole genome sequencing data of hepatic progenitor cells suggest these cells may not be a direct cell-of-origin for liver cancers. These results provide novel insights on the nature and potential contributors of cell-of-origins for primary liver cancers.

Abstract Background Accumulating evidence suggests that tobacco smoking affects the susceptibility to and severity of chronic periodontitis. Epigenetics may explain the role of smoking in the development and progress of periodontal disease. In this study, we performed transcriptomic and methylomic analyses of non-periodontitis and periodontitis-affected gingival tissues according to smoking status. Methods Human gingival tissues were obtained from 20 patients, including non-smokers with and without periodontitis (n = 5 per group) and smokers with and without periodontitis (n = 5 per group). Total RNA and genomic DNA were isolated, and their quality was validated according to strict standards. The Illumina NextSeq500 sequencing system was used to generate transcriptome and methylome datasets. Results Comprehensive analysis, including between-group correlation, differential gene expression, DNA methylation, gene set enrichment, and protein-protein interaction, indicated that smoking may change the transcription and methylation states of extracellular matrix (ECM) organization-related genes, which exacerbated the periodontal condition. Conclusions Our results suggest that smoking-related changes in DNA methylation patterns and subsequent alterations in the expression of genes coding for ECM components may be causally related to the increased susceptibility to periodontitis in smokers as they could influence ECM organization, which in turn may have an effect on disease characteristics.

Cancer: Chromatin marks underlie mutations for early cancer progression Environmental insults that change how DNA is packaged could lead to mutations responsible for the earliest stages of cancer. Hwajin Lee and colleagues at Seoul National University analyzed whole-genome sequencing data from precancerous tissues (B-cell and esophagus) and the matching cancer types (B-cell leukemia and esophageal cancer) from 173 individuals. They cross checked the mutational profiles against the epigenetic features that shape how DNA is wound into chromosomes, and found that these chromatin marks serve a central role in driving the overall mutation landscape. The authors suggest that gastric acid reflux, which is known to cause a precancerous condition known as Barrett’s esophagus, could be shifting the esophageal cells to become more stomach-like, and the resulting change in chromatin features might be triggering major mutation accumulations that affect subsequent cancer progression.

The forming process of ultra-high-strength steel (UHSS) may cause premature damage to the tool surface due to the high forming pressure. The damage to and wear of the tool surface increase maintenance costs and deteriorate the surface quality of the sheet products. Hence, a reliable prediction model for tool wear can help in the efficient management of the quality and productivity of formed sheet products of UHSS. In this study, a methodology is proposed for predicting the wear behavior of stamping tools that are used in the forming process of DP980 steel sheet. Pin-on-disk tests were conducted based on the Taguchi method to develop the tool wear prediction model. Using statistical analysis based on the signal-to-noise (S/N) ratio and ANOVA result, the contact pressure and the sliding distance were selected as the major contact parameters for tool wear. The Archard wear model has a limitation in predicting the nonlinear behavior of tool wear. Therefore, the power-law nonlinear regression model as a function of the contact pressure and the sliding distance was constructed. To verify the reliability of the constructed tool wear prediction model, the U-draw bending tests were designed. The modified U-draw bending test, which accelerates tool wear, is newly designed to evaluate the tool wear for different contact pressures and sliding distances. The modified die generated a contact pressure four times higher than that of the conventional die from the finite element (FE) simulation results. The tool wear prediction model was validated by comparing the predicted results with the experimental results of DP980 sheets formed using the physical vapor deposition (PVD) CrN-coated STD11 tool steel.