Journal of Integrative Bioinformatics最新文献

This study investigates the application of deep learning techniques for segmenting glands in histopathological images of colorectal cancer. We trained two convolutional neural network models, U-Net and DCAN, on a combination of the GlaS and CRAG datasets to enhance generalization across diverse histological appearances, selecting DCAN for its superior accuracy in delineating gland boundaries. The goal was to achieve robust gland segmentation applicable to whole slide images (WSIs) from The Cancer Genome Atlas (TCGA). Using the segmented glands, we extracted patient-level morphological features and used them to predict survival outcomes. A Cox proportional hazards model was trained on these features and achieved a high concordance index, indicating strong predictive performance. Patients were then stratified into high- and low-risk groups, with significant differences in survival distributions (log-rank p-value: 0.01317). In addition, we benchmarked our models against state-of-the-art gland segmentation methods on GlaS and CRAG, highlighting the trade-off between domain-specific accuracy and cross-dataset robustness.

Sustainable software development requires the software to remain accessible and maintainable over long time. This is particularly challenging in a scientific context. For example, fewer than one third of tools and platforms for biological network representation, analysis, and visualisation have been available and supported over a period of 15 years. One of those tools is Vanted, which has been developed and actively supported over the past 20 years. In this work, we discuss sustainable software development in science and investigate which software tools for biological network representation, analysis, and visualisation are maintained over a period of at least 15 years. With Vanted as a case study, we highlight five key insights that we consider crucial for sustainable, long-term software development and software maintenance in science.

This study investigates the gut microbiome and metabolome of asthma patients treated with inhaled corticosteroids (ICS), some of whom experience adverse side effects. We analyzed stool samples from 24 participants, divided into three cohorts: asthma patients with side effects, those without, and healthy controls. Using next-generation sequencing and LC-MS/MS metabolomics, we identified significant differences in bacterial species and metabolites. Multi-Omics Factor Analysis (MOFA) and Global Sensitivity Analysis-Partial Rank Correlation Coefficient (GSA-PRCC) provided insights into key contributors to side effects, such as tryptophan depletion and altered linolenate and glucose-1-phosphate levels. The study proposes dietary or probiotic interventions to mitigate side effects. Despite the limited sample size, these findings provide a basis for personalized asthma management approaches. Further studies are required to confirm initial fundings.

The rapid advancement of Next-Generation Sequencing (NGS) technologies has revolutionized the field of genomics, producing large volumes of data that necessitate sophisticated analytical techniques. This paper introduces a Deep Learning model designed to predict the pathogenicity of genetic variants, a vital component in advancing personalized medicine. The model is trained on a dataset derived from the analysis of NGS outputs, containing a combination of well-defined and ambiguous genetic variants. By employing a semi-supervised learning approach, the model efficiently utilizes both confidently labeled and less certain data. At the core of the methodology is the Feature Tokenizer Transformer architecture, which processes both numerical and categorical genomic information. The preprocessing pipeline includes key steps such as data imputation, scaling, and encoding to ensure high data quality. The results highlight the model's impressive accuracy, particularly in detecting confidently labeled variants, while also addressing the impact of its predictions on less certain (soft-labeled) data.

Stem cells are capable of self-renewal and differentiation into various cell types, showing significant potential for cellular therapies and regenerative medicine, particularly in cardiovascular diseases. The differentiation to cardiomyocytes replicates the embryonic heart development, potentially supporting cardiac regeneration. Cardiomyogenesis is controlled by complex post-transcriptional regulation that affects the construction of gene regulatory networks (GRNs), such as: alternative polyadenylation (APA), length changes in untranslated regulatory regions (3'UTRs), and microRNA (miRNA) regulation. To deepen our understanding of the cardiomyogenesis process, we have modeled a GRN for each day of cardiomyocyte differentiation. Then, each GRN was automatically transformed by four transformation rules to a Petri net and simulated using the software VANESA. The Petri nets highlighted the relationship between genes and alternative isoforms, emphasizing the inhibition of miRNA on APA isoforms with varying 3'UTR lengths. Moreover, in silico simulation of miRNA knockout enabled the visualization of the consequential effects on isoform expression. Our Petri net models provide a resourceful tool and holistic perspective to investigate the functional orchestra of transcript regulation that differentiate hESCs to cardiomyocytes. Additionally, the models can be adapted to investigate post-transcriptional GRN in other biological contexts.

This study explores the use of deep learning to analyze genetic data and predict phenotypic traits associated with schizophrenia, a complex psychiatric disorder with a strong hereditary component yet incomplete genetic characterization. We applied Convolutional Neural Networks models to a large-scale case-control exome sequencing dataset from the Swedish population to identify genetic patterns linked to schizophrenia. To enhance model performance and reduce overfitting, we employed advanced optimization techniques, including dropout layers, learning rate scheduling, batch normalization, and early stopping. Following systematic refinements in data preprocessing, model architecture, and hyperparameter tuning, the final model achieved an accuracy of 80 %. These results demonstrate the potential of deep learning approaches to uncover intricate genotype-phenotype relationships and support their future integration into precision medicine and genetic diagnostics for psychiatric disorders such as schizophrenia.

Accurate mitosis detection is essential for cancer diagnosis and treatment. Traditional manual counting by pathologists is time-consuming and may cause errors. This research investigates automated mitosis detection in stained histopathological images using Deep Learning (DL) techniques, particularly object detection models. We propose a two-stage object detection model based on Faster R-CNN to effectively detect mitosis within histopathological images. The stain augmentation and normalization techniques are also applied to address the significant challenge of domain shift in histopathological image analysis. The experiments are conducted using the MIDOG++ dataset, the most recent dataset from the MIDOG challenge. This research builds on our previous work, in which two one-stage frameworks, in particular on RetinaNet using fastai and PyTorch, are proposed. Our results indicate favorable F1-scores across various scenarios and tumor types, demonstrating the effectiveness of the object detection models. In addition, Faster R-CNN with stain techniques provides the most accurate and reliable mitosis detection, while RetinaNet models exhibit faster performance. Our results highlight the importance of handling domain shifts and the number of mitotic figures for robust diagnostic tools.

Predicting Drug-Drug interaction (DDI)-induced adverse drug reactions (ADRs) using computational methods is challenging due to the availability of limited data samples, data sparsity, and high dimensionality. The issue of class imbalance further increases the intricacy of prediction. Different computational techniques have been presented for predicting DDI-induced ADRs in the general population; however, the area of DDI-induced pregnancy and neonatal ADRs has been underexplored. In the present work, a sparse ensemble-based computational approach is proposed that leverages SMILES strings as features, addresses high-dimensional and sparse data using Sparse Principal Component Analysis (SPCA), mitigates class imbalance with the Multilabel Synthetic Minority Oversampling Technique (MLSMOTE), and predicts pregnancy and neonatal ADRs through a stacking ensemble model. The SPCA has been evaluated for handling sparse data and shown 2.67 %-5.45 % improvement compared to PCA. The proposed stacking ensemble model has outperformed six state-of-the-art predictors regarding micro and macro scores for True Positive Rate (TPR), F1 Score, False Positive Rate (FPR), Precision, Hamming Loss, and ROC-AUC Score with 1.16 %-14.94 %.

Left ventricular non-compaction is a cardiac condition marked by excessive trabeculae in the left ventricle's inner wall. Although various methods exist to measure these structures, the medical community still lacks consensus on the best approach. Previously, we developed DL-LVTQ, a tool based on a UNet neural network, to quantify trabeculae in this region. In this study, we expand the dataset to include new patients with Titin cardiomyopathy and healthy individuals with fewer trabeculae, requiring retraining of our models to enhance predictions. We also propose ViTUNeT, a neural network architecture combining U-Net and Vision Transformers to segment the left ventricle more accurately. Additionally, we train a YOLOv8 model to detect the ventricle and integrate it with ViTUNeT model to focus on the region of interest. Results from ViTUNet and YOLOv8 are similar to DL-LVTQ, suggesting dataset quality limits further accuracy improvements. To test this, we analyze MRI images and develop a method using two YOLOv8 models to identify and remove problematic images, leading to better results. Combining YOLOv8 with deep learning networks offers a promising approach for improving cardiac image analysis and segmentation.