Accurate immune cell composition profiling is crucial for understanding immunological dynamics and disease mechanisms. Bulk RNA sequencing (bulk RNA-seq) is widely employed due to its cost-effectiveness and scalability; however, it lacks the resolution to identify cell-specific gene expression. To address this limitation, we propose a self-attention enhanced deep learning model designed for precise immune cell deconvolution from bulk RNA-seq data. We systematically annotated immune cell types from four single-cell RNA-seq (scRNA-seq) peripheral blood mononuclear cell (PBMC) datasets and validated these annotations against established automated identification tools (SingleR, Seurat, scPred, ScType). Leveraging these annotations, we generated realistic pseudo-bulk RNA-seq training samples using Dirichlet-distribution-based composition sampling, significantly enhancing the model’s performance, particularly for rare cell populations. Comparative evaluations demonstrated that our self-attention enhanced deep learning model consistently outperformed existing approaches, including CIBERSORTx and Scaden, achieving lower prediction errors and higher correlations on benchmark PBMC datasets. Integrating multi-head self-attention allowed the model to dynamically capture intricate dependencies among gene expression features, substantially improving deconvolution accuracy for specific cell subsets. While demonstrating robust performance on PBMC datasets, we acknowledge that broader validation is essential due to potential limitations in generalizability across different tissue types and conditions. Our study highlights the potential of self-attention mechanisms and realistic training data generation strategies to enhance computational deconvolution techniques, providing valuable tools for clinical diagnostics and translational immunology research.

Kinases play a critical role in regulating fundamental cellular processes, including metabolism, signal transduction, and cell growth, primarily through phosphorylation. The dysregulation of kinase activity is implicated in various diseases, highlighting the urgent need for robust and interpretable methodologies to profile this activity. Current approaches frequently depend on overly complex or limited datasets, lack generalizability, or fail to provide meaningful biological insights into the mechanisms governing kinase activity. To address these challenges, we developed an explainable deep learning framework that leverages mass spectrometry-based phosphoproteomics data to profile kinase activity effectively. Our study systematically evaluated deep neural networks (DNNs) and convolutional neural networks (CNNs), incorporating a diverse set of feature inputs, including phosphorylation sites and kinase-substrate relationships. A notable finding was that a three-layer CNN, optimized through rigorous feature selection techniques, demonstrated superior performance, achieving substantial improvements in prediction accuracy and stability when compared to established methods such as kinase-substrate enrichment analysis (KSEA) and the kinase activity ranking pipeline (KARP). We integrated Shapley additive explanations (SHAP) values to enhance interpretability, illuminating biologically significant phosphorylation sites. For example, PAK2-related phosphorylation sites associated with the progression of colon adenocarcinoma and CAMK2D sites integral to adrenergic signaling were identified, thereby effectively linking computational predictions to established molecular pathways. This research illustrates the potential of explainable artificial intelligence in advancing kinase activity profiling by providing accurate and interpretable predictions. Our framework is valuable for elucidating disease mechanisms and identifying therapeutic targets, facilitating broader applications in precision medicine.

Viral titer measurement is vital in virology, offering insights into viral dynamics, disease severity, and treatment efficacy. This article underscores its importance across research domains and introduces BacCal (Baculovirus Calculator), a specialized software for streamlining viral titer experiments. BacCal automates titration using the Reed-Muench method, providing a user-friendly interface for inputting parameters and analyzing results. It enables precise quantification of viral concentrations, aiding in understanding virus-host interactions and replication kinetics. BacCal enhances quality control in virology and diagnostic assay production, ensuring consistency. Analysis involves preparing plates, inoculating cells, and assessing effects, with TCID50 calculation and optional PFU conversion. BacCal features localized data storage, preserving conditions for reproducibility. By integrating automated titration and robust data management, BacCal advances virology research, facilitating efficient experimentation and safeguarding critical data.

Rapid identification of antibiotic-resistant infections is crucial, as antimicrobial resistance is a global health crisis. Yet, conventional antibiotic susceptibility tests (AST) often require days to yield results. Matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) has emerged as a rapid, cost-effective tool for bacterial identification and shows promise for resistance profiling by detecting spectral biomarkers. In this study, we harness MALDI-TOF MS with machine learning and deep learning to predict ciprofloxacin resistance across four Gram-negative bacteria, Escherichia coli, Klebsiella pneumoniae, Acinetobacter baumannii, and Acinetobacter nosocomialis, using a cross-species "basket-wise" approach. We extracted features from mass spectra using kernel density estimation-based peak detection and m/z binning, then trained a random forest (RF) classifier and a convolutional neural network (CNN) to distinguish ciprofloxacin-resistant and susceptible isolates. To interpret the models, we employed dual feature importance analyses: gradient-weighted class activation mapping (Grad-CAM) for the CNN to highlight critical m/z regions and an ensemble RF-based method to identify significant peak features. The CNN achieved higher overall accuracy than the RF, especially in three of four species, while the ensemble RF approach identified interpretable sets of around 20 important m/z peaks per organism. Several informative peaks overlapped between species, indicating some common resistance-associated spectral signatures. However, no single universal marker was found across all species. These findings demonstrate an AI-enhanced MALDI-TOF MS framework for rapid AMR detection, yielding accurate predictions and interpretable spectral markers. The approach highlights clinical potential to guide effective therapy and bolster antimicrobial stewardship, particularly for underrepresented pathogens such as A. nosocomialis.

Traditional Chinese Medicine (TCM), with its extensive knowledge base documented in ancient texts, offers a unique resource for contemporary drug discovery, particularly in combatting microbial infections. The success of antimalarial drugs like artemisinin and artesunate, derived from the TCM herb Artemisia annua L., exemplifies the potential of TCM-derived small molecules. This rich repository of natural products and intricate molecular structures could reveal novel compounds with unexplored mechanisms of action. Our study employs a multifaceted approach that combines text mining, detailed textual analysis, and modern antibacterial molecular prediction methodologies to unlock the potential of ancient TCM remedies. We use external knowledge maps, which include databases of known bioactive compounds and their targets, to identify promising TCM candidates. This approach leverages both historical texts and contemporary scientific data to explore the therapeutic potential of TCM. We discovered that herb patterns DiYu→ZeXie and Kushen→ShengJiang potentially combat both Grams-positive and Grams-negative bacteria. We utilized the AntiBac-Pred online tool to identify and analyze the chemical components of herbs, integrating data from ancient texts and TCMDB@Taiwan external knowledge graph. The DiYu→ZeXie groups showed antimicrobial potential against resistant Staphylococcus simulans, while the Kushen→ShengJiang groups exhibited dual antimicrobial effects against Bacillus subtilis. Exploring TCM's extensive repository offers numerous opportunities for discovering therapeutically active compounds. Our synergistic approach, which combines ancient wisdom with modern science, holds significant promise for enhancing our ability to combat infectious diseases. This method could pave the way for a new era of personalized medicine, addressing the urgent need for innovative treatments against multidrug-resistant bacteria and viruses.

In recent years, antimicrobial peptides (AMPs) have become an emerging area of focus when developing therapeutics hot spot residues of proteins are dominant against infections. Importantly, AMPs are produced by virtually all known living organisms and are able to target a wide range of pathogenic microorganisms, including viruses, parasites, bacteria and fungi. Although several studies have proposed different machine learning methods to predict peptides as being AMPs, most do not consider the diversity of AMP activities. On this basis, we specifically investigated the sequence features of AMPs with a range of functional activities, including anti-parasitic, anti-viral, anti-cancer and anti-fungal activities and those that target mammals, Gram-positive and Gram-negative bacteria. A new scheme is proposed to systematically characterize and identify AMPs and their functional activities. The 1st stage of the proposed approach is to identify the AMPs, while the 2nd involves further characterization of their functional activities. Sequential forward selection was employed to extract potentially informative features that are possibly associated with the functional activities of the AMPs. These features include hydrophobicity, the normalized van der Waals volume, polarity, charge and solvent accessibility-all of which are essential attributes in classifying between AMPs and non-AMPs. The results revealed the 1st stage AMP classifier was able to achieve an area under the receiver operating characteristic curve (AUC) value of 0.9894. During the 2nd stage, we found pseudo amino acid composition to be an informative attribute when differentiating between AMPs in terms of their functional activities. The independent testing results demonstrated that the AUCs of the multi-class models were 0.7773, 0.9404, 0.8231, 0.8578, 0.8648, 0.8745 and 0.8672 for anti-parasitic, anti-viral, anti-cancer, anti-fungal AMPs and those that target mammals, Gram-positive and Gram-negative bacteria, respectively. The proposed scheme helps facilitate biological experiments related to the functional analysis of AMPs. Additionally, it was implemented as a user-friendly web server (AMPfun, http://fdblab.csie.ncu.edu.tw/AMPfun/index.html) that allows individuals to explore the antimicrobial functions of peptides of interest.

mRNA polyadenylation Is an essential mechanism in human genes and is direct linked to the termination of transcription. Alternative polyadenylation changes the length of the mature mRNA's 3'UTR. Since 3'UTRs have been shown to contain regulatory elements that control mRNA functioning, alternative polyadenylation plays an important role in controlling the expression of human genes. Prediction of polyadenylation sites can help with the identification of genes and aid our understanding of the mechanisms of alternative polyadenylation. In this study, we constructed a system for mRNA polyadenylation site prediction in human genes using SVM and based on an analysis of the sequence alignment between pair-end diTags (PET) and genome sequences. The PET sequences were mapped to the reference genome more accurate compared to earlier methods. We also analyzed single-site type and multiple-site type sequences PET sequence datasets and found that the frequencies of each nucleotide were different when the single-site type and multiple-site type PET sequences were compared.

Current pathway presentation method to the biologist is static graph. The analysis of differentially expressed genes using microarray gene expression data can help to find factors that affect diseases. However, the differentially expressed genes that are identified may be too large in number and it's difficult for biologist to pinpoint the correlations between genes and crucial points on pathway interactively. In this study, we propose a method that attempts to avoid this problem and allows the discovery of greater biological meaning than the traditional method. We select a gene pair set of interacting genes in a biological pathway and investigate the correlation in expression between the gene pairs under different condition (such as relapsed and non-relapsed breast cancer) using microarray gene expression data. We tested the approach using breast cancer relapsed and non-relapsed datasets in order to demonstrate that our method is both useful and reliable; very stable results were obtained when the same microarray platform was used. We finally use an interface to display correlations within a biological pathway.

Riboswitches are cis-acting genetic regulatory elements within a specific mRNA, and can regulate both transcription and translation by interacting with their corresponding metabolites. Recently, more and more riboswitches were identified and investigated about their roles in regulatory functions in different species. Both of the sequence contexts and structural conformations are important characteristics of riboswitches. None of previous developed tools, such Covariance Models (CMs), Riboswitch finder, and RibEx, provides a web server for efficiently searching homologous instances to known riboswitches and considers two crucial characteristics of each riboswitch, such as structural conformations and sequence contexts of functional regions. Therefore, we developed a systematic method to identify twelve kinds of riboswitches. The method is implemented and provided as a web server, RiboSW, to efficiently and conveniently identify riboswitches within messenger RNA sequences. RiboSW is now available on the web at http://bioinfo.csie.ncu.edu.tw/RiboSW/. The predictive accuracy of the proposed method is comparable with other previous tools. The efficiency of the proposed method for identifying riboswitches was improved in order to achieve a reasonable computational time required for the prediction. That makes it possible to have an accurate and convenient web server for biologists to obtain their analyzing results in a given mRNA sequence.

During gene expression, transcription factors are unable to bind to a transcription binding site (TFBS) involved in regulation if DNA methylation has occurred at the TFBS. Methyl-CpG-binding proteins may also occupy the TFBS and prevent the functioning of a transcription factor. Thus, the methylation status of CpG sites is an important issue when trying to understand gene regulation and shows strong correlation with the TFBS involved. In addition, CpG islands would seem to undergo cell-specific and tissue-specific me-thylation. Such differential methylation is presented at numerous genetic loci that are essential for development. Current DNA methylation site prediction tools need to be improved so that they include TFBS features and have greater accuracy in terms of the DNA region that is involved in methylation. We developed models that compare the differences across these regions and tissues. The TFBSs, DNA properties and DNA distribution were used as features for this classification. From the results, we found some TFBSs that were able to discriminate whether a sequence was methylated or not. The sensitivity, specificity and accuracy estimated using 10-fold cross validation were 90.8%, 80.54%, and 86.07%, respectively. Thus, for these four regions and twelve tissues, the performance levels (ACC) were all greater than 80%. We propose that the differential features or methylations vary between the different regions because the features common to each DNA region made up only 50% of the top 70 features. An online predictor based on EpiMeP is available at http://140.115.51.41/EpiMeP/. Supplementary file is available at http://140.115.51.41/EpiMeP/supplementary.doc.

Recently, the H5N1 virus has had an increasingly important impact on human life. This is because more and more people are becoming infected with this virus, and the possibility of a serious pandemic with human to human transmission is looming. This might occur if the genome of this influenza virus mutates either by antigenic drift or by antigenic shift, especially if there is a mutation of the hemagglutinin (HA) glycoprotein. The HA is the surface glycoprotein, and it binds to sialic acid of the host cell surface receptor. Thus, the combination of HA and sialic acid are central to whether influenza virus infects humans. In this study, we selected 497 HA protein sequences from the National Center for Biotechnology Information (NCBI) Influenza Resource database, and used a decision tree method to identify discriminative amino acids in the HA protein sequences that may possibly influence the binding of HA to sialic acid. Four such amino acid positions at 54, 55, 241, and 281 were identified and these may play an important role in infection by H5N1 influenza virus.