Antibiotic resistance is a mounting global health challenge, demanding accelerated strategies for discovering new drugs and understanding their mechanism of action (MoA). In this study, we propose a computational framework to predict the MoA of natural antibiotics by leveraging Tanimoto molecular similarity metrics and network-based clustering. A curated dataset of known antibiotics with established MoA's was used to generate a similarity network, into which predicted natural antibiotics were integrated. Using the DPClus algorithm, we identified structurally coherent clusters that frequently aligned with known functional categories. The results suggest that predicted antibiotics sharing structural clusters with characterized compounds are likely to exhibit similar biological activities. Our approach provides an interpretable and scalable method for prioritizing novel antibiotic candidates for further validation, contributing to faster and more informed drug discovery pipelines.

This study employs a multi-faceted approach to identify potential natural antibiotics derived from plants used in the Unani formula. The first approach involves a supervised network analysis that utilizes distance measurement to analyze the interconnectivity of the network data. This approach identifies 26 candidate plants with the potential for natural antibiotics. The second approach involves machine learning techniques, specifically deep learning methods, to extract relevant features from the Unani data. This method produces a list of 29 potential plants that exhibit characteristics of natural antibiotics. Notably, seven plants overlap between the approaches - Piper longum, Trachyspermum ammi carum copticum, Santalum album, Cyperus rotundus, Vitis vinifera, Matricaria chamomilla and Zingiber officinale - shown in the literature to exhibit antibacterial properties direct or indirect. The study employs two analytical methods to comprehensively identify potential plants with natural antibiotic properties from the Unani formula. These findings could have significant implications for developing novel antibiotics to combat antibiotic-resistant pathogens.

In order to address antibiotics resistance, multi-drug resistance, and superbugs phenomena, our research explored the utility of Jamu ingredients on the molecular level to predict new natural antibiotic candidates. Jamu is one of the popular traditional medicines from Indonesia, with different therapeutics usage including curing diseases caused by bacterial infection. We used three types of machine learning methods, such as Random Forest (RF), Support Vector Machine (SVM), Deep Learning (DL), to classify Jamu formulas according to their effectiveness against different types of bacterial diseases. The best accuracy for RF, SVM, and DL models are 89%, 84%, and 80%, respectively. We extracted the potential compounds based on the best model as candidate antibiotics corresponding to five groups of efficacies, e.g., digestive systems, respiratory systems, reproductive systems, skin and soft tissue, and urinary systems. Overall, we mined 111 compounds, and many of them could be validated by published literature, and considering structural similarities with known antibiotics.

Sleep screening is not only a major tool in the assessment of pathophysiology, but also a bridge between the central neuronal systems and behaviour/cognition. Automatic sleep staging is an alternative for the time-consuming gold standard manual scoring procedure. Most of the existing works designed such procedure by using deep neural networks without considering the medical criterion of the sleep staging task. We argue that capturing the stage-specific features which meet the criterion is of significant importance for the automatic sleep staging alternative. In this work we propose an end-to-end sleep staging simulator based on mixed neural networks, i.e., CNN, LSTM, and Transformer. The framework consists of two subnetworks: stage dependent feature mapping network which is constructed by the idea of physiological sleep nature, and an attention-based parallel staging network. Moreover, we adopt a mixed precision training strategy to quantize the model for exploring feasible usage in the clinical settings. Through an experiment with a large EEG database (Sleep Heart Health Study), the proposed method has a competitive stage scoring performance, especially in stages Wake, N2, and N3, with higher precision of 0.92, 0.85, and 0.86, respectively. Our study proves that the quantized model has potential capability for further application in the clinical staging task.

The gut microbiota is crucial for human physiology and susceptibility to diseases. Knowing the AMR phenotype canfacilitate the understanding of the impact of antibiotics administration on the gut microbiota. Nowadays, whole-genome sequencing for antibiotic susceptibility testing (WGS-AST) is widely used in clinical microbiology to predict the AMR phenotype. To release the limitations of the genomic information and improve the WGS-AST prediction, we propose an integrated multi-omics approach, employing a deep generative neural network (VAE: variational auto-encoder). We evaluate the proposed approach by two machine learning techniques (i.e., K-means for clustering and Random Forest for classification). Our evaluation results show that the integrated multi-omics approach achieves relatively better performance than the conventional WGS-AST. Moreover, the integrated multi-omics approach is able to visually reveal AMR phenotype of the gutmicrobiota via antibacterial spectrum. Our work provides evidence that multi-omics information is useful to enhance the WGS-AST prediction.

Recently, deep learning-based methods have been successfully proposed for electrophysiology signal-based sleep staging with promising results. Most existing methods use convolutional layers and recurrent-based architectures to implement a model structure from feature extraction to sequence signal classification. In this study, we propose a method of segmenting electroencephalogram (EEG) and electrooculogram (EOG) data according to frequency bands and construct a Transformer based automatic sleep classification model on top of it. The results show that the classifications of the stage Wake, N3, and REM outperform the state-of-art works, with the Fl-scores of 0.92, 0.85 and 0.91. Our work is the first attempt to explore the feasibility of a truth-involved Transformer-based model with a large-scale sleep database.

Due to the inherent variability such as inter-users anatomical variability and the inter-systems differences, the design of new EEG-based index and a reliable model for sleep stages classification is still the main topic in sleep science. The unsupervised deep learning framework-variational autoencoder (VAE) which can capture the major characteristics of the input by imposing a Gaussian prior distribution on the latent features is suitable in EEG characterization and reconstruction. Although vanilla VAE and convolutional autoencoder (CAE) have been tried, it has yet been discussed that whether a deep structure or a multi-scale structure is more appropriate. In this paper, we constructed a shallow iVAE model, which will capture the multi-scale features of the spectrogram of EEG by replacing the main structure in encoder and decoder with the inception-like structure. By comparing with the vanilla VAE and the CAE, a more accurate reconstruction and a better classification using the latent features of the iVAE can be confirmed.

In this paper, we propose a novel biclustering approach called BiClusO. Biclustering can be applied to various types of bipartite data such as gene-condition or gene-disease relations. For example, we applied BiClusO to bipartite relations between species and volatile organic compounds (VOCs). VOCs, which are emitted by different species, have huge environmental and ecological impacts. The biosynthesis of VOCs depends on different metabolic pathways which can be used to categorize the species. A previous study related to the KNApSAcK VOC database classified microorganisms based on their VOC profiles, which confirmed the consistency between VOC-based and pathogenicity-based classifications. However, due to limited data, classification of all species in terms of VOC profiles was not performed. In this study, we enriched our database with additional data collected from different online sources and journals. Then, by applying BiClusO to species-VOC relational data, we determined that VOC-based classification is consistent with taxonomy-based classification of the species. We also assessed the diversity of VOC pathways across different kingdoms of species.

A biomarker (short for biological marker) is a medical sign of a disease or condition which indicates a normal or abnormal state of a body. The biomarker is a key factor in the analysis of diseases and also for analyzing inter disease relations. In the previous study, we designed and developed a human biomarker (metabolites and proteins) database and the database is currently available online. This work was supported by the Ministry of Education, Japan and NAIST Big Data Project. We have used our previously developed database and collected 486 human biomarkers and their respective diseases. We determined the similarity among NCBI disease classes based on associated biomarker fingerprints. For this purpose, we collected biomarker PubChem IDs and using them downloaded the SDF files in a batch, then with those molecular description files determined their atom pair fingerprints using ChemmineR package. We constructed a network of biomarkers based on Tanimoto similarity between their fingerprints and applied DPclusO algorithm to find clusters consisting of biomarkers with similar chemical structures. We also conducted hierarchical clustering of the biomarkers. We categorized all the diseases in our data into 18 NCBI disease classes. Combining all information, we finally determined inter disease relations based on structural similarity between biomarkers.

Cardiotoxicity caused by drug candidates and chemical compounds that block hERG channels may lead to malignant ventricular arrhythmias and even sudden cardiac death (SCD). Various in-silico models have been built to predict the cardiotoxicity during early stages of drug design. The largest public database of hERG-related compounds by integrating several major databases has been constructed recently, which made it possible to build more sophisticated machine learning models for accurate prediction of cardiotoxicity. Here we developed a novel molecular graph convolution neural network (MGCNN) model, based on the new integrated database. The MGCNN models were built by altering the number of graph convolutional layers (GC) from 1 to 5. A random forest (RF) model input with the extended-connectivity fingerprint (ECFP) of different maximal radii (1 ~ 5) was built to enable a direct comparison with the MCGNN models. We found that the MGCNN model with 2 GCs has the best performance in terms of the ROC-AUC-score (0.84), whereas the RF model input with ECFP has a stable performance (0.77 ~ 0.80) over the preset radii. The machine learning models promise a potential new approach for harnessing the big data to achieve accurate prediction of drug cardiotoxicity.

BACKGROUND: Alkaloids, a class of organic compounds that contain nitrogen bases, are mainly synthesized as secondary metabolites in plants and fungi, and they have a wide range of bioactivities. Although there are thousands of compounds in this class, few of their biosynthesis pathways are fully identified. In this study, we constructed a model to predict their precursors based on a novel kind of neural network called the molecular graph convolutional neural network. Molecular similarity is a crucial metric in the analysis of qualitative structure-activity relationships. However, it is sometimes difficult for current fingerprint representations to emphasize specific features for the target problems efficiently. It is advantageous to allow the model to select the appropriate features according to data-driven decisions for extracting more useful information, which influences a classification or regression problem substantially. RESULTS: In this study, we applied a neural network architecture for undirected graph representation of molecules. By encoding a molecule as an abstract graph and applying "convolution" on the graph and training the weight of the neural network framework, the neural network can optimize feature selection for the training problem. By incorporating the effects from adjacent atoms recursively, graph convolutional neural networks can extract the features of latent atoms that represent chemical features of a molecule efficiently. In order to investigate alkaloid biosynthesis, we trained the network to distinguish the precursors of 566 alkaloids, which are almost all of the alkaloids whose biosynthesis pathways are known, and showed that the model could predict starting substances with an averaged accuracy of 97.5%. CONCLUSION: We have showed that our model can predict more accurately compared to the random forest and general neural network when the variables and fingerprints are not selected, while the performance is comparable when we carefully select 507 variables from 18000 dimensions of descriptors. The prediction of pathways contributes to understanding of alkaloid synthesis mechanisms and the application of graph based neural network models to similar problems in bioinformatics would therefore be beneficial. We applied our model to evaluate the precursors of biosynthesis of 12000 alkaloids found in various organisms and found power-low-like distribution.

BACKGROUND: There are different and complicated associations between genes and diseases. Finding the causal associations between genes and specific diseases is still challenging. In this work we present a method to predict novel associations of genes and pathways with inflammatory bowel disease (IBD) by integrating information of differential gene expression, protein-protein interaction and known disease genes related to IBD. RESULTS: We downloaded IBD gene expression data from NCBI's Gene Expression Omnibus, performed statistical analysis to determine differentially expressed genes, collected known IBD genes from DisGeNet database, which were used to construct a IBD related PPI network with HIPPIE database. We adapted our graph-based clustering algorithm DPClusO to cluster the disease PPI network. We evaluated the statistical significance of the identified clusters in the context of determining the richness of IBD genes using Fisher's exact test and predicted novel genes related to IBD. We showed 93.8% of our predictions are correct in the context of other databases and published literatures related to IBD. CONCLUSIONS: Finding disease-causing genes is necessary for developing drugs with synergistic effect targeting many genes simultaneously. Here we present an approach to identify novel disease genes and pathways and discuss our approach in the context of IBD. The approach can be generalized to find disease-associated genes for other diseases.

Conventionally, workflows examining transcription regulation networks from gene expression data involve distinct analytical steps. There is a need for pipelines that unify data mining and inference deduction into a singular framework to enhance interpretation and hypotheses generation. We propose a workflow that merges network construction with gene expression data mining focusing on regulation processes in the context of transcription factor driven gene regulation. The pipeline implements pathway-based modularization of expression profiles into functional units to improve biological interpretation. The integrated workflow was implemented as a web application software (TransReguloNet) with functions that enable pathway visualization and comparison of transcription factor activity between sample conditions defined in the experimental design. The pipeline merges differential expression, network construction, pathway-based abstraction, clustering and visualization. The framework was applied in analysis of actual expression datasets related to lung, breast and prostrate cancer.

We propose a room-shaped information environment called Ambient Suite that enhances interpersonal communication. In Ambient Suite, the room itself works as both sensors to estimate the conversation states of participants and displays to present information to stimulate conversation. This paper introduces an implementation assumed standing-party situations as a typical use case of Ambient Suite. From the result of user study using its implementation, we confirmed that our system adequately encouraged participant conversations.

In this paper, we present our vision on large-scale and dynamic social network analysis in real environment, which is expected to be enabled by introduction of large-scale heterogeneous sensors in ambient environment. We address challenges toward realization of large-scale dynamic social network analysis in real environment, and discuss several promising applications. We finally present our preliminary experimental results of dynamic social network analysis for six-person social gatherings in real environment.

MOTIVATION: High-density DNA microarrays provide us with useful tools for analyzing DNA and RNA comprehensively. However, the background signal caused by the non-specific binding (NSB) between probe and target makes it difficult to obtain accurate measurements. To remove the background signal, there is a set of background probes on Affymetrix Exon arrays to represent the amount of non-specific signals, and an accurate estimation of non-specific signals using these background probes is desirable for improvement of microarray analyses. RESULTS: We developed a thermodynamic model of NSB on short nucleotide microarrays in which the NSBs are modeled by duplex formation of probes and multiple hypothetical targets. We fitted the observed signal intensities of the background probes with those expected by the model to obtain the model parameters. As a result, we found that the presented model can improve the accuracy of prediction of non-specific signals in comparison with previously proposed methods. This result will provide a useful method to correct for the background signal in oligonucleotide microarray analysis. AVAILABILITY: The software is implemented in the R language and can be downloaded from our website (http://www-shimizu.ist.osaka-u.ac.jp/shimizu_lab/MSNS/).

MOTIVATION: High-density DNA microarrays provide useful tools to analyze gene expression comprehensively. However, it is still difficult to obtain accurate expression levels from the observed microarray data because the signal intensity is affected by complicated factors involving probe-target hybridization, such as non-linear behavior of hybridization, non-specific hybridization, and folding of probe and target oligonucleotides. Various methods for microarray data analysis have been proposed to address this problem. In our previous report, we presented a benchmark analysis of probe-target hybridization using artificially synthesized oligonucleotides as targets, in which the effect of non-specific hybridization was negligible. The results showed that the preceding models explained the behavior of probe-target hybridization only within a narrow range of target concentrations. More accurate models are required for quantitative expression analysis. RESULTS: The experiments showed that finiteness of both probe and target molecules should be considered to explain the hybridization behavior. In this article, we present an extension of the Langmuir model that reproduces the experimental results consistently. In this model, we introduced the effects of secondary structure formation, and dissociation of the probe-target duplex during washing after hybridization. The results will provide useful methods for the understanding and analysis of microarray experiments. AVAILABILITY: The method was implemented for the R software and can be downloaded from our website (http://www-shimizu.ist.osaka-u.ac.jp/shimizu_lab/FHarray/).

In order for an artificial life (Alife) system to evolve complex creatures, an artificial environment prepared by a designer has to satisfy several conditions. To clarify this requirement, we first assume that an artificial environment implemented in the computational medium is composed of an information space in which elementary symbols move around and react with each other according to human-prepared elementary rules. As fundamental properties of these factors (space, symbols, transportation, and reaction), we present ten criteria from a comparison with the biochemical reaction space in the real world. Then, in the latter half of the article, we take several computational Alife systems one by one, and assess them in terms of the proposed criteria. The assessment can be used not only for improving previous Alife systems but also for devising new Alife models in which complex forms of artificial creatures can be expected to evolve.