We have fully integrated public chromatin chromatin immunoprecipitation sequencing (ChIP‐seq) and DNase‐seq data ( n > 70,000) derived from six representative model organisms (human, mouse, rat, fruit fly, nematode, and budding yeast), and have devised a data‐mining platform—designated ChIP‐Atlas ( http://chip-atlas.org ). ChIP‐Atlas is able to show alignment and peak‐call results for all public ChIP‐seq and DNase‐seq data archived in the NCBI Sequence Read Archive (SRA), which encompasses data derived from GEO, ArrayExpress, DDBJ, ENCODE, Roadmap Epigenomics, and the scientific literature. All peak‐call data are integrated to visualize multiple histone modifications and binding sites of transcriptional regulators (TRs) at given genomic loci. The integrated data can be further analyzed to show TR–gene and TR–TR interactions, as well as to examine enrichment of protein binding for given multiple genomic coordinates or gene names. ChIP‐Atlas is superior to other platforms in terms of data number and functionality for data mining across thousands of ChIP‐seq experiments, and it provides insight into gene regulatory networks and epigenetic mechanisms.

Motivation: In bioinformatics, machine learning-based methods that predict the compound–protein interactions (CPIs) play an important role in the virtual screening for drug discovery. Recently, end-to-end representation learning for discrete symbolic data (e.g. words in natural language processing) using deep neural networks has demonstrated excellent performance on various difficult problems. For the CPI problem, data are provided as discrete symbolic data, i.e. compounds are represented as graphs where the vertices are atoms, the edges are chemical bonds, and proteins are sequences in which the characters are amino acids. In this study, we investigate the use of end-to-end representation learning for compounds and proteins, integrate the representations, and develop a new CPI prediction approach by combining a graph neural network (GNN) for compounds and a convolutional neural network (CNN) for proteins. Results: Our experiments using three CPI datasets demonstrated that the proposed end-to-end approach achieves competitive or higher performance as compared to various existing CPI prediction methods. In addition, the proposed approach significantly outperformed existing methods on an unbalanced dataset. This suggests that data-driven representations of compounds and proteins obtained by end-to-end GNNs and CNNs are more robust than traditional chemical and biological features obtained from databases. Although analyzing deep learning models is difficult due to their black-box nature, we address this issue using a neural attention mechanism, which allows us to consider which subsequences in a protein are more important for a drug compound when predicting its interaction. The neural attention mechanism also provides effective visualization, which makes it easier to analyze a model even when modeling is performed using real-valued representations instead of discrete features. Availability and implementation: https://github.com/masashitsubaki Supplementary information: Supplementary data are available at Bioinformatics online.

One of the most powerful techniques for attributing functions to genes in uni- and multicellular organisms is comprehensive analysis of mutant traits. In this study, systematic and quantitative analyses of mutant traits are achieved in the budding yeast Saccharomyces cerevisiae by investigating morphological phenotypes. Analysis of fluorescent microscopic images of triple-stained cells makes it possible to treat morphological variations as quantitative traits. Deletion of nearly half of the yeast genes not essential for growth affects these morphological traits. Similar morphological phenotypes are caused by deletions of functionally related genes, enabling a functional assignment of a locus to a specific cellular pathway. The high-dimensional phenotypic analysis of defined yeast mutant strains provides another step toward attributing gene function to all of the genes in the yeast genome.

The notion of species as reproductively isolated units related through a bifurcating tree implies that gene trees should generally agree with the species tree and that sister taxa should not share polymorphisms unless they diverged recently and should be equally closely related to outgroups. It is now possible to evaluate this model systematically. We sequenced multiple individuals from 27 described taxa representing the entire Arabidopsis genus. Cluster analysis identified seven groups, corresponding to described species that capture the structure of the genus. However, at the level of gene trees, only the separation of Arabidopsis thaliana from the remaining species was universally supported, and, overall, the amount of shared polymorphism demonstrated that reproductive isolation was considerably more recent than the estimated divergence times. We uncovered multiple cases of past gene flow that contradict a bifurcating species tree. Finally, we showed that the pattern of divergence differs between gene ontologies, suggesting a role for selection.

In recent years, advances in artificial intelligence (AI) technology have led to the rapid clinical implementation of devices with AI technology in the medical field. More than 60 AI-equipped medical devices have already been approved by the Food and Drug Administration (FDA) in the United States, and the active introduction of AI technology is considered to be an inevitable trend in the future of medicine. In the field of oncology, clinical applications of medical devices using AI technology are already underway, mainly in radiology, and AI technology is expected to be positioned as an important core technology. In particular, “precision medicine,” a medical treatment that selects the most appropriate treatment for each patient based on a vast amount of medical data such as genome information, has become a worldwide trend; AI technology is expected to be utilized in the process of extracting truly useful information from a large amount of medical data and applying it to diagnosis and treatment. In this review, we would like to introduce the history of AI technology and the current state of medical AI, especially in the oncology field, as well as discuss the possibilities and challenges of AI technology in the medical field.