Explore the vast range of titles available.

[...]with the advent of NGS, it now takes a day and less than USD 1000 for the same analysis [4]. [...]with the advent of such high-speed sequencers, the amount of data obtained in medical research is enormous, and the term “big data” is now common in medical research. [...]more than 60 AI-powered medical devices are approved by the Food and Drug Administration (FDA) in the United States, and the use of AI in the medical field is trending worldwide [2]. Regarding radiation image analysis, Akatsuka et al. analyzed magnetic resonance images of the prostate with deep learning, compared them with observations by radiologists and pathologists, and showed that deep learning could identify cancerous areas at a high rate, and could also find useful clues for clinical diagnosis even when the cancer was not visible [10]. In terms of omics analysis, Tanaka et al. used Bayesian networks to construct an Epithelial–Mesenchymal Transition (EMT) network representing gene–gene interactions, and showed that the sample-specific edge contribution value pattern of this EMT network characterized the survival rate of lung cancer patients [20].

Key Points Lysine methylation is widely recognized as a fundamental post-translational modification. Most protein lysine methyltransferases (PKMTs) contain the SET domain, but several non-SET proteins such as DOT1-like histone H3 lysine 79 methyltransferase (DOT1L), methyltransferase-like 10 (METTL10) and METTL21A are also known to have lysine N -methyltransferase activity. Protein lysine demethylases (PKDMs) consist of the lysine-specific demethylase 1 (LSD1) family, which are flavin-dependent monoamine oxidases, and the Jumonji C (JmjC) domain-containing proteins, which are α-ketoglutarate-dependent Fe(ii) dioxygenases. The biological importance of protein lysine methylation in cancer can be categorized into five different functions: effect on other protein modifications; protein–protein interactions; protein stability; subcellular localization; and promoter binding. Although the most widely recognized function of PKMTs and PKDMs in cancer is their effects on histones and epigenetic regulation, nearly 20 non-histone proteins related to human cancer, including p53 and RB1, have also been discovered to be methylated at lysine residues. Somatic mutations of PKMTs and PKDMs are frequently found in human cancer, and it is possible that they may affect the methylation of non-histone substrates. Inhibitors targeting PKMTs and PKDMs are considered to be promising agents for anticancer therapy, and it is important that a thorough understanding of all of the substrates of these enzymes is made to discern the precise mechanism of action of these inhibitors. Although dysregulation of histone methylation has been widely studied in cancer, accumulating evidence suggests that cancer-relevant non-histone proteins such as p53, RB1 and signal transducer and activator of transcription 3 (STAT3) are also regulated by lysine methylation. This Review summarizes the possible functions of non-histone protein lysine methylation in cancer. Several protein lysine methyltransferases and demethylases have been identified to have critical roles in histone modification. A large body of evidence has indicated that their dysregulation is involved in the development and progression of various diseases, including cancer, and these enzymes are now considered to be potential therapeutic targets. Although most studies have focused on histone methylation, many reports have revealed that these enzymes also regulate the methylation dynamics of non-histone proteins such as p53, RB1 and STAT3 (signal transducer and activator of transcription 3), which have important roles in human tumorigenesis. In this Review, we summarize the molecular functions of protein lysine methylation and its involvement in human cancer, with a particular focus on lysine methylation of non-histone proteins.

Protein methylation is one of the important post‐translational modifications. Although its biological and physiological functions were unknown for a long time, we and others have characterized a number of protein methyltransferases, which have unveiled the critical functions of protein methylation in various cellular processes, in particular, in epigenetic regulation. In addition, it had been believed that protein methylation is an irreversible phenomenon, but through identification of a variety of protein demethylases, protein methylation is now considered to be dynamically regulated similar to protein phosphorylation. A large amount of evidence indicated that protein methylation has a pivotal role in post‐translational modification of histone proteins as well as non‐histone proteins and is involved in various processes of cancer development and progression. As dysregulation of this modification has been observed frequently in various types of cancer, small‐molecule inhibitors targeting protein methyltransferases and demethylases have been actively developed as anticancer drugs; clinical trials for some of these drugs have already begun. In this review, we discuss the biological and physiological importance of protein methylation in human cancer, especially focusing on the significance of protein methyltransferases as emerging targets for anticancer therapy. Although protein methylation was found around a half‐century ago, biological and physiological functions of protein methylation remained unknown for a long time. In the 21st century, we and other researchers characterized a number of protein methyltransferases and elucidated their functions, in particular focusing on their epigenetic regulation through histone methylation. Now, protein methyltransferases are attracting considerable attention as new targets for development of anticancer therapy.

Deep learning is a promising method for medical image analysis because it can automatically acquire meaningful representations from raw data. However, a technical challenge lies in the difficulty of determining which types of internal representation are associated with a specific task, because feature vectors can vary dynamically according to individual inputs. Here, based on the magnetic resonance imaging (MRI) of gliomas, we propose a novel method to extract a shareable set of feature vectors that encode various parts in tumor imaging phenotypes. By applying vector quantization to latent representations, features extracted by an encoder are replaced with a fixed set of feature vectors. Hence, the set of feature vectors can be used in downstream tasks as imaging markers, which we call deep radiomics. Using deep radiomics, a classifier is established using logistic regression to predict the glioma grade with 90% accuracy. We also devise an algorithm to visualize the image region encoded by each feature vector, and demonstrate that the classification model preferentially relies on feature vectors associated with the presence or absence of contrast enhancement in tumor regions. Our proposal provides a data-driven approach to enhance the understanding of the imaging appearance of gliomas.

Recent studies have demonstrated the usefulness of convolutional neural networks (CNNs) to classify images of melanoma, with accuracies comparable to those achieved by dermatologists. However, the performance of a CNN trained with only clinical images of a pigmented skin lesion in a clinical image classification task, in competition with dermatologists, has not been reported to date. In this study, we extracted 5846 clinical images of pigmented skin lesions from 3551 patients. Pigmented skin lesions included malignant tumors (malignant melanoma and basal cell carcinoma) and benign tumors (nevus, seborrhoeic keratosis, senile lentigo, and hematoma/hemangioma). We created the test dataset by randomly selecting 666 patients out of them and picking one image per patient, and created the training dataset by giving bounding-box annotations to the rest of the images (4732 images, 2885 patients). Subsequently, we trained a faster, region-based CNN (FRCNN) with the training dataset and checked the performance of the model on the test dataset. In addition, ten board-certified dermatologists (BCDs) and ten dermatologic trainees (TRNs) took the same tests, and we compared their diagnostic accuracy with FRCNN. For six-class classification, the accuracy of FRCNN was 86.2%, and that of the BCDs and TRNs was 79.5% (p = 0.0081) and 75.1% (p < 0.00001), respectively. For two-class classification (benign or malignant), the accuracy, sensitivity, and specificity were 91.5%, 83.3%, and 94.5% by FRCNN; 86.6%, 86.3%, and 86.6% by BCD; and 85.3%, 83.5%, and 85.9% by TRN, respectively. False positive rates and positive predictive values were 5.5% and 84.7% by FRCNN, 13.4% and 70.5% by BCD, and 14.1% and 68.5% by TRN, respectively. We compared the classification performance of FRCNN with 20 dermatologists. As a result, the classification accuracy of FRCNN was better than that of the dermatologists. In the future, we plan to implement this system in society and have it used by the general public, in order to improve the prognosis of skin cancer.

Gaps in colonoscopy skills among endoscopists, primarily due to experience, have been identified, and solutions are critically needed. Hence, the development of a real-time robust detection system for colorectal neoplasms is considered to significantly reduce the risk of missed lesions during colonoscopy. Here, we develop an artificial intelligence (AI) system that automatically detects early signs of colorectal cancer during colonoscopy; the AI system shows the sensitivity and specificity are 97.3% (95% confidence interval [CI] = 95.9%–98.4%) and 99.0% (95% CI = 98.6%–99.2%), respectively, and the area under the curve is 0.975 (95% CI = 0.964–0.986) in the validation set. Moreover, the sensitivities are 98.0% (95% CI = 96.6%–98.8%) in the polypoid subgroup and 93.7% (95% CI = 87.6%–96.9%) in the non-polypoid subgroup; To accelerate the detection, tensor metrics in the trained model was decomposed, and the system can predict cancerous regions 21.9 ms/image on average. These findings suggest that the system is sufficient to support endoscopists in the high detection against non-polypoid lesions, which are frequently missed by optical colonoscopy. This AI system can alert endoscopists in real-time to avoid missing abnormalities such as non-polypoid polyps during colonoscopy, improving the early detection of this disease.

The human microbiome plays an essential role in the human immune system, food digestion, and protection from harmful bacteria by colonizing the human intestine. Recently, although the human microbiome affects colorectal cancer (CRC) treatment, the mode of action between the microbiome and CRC remains unclear. This study showed that propionate suppressed CRC growth by promoting the proteasomal degradation of euchromatic histone-lysine N-methyltransferase 2 (EHMT2) through HECT domain E3 ubiquitin protein ligase 2 (HECTD2) upregulation. In addition, EHMT2 downregulation reduced the H3K9me2 level on the promoter region of tumor necrosis factor α-induced protein 1 (TNFAIP1) as a novel direct target of EHMT2. Subsequently, TNFAIP1 upregulation induced the apoptosis of CRC cells. Furthermore, using Bacteroides thetaiotaomicron culture medium, we confirmed EHMT2 downregulation via upregulation of HECTD2 and TNFAIP1 upregulation. Finally, we observed the synergistic effect of propionate and an EHMT2 inhibitor (BIX01294) in 3D spheroid culture models. Thus, we suggest the anticancer effects of propionate and EHMT2 as therapeutic targets for colon cancer treatment and may provide the possibility for the synergistic effects of an EHMT2 inhibitor and microbiome in CRC treatment.

To clarify the mechanisms of diseases, such as cancer, studies analyzing genetic mutations have been actively conducted for a long time, and a large number of achievements have already been reported. Indeed, genomic medicine is considered the core discipline of precision medicine, and currently, the clinical application of cutting-edge genomic medicine aimed at improving the prevention, diagnosis and treatment of a wide range of diseases is promoted. However, although the Human Genome Project was completed in 2003 and large-scale genetic analyses have since been accomplished worldwide with the development of next-generation sequencing (NGS), explaining the mechanism of disease onset only using genetic variation has been recognized as difficult. Meanwhile, the importance of epigenetics, which describes inheritance by mechanisms other than the genomic DNA sequence, has recently attracted attention, and, in particular, many studies have reported the involvement of epigenetic deregulation in human cancer. So far, given that genetic and epigenetic studies tend to be accomplished independently, physiological relationships between genetics and epigenetics in diseases remain almost unknown. Since this situation may be a disadvantage to developing precision medicine, the integrated understanding of genetic variation and epigenetic deregulation appears to be now critical. Importantly, the current progress of artificial intelligence (AI) technologies, such as machine learning and deep learning, is remarkable and enables multimodal analyses of big omics data. In this regard, it is important to develop a platform that can conduct multimodal analysis of medical big data using AI as this may accelerate the realization of precision medicine. In this review, we discuss the importance of genome-wide epigenetic and multiomics analyses using AI in the era of precision medicine.

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.

The clinical features of sporadic mismatch repair deficiency (MMRd) and Lynch syndrome (LS) in Japanese patients with endometrial cancer (EC) were examined by evaluating the prevalence and prognostic factors of LS and sporadic MMRd in patients with EC. Targeted sequencing of five LS susceptibility genes ( MLH1 , MSH2 , MSH6 , PMS2 , and EPCAM ) was carried out in 443 patients with EC who were pathologically diagnosed with EC at the National Cancer Center Hospital between 2011 and 2018. Pathogenic variants in these genes were detected in 16 patients (3.7%). Immunohistochemistry for MMR proteins was undertaken in 337 of the 433 (77.9%) EC patients, and 91 patients (27.0%) showed absent expression of at least one MMR protein. The 13 cases of LS with MMR protein loss (93.8%) showed a favorable prognosis with a 5‐year overall survival (OS) rate of 100%, although there was no statistically significant difference between this group and the sporadic MMRd group ( p  = 0.27). In the MMRd without LS group, the 5‐year OS rate was significantly worse in seven patients with an aberrant p53 expression pattern than in those with p53 WT (53.6% vs. 93.9%, log‐rank test; p  = 0.0016). These results suggest that p53 abnormalities and pathogenic germline variants in MMR genes could be potential biomarkers for the molecular classification of EC with MMRd.