Image-based deep learning model using DNA methylation data predicts the origin of cancer of unknown primary.

Cancer of unknown primary (CUP) is a rare type of metastatic cancer in which the origin of the tumor is unknown. Since the treatment strategy for patients with metastatic tumors depends on knowing the primary site, accurate identification of the origin site is important. Here, we developed an image-based deep-learning model that utilizes a vision transformer algorithm for predicting the origin of CUP. Using DNA methylation dataset of 8,233 primary tumors from The Cancer Genome Atlas (TCGA), we categorized 29 cancer types into 18 organ classes and extracted 2,312 differentially methylated CpG sites (DMCs) from non-squamous cancer group and 420 DMCs from squamous cell cancer group. Using these DMCs, we created organ-specific DNA methylation images and used them for model training and testing. Model performance was evaluated using 394 metastatic cancer samples from TCGA (TCGA-meta) and 995 samples (693 primary and 302 metastatic cancers) obtained from 20 independent external studies. We identified that the DNA methylation image reveals a distinct pattern based on the origin of cancer. Our model achieved an overall accuracy of 96.95 % in the TCGA-meta dataset. In the external validation datasets, our classifier achieved overall accuracies of 96.39 % and 94.37 % in primary and metastatic tumors, respectively. Especially, the overall accuracies for both primary and metastatic samples of non-squamous cell cancer were exceptionally high, with 96.79 % and 96.85 %, respectively.

Synergistic Integration of Machine Learning with Microstructure/Composition-Designed SnO2 and WO3 Breath Sensors.

A high-performance semiconductor metal oxide gas sensing strategy is proposed for efficient sensor-based disease prediction by integrating a machine learning methodology with complementary sensor arrays composed of SnO2- and WO3-based sensors. The six sensors, including SnO2- and WO3-based sensors and neural network algorithms, were used to measure gas mixtures. The six constituent sensors were subjected to acetone and hydrogen environments to monitor the effect of diet and/or irritable bowel syndrome (IBS) under the interference of ethanol. The SnO2- and WO3-based sensors suffer from poor discrimination ability if sensors (a single sensor or multiple sensors) within the same group (SnO2- or WO3-based) are separately applied, even when deep learning is applied to enhance the sensing operation. However, hybrid integration is proven to be effective in discerning acetone from hydrogen even in a two-sensor configuration through the synergistic contribution of supervised learning, i.e., neural network approaches involving deep neural networks (DNNs) and convolutional neural networks (CNNs). DNN-based numeric data and CNN-based image data can be exploited for discriminating acetone and hydrogen, with the aim of predicting the status of an exercise-driven diet and IBS. The ramifications of the proposed hybrid sensor combinations and machine learning for the high-performance breath sensor domain are discussed.

Rational design of hybrid sensor arrays combined synergistically with machine learning for rapid response to a hazardous gas leak environment in chemical plants.

Combinations of semiconductor metal oxide (SMO) sensors, electrochemical (EC) sensors, and photoionization detection (PID) sensors were used to discriminate chemical hazards on the basis of machine learning. Sensing data inputs were exploited in the form of either numerical or image data formats, and the classification of chemical hazards with high accuracy was achieved in both cases. Even a small amount of gas sensing or purging data (input for ∼30 s) input can be exploited in machine-learning-based gas discrimination. SMO sensors exhibit high performance even in a single-sensor mode, presumably because of the intrinsic cross-sensitivity of metal oxides, which is otherwise considered a major disadvantage of SMO sensors. EC sensors were enhanced through synergistic integration of sensor combinations with machine learning. For precision detection of multiple target analytes, a minimum number of sensors can be proposed for gas detection/discrimination by combining sensors with dissimilar operating principles. The Type I hybrid sensor combines one SMO sensor, one EC sensor, and one PID sensor and is used to identify NH3 gas mixed with sulfur compounds in simulations of NH3 gas leak accidents in chemical plants. The portable remote sensing module made with a Type I hybrid sensor and LTE module can identify mixed NH3 gas with a detection time of 60 s, demonstrating the potential of the proposed system to quickly respond to hazardous gas leak accidents and prevent additional damage to the environment.

Central neurocytoma exhibits radial glial cell signatures with FGFR3 hypomethylation and overexpression.

We explored the genomic events underlying central neurocytoma (CN), a rare neoplasm of the central nervous system, via multiomics approaches, including whole-exome sequencing, bulk and single-nuclei RNA sequencing, and methylation sequencing. We identified FGFR3 hypomethylation leading to FGFR3 overexpression as a major event in the ontogeny of CN that affects crucial downstream events, such as aberrant PI3K-AKT activity and neuronal development pathways. Furthermore, we found similarities between CN and radial glial cells based on analyses of gene markers and CN tumor cells and postulate that CN tumorigenesis is due to dysregulation of radial glial cell differentiation into neurons. Our data demonstrate the potential role of FGFR3 as one of the leading drivers of tumorigenesis in CN.