Identifying novel drug–target interactions (DTIs) plays an important role in drug discovery. Most of the computational methods developed for predicting DTIs use binary classification, whose goal is to determine whether or not a drug–target (DT) pair interacts. However, it is more meaningful but also more challenging to predict the binding affinity that describes the strength of the interaction between a DT pair. If the binding affinity is not sufficiently large, such drug may not be useful. Therefore, the methods for predicting DT binding affinities are very valuable. The increase in novel public affinity data available in the DT-related databases enables advanced deep learning techniques to be used to predict binding affinities. In this paper, we propose a similarity-based model that applies 2-dimensional (2D) convolutional neural network (CNN) to the outer products between column vectors of two similarity matrices for the drugs and targets to predict DT binding affinities. To our best knowledge, this is the first application of 2D CNN in similarity-based DT binding affinity prediction. The validation results on multiple public datasets show that the proposed model is an effective approach for DT binding affinity prediction and can be quite helpful in drug development process.

Comet assay is a widely used method, especially in the field of genotoxicity, to quantify and measure DNA damage visually at the level of individual cells with high sensitivity and efficiency. Generally, computer programs are used to analyze comet assay output images following two main steps. First, each comet region must be located and segmented, and next, it is scored using common metrics (e.g., tail length and tail moment). Currently, most studies on comet assay image analysis have adopted hand-crafted features rather than the recent and effective deep learning (DL) methods. In this paper, however, we propose a DL-based baseline method, called DeepComet, for comet segmentation. Furthermore, we created a trainable and testable comet assay image dataset that contains 1037 comet assay images with 8271 manually annotated comet objects. From the comet segmentation test results with the proposed dataset, the DeepComet achieves high average precision (AP), which is an essential metric in image segmentation and detection tasks. A comparative analysis was performed between the DeepComet and the state-of-the-arts automatic comet segmentation programs on the dataset. Besides, we found that the DeepComet records high correlations with a commercial comet analysis tool, which suggests that the DeepComet is suitable for practical application.

Molecular testing is increasingly important in cancer diagnosis. Targeted next generation sequencing (NGS) is widely accepted method but structural variation (SV) detection by targeted NGS remains challenging. In the brain tumor, identification of molecular alterations, including 1p/19q co-deletion, is essential for accurate glial tumor classification. Hence, we used targeted NGS to detect 1p/19q co-deletion using a newly developed deep learning (DL) model in 61 tumors, including 19 oligodendroglial tumors. An ensemble 1-dimentional convolution neural network was developed and used to detect the 1p/19q co-deletion. External validation was performed using 427 low-grade glial tumors from The Cancer Genome Atlas (TCGA). Manual review of the copy number plot from the targeted NGS identified the 1p/19q co-deletion in all 19 oligodendroglial tumors. Our DL model also perfectly detected the 1p/19q co-deletion (area under the curve, AUC = 1) in the testing set, and yielded reproducible results (AUC = 0.9652) in the validation set (n = 427), although the validation data were generated on a completely different platform (SNP Array 6.0 platform). In conclusion, targeted NGS using a cancer gene panel is a promising approach for classifying glial tumors, and DL can be successfully integrated for the SV detection in NGS data.

This study aimed to investigate the clinical significance of systemic inflammation markers (SIMs)—including neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), and lymphocyte-to-monocyte ratio (LMR)—in patients with newly diagnosed, previously untreated hepatocellular carcinoma (HCC). The present study was performed using prospectively collected registry data of newly diagnosed, previously untreated HCC from a single institution. The training set included 6619 patients from 2005 to 2013 and the validation set included 2084 patients from 2014 to 2016. The SIMs as continuous variables significantly affected the overall survival (OS), and the optimal cut-off value of NLR, PLR, and LMR was 3.0, 100.0, and 3.0, respectively. There were significant correlations between SIMs and the albumin-bilirubin grade/Child-Turcotte-Pugh class (indicative of liver function status) and the staging system/portal vein invasion (indicative of the tumor burden). The OS curves were well stratified according to the prognostic model of SIMs and validated using the bootstrap method (1000 times, C-index 0.6367, 95% confidence interval (CI) 0.6274–0.6459) and validation cohort (C-index 0.6810, 95% CI 0.6570–0.7049). SIMs showed significant prognostic ability for OS, independent of liver function and tumor extent, although these factors were significantly correlated with SIMs in patients with newly diagnosed, previously untreated HCC.

Limited data are available regarding optimal treatment for refractory Mycobacterium avium complex-pulmonary disease (MAC-PD). We evaluated outcomes of inhaled amikacin (AMK) with clofazimine (CFZ) regimens as an add-on salvage therapy for refractory MAC-PD. We retrospectively analyzed 52 patients with refractory MAC-PD, characterized by persistently positive sputum cultures despite >6 months of treatment. Thirty-five (67%) patients had M. intracellulare-PD, and 17 (33%) patients had M. avium-PD. Twenty-seven (52%) patients received the salvage therapy for ≥12 months, whereas 25 (48%) patients were treated for <12 months due to adverse effects or other reasons. Seventeen (33%) patients had culture conversion: 10 (10/27) in the ≥12-month treatment group and seven (7/25) in the <12-month treatment group (p = 0.488). Microbiological cure, defined as maintenance of culture negativity, was achieved in 12 (23%) patients; six (6/12) with accompanying symptomatic improvement were considered to have reached cure. Clinical cure, defined as symptomatic improvement with <3 consecutive negative cultures, was achieved in three (6%) patients. Overall, 15 (29%) patients achieved favorable outcomes, including microbiological cure, cure, and clinical cure. Inhaled AMK with CFZ may provide favorable outcomes in some patients with refractory MAC-PD. However, given the adverse effects, more effective strategies are needed to maintain these therapeutic regimens.