In silico prediction for toxicity of chemicals is required to reduce cost, time, and animal testing. However, predicting hepatocellular hypertrophy, which often affects the derivation of the No-Observed-Adverse-Effect Level in repeated dose toxicity studies, is difficult because pathological findings are diverse, mechanisms are largely unknown, and a wide variety of chemical structures exists. Therefore, a method for predicting the hepatocellular hypertrophy of diverse chemicals without complete understanding of their mechanisms is necessary. In this study, we developed predictive classification models of hepatocellular hypertrophy using machine learning-specifically, deep learning, random forest, and support vector machine. We extracted hepatocellular hypertrophy data on rats from 2 toxicological databases, our original database developed from risk assessment reports such as pesticides, and the Hazard Evaluation Support System Integrated Platform. Then, we constructed prediction models based on molecular descriptors and evaluated their performance using independent test chemicals datasets, which differed from the training chemicals datasets. Further, we defined the applicability domain (AD), which generally limits the application for chemicals, as structurally similar to the training chemicals dataset. The best model was found to be the support vector machine model using the Hazard Evaluation Support System Integrated Platform dataset, which was trained with 251 chemicals and predicted 214 test chemicals inside the applicability domain. It afforded a prediction accuracy of 0.76, sensitivity of 0.90, and area under the curve of 0.81. These in silico predictive classification models could be reliable tools for hepatocellular hypertrophy assessments and can facilitate the development of in silico models for toxicity prediction.

A systematic review of the differences in the efficacy of dipeptidyl peptidase-4 (DPP-4) inhibitors between Japanese and non-Japanese subjects was conducted. We searched for randomized controlled trials in patients with type 2 diabetes mellitus (T2DM) that studied the intervention of a DPP-4 inhibitor once-daily vs. placebo, as monotherapy or as add-on therapy. Data regarding placebo-corrected HbA1c reduction and trough DPP-4 inhibition rate after ≥12 weeks' treatment were extracted. In the 12 eligible studies, linear regression analysis revealed that the hemoglobin A1c (HbA1c) reduction at each DPP-4 inhibition level was larger in studies involving Japanese patients than in studies involving non-Japanese patients, with statistical significance between the two groups (P < 0.0001). Sensitivity analysis excluding studies of add-on therapies supported the robustness of the result. Our study indicated that DPP-4 inhibitors show greater efficacy in Japanese patients than in non-Japanese patients, which may be an important consideration in the global development strategy of new diabetic medications.

Phthalate esters (PEs) are widely used as plasticizers in various kinds of plastic products. Some PEs have been known to induce developmental and reproductive toxicity (DART) as well as hepatotoxicity in laboratory animals. In some cases of DART, the strength of toxicity of PEs depends on the side chain lengths, while the relationship between hepatotoxicity and side chain length is unknown. Therefore, in this study, we compared DART and hepatotoxicity in rats, focusing on 6 PEs with different side chains. We collected toxicity data of 6 PEs, namely, n-butyl benzyl phthalate (BBP), din -butyl phthalate (DBP), di(2-ethylhexyl) phthalate (DEHP), di-isodecyl phthalate (DIDP), di-isononyl phthalate (DINP), and di-noctyl phthalate (DNOP), from open data source, then, we constructed the toxicity database to comprehensively and efficiently compare the toxicity effects. When we compared DART using the toxicity database, we found that BBP, DBP, and DEHP with short side chains showed strong toxicities against the reproductive organs of male offspring, and the No-Observed-Adverse-Effect Levels (NOAELs) of BBP, DBP, and DEHP were lower than DIDP, DINP, and DNOP with long side chains. Comparing hepatotoxicities, the lowest NOAEL was shown 14 mg/kg/day for DEHP, based on liver weight gain with histopathological changes. However, as BBP and DBP showed higher NOAEL than the other 3 PEs (DIDP, DINP, and DNOP), we conclude that hepatotoxicity does not depend on the length of side chain. Concerning side chain length of PEs, we effectively utilized our constructed database and found that DART and hepatotoxicity in rats showed different modes of toxicities.

We explored efficacy of dipeptidyl peptidase-4 inhibitors (DPP-4is) and sodium-glucose co-transporter 2 inhibitors (SGLT2is) between Japanese and non-Japanese patients with type 2 diabetes mellitus by conducting a systematic review and metaanalysis. A literature search of public databases before May 2017 identified 91 (DPP-4i) and 63 (SGLT2i) randomized placebocontrolled trials (> 12-week treatment). Multivariate meta-regression analysis identified baseline hemoglobin A1c (HbA1c) levels and placebo responses as covariates affecting efficacy of two agent classes independently of study region (Japanese/ non-Japanese). When accounted for covariates, DPP-4i caused more pronounced HbA1c reduction in Japanese studies than in non-Japanese studies by 0.18% difference (P < 0.05) while causing no difference in fasting plasma glucose reduction between regions. On the other hand, when adjusted by baseline HbA1c levels and placebo responses, efficacy of SGLT2i were comparable between regions. The contrasting results for two agent classes indicate that drug efficacy is affected by different pathophysiology at its therapeutic action point.

Severe cutaneous adverse reactions (SCARs), such as Stevens–Johnson syndrome/toxic epidermal necrolysis and drug‐induced hypersensitivity syndrome, are rare and occasionally fatal. However, it is difficult to detect SCARs at the drug development stage, necessitating a new approach for prediction. Therefore, in this study, using the chemical structure information of SCAR‐causative drugs from the Japanese Adverse Drug Event Report (JADER) database, we tried to develop a predictive classification model of SCAR through deep learning. In the JADER database from 2004 to 2017, we defined 185 SCAR‐positive drugs and 195 SCAR‐negative drugs using proportional reporting ratios as the signal detection method, and the total number of reports. These SCAR‐positive and SCAR‐negative drugs were randomly divided into the training dataset for model construction and the test dataset for evaluation. The model performance was evaluated in the independent test dataset inside the applicability domain (AD), which is the chemical space for reliable prediction results. Using the deep learning model with molecular descriptors as the drug structure information, the area under the curve was 0.76 for the 148 drugs of the test dataset inside the AD. The method developed in the present study allows for utilizing the JADER database for SCAR classification, with potential to improve screening efficiency in the development of new drugs. This method may also help to noninvasively identify the causative drug, and help assess the causality between drugs and SCARs in postmarketing surveillance.