Drug-induced liver injury (DILI) is one of the major safety concerns in drug development. Although various toxicological studies assessing DILI risk have been developed, these methods were not sufficient in predicting DILI in humans. Thus, developing new tools and approaches to better predict DILI risk in humans has become an important and urgent task. In this study, we aimed to develop a computational model for assessment of the DILI risk with using a larger scale human dataset and Naïve Bayes classifier. The established Naïve Bayes prediction model was evaluated by 5-fold cross validation and an external test set. For the training set, the overall prediction accuracy of the 5-fold cross validation was 94.0 %. The sensitivity, specificity, positive predictive value and negative predictive value were 97.1, 89.2, 93.5 and 95.1 %, respectively. The test set with the concordance of 72.6 %, sensitivity of 72.5 %, specificity of 72.7 %, positive predictive value of 80.4 %, negative predictive value of 63.2 %. Furthermore, some important molecular descriptors related to DILI risk and some toxic/non-toxic fragments were identified. Thus, we hope the prediction model established here would be employed for the assessment of human DILI risk, and the obtained molecular descriptors and substructures should be taken into consideration in the design of new candidate compounds to help medicinal chemists rationally select the chemicals with the best prospects to be effective and safe.

Background The National Comprehensive Cancer Network's Rectal Cancer Guideline Panel recommends American Joint Committee of Cancer and College of American Pathologists (AJCC/CAP) tumor regression grading (TRG) system to evaluate pathologic response to neoadjuvant chemoradiotherapy for locally advanced rectal cancer (LARC). Yet, the clinical significance of the AJCC/CAP TRG system has not been fully defined. Materials and Methods This was a multicenter, retrospectively recruited, and prospectively maintained cohort study. Patients with LARC from one institution formed the discovery set, and cases from external independent institutions formed a validation set to verify the findings from discovery set. Overall survival (OS), disease‐free survival (DFS), local recurrence‐free survival (LRFS), and distant metastasis‐free survival (DMFS) were assessed by Kaplan‐Meier analysis, log‐rank test, and Cox regression model. Results The discovery set (940 cases) found, and the validation set (2,156 cases) further confirmed, that inferior AJCC/CAP TRG categories were closely /ccorrelated with unfavorable survival (OS, DFS, LRFS, and DMFS) and higher risk of disease progression (death, accumulative relapse, local recurrence, and distant metastasis) (all p < .05). Significantly, pairwise comparison revealed that any two of four TRG categories had the distinguished survival and risk of disease progression. After propensity score matching, AJCC/CAP TRG0 category (pathological complete response) patients treated with or without adjuvant chemotherapy displayed similar survival of OS, DFS, LRFS, and DMFS (all p > .05). For AJCC/CAP TRG1–3 cases, adjuvant chemotherapy treatment significantly improved 3‐year OS (90.2% vs. 84.6%, p < .001). Multivariate analysis demonstrated the AJCC/CAP TRG system was an independent prognostic surrogate. Conclusion AJCC/CAP TRG system, an accurate prognostic surrogate, appears ideal for further strategizing adjuvant chemotherapy for LARC. Implications for Practice The National Comprehensive Cancer Network recommends the American Joint Committee of Cancer and College of American Pathologists (AJCC/CAP) tumor regression grading (TRG) four‐category system to evaluate the pathologic response to neoadjuvant treatment for patients with locally advanced rectal cancer; however, the clinical significance of the AJCC/CAP TRG system has not yet been clearly addressed. This study found, for the first time, that any two of four AJCC/CAP TRG categories had the distinguished long‐term survival outcome. Importantly, adjuvant chemotherapy may improve the 3‐year overall survival for AJCC/CAP TRG1–3 category patients but not for AJCC/CAP TRG0 category patients. Thus, AJCC/CAP TRG system, an accurate surrogate of long‐term survival outcome, is useful in guiding adjuvant chemotherapy management for rectal cancer.

No abstract

Online multi-object tracking (MOT) has broad applications in time-critical video analysis scenarios such as advanced driver-assistance systems (ADASs) and autonomous driving. In this paper, the proposed system aims at tracking multiple vehicles in the front view of an onboard monocular camera. The vehicle detection probes are customized to generate high precision detection, which plays a basic role in the following tracking-by-detection method. A novel Siamese network with a spatial pyramid pooling (SPP) layer is applied to calculate pairwise appearance similarity. The motion model captured from the refined bounding box provides the relative movements and aspects. The online-learned policy treats each tracking period as a Markov decision process (MDP) to maintain long-term, robust tracking. The proposed method is validated in a moving vehicle with an onboard NVIDIA Jetson TX2 and returns real-time speeds. Compared with other methods on KITTI and self-collected datasets, our method achieves significant performance in terms of the “Mostly-tracked”, “Fragmentation”, and “ID switch” variables.