Specific cytogenetic alterations and changes in DNA methylation are involved in leukemogenesis. Benzene, an established human leukemogen, is known to induce cytogenetic changes through its active metabolites including hydroquinone (HQ), but the specific alterations have not been fully characterized. Global DNA hypomethylation was reported in a population exposed to benzene, but has not been confirmed in vitro. In this study, we examined cytogenetic changes in chromosomes 5, 7, 8, 11 and 21, and global DNA methylation in human TK6 lymphoblastoid cells treated with HQ for 48 h, and compared the HQ-induced alterations with those induced by two well-known leukemogens, melphalan, an alkylating agent, and etoposide, a DNA topoisomerase II inhibitor. We found that rather than inducing cytogenetic alterations distinct from those induced by melphalan and etoposide, HQ induced alterations characteristic of each agent. HQ induced global DNA hypomethylation at a level intermediate to melphalan (no effect) and etoposide (potent effect). These results suggest that HQ may act similar to an alkylating agent and also similar to a DNA topoisomerase II inhibitor in living cells, both of which may be potential mechanisms of benzene toxicity. In addition to cytogenetic changes, global DNA hypomethylation may be another mechanism underlying the leukemogenicity of benzene.

In many applications, one works with neural network models trained by someone else. For such pretrained models, one may not have access to training data or test data. Moreover, one may not know details about the model, e.g., the specifics of the training data, the loss function, the hyperparameter values, etc. Given one or many pretrained models, it is a challenge to say anything about the expected performance or quality of the models. Here, we address this challenge by providing a detailed meta-analysis of hundreds of publicly available pretrained models. We examine norm-based capacity control metrics as well as power law based metrics from the recently-developed Theory of Heavy-Tailed Self Regularization. We find that norm based metrics correlate well with reported test accuracies for well-trained models, but that they often cannot distinguish well-trained versus poorly trained models. We also find that power law based metrics can do much better—quantitatively better at discriminating among series of well-trained models with a given architecture; and qualitatively better at discriminating well-trained versus poorly trained models. These methods can be used to identify when a pretrained neural network has problems that cannot be detected simply by examining training/test accuracies.

No abstract

Crop above-ground biomass (AGB) is a key parameter used for monitoring crop growth and predicting yield in precision agriculture. Estimating the crop AGB at a field scale through the use of unmanned aerial vehicles (UAVs) is promising for agronomic application, but the robustness of the methods used for estimation needs to be balanced with practical application. In this study, three UAV remote sensing flight missions (using a multiSPEC-4C multispectral camera, a Micasense RedEdge-M multispectral camera, and an Alpha Series AL3-32 Light Detection and Ranging (LiDAR) sensor onboard three different UAV platforms) were conducted above three long-term experimental plots with different tillage treatments in 2018. We investigated the performances of the multi-source UAV-based 3D point clouds at multi-spatial scales using the traditional multi-variable linear regression model (OLS), random forest (RF), backpropagation neural network (BP), and support vector machine (SVM) methods for accurate AGB estimation. Results showed that crop height (CH) was a robust proxy for AGB estimation, and that high spatial resolution in CH datasets helps to improve maize AGB estimation. Furthermore, the OLS, RF, BP, and SVM methods all maintained an acceptable accuracy for AGB estimation; however, the SVM and RF methods performed slightly more robustly. This study is expected to optimize UAV systems and algorithms for specific agronomic applications.