Shiyang Cheng

Recently, increasing attention has been focused on the intergenerational toxicity of environmental contaminants. Tris(1,3-dichloro-2-propyl)phosphate (TDCIPP) is a widely detected contaminant in aquatic environments, but its paternally mediated intergenerational toxicity in vertebrates has remained insufficiently elucidated. In this study, zebrafish at 50 days postfertilization (dpf) were exposed to environmentally relevant concentrations (55, 550, and 5500 ng/L) of TDCIPP for 150 days. Following exposure, the males were paired with unexposed females, and cardiotoxicity and hepatotoxicity were assessed in the offspring larvae. It was found that TDCIPP accumulated in F0 testes but not in the offspring embryos. Furthermore, paternal exposure to TDCIPP led to an increased heart rate, abnormal cardiac morphology, and significantly elevated ventricular wall thickness in the offspring zebrafish. Additionally, lipid metabolism disorders, abnormal liver morphology, and functional impairment were also observed in the offspring. Moreover, paternal exposure to TDCIPP down-regulated the expression of the hepcidin antimicrobial peptide gene (hamp) in the offspring larvae, leading to iron overload, which might contribute to the observed cardiotoxicity and lipid metabolism disorders in the offspring, as well as the subsequent development of hepatotoxicity. Furthermore, the up-regulation of miR-184 in F0 testes and offspring larvae accounted for the suppression of hamp expression following paternal exposure to TDCIPP. Our findings reveal that paternal exposure to TDCIPP induces up-regulation of miR-184 in F0 testes, and this overexpressed microRNA can be transmitted to the offspring, subsequently inhibiting hamp expression, leading to iron overload and consequently contributing to cardiotoxicity and hepatotoxicity in the offspring.

Amines are widespread environmental pollutants that may pose health risks. Specifically, the N-dealkylation of amines mediated by cytochrome P450 enzymes (P450) could influence their metabolic transformation safety. However, conventional experimental and computational chemistry methods make it difficult to conduct high-throughput screening of N-dealkylation of emerging amine contaminants. Machine learning has been widely used to identify sources of environmental pollutants and predict their toxicity. However, its application in screening critical biotransformation pathways for organic pollutants has been rarely reported. In this study, we first constructed a large dataset comprising 286 emerging amine pollutants through a thorough search of databases and literature. Then, we applied four machine learning methods—random forest, gradient boosting decision tree, extreme gradient boosting, and multi-layer perceptron—to develop binary classification models for N-dealkylation. These models were based on seven carefully selected molecular descriptors that represent reactivity-fit and structural-fit. Among the predictive models, the extreme gradient boosting shows the highest prediction accuracy of 81.0%. The SlogP_VSA2 descriptor is the primary factor influencing predictions of N-dealkylation metabolism. Then an ensemble model was generated that uses a consensus strategy to integrate three different algorithms, whose performance is generally better than any single algorithm, with an accuracy rate of 86.2%. Therefore, the classification model developed in this work can provide methodological support for the high-throughput screening of N-dealkylation of amine pollutants.

Grapheme-to-phoneme conversion (G2P) is the task of converting letters (grapheme sequences) into their pronunciations (phoneme sequences). It plays a crucial role in natural language processing, text-to-speech synthesis, and automatic speech recognition systems. This paper provides a systematical overview of the G2P conversion from different perspectives. The conversion methods are first presented in the paper; detailed discussions are conducted on methods based on deep learning technology. For each method, the key ideas, advantages, disadvantages, and representative models are summarized. This paper then mentioned the learning strategies and multilingual G2P conversions. Finally, this paper summarized the commonly used monolingual and multilingual datasets, including Mandarin, Japanese, Arabic, etc. Two tables illustrated the performance of various methods with relative datasets. After making a general overall of G2P conversion, this paper concluded with the current issues and the future directions of deep learning-based G2P conversion.

Face tracking serves as the crucial initial step in mobile applications trying to analyse target faces over time in mobile settings. However, this problem has received little attention, mainly due to the scarcity of dedicated face tracking benchmarks. In this work, we introduce MobiFace, the first dataset for single face tracking in mobile situations. It consists of 80 unedited live-streaming mobile videos captured by 70 different smartphone users in fully unconstrained environments. Over 95K bounding boxes are manually labelled. The videos are carefully selected to cover typical smartphone usage. The videos are also annotated with 14 attributes, including 6 newly proposed attributes and 8 commonly seen in object tracking. 36 state-of-the-art trackers, including facial landmark trackers, generic object trackers and trackers that we have fine-tuned or improved, are evaluated. The results suggest that mobile face tracking cannot be solved through existing approaches. In addition, we show that fine-tuning on the MobiFace training data significantly boosts the performance of deep learning-based trackers, suggesting that MobiFace captures the unique characteristics of mobile face tracking. Our goal is to offer the community a diverse dataset to enable the design and evaluation of mobile face trackers. The dataset, annotations and the evaluation server will be on https://mobiface.github.io/.