Hua Gao

Wei Huang, Bingyang Zhang, Kaituo Zhang et al.

The task of anomaly detection is to separate anomalous data from normal data in the dataset. Models such as deep convolutional autoencoder (CAE) network and deep supporting vector data description (SVDD) model have been universally employed and have demonstrated significant success in detecting anomalies. However, the over-reconstruction ability of CAE network for anomalous data can easily lead to high false negative rate in detecting anomalous data. On the other hand, the deep SVDD model has the drawback of feature collapse, which leads to a decrease of detection accuracy for anomalies. To address these problems, we propose the Improved AutoEncoder with LSTM module and Kullback-Leibler divergence (IAE-LSTM-KL) model in this paper. An LSTM network is added after the encoder to memorize feature representations of normal data. In the meanwhile, the phenomenon of feature collapse can also be mitigated by penalizing the featured input to SVDD module via KL divergence. The efficacy of the IAE-LSTM-KL model is validated through experiments on both synthetic and real-world datasets. Experimental results show that IAE-LSTM-KL model yields higher detection accuracy for anomalies. In addition, it is also found that the IAE-LSTM-KL model demonstrates enhanced robustness to contaminated outliers in the dataset. All code may be found at https://github.com/crazyn2/IAE-LSTM-KL_codes

Shirui Wang, Zhihui Tang, Huaxia Yang et al.

Large language models (LLMs) hold promise in clinical decision support but face major challenges in safety evaluation and effectiveness validation. We developed the Clinical Safety-Effectiveness Dual-Track Benchmark (CSEDB), a multidimensional framework built on clinical expert consensus, encompassing 30 criteria covering critical areas like critical illness recognition, guideline adherence, and medication safety, with weighted consequence measures. Thirty-two specialist physicians developed and reviewed 2,069 open-ended Q&A items aligned with these criteria, spanning 26 clinical departments to simulate real-world scenarios. Benchmark testing of six LLMs revealed moderate overall performance (average total score 57.2%, safety 54.7%, effectiveness 62.3%), with a significant 13.3% performance drop in high-risk scenarios (p < 0.0001). Domain-specific medical LLMs showed consistent performance advantages over general-purpose models, with relatively higher top scores in safety (0.912) and effectiveness (0.861). The findings of this study not only provide a standardized metric for evaluating the clinical application of medical LLMs, facilitating comparative analyses, risk exposure identification, and improvement directions across different scenarios, but also hold the potential to promote safer and more effective deployment of large language models in healthcare environments.

Weiwen Ji, Jin Feng, Yueqi Liu et al.

Recently, deep-learning weather forecasting models have surpassed traditional numerical models in terms of the accuracy of meteorological variables. However, there is considerable potential for improvements in precipitation forecasts, especially for heavy precipitation events. To address this deficiency, we propose Leadsee-Precip, a global deep learning model to generate precipitation from meteorological circulation fields. The model utilizes an information balance scheme to tackle the challenges of predicting heavy precipitation caused by the long-tail distribution of precipitation data. Additionally, more accurate satellite and radar-based precipitation retrievals are used as training targets. Compared to artificial intelligence global weather models, the heavy precipitation from Leadsee-Precip is more consistent with observations and shows competitive performance against global numerical weather prediction models. Leadsee-Precip can be integrated with any global circulation model to generate precipitation forecasts. But the deviations between the predicted and the ground-truth circulation fields may lead to a weakened precipitation forecast, which could potentially be mitigated by further fine-tuning based on the predicted circulation fields.

Kevin Yang, Kyle Swanson, Wengong Jin et al.

Advancements in neural machinery have led to a wide range of algorithmic solutions for molecular property prediction. Two classes of models in particular have yielded promising results: neural networks applied to computed molecular fingerprints or expert-crafted descriptors, and graph convolutional neural networks that construct a learned molecular representation by operating on the graph structure of the molecule. However, recent literature has yet to clearly determine which of these two methods is superior when generalizing to new chemical space. Furthermore, prior research has rarely examined these new models in industry research settings in comparison to existing employed models. In this paper, we benchmark models extensively on 19 public and 16 proprietary industrial datasets spanning a wide variety of chemical endpoints. In addition, we introduce a graph convolutional model that consistently matches or outperforms models using fixed molecular descriptors as well as previous graph neural architectures on both public and proprietary datasets. Our empirical findings indicate that while approaches based on these representations have yet to reach the level of experimental reproducibility, our proposed model nevertheless offers significant improvements over models currently used in industrial workflows.

Ke Liu, Xiangyan Sun, Lei Jia et al.

Absorption, distribution, metabolism, and excretion (ADME) studies are critical for drug discovery. Conventionally, these tasks, together with other chemical property predictions, rely on domain-specific feature descriptors, or fingerprints. Following the recent success of neural networks, we developed Chemi-Net, a completely data-driven, domain knowledge-free, deep learning method for ADME property prediction. To compare the relative performance of Chemi-Net with Cubist, one of the popular machine learning programs used by Amgen, a large-scale ADME property prediction study was performed on-site at Amgen. The results showed that our deep neural network method improved current methods by a large margin. We foresee that the significantly increased accuracy of ADME prediction seen with Chemi-Net over Cubist will greatly accelerate drug discovery.

Rohit Muthyala, Sam Wood, Yi Jin et al.

According to a report online, more than 200 million unique users search for jobs online every month. This incredibly large and fast growing demand has enticed software giants such as Google and Facebook to enter this space, which was previously dominated by companies such as LinkedIn, Indeed and CareerBuilder. Recently, Google released their "AI-powered Jobs Search Engine", "Google For Jobs" while Facebook released "Facebook Jobs" within their platform. These current job search engines and platforms allow users to search for jobs based on general narrow filters such as job title, date posted, experience level, company and salary. However, they have severely limited filters relating to skill sets such as C++, Python, and Java and company related attributes such as employee size, revenue, technographics and micro-industries. These specialized filters can help applicants and companies connect at a very personalized, relevant and deeper level. In this paper we present a framework that provides an end-to-end "Data-driven Jobs Search Engine". In addition, users can also receive potential contacts of recruiters and senior positions for connection and networking opportunities. The high level implementation of the framework is described as follows: 1) Collect job postings data in the United States, 2) Extract meaningful tokens from the postings data using ETL pipelines, 3) Normalize the data set to link company names to their specific company websites, 4) Extract and ranking the skill sets, 5) Link the company names and websites to their respective company level attributes with the EVERSTRING Company API, 6) Run user-specific search queries on the database to identify relevant job postings and 7) Rank the job search results. This framework offers a highly customizable and highly targeted search experience for end users.