The recent development of single-cell genomics requires more powerful computational tools to differentiate between different phenotypes, and rare cell identification has been one of the most important problems in this area. Recent data-driven approaches usually adopt feature selection techniques to identify important genes for anomaly detection, which require extensive training data or domain knowledge from experts. In comparison, large language models (LLMs) have achieved certain progress in scientific research with strong generalization ability, which has shown potential in this area. In this paper, we make an attempt to comprehensively evaluate the performance of in-context learning with LLMs in rare cell identification. In particular, we carefully design a chain-of-thought prompt combining token probability analysis and cross-query comparison to generate scores to identify rare cells. From the experimental results on benchmark datasets, we find that LLMs are competitive compared to existing training-based methods, which demonstrates extensive potential for rare cell identification. Our source code and data are available at https://github.com/Hyan-Yao/InContextCells/.

The symmetry and geometry of a crystal fundamentally determine its various physical and chemical properties. However, crystal structure prediction, including space group determination and crystal structure optimization, remains an ongoing challenge because traditional DFT-based approaches are time- and computational-intensive even for one specific set of material, not to mention structure prediction of massive materials. This paper determines the geometric structure of massive crystals solely from chemical formulae from scratch. In addition, due to various phases or changing environmental conditions, different pressure and temperature for example, there could be multiple crystal structures corresponding to one chemical formula (MS4OF), which has been overlooked or poorly addressed in previous research. Hereby, we propose a Physics-informed Conditional Variational Auto Encoder (PCVAE) to encode possible symmetry and geometry distribution as well as various phases of a crystal with Gaussian distributions. PCVAE achieves a new state-of-the-art in crystal structure prediction. Extensive experiments demonstrate the strong predictive power of PCVAE. The code and datasets are available at https://github.com/zjuKeLiu/PCVAE.

Medication recommendation is a crucial task for intelligent healthcare systems. Previous studies mainly recommend medications with electronic health records (EHRs). However, some details of interactions between doctors and patients may be ignored or omitted in EHRs, which are essential for automatic medication recommendation. Therefore, we make the first attempt to recommend medications with the conversations between doctors and patients. In this work, we construct DIALMED, the first high-quality dataset for medical dialogue-based medication recommendation task. It contains 11, 996 medical dialogues related to 16 common diseases from 3 departments and 70 corresponding common medications. Furthermore, we propose a Dialogue structure and Disease knowledge aware Network (DDN), where a QA Dialogue Graph mechanism is designed to model the dialogue structure and the knowledge graph is used to introduce external disease knowledge. The extensive experimental results demonstrate that the proposed method is a promising solution to recommend medications with medical dialogues. The dataset and code are available at https://github.com/f-window/DialMed.

The feasibility of ultrasonic Nakagami imaging to evaluate thermal lesions by high-intensity focused ultrasound and microwave ablation was explored in ex vivo and in vivo liver models. Dynamic changes of the ultrasonic Nakagami parameter in thermal lesions were calculated, and ultrasonic B-mode and Nakagami images were reconstructed simultaneously. The contrast-to-noise ratio (CNR) between thermal lesions and normal tissue was used to estimate the contrast resolution of the monitoring images. After thermal ablation, a bright hyper-echoic region appeared in the ultrasonic B-mode and Nakagami images, identifying the thermal lesion. During thermal ablation, mean values of Nakagami parameter showed an increasing trend from 0.72 to 1.01 for the ex vivo model and 0.54 to 0.72 for the in vivo model. After thermal ablation, mean CNR values of the ultrasonic Nakagami images were 1.29 dB (ex vivo) and 0.80 dB (in vivo), significantly higher ( ) than those for B-mode images. Thermal lesion size, assessed using ultrasonic Nakagami images, shows a good correlation to those obtained from the gross-pathology images (for the ex vivo model: length, = 0.96; width, = 0.90; for the in vivo model: length, = 0.95; width, = 0.85). This preliminary study suggests that ultrasonic Nakagami parameter may have a potential use in evaluating the formation of thermal lesions with better image contrast. Moreover, ultrasonic Nakagami imaging combined with B-mode imaging may be utilized as an alternative modality in developing monitoring systems for image-guided thermal ablation treatments.