Artificial intelligence methods are developing rapidly in the medical field.However,the effectiveness of model training relies heavily on the support of sufficient sample sizes.Due to various constraints such as privacy,security,ethics,and costs in the medical field,it is rather difficult to obtain a large number of labeled training samples.Problems like the scarcity of rare disease cases,the lack of biological data for drug molecule mining,and the shortage of high-quality annotations for medical images significantly reduce the ability of models to learn from observed data,which in turn leads to poor prediction performance.In this context,constructing efficient learning artificial intelligence models for small sample data is of far-reaching significance both theoretically and practically.On the one hand,it can help to explore potential patterns when samples are insufficient in the early stage of new research.On the other hand,high-quality models can effectively reduce the cost of manual annotation,shorten the research cycle,and provide opportunities for solving challenging problems in medical research where it is difficult to collect a sufficient number of samples.Driven by both the expected advantages and actual needs,the research on artificial intelligence for small sample data has gradually become a highly anticipated and important research direction.This review systematically collates and summarizes the principles,advantages,disadvantages,applicable scenarios,and principal challenges associated with six artificial intelligence methods currently employed in the context of small-sample medical data,namely generative adversarial networks,graph neural networks,transfer learning,reinforcement learning,and Meta-learning.Furthermore,the review provides an extensive outlook and in-depth contemplation on the future trajectory of artificial intelligence methodologies in the realm of small sample data in medicine.

Artificial intelligence methods are developing rapidly in the medical field.However,the effectiveness of model training relies heavily on the support of sufficient sample sizes.Due to various constraints such as privacy,security,ethics,and costs in the medical field,it is rather difficult to obtain a large number of labeled training samples.Problems like the scarcity of rare disease cases,the lack of biological data for drug molecule mining,and the shortage of high-quality annotations for medical images significantly reduce the ability of models to learn from observed data,which in turn leads to poor prediction performance.In this context,constructing efficient learning artificial intelligence models for small sample data is of far-reaching significance both theoretically and practically.On the one hand,it can help to explore potential patterns when samples are insufficient in the early stage of new research.On the other hand,high-quality models can effectively reduce the cost of manual annotation,shorten the research cycle,and provide opportunities for solving challenging problems in medical research where it is difficult to collect a sufficient number of samples.Driven by both the expected advantages and actual needs,the research on artificial intelligence for small sample data has gradually become a highly anticipated and important research direction.This review systematically collates and summarizes the principles,advantages,disadvantages,applicable scenarios,and principal challenges associated with six artificial intelligence methods currently employed in the context of small-sample medical data,namely generative adversarial networks,graph neural networks,transfer learning,reinforcement learning,and Meta-learning.Furthermore,the review provides an extensive outlook and in-depth contemplation on the future trajectory of artificial intelligence methodologies in the realm of small sample data in medicine.

This paper reviews the research progress on live-cell super-resolution fluorescence microscopy, discusses the current research status and hotspots in this field, and summarizes the technological application of super-resolution fluorescence microscopy for live-cell imaging. To date, this field has gained progress in numerous aspects. Specifically, the structured illumination microscopy, stimulated emission depletion microscopy, and the recently introduced minimal photon fluxes microscopy are the current research hotspots. According to the current progress in this field, future development trend is likely to be largely driven by artificial intelligence as well as advances in fluorescent probes and relevant labelling methods.
Artificial Intelligence ; Microscopy, Fluorescence ; Fluorescent Dyes ; Technology

Intrinsically disordered proteins (IDPs) are proteins or protein regions that fail to get folded into definite three-dimensional structures but participate in various biological processes and perform specific functions. Defying the traditional protein "sequence-structure-function" paradigm, they enrich the protein "structure-function" diversity. Ubiquitous in organisms, they show extreme hydrophilicity, charged amino acids, and highly repetitive amino acid sequences, with simple arrangement. As a result, they feature highly variable binding affinities and high coordination, which facilitate their functions. IDPs play an important role in cell stress response, which can improve the tolerance to a variety of stresses, such as freezing, high salt, heat shock, and desiccation. In this study, we briefed the characteristics, classifications, and identification of IDPs, summarized the molecular mechanism in improving cell stress resistance, and described the potential applications.
Freezing ; Intrinsically Disordered Proteins/metabolism* ; Protein Conformation