10 March 2025 in Nature Communications
Computational pathology, utilizing whole slide images (WSIs) for pathological diagnosis, has advanced the development of intelligent healthcare. However, the scarcity of annotated data and histological differences hinder the general application of existing methods. Extensive histopathological data and the robustness of self-supervised models in small-scale data demonstrate promising prospects for developing foundation pathology models. Here we show BEPH (BEiT-based model Pre-training on Histopathological image), a foundation model that leverages self-supervised learning to learn meaningful representations from 11 million unlabeled histopathological images. These representations are then efficiently adapted to various tasks, including patch-level cancer diagnosis, WSI-level cancer classification, and survival prediction for multiple cancer subtypes. By leveraging the masked image modeling (MIM) pre-training approach, BEPH offers an efficient solution to enhance model performance, reduce the reliance on expert annotations, and facilitate the broader application of artificial intelligence in clinical settings. The pre-trained model is available at https://github.com/Zhcyoung/BEPH.
21 October 2023 in Journal of Advanced Research
Cytochrome P450 enzymes (P450s) are recognized as the most versatile catalysts worldwide, playing vital roles in numerous biological metabolism and biosynthesis processes across all kingdoms of life. Despite the vast number of P450 genes available in databases (over 300,000), only a small fraction of them (less than 0.2 %) have undergone functional characterization. To provide a convenient platform with abundant information on P450s and their corresponding reactions, we introduce the P450Rdb database, a manually curated resource compiles literature-supported reactions catalyzed by P450s. All the P450s and Reactions were manually curated from the literature and known databases. Subsequently, the P450 reactions organized and categorized according to their chemical reaction type and site. The website was developed using HTML and PHP languages, with the MySQL server utilized for data storage. The current version of P450Rdb catalogs over 1,600 reactions, involving more than 590 P450s across a diverse range of over 200 species. Additionally, it offers a user-friendly interface with comprehensive information, enabling easy querying, browsing, and analysis of P450s and their corresponding reactions. P450Rdb is free available at http://www.cellknowledge.com.cn/p450rdb/. We believe that this database will significantly promote structural and functional research on P450s, thereby fostering advancements in the fields of natural product synthesis, pharmaceutical engineering, biotechnological applications, agricultural and crop improvement, and the chemical industry.
8 September 2021 in Synthetic and Systems Biotechnology
Protein design has become a powerful method to expand the number of natural proteins and design customized proteins according to demands. Domain-based protein design spares the need to create novel elements from scratch, which makes it a more efficient strategy than scratch-based protein design in designing multi-domain proteins, protein complexes and biomaterials. As the surface shape plays a central role in domain-domain and protein-protein interactions, a global map of the surface shapes of all domains should be very beneficial for domain-based protein design. Therefore, in this study, we characterized the surface shapes of protein domains, collected from CATH and SCOP databases, with their 3D-Zernike descriptors (3DZDs). Then similarities of domain shape features were identified, and all domains were classified accordingly. The preferences of the combinations of domains between different clusters were analyzed in natural proteins from the Protein Data Bank. A user-friendly website, termed CPD3DS, was also developed for storage, retrieval, analyses and visualization of our results. This work not only provides an overall view of protein domain shapes by showing their variety and similarities, but also opens up a new avenue to understand the properties of protein structural domains, and design principles of protein architectures.