Kemmler Emanuel, Fath Emma Katherine, Preissner Robert, Banerjee Priyanka
Charité-Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Institute of Physiology, Charitéplatz 1, 10117 Berlin, Germany.
University of Potsdam, Nutritional Toxicology, Institute of Nutrition Science, Am Neuen Palais 10, 14469 Potsdam, Germany.
Nucleic Acids Res. 2025 Jul 7;53(W1):W4-W10. doi: 10.1093/nar/gkaf383.
Identifying allergenic proteins in raw materials can help reformulate products to make them safer for sensitive populations. Computational tools are powerful for identifying the allergenic potential of proteins and chemicals in food and personal care products. These tools can help minimize allergic risks and guide safer product development by leveraging sequence analysis, structural modelling, and epitope mapping. Food allergens can sometimes impact how a drug is processed or worsen allergic responses. These interactions can pose significant health risks and complicate treatment plans. In addition to this, certain foods can influence how drugs are absorbed, metabolized, or broken down in the body. While not all interactions trigger allergies, they may amplify reactions or side effects. Cross-reactivity occurs when proteins in foods share structural similarities with components in certain drugs, leading the immune system to react to both mistakenly. Here, we present AllergyPred, a web server that predicts both protein- and chemical-based allergens. Five different models take protein IDs, sequences, chemical IDs, and structures as inputs for predicting respective allergy endpoints. The AllergyPred web server is free and open to all users, and there is no login requirement. It can be accessed via https://allergypred.charite.de/AllergyPred/. The prediction results will be presented in the form of a table and can be downloaded in several file formats supporting users to report the results for the respective projects.
识别原材料中的致敏蛋白有助于重新制定产品配方，使其对敏感人群更安全。计算工具在识别食品和个人护理产品中蛋白质和化学物质的致敏潜力方面功能强大。这些工具可以通过利用序列分析、结构建模和表位作图来帮助将过敏风险降至最低，并指导更安全的产品开发。食物过敏原有时会影响药物的处理方式或加重过敏反应。这些相互作用可能带来重大健康风险，并使治疗方案复杂化。除此之外，某些食物会影响药物在体内的吸收、代谢或分解方式。虽然并非所有相互作用都会引发过敏，但它们可能会放大反应或副作用。当食物中的蛋白质与某些药物中的成分在结构上有相似之处时，就会发生交叉反应，导致免疫系统对两者都产生错误反应。在此，我们展示了AllergyPred，这是一个预测基于蛋白质和化学物质的过敏原的网络服务器。五种不同的模型将蛋白质ID、序列、化学ID和结构作为输入，用于预测各自的过敏终点。AllergyPred网络服务器免费向所有用户开放，无需登录。可通过https://allergypred.charite.de/AllergyPred/访问。预测结果将以表格形式呈现，并可下载为多种文件格式，以支持用户报告各自项目的结果。
