Benigni Romualdo, Giuliani Alessandro
Laboratory of Comparative Toxicology and Ecotoxicology, Istituto Superiore di Sanita, Viale Regina Elena 299, 00161 Rome, Italy.
Bioinformatics. 2003 Jul 1;19(10):1194-200. doi: 10.1093/bioinformatics/btg099.
Chemical carcinogenicity is of primary interest, because it drives much of the current regulatory actions regarding new and existing chemicals, and its experimental determination involves time-consuming and expensive animal testing. Both academia and private companies are actively trying to develop SAR and QSAR models. This paper reviews the new Predictive Toxicology Challenge (PTC) results, by putting them into the context of previous attempts.
A marked dependency of the prediction ability of the different algorithms on the training sets was observed, pointing to a still insufficient coverage of the chemical carcinogens 'universe'. A theoretical treatment of the possible developments of the Artificial Intelligence approaches is sketched.
化学致癌性是主要关注的问题，因为它推动了当前许多关于新化学品和现有化学品的监管行动，并且其实验测定涉及耗时且昂贵的动物试验。学术界和私营公司都在积极尝试开发结构-活性关系（SAR）和定量结构-活性关系（QSAR）模型。本文通过将新的预测毒理学挑战（PTC）结果置于先前尝试的背景下进行了综述。
观察到不同算法的预测能力对训练集有显著依赖性，这表明对化学致癌物“总体”的覆盖仍然不足。概述了人工智能方法可能发展的理论处理方法。
