<p>指南者留学全国统一咨询热线：<a href="tel:4001831832" style="color:#1677ff; text-decoration:none;">400-183-1832</a>，全国各地区、各分公司联系方式均为此号码。</p><p><span style="color: #464e52; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 18px; white-space: pre-line; float: none; display: inline;">研究人员开发了一种新的人工智能算法，可以生成类似药物的分子，并且可以针对特定的药物靶点进行定制。</span></p> <p>&nbsp;</p> <p><img src="https://info.compassedu.hk/sucai/content/1727667306493/1727667306493.webp" width="780" height="440" /></p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">&nbsp;</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">伦敦国王学院和伦敦帝国理工学院的研究人员开发了一种新的人工智能算法，可以在几秒钟内生成数千个虚拟药物样分子。</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">&nbsp;</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">这种基于计算机的工具在开发针对特定药物靶点的新药方面可能很有价值。</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">&nbsp;</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">虚拟文库筛选是早期药物发现的重要步骤，它涉及使用计算工具搜索现有化合物的数据库，</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">&nbsp;</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">以找到那些结构最有可能与特定药物靶点结合的化合物，就像拼图的两块拼图一样组合在一起。</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">&nbsp;</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">一旦确定了合适的化合物，它们就会在实验室的细胞和动物模型中进行优化和测试，然后再进入临床试验。</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">&nbsp;</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">但现有虚拟文库的一个局限性是，对合适化合物的搜索仅限于文库中已经存在的化合物，因此难以识别新的潜在药物。</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">&nbsp;</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">研究人员开发了一种名为 DrugSynthMC（使用 Monte Carlo 的药物合成）的新 AI 算法，</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">&nbsp;</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">该算法通过从头开始每秒生成数千个类药物分子的化学结构来扩展药物库中的多样性。</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">&nbsp;</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">该方法在 <a style="box-sizing: border-box; color: #0a2d50; font-family: KingsBureauGrotFiveOne, sans-serif; text-decoration-line: underline;" href="https://pubs.acs.org/doi/10.1021/acs.jcim.4c01451" target="_blank" rel="noopener"><em style="box-sizing: border-box;">Journal of Chemical Information and Modeling</em></a> 中进行了概述<em style="box-sizing: border-box;">。</em></p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">&nbsp;</p> <p><strong><span style="color: #41acbd;">&ldquo;DrugSynthMC 非常高效和快速，因为与许多其他从头药物设计工具不同，</span></strong></p> <p>&nbsp;</p> <p><strong><span style="color: #41acbd;">它不依赖于使用训练数据集或神经网络架构&rdquo;。</span></strong></p> <p>&nbsp;</p> <p><strong><span style="color: #41acbd;">&mdash;&mdash;国王大学分子生物化学高级讲师、该研究的共同高级作者 Filippo Prischi 博士</span></strong></p> <p>&nbsp;</p> <p>&nbsp;</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">&ldquo;我们表明，DrugSynthMC 可以扩展可用库中化合物的化学多样性，克服现有药物集合的局限性，&rdquo;Prischi 博士说。</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">&nbsp;</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">DrugSynthMC 使用一种称为蒙特卡洛树搜索的算法&mdash;&mdash;一种根据定义的一组操作预测所有可能结果的数学技术。</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">&nbsp;</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">在这种情况下，DrugSynthMC 按照一小组指令以简单的文本格式构建分子的化学结构，旨在最大限度地发挥口服药物的重要特征。</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">&nbsp;</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">该团队发现，该算法成功地生成了高比例的易于合成、可溶且无毒的化合物。</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">&nbsp;</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">重要的是，DrugSynthMC 可以定制以筛选最有可能与特定生物靶标结合的分子。</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">&nbsp;</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">该团队认为，人工智能算法未来的主要用途将是识别和优化针对与特定疾病相关的蛋白质靶标的化合物。</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">&nbsp;</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">&ldquo;尽管这是一个相当简单的算法，但它比任何已经测试或发表的更复杂的算法都要高效得多，</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">&nbsp;</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">并且将在人工智能驱动的定制治疗靶点药物发现中非常有用。&ldquo;</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">&nbsp;</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">伦敦帝国理工学院癌细胞信号读者、该研究的共同高级作者 Olivier Pardo 博士说。</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">&nbsp;</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">该工具公开可供研究界<a style="box-sizing: border-box; color: #0a2d50; font-family: KingsBureauGrotFiveOne, sans-serif; text-decoration-line: underline;" href="https://github.com/RoucairolMilo/DrugSynthMC" target="_blank" rel="noopener">使用</a>。</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">&nbsp;</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">&nbsp;</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">这项工作是与法国巴黎第九大学 PRAIRIE 研究所的 Tristan Cazenave 教授和 Milo Roucairol 合作进行的。</p> <p class="Paragraphstyled__ParagraphStyled-sc-176xsi4-0 jfWPBd" style="box-sizing: border-box; margin-top: 0px; margin-bottom: 1.5rem; white-space: pre-line; font-family: KingsBureauGrotFiveOne, sans-serif; font-size: 1.125rem; line-height: 1.6; color: #464e52;">这项工作部分得到了法国政府的支持。</p>