共检索到135条,权限内显示50条;
[前沿资讯 ] 中国科学院深圳先进技术研究院合成生物学研究所研究基于对比学习的酶促反应分类AI模型 进入全文
中国科学院深圳先进技术研究院
中国科学院深圳先进技术研究院的罗小舟领衔的研究团队，近日在Journal of Cheminformatics期刊发表重要研究成果"CLAIRE: A Contrastive Learning-based Predictor for EC Number of Chemical Reactions"。在该研究成果中，团队利用对比学习，数据扩增，以及基于化学反应预训练模型的特征提取（embedding）策略，构建了一个用于预测EC分类编号的高效人工智能模型（CLAIRE）。作者将CLAIRE与当前最领先的Theia模型进行了对比。Theia是2023年由瑞士洛桑联邦理工学院的科学家Daniel Probst发表在Journal of Cheminformatics期刊上的基于常规深度学习的模型——然而常规深度学习方法不能有效解决数据不平衡的问题。借助对比学习和数据扩增的策略，CLAIRE展现出了优异的性能——在测试集上，CLAIRE比Theia有数倍的准确率提升，且在三级EC分类编号预测之间的一致性也显著高于Theia。此外，作者利用酵母菌的代谢模型构建了另一个大型独立测试集。在该数据集中，CLAIRE的表现也显著高于Theia。 通过一系列严格的评估，研究人员展示了CLAIRE的强大能力：在酵母代谢模型中，它成功区分了真实的酶-反应配对与错误配对。代谢模型是生物体内代谢反应的定量化表示，涵盖基因、酶、代谢物及其细胞内分布，广泛应用于代谢工程和通量平衡分析等领域。CLAIRE的加入使得研究人员能够更高效地分析和注释反应网络，为代谢研究提供了全新可能。此外，CLAIRE在逆合成路径规划和药物代谢预测等关键领域展示出巨大应用潜力。逆合成预测旨在推断生成目标化合物所需的原料及反应路径。在这一过程中，多个中间产物可能生成大量候选反应。通过CLAIRE预测的EC编号，可为这些反应分配相关酶，大幅提升最终目标化合物成功合成的可能性。另外，药物在人体内的代谢转化及路径是评估其安全性和有效性的重要环节。通过对潜在反应注释EC编号，CLAIRE能够清晰描绘可能的药物代谢路径，为毒性评估及药物开发提供有力支持。总而言之，该项成果在代谢工程和合成生物学领域中有着广泛的应用。
[前沿资讯 ] 天津工业生物技术研究所实现大肠杆菌实时动态调控葡萄糖摄取率及中心途径代谢 进入全文
中科院天津工业生物技术研究所
近日，中国科学院天津工业生物技术研究所张大伟研究员带领的蛋白表达系统与微生物代谢研究团队开发了实时动态监测大肠杆菌葡萄糖吸收速率的方法及其遗传回路，能够动态调节葡萄糖摄取速率及相关代谢途径的碳通量。在大肠杆菌摄取葡萄糖时，会经历一系列复杂的过程，包括跨膜转运、磷酸化、去磷酸化、辅助蛋白招募，以及相关因子的表达或抑制等。基于此调控机制，研究团队开发出了能够实时响应葡萄糖摄取速率的生物传感器（GURBs）（图1），并建立了对葡萄糖摄取速率和中央代谢流进行正负调节的遗传回路。GURBs的性能和灵敏度在不同条件下得到了验证。在线荧光和离线葡萄糖检测技术表明，GURBs可以直接测量葡萄糖摄取速率。GURBs被应用于氨基酸，维生素，有机酸等产品合成（图2），通过调控中央代谢途径代谢流，或调控遗传回路的激活或抑制，有效的提高了其产量。这些结果表明，GURBs可以根据葡萄糖摄取速率动态调节葡萄糖摄取率，及中央代谢和相关途径的碳通量，从而提高目标产品产量。葡萄糖作为细胞摄取碳源的第一步，建立其实时监测及动态调控技术十分重要，通过基因回路优化代谢流分配，不仅能很好地适应培养环境变化，还能有效平衡细胞生长与产物合成之间的代谢竞争，合理分配和利用碳资源，为合成生物设计与细胞工厂的构建提供了重要工具和更多选择。
[前沿资讯 ] 中国科学院深圳先进技术研究院综述肠道微生物群落建模研究进展 进入全文
https://www.siat.ac.cn/kyjz2016/202501/t20250120_7520256.html
近日，中国科学院深圳先进技术研究院陈禹课题组与查尔姆斯理工大学Jens Nielsen教授合作，在Current Opinion in Biotechnology期刊发表综述文章“Personalized gut microbial community modeling by leveraging genome-scale metabolic models and metagenomics”。陈禹研究员和Jens Nielsen教授为文章的共同通讯作者，研究助理李龙涛为第一作者。该工作获得了国家重点研发计划及深圳合成生物学创新研究院的支持。 文章首先回顾了近些年GEM相关资源与建模工具（如AGORA2，CarveMe等）及其在肠道微生物研究中的应用，然后介绍了构建个性化人类肠道Co-GEM的两种主流策略 （图1）：一是通过宏基因组中获得的微生物分类信息与已有的多个菌株的GEM资源整合构建Co-GEM；二是直接利用宏基因组测序数据构建GEM并结合环境中微生物分类信息来构建Co-GEM。最后，文章总结了该领域的挑战与展望。首要挑战便是不同数据库与GEM资源之间的标准化，目前不同GEM和数据库之间的代谢物、反应等关键信息存在多种不同的格式和命名规则。单一模型的性能是群落建模的基础，基于先验知识对GEM进行多约束（比如酶动力学参数，蛋白限制等）的整合至关重要。例如，最新的GECKO 3.0工具通过构建酶约束模型显著提升了模型的预测能力，有望运用于肠道微生物模型构建。此外，新的“泛”模型构建方法，比如MIGRENE和Pan-draft等，使得构建个性化肠道Co-GEM成为了可能；而多组学数据的整合以及机器学习和神经网络方法也能够进一步提升模型性能。随着新方法的不断涌现并应用在提高Co-GEM的性能上，相信在不久的将来，将能从肠道微生物的角度为人类健康与疾病提供更深入的见解。
[学术文献 ] Targeting protein–ligand neosurfaces with a generalizable deep learning tool 进入全文
Nature
Molecular recognition events between proteins drive biological processes in living systems1. However, higher levels of mechanistic regulation have emerged, in which protein-protein interactions are conditioned to small molecules2, 3, 4-5. Despite recent advances, computational tools for the design of new chemically induced protein interactions have remained a challenging task for the field6,7. Here we present a computational strategy for the design of proteins that target neosurfaces, that is, surfaces arising from protein-ligand complexes. To develop this strategy, we leveraged a geometric deep learning approach based on learned molecular surface representations8,9 and experimentally validated binders against three drug-bound protein complexes: Bcl2-venetoclax, DB3-progesterone and PDF1-actinonin. All binders demonstrated high affinities and accurate specificities, as assessed by mutational and structural characterization. Remarkably, surface fingerprints previously trained only on proteins could be applied to neosurfaces induced by interactions with small molecules, providing a powerful demonstration of generalizability that is uncommon in other deep learning approaches. We anticipate that such designed chemically induced protein interactions will have the potential to expand the sensing repertoire and the assembly of new synthetic pathways in engineered cells for innovative drug-controlled cell-based therapies10.
[学术文献 ] Protein Engineering of Substrate Specificity toward Nitrilases: Strategies and Challenges 进入全文
Journal of Agricultural and Food Chemistry
Nitrilase is extensively applied across diverse sectors owing to its unique catalytic properties. Nevertheless, in industrial production, nitrilases often face issues such as low catalytic efficiency, limited substrate range, suboptimal selectivity, and side reaction products, which have garnered heightened attention. With the widespread recognition that the structure of enzymes has a direct impact on their catalytic properties, an increasing number of researchers are beginning to optimize the functional characteristics of nitrilases by modifying their structures, in order to meet specific industrial or biotechnology application needs. Particularly in the artificial intelligence era, the innovative application of computer-aided design in enzyme engineering offers remarkable opportunities to tailor nitrilases for the widespread production of high-value products. In this discussion, we will briefly examine the structural mechanism of nitrilase. An overview of the protein engineering strategies of substrate preference, regioselectivity and stereoselectivity are explored combined with some representative examples recently in terms of the substrate specificity of enzyme. The future research trends in this field are also prospected.
[学术文献 ] Metabolic Engineering of Escherichia coli for De Novo Biosynthesis of the Platform Chemical Pelletierin 进入全文
ACS Sustainable Chemistry & Engineering
Pelletierine is a versatile plant alkaloid having a C5N–C3 structure from which numerous chemicals can be derived. One notable derivative is huperzine A (HupA) which may alleviate the symptoms of Alzheimer’s disease. Currently, industrial production of pelletierine relies primarily on chemical synthesis and plant extraction. However, chemical synthesis leads to analogues that complicate product separation, and plant extraction is constrained by limited resources. Herein, we report that pelletierine can be produced by recombinant Escherichia coli in which the engineered pelletierine biosynthesis pathway comprises four modules involving seven key genes native to E. coli, three genes from other bacteria, and three genes from plants. To overproduce pelletierine, the intrinsic l-lysine biosynthesis pathway in E. coli was simplified, and a clustered regularly interspaced short palindromic repeats (CRISPR) interference (CRISPRi) system was engineered to minimize the byproducts. Moreover, the transporter MatC was overexpressed to enhance the intracellular concentration of 3-oxoglutaryl ketide, which is another precursor of pelletierine. Based on the aforementioned manipulations, the resulting recombinant E. coli harboring the pelletierine biosynthesis pathway and CRISPRi system produced 3.40 and 8.23 mg/L pelletierine in a shake-flask and a 5 L bioreactor, respectively. This is the first report of microbial production of pelletierine, which represents a sustainable route to produce the precursor of HupA and beyond.
