Protocol for CAROM: A machine learning tool to predict post-translational regulation from metabolic signatures.
Protocol for CAROM: A machine learning tool to predict post-translational regulation from metabolic signatures.
复制标题
DOI：
10.1016/j.xpro.2022.101799
复制
发表时间：
2022-12-16
期刊：
影响因子：
--
通讯作者：
Chandrasekaran, Sriram
中科院分区：
文献类型：
--
作者：
Smith, Kirk;Rhoads, Nicole;Chandrasekaran, Sriram
CAROM是一种计算工具，它结合了基因组尺度代谢网络（GEMs）和机器学习来识别翻译后修饰（PTMs）的酶靶点。条件特异性酶和反应性质用于预测多种生物的磷酸化和乙酰化目标。CAROM受到GEMs和相关通量平衡分析（FBA）精度的影响，它们产生模型的输入。我们使用大肠杆菌的多组学数据证明了该方案。有关使用和执行本协议的完整详情，请参阅。CAROM使用条件特异性酶和反应特性来预测PTM蛋白质组学数据，GEMs用于训练和调整XGBoost模型，为任何具有可用GEM和组学数据的生物体构建PTM模型，使用Shapley值解释CAROM的预测，出版商注：进行任何实验方案都需要遵守当地机构的实验室安全和伦理指导方针。CAROM是一种计算工具，它结合了基因组尺度代谢网络（GEMs）和机器学习来识别翻译后修饰（PTMs）的酶靶点。条件特异性酶和反应性质用于预测多种生物的磷酸化和乙酰化目标。CAROM受到GEMs和相关通量平衡分析（FBA）精度的影响，它们产生模型的输入。我们使用大肠杆菌的多组学数据证明了该方案。
This protocol describes CAROM, a computational tool that combines genome-scale metabolic networks (GEMs) and machine learning to identify enzyme targets of post-translational modifications (PTMs). Condition-specific enzyme and reaction properties are used to predict targets of phosphorylation and acetylation in multiple organisms. CAROM is influenced by the accuracy of GEMs and associated flux-balance analysis (FBA), which generate the inputs of the model. We demonstrate the protocol using multi-omics data from E. coli. For complete details on the use and execution of this protocol, please refer to. CAROM uses condition-specific enzyme and reaction properties to predict PTMs Proteomics data and GEMs are used to train and tune XGBoost models Construct PTM models for any organism with available GEM and omics data Explain CAROM’s predictions using Shapley values Publisher’s note: Undertaking any experimental protocol requires adherence to local institutional guidelines for laboratory safety and ethics. This protocol describes CAROM, a computational tool that combines genome-scale metabolic networks (GEMs) and machine learning to identify enzyme targets of post-translational modifications (PTMs). Condition-specific enzyme and reaction properties are used to predict targets of phosphorylation and acetylation in multiple organisms. CAROM is influenced by the accuracy of GEMs and associated flux-balance analysis (FBA), which generate the inputs of the model. We demonstrate the protocol using multi-omics data from E. coli.
登录
查看更多内容
影响因子：
9.9
作者：
Orth, Jeffrey D.;Conrad, Tom M.;Na, Jessica;Lerman, Joshua A.;Nam, Hojung;Feist, Adam M.;Palsson, Bernhard O.
通讯作者：
Palsson, Bernhard O.
DOI：
10.1007/978-1-4939-9224-9_14
发表时间：
2019-01-01
期刊：
COMPUTATIONAL STEM CELL BIOLOGY: METHODS AND PROTOCOLS
影响因子：
--
作者：
Shen, Fangzhou;Cheek, Camden;Chandrasekaran, Sriram
通讯作者：
Chandrasekaran, Sriram
影响因子：
5.8
作者：
Smith K;Shen F;Lee HJ;Chandrasekaran S
通讯作者：
Chandrasekaran S
影响因子：
9.9
作者：
Weinert, Brian T.;Iesmantavicius, Vytautas;Moustafa, Tarek;Scholz, Christian;Wagner, Sebastian A.;Magnes, Christoph;Zechner, Rudolf;Choudhary, Chunaram
通讯作者：
Choudhary, Chunaram
影响因子：
8.8
作者：
Chandrasekaran S;Zhang J;Sun Z;Zhang L;Ross CA;Huang YC;Asara JM;Li H;Daley GQ;Collins JJ
通讯作者：
Collins JJ