Protocol for using Ciclops to build models trained on cross-platform transcriptome data for clinical outcome prediction.
Protocol for using Ciclops to build models trained on cross-platform transcriptome data for clinical outcome prediction.
复制标题
DOI:
10.1016/j.xpro.2022.101583
复制
发表时间:
2022-09-16
期刊:
影响因子:
--
通讯作者:
Guan, Yuanfang
中科院分区:
文献类型:
--
作者:
Chou, Elysia;Zhang, Hanrui;Guan, Yuanfang
Designing robust, generalizable models based on cross-platform data to predict clinical outcomes remains challenging. Building explainable models is important because models may perform differently depending on the conditions of the samples. Here, we describe the use of Ciclops (cross-platform training in clinical outcome predictions), freely available software that can build explainable models to deliver across cross-platform datasets for predicting clinical outcomes. This protocol also utilizes SHAP, a post-training analysis allowing for assessing potential biomarkers of the clinical outcome under study. For complete details on the use and execution of this protocol, please refer to. Build robust clinical outcome prediction models using cross-platform transcriptome data Applicable to datasets from different studies measuring different clinical outcomes Perform key preprocessing steps of imputation and cross-platform quantile normalization Analyze feature importance in LightGBM, XGBoost, and Random Forest models with SHAP Publisher’s note: Undertaking any experimental protocol requires adherence to local institutional guidelines for laboratory safety and ethics. Designing robust, generalizable models based on cross-platform data to predict clinical outcomes remains challenging. Building explainable models is important because models may perform differently depending on the conditions of the samples. Here, we describe the use of Ciclops (cross-platform training in clinical outcome predictions), freely available software that can build explainable models to deliver across cross-platform datasets for predicting clinical outcomes. This protocol also utilizes SHAP, a post-training analysis allowing for assessing potential biomarkers of the clinical outcome under study.
登录
查看更多内容
影响因子:
16.6
作者:
Mok S;Stokes BH;Gnädig NF;Ross LS;Yeo T;Amaratunga C;Allman E;Solyakov L;Bottrill AR;Tripathi J;Fairhurst RM;Llinás M;Bozdech Z;Tobin AB;Fidock DA
通讯作者:
Fidock DA
DOI:
10.1038/tpj.2010.34
发表时间:
2010-08
期刊:
The pharmacogenomics journal
影响因子:
--
作者:
Fan X;Lobenhofer EK;Chen M;Shi W;Huang J;Luo J;Zhang J;Walker SJ;Chu TM;Li L;Wolfinger R;Bao W;Paules RS;Bushel PR;Li J;Shi T;Nikolskaya T;Nikolsky Y;Hong H;Deng Y;Cheng Y;Fang H;Shi L;Tong W
通讯作者:
Tong W
影响因子:
64.8
作者:
Harris CR;Millman KJ;van der Walt SJ;Gommers R;Virtanen P;Cournapeau D;Wieser E;Taylor J;Berg S;Smith NJ;Kern R;Picus M;Hoyer S;van Kerkwijk MH;Brett M;Haldane A;Del Río JF;Wiebe M;Peterson P;Gérard-Marchant P;Sheppard K;Reddy T;Weckesser W;Abbasi H;Gohlke C;Oliphant TE
通讯作者:
Oliphant TE
影响因子:
5.8
作者:
Zhang H;Guo J;Li H;Guan Y
通讯作者:
Guan Y
影响因子:
46.9
作者:
Guo, Lei;Lobenhofer, Edward K.;Shi, Leming
通讯作者:
Shi, Leming