AUTHOR=Chen Ruzhen , Wang Xun , Deng Xinru , Chen Lanhui , Liu Zhongyang , Li Dong TITLE=CPDR: An R Package of Recommending Personalized Drugs for Cancer Patients by Reversing the Individual’s Disease-Related Signature JOURNAL=Frontiers in Pharmacology VOLUME=13 YEAR=2022 URL=https://www.frontiersin.org/journals/pharmacology/articles/10.3389/fphar.2022.904909 DOI=10.3389/fphar.2022.904909 ISSN=1663-9812 ABSTRACT=

Due to cancer heterogeneity, only some patients can benefit from drug therapy. The personalized drug usage is important for improving the treatment response rate of cancer patients. The value of the transcriptome of patients has been recently demonstrated in guiding personalized drug use, and the Connectivity Map (CMAP) is a reliable computational approach for drug recommendation. However, there is still no personalized drug recommendation tool based on transcriptomic profiles of patients and CMAP. To fill this gap, here, we proposed such a feasible workflow and a user-friendly R package—Cancer-Personalized Drug Recommendation (CPDR). CPDR has three features. 1) It identifies the individual disease signature by using the patient subgroup with transcriptomic profiles similar to those of the input patient. 2) Transcriptomic profile purification is supported for the subgroup with high infiltration of non-cancerous cells. 3) It supports in silico drug efficacy assessment using drug sensitivity data on cancer cell lines. We demonstrated the workflow of CPDR with the aid of a colorectal cancer dataset from GEO and performed the in silico validation of drug efficacy. We further assessed the performance of CPDR by a pancreatic cancer dataset with clinical response to gemcitabine. The results showed that CPDR can recommend promising therapeutic agents for the individual patient. The CPDR R package is available at https://github.com/AllenSpike/CPDR.