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=Volume 13 - 2022

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 part of patients can benefit from medical therapy. Personalized drug use is crucial for improving the treatment response rate of cancer patients. Recently, Patient-derived transcriptomic data has demonstrated its value in guiding personalized drug use, and the seminal computational approach - Connectivity map (CMAP) is hopeful used at the individual level. However, there is currently no personalized drug recommendation tool based on patient-derived transcriptomic data 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’s disease-related signature by using the patient subgroup with transcriptomic profiles similar to that of the input patient. 2) Purification of transcriptomic profile is supported for the subgroup with high infiltration of non-cancerous cells.  3) It supports in silico drug efficacy assessment using drug sensitivity data of 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 reliable therapeutic agents for the individual patient. CPDR R package is available at https://github.com/AllenSpike/CPDR.