한국제약바이오협회

본 DB에서는 해당 논문의 원본데이터 및 이를 활용한 다른 논문의 전처리 데이터의 정보를 제공하고 있습니다.

원저작물에 대한 권리는 해당 연구자 및 기관에 있습니다.

Understanding transcriptional responses to chemical perturbations is central to drug discovery, but exhaustive experimental screening of disease-compound combinations is unfeasible. To overcome this limitation, here we introduce PRnet, a perturbation-conditioned deep generative model that predicts transcriptional responses to novel chemical perturbations that have never experimentally perturbed at bulk and single-cell levels. Evaluations indicate that PRnet outperforms alternative methods in predicting responses across novel compounds, pathways, and cell lines. PRnet enables gene-level response interpretation and in-silico drug screening for diseases based on gene signatures. PRnet further identifies and experimentally validates novel compound candidates against small cell lung cancer and colorectal cancer. Lastly, PRnet generates a large-scale integration atlas of perturbation profiles, covering 88 cell lines, 52 tissues, and various compound libraries. PRnet provides a robust and scalable candidate recommendation workflow and successfully recommends drug candidates for 233 diseases. Overall, PRnet is an effective and valuable tool for gene-based therapeutics screening.

For the bulk and single-cell datasets, we used expression profiles from the L1000¹ and the sci-Plex3² datasets. The L1000 and the sci-Plex3 datasets were downloaded from the Gene Expression Omnibus with the accession number (GSE92742) and (GSM4150378), respectively. Small cell lung cancer is available from The Cancer Cell Line Encyclopedia Project (CCLE) (https://sites.broadinstitute.org/ccle/). The gene signatures of diseases were downloaded from CREEDS. The scRNA-seq data of patients were downloaded from the Genome Sequence Archive for Humans at the BIG data center, Beijing Institute of Genomics, Chinese Academy of Sciences, and China National Center for Bioinformation under accession number (OMIX005223). We provided a website (prnet.drai.cn) to browse and download compound libraries and predicted results. The predicted signature results data in this paper have been deposited in the OMIX^65,66, China National Center for Bioinformation / Beijing Institute of Genomics, Chinese Academy of Sciences (https://ngdc.cncb.ac.cn/omixdatabase under accession code OMIX006910). Source data are provided in this paper.