{"title":"Identification and model construction of survival-associated proteins for pancreatic cancer based on deep learning","authors":"","doi":"10.1016/j.future.2024.07.023","DOIUrl":null,"url":null,"abstract":"<div><p>Pancreatic cancer (PC) is a malignancy typified by its insidious onset, rapid progression, limited resectability, poor treatment response, and exceedingly dismal prognosis. The transition from precursor lesions to infiltrating malignant tumors in pancreatic cancer is concomitant with the accrual of genetic mutations. The elucidation of proteins linked to the prognosis of pancreatic cancer holds paramount importance in the realm of pancreatic cancer management. Herein, we introduce DeepPCSA, a model tailored for the screening of target proteins and the prediction of survival time, employing both conventional methodologies and deep learning techniques for patient survival analysis. This framework leverages the LASSOCOX regression approach on differentially expressed genes (DEGs) to discern pivotal genes, succeeded by the development of a prognostic model employing convolutional and fully connected layers to prognosticate patient survival duration. Furthermore, we account for covariates such as age, gender, and other pertinent factors for independent prognostic scrutiny, affirming the autonomy of our model as a prognostic determinant. Employing unsupervised clustering methodologies, we delineated two molecular subtypes delineated by disparate biological processes. Ultimately, via drug sensitivity analysis, we delineated the interrelation between survival duration and pharmaceuticals, substantiating the necessity for tailored drug interventions catering to patients of varying risk strata.</p></div>","PeriodicalId":55132,"journal":{"name":"Future Generation Computer Systems-The International Journal of Escience","volume":null,"pages":null},"PeriodicalIF":6.2000,"publicationDate":"2024-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Future Generation Computer Systems-The International Journal of Escience","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0167739X24003881","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, THEORY & METHODS","Score":null,"Total":0}
引用次数: 0
Abstract
Pancreatic cancer (PC) is a malignancy typified by its insidious onset, rapid progression, limited resectability, poor treatment response, and exceedingly dismal prognosis. The transition from precursor lesions to infiltrating malignant tumors in pancreatic cancer is concomitant with the accrual of genetic mutations. The elucidation of proteins linked to the prognosis of pancreatic cancer holds paramount importance in the realm of pancreatic cancer management. Herein, we introduce DeepPCSA, a model tailored for the screening of target proteins and the prediction of survival time, employing both conventional methodologies and deep learning techniques for patient survival analysis. This framework leverages the LASSOCOX regression approach on differentially expressed genes (DEGs) to discern pivotal genes, succeeded by the development of a prognostic model employing convolutional and fully connected layers to prognosticate patient survival duration. Furthermore, we account for covariates such as age, gender, and other pertinent factors for independent prognostic scrutiny, affirming the autonomy of our model as a prognostic determinant. Employing unsupervised clustering methodologies, we delineated two molecular subtypes delineated by disparate biological processes. Ultimately, via drug sensitivity analysis, we delineated the interrelation between survival duration and pharmaceuticals, substantiating the necessity for tailored drug interventions catering to patients of varying risk strata.
期刊介绍:
Computing infrastructures and systems are constantly evolving, resulting in increasingly complex and collaborative scientific applications. To cope with these advancements, there is a growing need for collaborative tools that can effectively map, control, and execute these applications.
Furthermore, with the explosion of Big Data, there is a requirement for innovative methods and infrastructures to collect, analyze, and derive meaningful insights from the vast amount of data generated. This necessitates the integration of computational and storage capabilities, databases, sensors, and human collaboration.
Future Generation Computer Systems aims to pioneer advancements in distributed systems, collaborative environments, high-performance computing, and Big Data analytics. It strives to stay at the forefront of developments in grids, clouds, and the Internet of Things (IoT) to effectively address the challenges posed by these wide-area, fully distributed sensing and computing systems.