A deep neural network predictor to predict the sensitivity of neoadjuvant chemoradiotherapy in locally advanced rectal cancer

结直肠癌 放化疗 医学 肿瘤科 内科学 灵敏度(控制系统) 新辅助治疗 癌症 电子工程 乳腺癌 工程类
作者
Yuhao Liu,Jinming Shi,Wenyang Liu,Yuan Tang,Xingmei Shu,Ranjiaxi Wang,Yinan Chen,Xiaoqian Shi,Jing Jin,Dan Li
出处
期刊:Cancer Letters [Elsevier BV]
卷期号:589: 216641-216641 被引量:5
标识
DOI:10.1016/j.canlet.2024.216641
摘要

Neoadjuvant chemoradiotherapy (NCRT) is widely used for locally advanced rectal cancer (LARC). This study aimed to conduct an effective model to predict NCRT sensitivity and provide guidance for clinical treatment. Biomarkers for NCRT sensitivity were identified by applying transcriptome profiles using logistic regression and subsequently screened out by Spearman correlation analysis and four machine learning algorithms. A deep neural network (DNN) predictor was constructed by using in-house dataset and validate in two independent datasets. Additionally, a web-based program was developed. WNT/β-catenin signaling (WNT) and linoleic acid metabolism (LA) pathways were associated with NCRT sensitivity and prognosis in LARC, antagonistically. A DNN predictor with an 18-gene signature was conducted within in-house datasets. In two validation cohorts, area under ROC curve (AUC) achieved 0.706 and 0.897. The DNN subtypes were significantly associated with NCRT sensitivity, survival status et al. Moreover, NK and cytotoxic T cells were observed contribution to NCRT sensitivity while regulatory T, myeloid-derived suppressor cells and dysfunction of CD4 T effector memory cells could impede NCRT response. A DNN predictor could predict NCRT sensitivity in LARC and stratify LARC patients with different clinical and immunity characteristic.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
1秒前
科研怪完成签到 ,获得积分10
1秒前
淬h发布了新的文献求助10
2秒前
朝朝发布了新的文献求助10
2秒前
3秒前
超级炎彬发布了新的文献求助30
4秒前
4秒前
4秒前
4秒前
5秒前
reirei应助张俊敏采纳,获得10
6秒前
活力菠萝完成签到,获得积分10
7秒前
传奇3应助向北游采纳,获得10
7秒前
7秒前
乔垣结衣发布了新的文献求助30
8秒前
8秒前
9秒前
10秒前
10秒前
上官若男应助zhuan采纳,获得10
10秒前
10秒前
王梦豪发布了新的文献求助10
11秒前
pugongying完成签到,获得积分10
11秒前
1111完成签到,获得积分10
11秒前
ZQP发布了新的文献求助10
11秒前
科目三应助wx采纳,获得300
12秒前
liupangzi完成签到,获得积分10
12秒前
Zhang发布了新的文献求助10
12秒前
13秒前
Amanda发布了新的文献求助10
13秒前
小雨点完成签到 ,获得积分10
13秒前
大模型应助hqq采纳,获得10
14秒前
好好完成签到,获得积分10
14秒前
蒙蒙完成签到,获得积分10
15秒前
KUZ完成签到,获得积分20
15秒前
王磊完成签到,获得积分10
16秒前
16秒前
淬h完成签到,获得积分10
16秒前
Carlo发布了新的文献求助10
17秒前
17秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3970048
求助须知:如何正确求助?哪些是违规求助? 3514739
关于积分的说明 11175783
捐赠科研通 3250115
什么是DOI,文献DOI怎么找? 1795198
邀请新用户注册赠送积分活动 875630
科研通“疑难数据库(出版商)”最低求助积分说明 804951