❌

Normal view

Received β€” 6 March 2026 ⏭ Favourites

Systematic Identification of Molecular Signatures Dictating Therapeutic Effects of Clinically First-Line Chemotherapy Regimens for Human Gastric Cancer Patients Based on Organoid Model

βœ‡(Multiomics OR Omics) AND (Lung OR gastric OR Hepatocellular)
By: Jingwei Yang Β· Shuyue Qi Β· Yuan Gao Β· Jiansen Lu Β· Lin Deng Β· Xinglong Wu Β· Yifei Zhao Β· Yun Liu Β· Yanpeng Ma Β· Jiagui Song Β· Lixiang Xue Β· Lu Wen Β· Wei Fu Β· Fuchou Tang Β· Xin Zhou
5 March 2026 at 19:00

MedComm (2020). 2026 Mar 2;7(3):e70656. doi: 10.1002/mco2.70656. eCollection 2026 Mar.

ABSTRACT

Chemotherapy is the mainstay in the treatment of advanced gastric cancer (GC); yet, GC showed diverse responses to first-line chemotherapy regimens and the underlying molecular basis is still not clear. Here, we established a system that combined organoid-based chemotherapy regimen screening and transcriptome-based evaluation to identify underlying molecular signatures of different responses to chemotherapy. We generated 19 GC patient-derived organoids (PDOs) from surgically resected specimens with corresponding histological characteristics of parent tumors and tested all of the five most commonly used first-line chemotherapy regimens. Based on the treatment responses, PDOs were classified into double-sensitive, single-sensitive, and not-sensitive groups. PDOs that responded well to chemotherapy presented high expression levels of the P53 pathway genes and low expression levels of cell proliferative activity genes. Furthermore, the chemotherapy-based tumor classification of GC was established. The GC tumor classification was verified by multi-omics features from the TCGA dataset and public drug response datasets. In conclusion, this study systematically evaluated clinical chemotherapy regimens for GC and identified chemotherapy response-associated molecular signatures based on human GC organoids, which are beneficial to the precise treatments of GC.

PMID:41782964 | PMC:PMC12954136 | DOI:10.1002/mco2.70656

Received β€” 29 October 2025 ⏭ Favourites

Genotype-Phenotype Integration through Machine Learning and Personalized Gene Regulatory Networks for Cancer Metastasis Prediction

βœ‡cs.AI, q-bio.NC updates on arXiv.org
By: Jiwei Fu Β· Chunyu Yang Β· Charalampos P. Triantafyllidis
29 October 2025 at 12:00
arXiv:2510.23620v1 Announce Type: cross Abstract: Metastasis is the leading cause of cancer-related mortality, yet most predictive models rely on shallow architectures and neglect patient-specific regulatory mechanisms. Here, we integrate classical machine learning and deep learning to predict metastatic potential across multiple cancer types. Gene expression profiles from the Cancer Cell Line Encyclopedia were combined with a transcription factor-target prior from DoRothEA, focusing on nine metastasis-associated regulators. After selecting differential genes using the Kruskal-Wallis test, ElasticNet, Random Forest, and XGBoost models were trained for benchmarking. Personalized gene regulatory networks were then constructed using PANDA and LIONESS and analyzed through a graph attention neural network (GATv2) to learn topological and expression-based representations. While XGBoost achieved the highest AUROC (0.7051), the GNN captured non-linear regulatory dependencies at the patient level. These results demonstrate that combining traditional machine learning with graph-based deep learning enables a scalable and interpretable framework for metastasis risk prediction in precision oncology.
There are no more articles
❌