Machine learning-based in-silico analysis identifies signatures of lysyl oxidases for prognostic and therapeutic response prediction in cancer

Abstract Background Lysyl oxidases (LOX/LOXL1-4) are crucial for cancer progression, yet their transcriptional regulation, potential therapeutic targeting, prognostic value and involvement in immune regulation remain poorly understood. This study comprehensively evaluates LOX/LOXL expression in canc...

Full description

Saved in:
Bibliographic Details
Main Authors: Qingyu Xu, Ling Ma, Alexander Streuer, Eva Altrock, Nanni Schmitt, Felicitas Rapp, Alessa Klär, Verena Nowak, Julia Obländer, Nadine Weimer, Iris Palme, Melda Göl, Hong-hu Zhu, Wolf-Karsten Hofmann, Daniel Nowak, Vladimir Riabov
Format: Article
Language:English
Published: BMC 2025-04-01
Series:Cell Communication and Signaling
Subjects:
Online Access:https://doi.org/10.1186/s12964-025-02176-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850153520501620736
author Qingyu Xu
Ling Ma
Alexander Streuer
Eva Altrock
Nanni Schmitt
Felicitas Rapp
Alessa Klär
Verena Nowak
Julia Obländer
Nadine Weimer
Iris Palme
Melda Göl
Hong-hu Zhu
Wolf-Karsten Hofmann
Daniel Nowak
Vladimir Riabov
author_facet Qingyu Xu
Ling Ma
Alexander Streuer
Eva Altrock
Nanni Schmitt
Felicitas Rapp
Alessa Klär
Verena Nowak
Julia Obländer
Nadine Weimer
Iris Palme
Melda Göl
Hong-hu Zhu
Wolf-Karsten Hofmann
Daniel Nowak
Vladimir Riabov
author_sort Qingyu Xu
collection DOAJ
description Abstract Background Lysyl oxidases (LOX/LOXL1-4) are crucial for cancer progression, yet their transcriptional regulation, potential therapeutic targeting, prognostic value and involvement in immune regulation remain poorly understood. This study comprehensively evaluates LOX/LOXL expression in cancer and highlights cancer types where targeting these enzymes and developing LOX/LOXL-based prognostic models could have significant clinical relevance. Methods We assessed the association of LOX/LOXL expression with survival and drug sensitivity via analyzing public datasets (including bulk and single-cell RNA sequencing data of six datasets from Gene Expression Omnibus (GEO), Chinese Glioma Genome Atlas (CGGA) and Cancer Genome Atlas Program (TCGA)). We performed comprehensive machine learning-based bioinformatics analyses, including unsupervised consensus clustering, a total of 10 machine-learning algorithms for prognostic prediction and the Connectivity map tool for drug sensitivity prediction. Results The clinical significance of the LOX/LOXL family was evaluated across 33 cancer types. Overexpression of LOX/LOXL showed a strong correlation with tumor progression and poor survival, particularly in glioma. Therefore, we developed a novel prognostic model for glioma by integrating LOX/LOXL expression and its co-expressed genes. This model was highly predictive for overall survival in glioma patients, indicating significant clinical utility in prognostic assessment. Furthermore, our analysis uncovered a distinct LOXL2-overexpressing malignant cell population in recurrent glioma, characterized by activation of collagen, laminin, and semaphorin-3 pathways, along with enhanced epithelial-mesenchymal transition. Apart from glioma, our data revealed the role of LOXL3 overexpression in macrophages and in predicting the response to immune checkpoint blockade in bladder and renal cancers. Given the pro-tumor role of LOX/LOXL genes in most analyzed cancers, we identified potential therapeutic compounds, such as the VEGFR inhibitor cediranib, to target pan-LOX/LOXL overexpression in cancer. Conclusions Our study provides novel insights into the potential value of LOX/LOXL in cancer pathogenesis and treatment, and particularly its prognostic significance in glioma.
format Article
id doaj-art-bcf1865cec9c47dbbfc6848f1ad40a2b
institution OA Journals
issn 1478-811X
language English
publishDate 2025-04-01
publisher BMC
record_format Article
series Cell Communication and Signaling
spelling doaj-art-bcf1865cec9c47dbbfc6848f1ad40a2b2025-08-20T02:25:41ZengBMCCell Communication and Signaling1478-811X2025-04-0123111710.1186/s12964-025-02176-1Machine learning-based in-silico analysis identifies signatures of lysyl oxidases for prognostic and therapeutic response prediction in cancerQingyu Xu0Ling Ma1Alexander Streuer2Eva Altrock3Nanni Schmitt4Felicitas Rapp5Alessa Klär6Verena Nowak7Julia Obländer8Nadine Weimer9Iris Palme10Melda Göl11Hong-hu Zhu12Wolf-Karsten Hofmann13Daniel Nowak14Vladimir Riabov15Department of Hematology and Oncology, Medical Faculty Mannheim, Heidelberg UniversityDepartment of Hematology and Oncology, Medical Faculty Mannheim, Heidelberg UniversityDepartment of Hematology and Oncology, Medical Faculty Mannheim, Heidelberg UniversityDepartment of Hematology and Oncology, Medical Faculty Mannheim, Heidelberg UniversityDepartment of Hematology and Oncology, Medical Faculty Mannheim, Heidelberg UniversityDepartment of Hematology and Oncology, Medical Faculty Mannheim, Heidelberg UniversityDepartment of Hematology and Oncology, Medical Faculty Mannheim, Heidelberg UniversityDepartment of Hematology and Oncology, Medical Faculty Mannheim, Heidelberg UniversityDepartment of Hematology and Oncology, Medical Faculty Mannheim, Heidelberg UniversityDepartment of Hematology and Oncology, Medical Faculty Mannheim, Heidelberg UniversityDepartment of Hematology and Oncology, Medical Faculty Mannheim, Heidelberg UniversityDepartment of Hematology and Oncology, Medical Faculty Mannheim, Heidelberg UniversityDepartment of Hematology, Beijing Chao-Yang Hospital, Capital Medical UniversityDepartment of Hematology and Oncology, Medical Faculty Mannheim, Heidelberg UniversityDepartment of Hematology and Oncology, Medical Faculty Mannheim, Heidelberg UniversityDepartment of Hematology and Oncology, Medical Faculty Mannheim, Heidelberg UniversityAbstract Background Lysyl oxidases (LOX/LOXL1-4) are crucial for cancer progression, yet their transcriptional regulation, potential therapeutic targeting, prognostic value and involvement in immune regulation remain poorly understood. This study comprehensively evaluates LOX/LOXL expression in cancer and highlights cancer types where targeting these enzymes and developing LOX/LOXL-based prognostic models could have significant clinical relevance. Methods We assessed the association of LOX/LOXL expression with survival and drug sensitivity via analyzing public datasets (including bulk and single-cell RNA sequencing data of six datasets from Gene Expression Omnibus (GEO), Chinese Glioma Genome Atlas (CGGA) and Cancer Genome Atlas Program (TCGA)). We performed comprehensive machine learning-based bioinformatics analyses, including unsupervised consensus clustering, a total of 10 machine-learning algorithms for prognostic prediction and the Connectivity map tool for drug sensitivity prediction. Results The clinical significance of the LOX/LOXL family was evaluated across 33 cancer types. Overexpression of LOX/LOXL showed a strong correlation with tumor progression and poor survival, particularly in glioma. Therefore, we developed a novel prognostic model for glioma by integrating LOX/LOXL expression and its co-expressed genes. This model was highly predictive for overall survival in glioma patients, indicating significant clinical utility in prognostic assessment. Furthermore, our analysis uncovered a distinct LOXL2-overexpressing malignant cell population in recurrent glioma, characterized by activation of collagen, laminin, and semaphorin-3 pathways, along with enhanced epithelial-mesenchymal transition. Apart from glioma, our data revealed the role of LOXL3 overexpression in macrophages and in predicting the response to immune checkpoint blockade in bladder and renal cancers. Given the pro-tumor role of LOX/LOXL genes in most analyzed cancers, we identified potential therapeutic compounds, such as the VEGFR inhibitor cediranib, to target pan-LOX/LOXL overexpression in cancer. Conclusions Our study provides novel insights into the potential value of LOX/LOXL in cancer pathogenesis and treatment, and particularly its prognostic significance in glioma.https://doi.org/10.1186/s12964-025-02176-1Machine learningPan cancerLysyl oxidasesResponse predictionPrognostic model
spellingShingle Qingyu Xu
Ling Ma
Alexander Streuer
Eva Altrock
Nanni Schmitt
Felicitas Rapp
Alessa Klär
Verena Nowak
Julia Obländer
Nadine Weimer
Iris Palme
Melda Göl
Hong-hu Zhu
Wolf-Karsten Hofmann
Daniel Nowak
Vladimir Riabov
Machine learning-based in-silico analysis identifies signatures of lysyl oxidases for prognostic and therapeutic response prediction in cancer
Cell Communication and Signaling
Machine learning
Pan cancer
Lysyl oxidases
Response prediction
Prognostic model
title Machine learning-based in-silico analysis identifies signatures of lysyl oxidases for prognostic and therapeutic response prediction in cancer
title_full Machine learning-based in-silico analysis identifies signatures of lysyl oxidases for prognostic and therapeutic response prediction in cancer
title_fullStr Machine learning-based in-silico analysis identifies signatures of lysyl oxidases for prognostic and therapeutic response prediction in cancer
title_full_unstemmed Machine learning-based in-silico analysis identifies signatures of lysyl oxidases for prognostic and therapeutic response prediction in cancer
title_short Machine learning-based in-silico analysis identifies signatures of lysyl oxidases for prognostic and therapeutic response prediction in cancer
title_sort machine learning based in silico analysis identifies signatures of lysyl oxidases for prognostic and therapeutic response prediction in cancer
topic Machine learning
Pan cancer
Lysyl oxidases
Response prediction
Prognostic model
url https://doi.org/10.1186/s12964-025-02176-1
work_keys_str_mv AT qingyuxu machinelearningbasedinsilicoanalysisidentifiessignaturesoflysyloxidasesforprognosticandtherapeuticresponsepredictionincancer
AT lingma machinelearningbasedinsilicoanalysisidentifiessignaturesoflysyloxidasesforprognosticandtherapeuticresponsepredictionincancer
AT alexanderstreuer machinelearningbasedinsilicoanalysisidentifiessignaturesoflysyloxidasesforprognosticandtherapeuticresponsepredictionincancer
AT evaaltrock machinelearningbasedinsilicoanalysisidentifiessignaturesoflysyloxidasesforprognosticandtherapeuticresponsepredictionincancer
AT nannischmitt machinelearningbasedinsilicoanalysisidentifiessignaturesoflysyloxidasesforprognosticandtherapeuticresponsepredictionincancer
AT felicitasrapp machinelearningbasedinsilicoanalysisidentifiessignaturesoflysyloxidasesforprognosticandtherapeuticresponsepredictionincancer
AT alessaklar machinelearningbasedinsilicoanalysisidentifiessignaturesoflysyloxidasesforprognosticandtherapeuticresponsepredictionincancer
AT verenanowak machinelearningbasedinsilicoanalysisidentifiessignaturesoflysyloxidasesforprognosticandtherapeuticresponsepredictionincancer
AT juliaoblander machinelearningbasedinsilicoanalysisidentifiessignaturesoflysyloxidasesforprognosticandtherapeuticresponsepredictionincancer
AT nadineweimer machinelearningbasedinsilicoanalysisidentifiessignaturesoflysyloxidasesforprognosticandtherapeuticresponsepredictionincancer
AT irispalme machinelearningbasedinsilicoanalysisidentifiessignaturesoflysyloxidasesforprognosticandtherapeuticresponsepredictionincancer
AT meldagol machinelearningbasedinsilicoanalysisidentifiessignaturesoflysyloxidasesforprognosticandtherapeuticresponsepredictionincancer
AT honghuzhu machinelearningbasedinsilicoanalysisidentifiessignaturesoflysyloxidasesforprognosticandtherapeuticresponsepredictionincancer
AT wolfkarstenhofmann machinelearningbasedinsilicoanalysisidentifiessignaturesoflysyloxidasesforprognosticandtherapeuticresponsepredictionincancer
AT danielnowak machinelearningbasedinsilicoanalysisidentifiessignaturesoflysyloxidasesforprognosticandtherapeuticresponsepredictionincancer
AT vladimirriabov machinelearningbasedinsilicoanalysisidentifiessignaturesoflysyloxidasesforprognosticandtherapeuticresponsepredictionincancer