Improved personalized survival prediction of patients with diffuse large B-cell Lymphoma using gene expression profiling

Autor: Andrés Peleteiro Raíndo, Laura Bao Pérez, Aitor Abuin Blanco, José Ángel Díaz Arias, Adrián Mosquera Orgueira, Natalia Alonso Vence, Carlos Aliste Santos, José Luis Bello López, Beatriz Antelo Rodríguez, Miguel Cid López, Manuel Mateo Pérez Encinas, Ángeles Bendaña López, Marta Sonia González Pérez, Máximo Francisco Fraga Rodríguez
Jazyk: angličtina
Rok vydání: 2020
Předmět:
0301 basic medicine
Oncology
Male
Cancer Research
medicine.medical_specialty
Prognostic variable
Lymphoma
Survival
bcl-X Protein
Biology
lcsh:RC254-282
03 medical and health sciences
Tumor Necrosis Factor Receptor Superfamily
Member 9
0302 clinical medicine
Internal medicine
Genetics
medicine
Biomarkers
Tumor
Humans
Stage (cooking)
Transcriptomics
Survival analysis
Adaptor Proteins
Signal Transducing
Retrospective Studies
Proportional hazards model
Gene Expression Profiling
Computational Biology
RNA-Binding Proteins
Middle Aged
medicine.disease
lcsh:Neoplasms. Tumors. Oncology. Including cancer and carcinogens
Microarray Analysis
Prognosis
Survival Analysis
Baculoviral IAP Repeat-Containing 3 Protein
Random forest
Gene expression profiling
Gene Expression Regulation
Neoplastic
030104 developmental biology
030220 oncology & carcinogenesis
Test set
DLBCL
Female
Lymphoma
Large B-Cell
Diffuse
Prediction
Diffuse large B-cell lymphoma
Research Article
Unsupervised Machine Learning
Zdroj: BMC Cancer
BMC Cancer, Vol 20, Iss 1, Pp 1-9 (2020)
ISSN: 1471-2407
Popis: Background Thirty to forty percent of patients with Diffuse Large B-cell Lymphoma (DLBCL) have an adverse clinical evolution. The increased understanding of DLBCL biology has shed light on the clinical evolution of this pathology, leading to the discovery of prognostic factors based on gene expression data, genomic rearrangements and mutational subgroups. Nevertheless, additional efforts are needed in order to enable survival predictions at the patient level. In this study we investigated new machine learning-based models of survival using transcriptomic and clinical data. Methods Gene expression profiling (GEP) of in 2 different publicly available retrospective DLBCL cohorts were analyzed. Cox regression and unsupervised clustering were performed in order to identify probes associated with overall survival on the largest cohort. Random forests were created to model survival using combinations of GEP data, COO classification and clinical information. Cross-validation was used to compare model results in the training set, and Harrel’s concordance index (c-index) was used to assess model’s predictability. Results were validated in an independent test set. Results Two hundred thirty-three and sixty-four patients were included in the training and test set, respectively. Initially we derived and validated a 4-gene expression clusterization that was independently associated with lower survival in 20% of patients. This pattern included the following genes: TNFRSF9, BIRC3, BCL2L1 and G3BP2. Thereafter, we applied machine-learning models to predict survival. A set of 102 genes was highly predictive of disease outcome, outperforming available clinical information and COO classification. The final best model integrated clinical information, COO classification, 4-gene-based clusterization and the expression levels of 50 individual genes (training set c-index, 0.8404, test set c-index, 0.7942). Conclusion Our results indicate that DLBCL survival models based on the application of machine learning algorithms to gene expression and clinical data can largely outperform other important prognostic variables such as disease stage and COO. Head-to-head comparisons with other risk stratification models are needed to compare its usefulness.
Databáze: OpenAIRE
Externí odkaz: