Machine learning-based analysis of genomic and transcriptomic data unveils sarcoma clusters with superlative prognostic and predictive value
Esperanca-Martins, M.; Vasques, H.; Ravasqueira, M. S.; Lemos, M. M.; Fonseca, F.; Coutinho, D.; Lopez, J. A.; Huang, R. S. P.; Dias, S.; Gallego-Paez, L.; Costa, L.; Abecasis, N.; Goncalves, E.; Fernandes, I.
Show abstract
Soft tissue sarcomas (STS) histopathological classification system has several conceptual caveats, impacting prognostication and treatment. The clinical and molecular-based tools currently employed to estimate prognosis also have limitations. Clinically driven molecular profiling studies may cover these gaps. We performed DNA sequencing (DNAseq) and RNA sequencing (RNAseq), portraying the molecular profile of 102 samples of 3 of the most common STS subtypes. The RNAseq data was analyzed using unsupervised machine learning models, unravelling previously unknown molecular patterns and identifying 4 well-defined transcriptomic clusters. These transcriptomic clusters have a clear prognostic value, a finding that was externally validated. This transcriptomic cluster-based classifications prognostic value is superior to the prognostic accuracy of currently used clinical-based (SARCULATOR nomograms) and molecular-based (CINSARC) prognostication tools. The analysis of DNAseq data from the same cohort of samples revealed a plethora of unique and, in some cases, never documented molecular targets for precision treatment across different transcriptomic clusters.
Matching journals
The top 5 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Use of high-plex data reveals novel insights into the tumour microenvironment of clear cell renal cell carcinoma 96%
- Identification of atypical circulating tumor cells with prognostic value in metastatic breast cancer patients 95%
- COL7A1 expression improves prognosis prediction for patients with clear cell renal cell carcinoma atop of stage 94%
Similar papers in this journal
- ROLE OF cfDNA AND ctDNA TO IMPROVE THE RISK STRATIFICATION AND THE DISEASE FOLLOW-UP IN PATIENTS WITH ENDOMETRIAL CANCER: TOWARDS THE CLINICAL APPLICATION 95%
- Long-term patient-derived ovarian cancer organoids closely recapitulate tumor of origin and clinical response 94%
- The Immune landscape of solid pediatric tumors. 93%
Similar papers in this journal
- Regulatory FOXP3+ T cells in uterine sarcomas are associated with favorable prognosis, low extracellular matrix expression and reduced YAP activation 93%
- Genetic and Epigenetic Characterization of Sarcoma Stem Cells Across Subtypes Identifies EZH2 as a Therapeutic Target 93%
- Development and validation of a gene expression score to account for tumour purity and improve prognostication in breast cancer 93%
Similar papers in this journal
- Molecular diagnosis and prognosis of cancers of unknown-primary (CUPs): progress from a microRNA-based droplet digital PCR assay 95%
- Chemoresistome Mapping in Individual Breast Cancer Patients Unravels Diversity in Dynamic Transcriptional Adaptation 93%
- Data-driven discovery of gene expression markers distinguishing pediatric acute lymphoblastic leukemia subtypes 93%
Similar papers in this journal
- Analysis of Mutational Profile of Hypopharyngeal and Laryngeal Head and Neck Cancers Identifies KMT2C as a Potential Tumor Suppressor 94%
- Integrated molecular and pharmacological characterization of patient-derived xenografts from bladder and ureteral cancers identifies new potential therapies. 93%
- Novel kinome profiling technology reveals drug treatment is patient and 2D/3D model dependent in GBM 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.