A transcriptome-based deep neural network classifier for identifying the site of origin in mucinous cancer
Ontology highlight
ABSTRACT:
PROVIDER: PRJNA685029 | ENA |
REPOSITORIES: ENA
Dataset's files
| Action | DRS | |||
|---|---|---|---|---|
| SRR13249504_1.fastq.gz | Fastqsanger.gz | |||
| SRR13249504_2.fastq.gz | Fastqsanger.gz | |||
| SRR13249505_1.fastq.gz | Fastqsanger.gz | |||
| SRR13249505_2.fastq.gz | Fastqsanger.gz | |||
| SRR13249506_1.fastq.gz | Fastqsanger.gz |
Items per page: 5 1 - 5 of 12 |
Similar Datasets
Project description:Background There is a lack of tools for identifying the site of origin in mucinous cancer. This study aimed to evaluate the performance of a transcriptome-based classifier for identifying the site of origin in mucinous cancer. Methods Transcriptomic data of 1,878 non-mucinous and 82 mucinous cancer specimens, with 7 sites of origin, namely, the uterine cervix (CESC), colon (COAD), pancreas (PAAD), stomach (STAD), uterine endometrium (UCEC), uterine carcinosarcoma (UCS), and ovary (OV), obtained from The Cancer Genome Atlas, were used as the training and validation sets, respectively. Transcriptomic data of 14 mucinous cancer specimens from a tissue archive were used as the test set. For identifying the site of origin, a set of 100 differentially expressed genes for each site of origin was selected. After removing multiple iterations of the same gene, 626 genes were chosen, and their RNA expression profiles, at each site of origin, were used to train the deep neural network classifier. The performance of the classifier was estimated using the training, validation, and test sets. Results The accuracy of the model in the training set was 0.977, while that in the validation set was 0.939 (77/82). In the test set, the model showed an accuracy of 0.857 (12/14). t-SNE analysis revealed that samples in the test set were part of the clusters obtained for the training set. Conclusion Although limited by small sample size, we showed that a transcriptome-based classifier could correctly identify the site of origin of mucinous cancer.
2020-12-15 | GSE163126 | GEO
Project description:PurposeThere is a lack of tools for identifying the site of origin in mucinous cancer. This study aimed to evaluate the performance of a transcriptome-based classifier for identifying the site of origin in mucinous cancer.Materials and methodsTranscriptomic data of 1878 non-mucinous and 82 mucinous cancer specimens, with 7 sites of origin, namely, the uterine cervix (CESC), colon (COAD), pancreas (PAAD), stomach (STAD), uterine endometrium (UCEC), uterine carcinosarcoma (UCS), and ovary (OV), obtained from The Cancer Genome Atlas, were used as the training and validation sets, respectively. Transcriptomic data of 14 mucinous cancer specimens from a tissue archive were used as the test set. For identifying the site of origin, a set of 100 differentially expressed genes for each site of origin was selected. After removing multiple iterations of the same gene, 427 genes were chosen, and their RNA expression profiles, at each site of origin, were used to train the deep neural network classifier. The performance of the classifier was estimated using the training, validation, and test sets.ResultsThe accuracy of the model in the training set was 0.998, while that in the validation set was 0.939 (77/82). In the test set which is newly sequenced from a tissue archive, the model showed an accuracy of 0.857 (12/14). t-SNE analysis revealed that samples in the test set were part of the clusters obtained for the training set.ConclusionAlthough limited by small sample size, we showed that a transcriptome-based classifier could correctly identify the site of origin of mucinous cancer.
| S-EPMC9669684 | biostudies-literature
Project description:Mucinous colorectal adenocarcinoma
| PRJNA992109 | ENA
Project description:Introduction: Mucinous tumors are the second most common form of epithelial ovarian tumor, yet the cell of origin for this histological sub-type remains undetermined. While these tumors are thought to arise through a stepwise progression from benign cystadenoma to borderline tumor to invasive carcinoma, few studies have attempted to comprehensively characterize the genetic changes specific to this subtype or its precursors. Methods: To explore the spectrum of genomic alterations common to mucinous tumors we performed high resolution genome-wide copy number analysis, mutation screening by Sanger sequencing and immunohistochemistry on a series of primary ovarian mucinous cystadenomas (n=20) and borderline tumors (n=22). Results: Integration of copy number data, targeted mutation screening of RAS/RAF pathway members and immunohistochemistry reveals that p16 loss and RAS/RAF pathway alterations are highly recurrent events that occur early during mucinous tumor development. The frequency of concurrence of these events was observed in 40% of benign cystadenomas and 68% of borderline tumors. Conclusions: This study is the largest and highest resolution analysis of mucinous benign and borderline tumors performed to date and provides strong support for these lesions being precursors of primary ovarian mucinous adenocarcinoma. The high level of uniformity in the molecular events underlying the pathogenesis of mucinous ovarian tumors provides an opportunity for treatments targeting specific mutations and pathways. Copy number data was generated for 42 mucinous ovarian tumours (20 benign, 22 borderline). Epithelial and stromal DNA from the tumours and matched-normal lymphocyte DNA were all analysed. Processed/normalized data for the germline DNA samples are not provided because they themselves are normalised to a diploid copy number, making all the probe values 2, which is not informative.
2012-08-26 | E-GEOD-39076 | biostudies-arrayexpress
Project description:Introduction: Mucinous tumors are the second most common form of epithelial ovarian tumor, yet the cell of origin for this histological sub-type remains undetermined. While these tumors are thought to arise through a stepwise progression from benign cystadenoma to borderline tumor to invasive carcinoma, few studies have attempted to comprehensively characterize the genetic changes specific to this subtype or its precursors. Methods: To explore the spectrum of genomic alterations common to mucinous tumors we performed high resolution genome-wide copy number analysis, mutation screening by Sanger sequencing and immunohistochemistry on a series of primary ovarian mucinous cystadenomas (n=20) and borderline tumors (n=22). Results: Integration of copy number data, targeted mutation screening of RAS/RAF pathway members and immunohistochemistry reveals that p16 loss and RAS/RAF pathway alterations are highly recurrent events that occur early during mucinous tumor development. The frequency of concurrence of these events was observed in 40% of benign cystadenomas and 68% of borderline tumors. Conclusions: This study is the largest and highest resolution analysis of mucinous benign and borderline tumors performed to date and provides strong support for these lesions being precursors of primary ovarian mucinous adenocarcinoma. The high level of uniformity in the molecular events underlying the pathogenesis of mucinous ovarian tumors provides an opportunity for treatments targeting specific mutations and pathways.
2012-08-26 | GSE39076 | GEO
Project description:Background: With the incidence of papillary thyroid carcinoma rising worldwide, the decision about lobectomy versus total thyroidectomy will become relevant for an increasing number of patients. There exists no reliable biomarker for metastatic potential or tendency of recurrence that could assist in the risk stratification of patients. Objective: To develop a gene expression classifier for metastatic potential by measuring RNA expression in the primary tumor at the time of cancer surgery. Further, to investigate the ability of the gene expression classifier to identify metastatic and recurrent cases. Method: Genome-wide expression analyses. The development cohort consisted of freshly frozen tissues from 38 patients collected between the years 1986 and 2009. Validation was performed on a consecutive cohort of formalin fixated paraffin embedded surgical tissue specimens from 183 patients treated at Odense and Aarhus University Hospitals. Results: A 17 gene classifier (ADAMTS1, ANTXR1, C7, CXCL12, EBF1, FBLN2, FOSL2, GGT5, GPR124, JAM3, LRIG1, NDRG1, PRRX1, ROBO1, SORL1, TCF4, and ZEB1) was identified based on the expression values of these genes in the groups with and without metastasis in the development cohort. The 17 gene classifier for regional and/or distant metastasis identified was tested against the clinical status in the validation cohort. Sensitivity was 51.6% (95% CI 41.2%-61.8) and specificity 61.6 % (95% CI 50.5%-71.9%). Further, the Kaplan-Meyer method was used to estimate whether the classifier was useful as a prognostic marker for recurrences. Log-rank testing failed to identify any significance (p=0.32). Conclusion: A 17 gene classifier for metastatic potential was developed, and the results showed a clear biological difference between groups. However, through validation, the prognostic significance of this classifier could not be shown in identifying metastatic cases or in the ability of dichotomizing patients according to risk of recurrence after primary treatment. 38 patients with papillary thyroid carcinoma from a consecutive cohort of patients, no replicates
2015-01-20 | E-GEOD-65074 | biostudies-arrayexpress
Project description:Identifying the origin and mechanisms of pathological angiogenesis in neuroinflammatory diseases
| PRJNA867406 | ENA
Project description:Background: With the incidence of papillary thyroid carcinoma rising worldwide, the decision about lobectomy versus total thyroidectomy will become relevant for an increasing number of patients. There exists no reliable biomarker for metastatic potential or tendency of recurrence that could assist in the risk stratification of patients. Objective: To develop a gene expression classifier for metastatic potential by measuring RNA expression in the primary tumor at the time of cancer surgery. Further, to investigate the ability of the gene expression classifier to identify metastatic and recurrent cases. Method: Genome-wide expression analyses. The development cohort consisted of freshly frozen tissues from 38 patients collected between the years 1986 and 2009. Validation was performed on a consecutive cohort of formalin fixated paraffin embedded surgical tissue specimens from 183 patients treated at Odense and Aarhus University Hospitals. Results: A 17 gene classifier (ADAMTS1, ANTXR1, C7, CXCL12, EBF1, FBLN2, FOSL2, GGT5, GPR124, JAM3, LRIG1, NDRG1, PRRX1, ROBO1, SORL1, TCF4, and ZEB1) was identified based on the expression values of these genes in the groups with and without metastasis in the development cohort. The 17 gene classifier for regional and/or distant metastasis identified was tested against the clinical status in the validation cohort. Sensitivity was 51.6% (95% CI 41.2%-61.8) and specificity 61.6 % (95% CI 50.5%-71.9%). Further, the Kaplan-Meyer method was used to estimate whether the classifier was useful as a prognostic marker for recurrences. Log-rank testing failed to identify any significance (p=0.32). Conclusion: A 17 gene classifier for metastatic potential was developed, and the results showed a clear biological difference between groups. However, through validation, the prognostic significance of this classifier could not be shown in identifying metastatic cases or in the ability of dichotomizing patients according to risk of recurrence after primary treatment.
2015-01-20 | GSE65074 | GEO
Project description:Mucus is associated with poor prognosis of colorectal cancer, but its mechanism remains unclear. The aim of this study was to reveal the key proteins in mucinous colorectal cancer. In this study, high-resolution liquid chromatography tandem mass spectrometry (LC-MS / MS) combined with quantitative 6-plex tandem mass mass tag labeling was used to profile protein changes in the left and right sides of mucinous and non-mucinous colorectal cancer tissues. A total of 7432 proteins were identified and analyzed.
2020-11-28 | PXD022802 |
Project description:Transgenic mice (Scgb1a1-rtTA/[tetO]-KRAS.G12D/Nkx2-1+/-) develop mucinous lung tumors. Gene expression analysis was performed using mRNAs from the whole lungs of the mice compared to that of the control mice. We used microarrays to detail the global program of gene expression underlying development of mucinous lung tumors and identified distinct classes of up-regulated genes during this process. mRNAs were isolated from the whole lungs of the transgenic mice (Scgb1a1-rtTA/[tetO]-KRAS.G12D/Nkx2-1+/-) after 2 months doxycycline administration and hybridized on Affymetrix microarrays. We sought to identify genes induced in mucinous lung tumors.
2012-08-31 | E-GEOD-40508 | biostudies-arrayexpress