Putative biomarkers for predicting tumor sample purity based on gene expression data

Li, Yuanyuan; Umbach, David M.; Bingham, Adrienna; Li, Qi-Jing; Zhuang, Yuan; Li, Leping

doi:10.1186/s12864-019-6412-8

Cited by 28 publications

(23 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…6, November-December 2020: 306-312 researchers are increasingly using XGBoost in biomarker discovery. 12,33,34 To improve the prediction performance, we tuned hyperparameters using random search, which is more efficient than either a traditional manual or grid search and evaluates more of the search space, especially when the search space has more than three dimensions. 35 As we did not have an external data set to evaluate our model, we performed a sevenfold cross-validation with accuracy as the overall metric and sensitivity and specificity as the class-specific metrics.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Potential biomarker detection for liver cancer stem cell by machine learning approach

Farzane

Akbarzadeh

Ferdousi

et al. 2020

J. Contemp. Med. Sci.

View full text Add to dashboard Cite

Objectives: In this study, we aimed to identify putative biomarkers for identification and characterization of these cells in liver cancer. Methods: We employed a supervised machine learning method, XGBoost, to data from 13 GEO data series to classify samples using gene expression data. Results. Across the 376 samples (129 CSCs and 247 non-CSCs cases), XGBoost displayed high performance in the classification of data. XGBoost feature importance scores and SHAP (Shapley Additive explanation) values were used for the interpretation of results and analysis of individual gene importance. We confirmed that expression levels of a 10-gene set (PTGER3, AURKB, C15orf40, IDI2, OR8D1, NACA2, SERPINB6, L1CAM, SMC1A, and RASGRF1) were predictive. The results showed that these 10 genes can detect CSCs robustly with accuracy, sensitivity, and specificity of 97 %, 100 %, and 95 %, respectively. Conclusions. We suggest that the ten-gene set may be used as a biomarker set for detecting and characterizing CSCs using gene expression data.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Moreover, XGBoost is an optimized distributed gradient boosting that achieves state-of-the-art prediction performances. 12 Feature importance ranking using the common tree ensemble models such as XGBoost and gbm R packages may provide inconsistent results. These methods only consider the effect of splits along the decision path.…”

Section: Introductionmentioning

confidence: 99%

Potential biomarker detection for liver cancer stem cell by machine learning approach

Farzane

Akbarzadeh

Ferdousi

et al. 2020

J. Contemp. Med. Sci.

View full text Add to dashboard Cite

show abstract

“…Recently, tumor purity is inferred from different types of genomic data, such as somatic copy number data [18][19][20][21][22], somatic mutations data [23][24][25][26][27], gene expression data [28,29], and DNA methylation data [30][31][32][33]. The tumor purity obtained from these methods will be referred to as genomic tumor purity in this study.…”

Section: Introductionmentioning

confidence: 99%

Obtaining Spatially Resolved Tumor Purity Maps Using Deep Multiple Instance Learning In A Pan-cancer Study

Öner

Chen

Revkov

et al. 2021

Preprint

View full text Add to dashboard Cite

Tumor purity is the proportion of cancer cells in the tumor tissue. An accurate tumor purity estimation is crucial for accurate pathologic evaluation and for sample selection to minimize normal cell contamination in high throughput genomic analysis. We developed a novel deep multiple instance learning model predicting tumor purity from H&E stained digital histopathology slides. Our model successfully predicted tumor purity from slides of fresh-frozen sections in eight different TCGA cohorts and formalin-fixed paraffin-embedded sections in a local Singapore cohort. The predictions were highly consistent with genomic tumor purity values, which were inferred from genomic data and accepted as the golden standard. Besides, we obtained spatially resolved tumor purity maps and showed that tumor purity varies spatially within a sample. Our analyses on tumor purity maps also suggested that pathologists might have chosen high tumor content regions inside the slides during tumor purity estimation in the TCGA cohorts, which resulted in higher values than genomic tumor purity values. In short, our model can be utilized for high throughput sample selection for genomic analysis, which will help reduce pathologists’ workload and decrease inter-observer variability. Moreover, spatial tumor purity maps can help better understand the tumor microenvironment as a key determinant in tumor formation and therapeutic response.

show abstract

“…This study chose coiled-coil domain-containing protein 69 (CCDC69) as the target gene through bioinformatics analysis. Researchers used CCDC69 expression to predict tumor sample purity, 9 which is vital to immune infiltration. 10 Cui et al found that CCDC69 may reduce cisplatin resistance in ovarian cancer by activating P14ARF/MDM2/P53 signaling pathway.…”

Section: Introductionmentioning

confidence: 99%

Study on <em>CCDC69</em> interfering with the prognosis of patients with breast cancer through PPAR signal pathway

Zhang

Xia

2021

Eur J Histochem

View full text Add to dashboard Cite

Coiled-coil domain-containing protein 69 (CCDC69) is a novel gene and limited knowledge in known in breast cancer. In the present study, we aimed to explore the relationship between CCDC69 and breast cancer, demonstrate the clinicopathological significance and prognostic role of CCDC69 in breast cancer, and analyze the possible mechanism of CCDC69 affecting the prognosis of breast cancer. First, from GEO database, TIMER, GEPIA, and OncoLnc, we select CCDC69 as the potential gene which closely involved in breast cancer progression. Next, by real-time PCR detection, the expression of CCDC69 in breast cancer tissue was notably lower than that in normal breast tissues (p=0.0002). In addition, our immunohistochemistry (IHC) indicated that the positive expression rate of CCDC69 in the triple-negative breast cancer (TNBC) was lower than that in the non-TNBC (p=0.0362), and it was negatively correlated with the expression of Ki67 (p=0.001). Further enrichment analysis of CCDC69 and the similar genes performed on FunRich3.1.3 revealed that these genes were significantly associated with fat differentiation, and most of them were related to peroxisome proliferator-activated receptor (PPAR) signal pathway. Collectively, our findings suggest that CCDC69 is down regulated in breast cancer tissue especially in TNBC which has higher malignant grade and poorer clinical prognosis.

show abstract

Putative biomarkers for predicting tumor sample purity based on gene expression data

Cited by 28 publications

References 40 publications

Potential biomarker detection for liver cancer stem cell by machine learning approach

Potential biomarker detection for liver cancer stem cell by machine learning approach

Obtaining Spatially Resolved Tumor Purity Maps Using Deep Multiple Instance Learning In A Pan-cancer Study

Study on <em>CCDC69</em> interfering with the prognosis of patients with breast cancer through PPAR signal pathway

Contact Info

Product

Resources

About