scholarly journals A comparative study of different classification algorithms on RNA-Seq cancer data

2020 ◽  
pp. 24-35
Author(s):  
Nihat Yilmaz Simsek ◽  
Bulent Haznedar ◽  
Cihan Kuzudisli
Keyword(s):  
Clear Cell ◽  
Cell Cancer ◽  
Gene Mutations ◽  
Rna Seq ◽  
Accuracy Rate ◽  
Cancer Data ◽  
Diagnosis And Classification ◽  
Cancer Types ◽  
Artificial Neural Network Ann

Gene mutations are the most important reason of cancer diseases, and there are different kind of causing genes across these diseases. RNA-Seq technology enables us to allow for gathering information about many genes simultaneously; hence, RNA-Seq data can be used for cancer diagnosis and classification. In this study, RNA-Seq dataset for renal cell cancer is analysed using three different developed classification methods: random forest (RF), artificial neural network (ANN) and deep learning (DL). The genes in our dataset are related to the following cancer types: kidney renal papillary cell, kidney renal clear cell and kidney chromophore carcinomas. It suggests that the DL method gives the highest accuracy rate compared to RF and ANN for 95.15%, 91.83% and 89.22%, respectively. We believe that the results acquired in this study will make a contribution to the classification of cancer types and support doctors in their processes of decision making.   Keywords: Classification, gene-expression, RNA-Seq, DL.

scholarly journals The Cancer Genomic Atlas – “TO CONQUER CANCER”

2020 ◽  
Vol 0 ◽  
pp. 1-6
Author(s):  
Sai Sri Kavya Kadali ◽  
Rachna Gowlikar ◽  
Syeda Nooreen Fatima
Keyword(s):  
Genetic Basis ◽  
Data Repository ◽  
Rare Cancer ◽  
Cancer Data ◽  
Data Collection Process ◽  
Genomics And Proteomics ◽  
Prevention Studies ◽  
Cancer Types ◽  
Pan Cancer

The Cancer Genomic Atlas (TCGA) is a publicly accessible cancer data repository and tool that allows us to understand the molecular basis of cancer through the application of genomics and proteomics. So far, researchers have been able to diagnose 33 cancer types including 10 rare cancer types. The key features of TCGA are to make the data collection process publicly accessible for the better understanding of the molecular and genetic basis of cancer and its mechanism of action along with its prevention. Studies on different cancer types along with comprehensive pan cancer analysis have expanded the understanding and purpose of TCGA. Ever since its’ conceptualization, its’ high-throughput approach has provided a platform for the identification of genes and pathways involved in cancers and accurate classification of cancers.

Expression of endogenous retroviruses and response to immune checkpoint therapy in renal cell cancer.

2018 ◽  
Vol 36 (5_suppl) ◽  
pp. 104-104 ◽  
Author(s):  
Anshuman Panda ◽  
Aguirre De Cubas ◽  
Katy Beckermann ◽  
Gregory Riedlinger ◽  
Mark N. Stein ◽  
...  
Keyword(s):  
Immune Activation ◽  
Immune Checkpoint ◽  
Renal Cell ◽  
Clear Cell ◽  
Cell Cancer ◽  
Endogenous Retroviruses ◽  
Multiple Cancer ◽  
Checkpoint Activation ◽  
Cancer Types ◽  
Cell Renal Cancer

104 Background: In certain cancers, including renal cell carcinoma (RCC), no clear correlation exists between mutation burden and response to immune checkpoint therapy. To look for other markers of immune activation, we investigated the correlation between expression of endogenous retroviruses (ERV) and evidence of immune checkpoint activation in multiple cancer types. Methods: RNA-seq data of 4,910 tumors of 21 cancers from TCGA was analyzed to identify cancers in which there was correlation between ERV expression and evidence of immune checkpoint activation as shown by increased expression of immune checkpoint genes and evidence of CD8+ T-cell infiltration. Expression of candidate ERVs was measured by quantitative RT-PCR in a set of 20 RCC specimens. Results: In the TCGA clear-cell renal cancer, ER+HER2- breast cancer, and colon cancer datasets showed correlation between expression of a subset of ERVs and markers of local immune checkpoint activation. Using hierarchical clustering, tumors could be classified into 3 groups (high/intermediate/low) based on expression of these ERVs. In all these cancer types, the high ERV expressing group showed evidence of immune activation (robust immune infiltration with high CD8+ T cell fraction) and checkpoint (PD-1, CTLA-4) pathway over-expression. Expression of gene pathways associated with histone modification was significantly correlated with overall ERV expression, suggesting underlying dysregulation of chromatin silencing. Of ERVs analyzed ERV3.2 and ERVK-2 were most consistently associated with markers of immune checkpoint activation in multiple cancer types. For validation, expression of ERVs were measured in tumor sepcimens 20 clear cell renal cancer patients treated with immune checkpoint blockade. Expression of ERV3-2 and ERVK-2, was significantly increased in patients with clinical response to immune checkpoint therapy in this cohort. Conclusions: These data suggest that expression of ERV may be associated with activation of immune checkpoint pathways in renal cell cancer and may predict response to immune checkpoint therapy. Similar associations may also exist in some other solid tumors.

scholarly journals Pancancer survival analysis of cancer hallmark genes

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Ádám Nagy ◽  
Gyöngyi Munkácsy ◽  
Balázs Győrffy
Keyword(s):  
Survival Data ◽  
Proportional Hazards ◽  
Clear Cell ◽  
Genome Instability ◽  
Cell Cancer ◽  
Renal Clear Cell Carcinoma ◽  
Cox Proportional Hazards ◽  
Multiple Hypothesis Testing ◽  
Low Grade ◽  
Cancer Types

AbstractCancer hallmark genes are responsible for the most essential phenotypic characteristics of malignant transformation and progression. In this study, our aim was to estimate the prognostic effect of the established cancer hallmark genes in multiple distinct cancer types. RNA-seq HTSeq counts and survival data from 26 different tumor types were acquired from the TCGA repository. DESeq was used for normalization. Correlations between gene expression and survival were computed using the Cox proportional hazards regression and by plotting Kaplan–Meier survival plots. The false discovery rate was calculated to correct for multiple hypothesis testing. Signatures based on genes involved in genome instability and invasion reached significance in most individual cancer types. Thyroid and glioblastoma were independent of hallmark genes (61 and 54 genes significant, respectively), while renal clear cell cancer and low grade gliomas harbored the most prognostic changes (403 and 419 genes significant, respectively). The eight genes with the highest significance included BRCA1 (genome instability, HR 4.26, p < 1E−16), RUNX1 (sustaining proliferative signaling, HR 2.96, p = 3.1E−10) and SERPINE1 (inducing angiogenesis, HR 3.36, p = 1.5E−12) in low grade glioma, CDK1 (cell death resistance, HR = 5.67, p = 2.1E−10) in kidney papillary carcinoma, E2F1 (tumor suppressor, HR 0.38, p = 2.4E−05) and EREG (enabling replicative immortality, HR 3.23, p = 2.1E−07) in cervical cancer, FBP1 (deregulation of cellular energetics, HR 0.45, p = 2.8E−07) in kidney renal clear cell carcinoma and MYC (invasion and metastasis, HR 1.81, p = 5.8E−05) in bladder cancer. We observed unexpected heterogeneity and tissue specificity when correlating cancer hallmark genes and survival. These results will help to prioritize future targeted therapy development in different types of solid tumors.

scholarly journals Prognosis of ovarian clear cell cancer compared with other epithelial cancer types: A population‑based analysis

2020 ◽  
Author(s):  
Hong Liu ◽  
Yanbo Xu ◽  
Jiali Ji ◽  
Rongrong Dong ◽  
Huiqing Qiu ◽  
...  
Keyword(s):  
Clear Cell ◽  
Cell Cancer ◽  
Population Based ◽  
Epithelial Cancer ◽  
Cancer Types

scholarly journals ROTS: reproducible RNA-seq biomarker detector—prognostic markers for clear cell renal cell cancer

2015 ◽  
Vol 44 (1) ◽  
pp. e1-e1 ◽  
Author(s):  
Fatemeh Seyednasrollah ◽  
Krista Rantanen ◽  
Panu Jaakkola ◽  
Laura L. Elo
Keyword(s):  
Renal Cell Cancer ◽  
Renal Cell ◽  
Prognostic Markers ◽  
Clear Cell ◽  
Cell Cancer ◽  
Rna Seq

scholarly journals Discrepant Hemophilia A: An Underdiagnosed Disease Entity

2020 ◽  
Vol 154 (1) ◽  
pp. 78-87
Author(s):  
Ahmad Al-Huniti ◽  
Anjali Sharathkumar ◽  
Michelle Krantz ◽  
Karla Watkinson ◽  
Sharathkumar Bhagavathi
Keyword(s):  
Literature Review ◽  
Clinical Management ◽  
Hemophilia A ◽  
Gene Mutations ◽  
Retrospective Chart Review ◽  
Current Understanding ◽  
Pooled Prevalence ◽  
Diagnosis And Classification ◽  
High Index Of Suspicion

Abstract Objectives The term discrepant hemophilia A (DHA) denotes the discrepancy between factor VIII activity (FVIII:C) measured by different assay methodologies in patients with nonsevere hemophilia A (HA). The objective was to review the characteristics and the current understanding of mechanisms contributing to assay discrepancy in DHA. Methods Characteristics of the DHA patients treated were examined by retrospective chart review. In addition, a literature review was performed to determine the current understanding of DHA. Results Three cases of DHA were diagnosed based on bleeding phenotype: 2 cases represented missed diagnoses of HA, and 1 represented misclassification of hemophilia severity. The revised diagnosis and classification of hemophilia directly affected clinical management. Review of the literature identified 18 articles with an estimated pooled prevalence of 36% (95% CI, 23%-56%; I2 = 85%; P &lt; .01) among nonsevere HA. Furthermore, literature indicated that DHA is a feature of how different FVIII gene mutations affect FVIII:C activity within different assay methodologies. Conclusions Our experience and literature review suggested that DHA is not only a laboratory phenomenon—it can affect clinical management in a subset of patients. A high index of suspicion for DHA is necessary while evaluating bleeding patients and/or classifying nonsevere HA.

scholarly journals Defining Signatures of Arm-Wise Copy Number Change and Their Associated Drivers in Kidney Cancers

2019 ◽  
Vol 20 (22) ◽  
pp. 5762
Author(s):  
Graeme Benstead-Hume ◽  
Sarah K. Wooller ◽  
Jessica A Downs ◽  
Frances M. G. Pearl
Keyword(s):  
Cell Carcinoma ◽  
Copy Number ◽  
Clear Cell ◽  
Gene Mutations ◽  
The Cancer Genome Atlas ◽  
Tissue Type ◽  
Specific Gene ◽  
Cell Renal Cell Carcinoma ◽  
Tissue Samples ◽  
Cancer Data

Using pan-cancer data from The Cancer Genome Atlas (TCGA), we investigated how patterns in copy number alterations in cancer cells vary both by tissue type and as a function of genetic alteration. We find that patterns in both chromosomal ploidy and individual arm copy number are dependent on tumour type. We highlight for example, the significant losses in chromosome arm 3p and the gain of ploidy in 5q in kidney clear cell renal cell carcinoma tissue samples. We find that specific gene mutations are associated with genome-wide copy number changes. Using signatures derived from non-negative factorisation, we also find gene mutations that are associated with particular patterns of ploidy change. Finally, utilising a set of machine learning classifiers, we successfully predicted the presence of mutated genes in a sample using arm-wise copy number patterns as features. This demonstrates that mutations in specific genes are correlated and may lead to specific patterns of ploidy loss and gain across chromosome arms. Using these same classifiers, we highlight which arms are most predictive of commonly mutated genes in kidney renal clear cell carcinoma (KIRC).

scholarly journals Pancancer survival analysis of cancer hallmark genes

2020 ◽  
Author(s):  
Ádám Nagy ◽  
Gyöngyi Munkácsy ◽  
Balázs Győrffy
Keyword(s):  
Survival Data ◽  
Proportional Hazards ◽  
Clear Cell ◽  
Genome Instability ◽  
Cell Cancer ◽  
Renal Clear Cell Carcinoma ◽  
Cox Proportional Hazards ◽  
Multiple Hypothesis Testing ◽  
Low Grade ◽  
Cancer Types

ABSTRACTCancer hallmark genes are responsible for the most essential phenotypic characteristics of malignant transformation and progression. In this study, our aim was to estimate the prognostic effect of the established cancer hallmark genes in multiple distinct cancer types.RNA-seq HTSeq counts and survival data from 26 different tumor types were acquired from the TCGA repository. DESeq was used for normalization. Correlations between gene expression and survival were computed using the Cox proportional hazards regression and by plotting Kaplan-Meier survival plots. The false discovery rate was calculated to correct for multiple hypothesis testing.Signatures based on genes involved in genome instability and invasion reached significance in most individual cancer types. Thyroid and glioblastoma were independent of hallmark genes (61 and 54 genes significant, respectively), while renal clear cell cancer and low grade gliomas harbored the most prognostic changes (403 and 419 genes significant, respectively). The eight genes with the highest significance included BRCA1 (genome instability, HR=4.26, p<1E-16), RUNX1 (sustaining proliferative signaling, HR=2.96, p=3.1E-10) and SERPINE1 (inducing angiogenesis, HR=3.36, p=1.5E-12) in low grade glioma, CDK1 (cell death resistance, HR=5.67, p=2.1E-10) in kidney papillary carcinoma, E2F1 (tumor suppressor, HR=0.38, p=2.4E-05) and EREG (enabling replicative immortality, HR=3.23, p=2.1E-07) in cervical cancer, FBP1 (deregulation of cellular energetics, HR=0.45, p=2.8E-07) in kidney renal clear cell carcinoma and MYC (invasion and metastasis, HR=1.81, p=5.8E-05) in bladder cancer.We observed unexpected heterogeneity and tissue specificity when correlating cancer hallmark genes and survival. These results will help to prioritize future targeted therapy development in different types of solid tumors.

scholarly journals Peningkatan Akurasi Klasifikasi Ketidaktepatan Waktu Kelulusan Mahasiswa Menggunakan Metode Boosting Neural Network

Jurnal Varian ◽  
2020 ◽  
Vol 3 (2) ◽  
pp. 95-102
Author(s):  
I Ketut Putu Suniantara ◽  
Gede Suwardika ◽  
Siti Soraya
Keyword(s):  
Neural Network ◽  
Classification Accuracy ◽  
Feedforward Neural Network ◽  
Classification Model ◽  
Classification Problems ◽  
Accuracy Rate ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
And Training

Supervised learning in Machine learning is used to overcome classification problems with the Artificial Neural Network (ANN) approach. ANN has a few weaknesses in the operation and training process if the amount of data is large, resulting in poor classification accuracy. The results of the classification accuracy of Artificial Neural Networks will be better by using boosting. This study aims to develop a Boosting Feedforward Neural Network (FANN) classification model that can be implemented and used as a form of classification model that results in better accuracy, especially in the classification of the inaccuracy of Terbuka University students. The results showed the level of accuracy produced by the Feedforward Neural Network (FFNN) method had an accuracy rate of 72.93%. The application of boosting on FFN produces the best level of accuracy which is 74.44% at 500 iterations

Sign in / Sign up

Export Citation Format

Share Document