Browsing by Subject "Cox regression"

Now showing 1 - 7 of 7
  • Thumbnail Image
    Item
    Deep learning-based cancer survival prognosis from RNA-seq data: approaches and evaluations
    (BMC, 2020) Huang, Zhi; Johnson, Travis S.; Han, Zhi; Helm, Bryan; Cao, Sha; Zhang, Chi; Salama, Paul; Rizkalla, Maher; Yu, Christina Y.; Cheng, Jun; Xiang, Shunian; Zhan, Xiaohui; Zhang, Jie; Huang, Kun; Medicine, School of Medicine
    Background: Recent advances in kernel-based Deep Learning models have introduced a new era in medical research. Originally designed for pattern recognition and image processing, Deep Learning models are now applied to survival prognosis of cancer patients. Specifically, Deep Learning versions of the Cox proportional hazards models are trained with transcriptomic data to predict survival outcomes in cancer patients. Methods: In this study, a broad analysis was performed on TCGA cancers using a variety of Deep Learning-based models, including Cox-nnet, DeepSurv, and a method proposed by our group named AECOX (AutoEncoder with Cox regression network). Concordance index and p-value of the log-rank test are used to evaluate the model performances. Results: All models show competitive results across 12 cancer types. The last hidden layers of the Deep Learning approaches are lower dimensional representations of the input data that can be used for feature reduction and visualization. Furthermore, the prognosis performances reveal a negative correlation between model accuracy, overall survival time statistics, and tumor mutation burden (TMB), suggesting an association among overall survival time, TMB, and prognosis prediction accuracy. Conclusions: Deep Learning based algorithms demonstrate superior performances than traditional machine learning based models. The cancer prognosis results measured in concordance index are indistinguishable across models while are highly variable across cancers. These findings shedding some light into the relationships between patient characteristics and survival learnability on a pan-cancer level.
  • Thumbnail Image
    Item
    Genetic variants in the PIWI-piRNA pathway gene DCP1A predict melanoma disease-specific survival
    (Wiley, 2016-12-15) Zhang, Weikang; Liu, Hongliang; Yin, Jieyun; Wu, Wenting; Zhu, Dakai; Amos, Christopher I.; Fang, Shenying; Lee, Jeffrey E.; Han, Jiali; Wei, Qingyi; Department of Epidemiology, Richard M. Fairbanks School of Public Health
    The Piwi-piRNA pathway is important for germ cell maintenance, genome integrity, DNA methylation and retrotransposon control and thus may be involved in cancer development. In this study, we comprehensively analyzed prognostic roles of 3,116 common SNPs in PIWI-piRNA pathway genes in melanoma disease-specific survival. A published genome-wide association study (GWAS) by The University of Texas M.D. Anderson Cancer Center was used to identify associated SNPs, which were later validated by another GWAS from the Harvard Nurses' Health Study and Health Professionals Follow-up Study. After multiple testing correction, we found that there were 27 common SNPs in two genes (PIWIL4 and DCP1A) with false discovery rate < 0.2 in the discovery dataset. Three tagSNPs (i.e., rs7933369 and rs508485 in PIWIL4; rs11551405 in DCP1A) were replicated. The rs11551405 A allele, located at the 3' UTR microRNA binding site of DCP1A, was associated with an increased risk of melanoma disease-specific death in both discovery dataset [adjusted Hazards ratio (HR) = 1.66, 95% confidence interval (CI) = 1.21-2.27, p =1.50 × 10-3 ] and validation dataset (HR = 1.55, 95% CI = 1.03-2.34, p = 0.038), compared with the C allele, and their meta-analysis showed an HR of 1.62 (95% CI, 1.26-2.08, p =1.55 × 10-4 ). Using RNA-seq data from the 1000 Genomes Project, we found that DCP1A mRNA expression levels increased significantly with the A allele number of rs11551405. Additional large, prospective studies are needed to validate these findings.
  • Thumbnail Image
    Item
    Genetic variants in the vitamin D pathway genes VDBP and RXRA modulate cutaneous melanoma disease-specific survival
    (Wiley, 2016-03) Yin, Jieyun; Liu, Hongliang; Yi, Xiaohua; Wu, Wenting; Amos, Christopher I.; Feng, Shenying; Lee, Jeffrey E.; Han, Jiali; Wei, Qingyi; Department of Epidemiology, Richard M. Fairbanks School of Public Health
    Single nucleotide polymorphisms (SNPs) in the vitamin D pathway genes have been implicated in cutaneous melanoma (CM) risk, but their role in CM disease-specific survival (DSS) remains obscure. We comprehensively analyzed the prognostic roles of 2669 common SNPs in the vitamin D pathway genes using data from a published genome-wide association study (GWAS) at The University of Texas M.D. Anderson Cancer Center (MDACC) and then validated the SNPs of interest in another GWAS from the Nurses' Health Study and Health Professionals Follow-up Study. Among the 2669 SNPs, 203 were significantly associated with DSS in MDACC dataset (P < 0.05 and false-positive report probability < 0.2), of which 18 were the tag SNPs. In the replication, two of these 18 SNPs showed nominal significance: the VDBP rs12512631 T > C was associated with a better DSS [combined hazards ratio (HR) = 0.66]; and the same for RXRA rs7850212 C > A (combined HR = 0.38), which were further confirmed by the Fine and Gray competing-risks regression model. Further bioinformatics analyses indicated that these loci may modulate corresponding gene methylation status.
  • Thumbnail Image
    Item
    Genetic variants of PDGF signaling pathway genes predict cutaneous melanoma survival
    (Impact Journals, 2017-08-14) Li, Hong; Wang, Yanru; Liu, Hongliang; Shi, Qiong; Li, Hongyu; Wu, Wenting; Zhu, Dakai; Amos, Christopher I.; Fang, Shenying; Lee, Jeffrey E.; Li, Yi; Han, Jiali; Wei, Qingyi; Epidemiology, School of Public Health
    To investigate whether genetic variants of platelet-derived growth factor (PDGF) signaling pathway genes are associated with survival of cutaneous melanoma (CM) patients, we assessed associations of single-nucleotide polymorphisms in PDGF pathway with melanoma-specific survival in 858 CM patients of M.D. Anderson Cancer Center (MDACC). Additional data of 409 cases from Harvard University were also included for further analysis. We identified 13 SNPs in four genes (COL6A3, NCK2, COL5A1 and PRKCD) with a nominal P < 0.05 and false discovery rate (FDR) < 0.2 in MDACC dataset. Based on linkage disequilibrium, functional prediction and minor allele frequency, a representative SNP in each gene was selected. In the meta-analysis using MDACC and Harvard datasets, there were two SNPs associated with poor survival of CM patients: rs6707820 C>T in NCK2 (HR = 1.87, 95% CI = 1.35-2.59, Pmeta = 1.53E-5); and rs2306574 T>C in PRKCD (HR = 1.73, 95% CI = 1.33-2.24, Pmeta = 4.56E-6). Moreover, CM patients in MDACC with combined risk genotypes of these two loci had markedly poorer survival (HR = 2.47, 95% CI = 1.58-3.84, P < 0.001). Genetic variants of rs6707820 C>T in NCK2 and rs2306574 T>C in PRKCD of the PDGF signaling pathway may be biomarkers for melanoma survival.
  • Thumbnail Image
    Item
    Government Funding and Failure in Nonprofit Organizations
    (2011-03-15) Vance, Danielle L.; Bielefeld, Wolfgang; Lenkowsky, Leslie, 1946-; Steinberg, Richard
    For nonprofit organizations, securing and sustaining funding is essential to survival. Many nonprofit managers see government funding as ideal because of its perceived security (Grønbjerg, 1993; Froelich, 1999). However, there is little evidence to support the claim that such funds actually make nonprofits more sustainable, and some research has even suggested that nonprofits receiving “fickle” government funds are more likely to fail (Hager et al., 2004). The primary purpose of this work is to examine the relationship between government funding and nonprofit failure. Its secondary purpose is to understand the relationships between failure, government funding, and the causes for failure suggested by previous research—instability of the funding source and low funding diversification. To examine these relationships, I chose to use survival analysis and employed the Cox regression technique. Here, I analyzed the NCCS-Guidestar National Nonprofit Research Database, which archives nonprofit IRS filings from 1998 to 2003. This data set is noteworthy for its level of detail and its comprehensive nature. I found that organizations receiving government funding are less likely to fail, especially if this funding is part of a balanced portfolio. Organizations with higher percentages of nonprofit funding and organizations with less diversified overall portfolios do not. Furthermore, nonprofit organizations with less diversified portfolios were more likely to fail, and, among organizations receiving government funding, those with the highest percentage of their revenue from the government were more likely to fail than their counterparts with less funding.
  • Thumbnail Image
    Item
    Pseudogene-gene functional networks are prognostic of patient survival in breast cancer
    (BMC, 2020) Smerekanych, Sasha; Johnson, Travis S.; Huang, Kun; Zhang, Yan; Medicine, School of Medicine
    Background: Given the vast range of molecular mechanisms giving rise to breast cancer, it is unlikely universal cures exist. However, by providing a more precise prognosis for breast cancer patients through integrative models, treatments can become more individualized, resulting in more successful outcomes. Specifically, we combine gene expression, pseudogene expression, miRNA expression, clinical factors, and pseudogene-gene functional networks to generate these models for breast cancer prognostics. Establishing a LASSO-generated molecular gene signature revealed that the increased expression of genes STXBP5, GALP and LOC387646 indicate a poor prognosis for a breast cancer patient. We also found that increased CTSLP8 and RPS10P20 and decreased HLA-K pseudogene expression indicate poor prognosis for a patient. Perhaps most importantly we identified a pseudogene-gene interaction, GPS2-GPS2P1 (improved prognosis) that is prognostic where neither the gene nor pseudogene alone is prognostic of survival. Besides, miR-3923 was predicted to target GPS2 using miRanda, PicTar, and TargetScan, which imply modules of gene-pseudogene-miRNAs that are potentially functionally related to patient survival. Results: In our LASSO-based model, we take into account features including pseudogenes, genes and candidate pseudogene-gene interactions. Key biomarkers were identified from the features. The identification of key biomarkers in combination with significant clinical factors (such as stage and radiation therapy status) should be considered as well, enabling a specific prognostic prediction and future treatment plan for an individual patient. Here we used our PseudoFuN web application to identify the candidate pseudogene-gene interactions as candidate features in our integrative models. We further identified potential miRNAs targeting those features in our models using PseudoFuN as well. From this study, we present an interpretable survival model based on LASSO and decision trees, we also provide a novel feature set which includes pseudogene-gene interaction terms that have been ignored by previous prognostic models. We find that some interaction terms for pseudogenes and genes are significantly prognostic of survival. These interactions are cross-over interactions, where the impact of the gene expression on survival changes with pseudogene expression and vice versa. These may imply more complicated regulation mechanisms than previously understood. Conclusions: We recommend these novel feature sets be considered when training other types of prognostic models as well, which may provide more comprehensive insights into personalized treatment decisions.
  • Thumbnail Image
    Item
    SALMON: Survival Analysis Learning With Multi-Omics Neural Networks on Breast Cancer
    (Frontiers Media, 2019-03-08) Huang, Zhi; Zhan, Xiaohui; Xiang, Shunian; Johnson, Travis S.; Helm, Bryan; Yu, Christina Y.; Zhang, Jie; Salama, Paul; Rizkalla, Maher; Han, Zhi; Huang, Kun; Department of Medicine, Indiana University School of Medicine
    Improved cancer prognosis is a central goal for precision health medicine. Though many models can predict differential survival from data, there is a strong need for sophisticated algorithms that can aggregate and filter relevant predictors from increasingly complex data inputs. In turn, these models should provide deeper insight into which types of data are most relevant to improve prognosis. Deep Learning-based neural networks offer a potential solution for both problems because they are highly flexible and account for data complexity in a non-linear fashion. In this study, we implement Deep Learning-based networks to determine how gene expression data predicts Cox regression survival in breast cancer. We accomplish this through an algorithm called SALMON (Survival Analysis Learning with Multi-Omics Neural Networks), which aggregates and simplifies gene expression data and cancer biomarkers to enable prognosis prediction. The results revealed improved performance when more omics data were used in model construction. Rather than use raw gene expression values as model inputs, we innovatively use eigengene modules from the result of gene co-expression network analysis. The corresponding high impact co-expression modules and other omics data are identified by feature selection technique, then examined by conducting enrichment analysis and exploiting biological functions, escalated the interpretation of input feature from gene level to co-expression modules level. Our study shows the feasibility of discovering breast cancer related co-expression modules, sketch a blueprint of future endeavors on Deep Learning-based survival analysis. SALMON source code is available at https://github.com/huangzhii/SALMON/.