MaxMIF: A New Method for Identifying Cancer Driver Genes through Effective Data Integration

Hou, Yingnan; Gao, Bo; Li, Guojun; Su, Zhengchang

doi:10.1002/advs.201800640

Cited by 34 publications

(27 citation statements)

References 44 publications

(66 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, they have some known limitations, such as a high false positive rate, and they often fail to detect driver genes with low mutation frequencies (Bashashati et al, 2012 ; Koboldt et al, 2012 ; Muzny et al, 2012 ). Based on the hypothesis that gene mutations tend to converge on a few biological pathways, some pathway-based methods attempt to identify cancer driver modules consisting of multiple genes rather than individual genes using some biological prior knowledge (Bashashati et al, 2012 ; Paull et al, 2013 ; Leiserson et al, 2015 ; Gao et al, 2017 ; Hou et al, 2018 ; Carlin et al, 2019 ). However, the application of these methods is limited by the incompleteness of prior knowledge database.…”

Section: Introductionmentioning

confidence: 99%

FI-Net: Identification of Cancer Driver Genes by Using Functional Impact Prediction Neural Network

Qin

et al. 2020

Front. Genet.

View full text Add to dashboard Cite

Identification of driver genes, whose mutations cause the development of tumors, is crucial for the improvement of cancer research and precision medicine. To overcome the problem that the traditional frequency-based methods cannot detect lowly recurrently mutated driver genes, researchers have focused on the functional impact of gene mutations and proposed the function-based methods. However, most of the function-based methods estimate the distribution of the null model through the non-parametric method, which is sensitive to sample size. Besides, such methods could probably lead to underselection or overselection results. In this study, we proposed a method to identify driver genes by using functional impact prediction neural network (FI-net). An artificial neural network as a parametric model was constructed to estimate the functional impact scores for genes, in which multi-omics features were used as the multivariate inputs. Then the estimation of the background distribution and the identification of driver genes were conducted in each cluster obtained by the hierarchical clustering algorithm. We applied FI-net and other 22 state-of-the-art methods to 31 datasets from The Cancer Genome Atlas project. According to the comprehensive evaluation criterion, FI-net was powerful among various datasets and outperformed the other methods in terms of the overlap fraction with Cancer Gene Census and Network of Cancer Genes database, and the consensus in predictions among methods. Furthermore, the results illustrated that FI-net can identify known and potential novel driver genes.

show abstract

Section: Introductionmentioning

confidence: 99%

FI-Net: Identification of Cancer Driver Genes by Using Functional Impact Prediction Neural Network

Qin

et al. 2020

Front. Genet.

View full text Add to dashboard Cite

show abstract

“…The MaxMIF ( 23 ), which outperformed the existing state-of-the-art methods (including MUFFINN ( 24 ), MuttSig2 ( 25 ), MutSigCV ( 26 ), et al) on TCGA pan-cancer datasets, was introduced to distinguish the cancer driver genes from the passenger genes. MaxMIF integrated the somatic mutation data and molecular interaction data by a maximal mutational impact function.…”

Section: Methodsmentioning

confidence: 99%

The Clinical and Molecular Characterization of Gastric Cancer Patients in Qinghai-Tibetan Plateau

Rong

Zhang

et al. 2020

Front. Oncol.

View full text Add to dashboard Cite

Gastric cancer was the fifth most common malignancy and the third deadliest cancer (738,000 deaths in 2018) in the world. The analysis of its molecular characteristics has been complicated by histological and intratumor heterogeneity. Furthermore, the previous studies indicate that the incidence of gastric cancer shows wide geographical variation. As the largest and highest region in China, Qinghai-Tibetan Plateau (QTP) is one of the important global biodiversity hotspots. Here, to better understand the mechanism of gastric cancer and offer the targeted therapeutic strategies specially designed for patients in QTP, we collect tumor and blood samples from 30 primary gastric adenocarcinoma cancer patients at Qinghai Provincial People's Hospital. We discuss the clinical and molecular characteristics for these patients that have been ascribed to the unique features in this place, including high altitude (the average height above sea level is around 4,000 m), multi-ethnic groups, and the specific ways of life or habits (such as eating too much beef and mutton, have alcohol and cigarette problem, et al.). By comparing with the western gastric cancer patients collected from TCGA data portal, some unique characteristics for patients in QTP are suggested. They include high incidence in younger people, most of tumor are located in body, most of SNP are detected in chromosome 7, and the very different molecular atlas in minor ethnic groups and Han Chinese. These characteristics will provide the unprecedented opportunity to increase the efficacy for diagnosis and prognosis of gastric cancer in QTP. Furthermore, to suggest the targeted therapeutics specially designed for these 30 patients, an adapted kernel-based learning model and a compilation of pharmacogenomics data of 462 patient-derived tumor cells (PDCs) that illustrate the diverse genetic and molecular backgrounds of cancer patients, were introduced. In conclusion, our study offers a big opportunity to better understand the mechanism of gastric cancer in QTP and guide the optimal patient-tailored therapy for them.

show abstract

“…For example, in the Asthma comparison we considered all subsets of size 6 to 402 in increments of 3. These AUCs enabled us to fit a "standard curve" for each comparison, from which we could interpolate the mean number of samples gained by using GEOlimma given initial numbers of 6,9,12, and 15 (Asthma) samples. Figure SFig-ure5 presents the AUC standard curves and Table 3 summarizes the distribution of GEOlimma effective sample sizes for each comparison.…”

Section: Geolimma Methods Application On Four Validation Datasetsmentioning

confidence: 99%

GEOlimma: Differential Expression Analysis and Feature Selection Using Pre-Existing Microarray Data

Townsend

Daigle

2019

Preprint

View full text Add to dashboard Cite

Background: Differential expression and feature selection analyses are essential steps for the development of accurate diagnostic/prognostic classifiers of complicated human diseases using transcriptomics data. These steps are particularly challenging due to the curse of dimensionality and the presence of technical and biological noise. A promising strategy for overcoming these challenges is the incorporation of pre-existing transcriptomics data in the identification of differentially expressed (DE) genes. This approach has the potential to improve the quality of selected genes, increase classification performance, and enhance biological interpretability. While a number of methods have been developed that use pre-existing data for differential expression analysis, existing methods do not leverage the identities of experimental conditions to create a robust metric for identifying DE genes.Results: In this study, we propose a novel differential expression and feature selection method-GEOlimma-which combines pre-existing microarray data from the Gene Expression Omnibus (GEO) with the widely-applied Limma method for differential expression analysis. We first quantify differential gene expression across 2481 pairwise comparisons from 602 curated GEO Datasets, and we convert differential expression frequencies to DE prior probabilities. Genes with high DE prior probabilities show enrichment in cell growth and death, signal transduction, and cancer-related biological pathways, while genes with low prior probabilities were enriched in sensory system pathways. We then applied GEOlimma to four differential expression comparisons within two human disease datasets and performed differential expression, feature selection, and supervised classification analyses. Our results suggest that use of GEOlimma provides greater experimental power to detect DE genes compared to Limma, due to its increased effective sample size. Furthermore, in a supervised classification analysis using GEOlimma as a feature selection method, we observed similar or better classification performance than Limma given small, noisy subsets of an asthma dataset.Conclusions: Our results demonstrate that GEOlimma is a more effective method for differential gene expression and feature selection analyses compared to the standard Limma method. Due to its focus on gene-level differential expression, GEOlimma also has the potential to be applied to other high-throughput biological datasets.

show abstract

MaxMIF: A New Method for Identifying Cancer Driver Genes through Effective Data Integration

Cited by 34 publications

References 44 publications

FI-Net: Identification of Cancer Driver Genes by Using Functional Impact Prediction Neural Network

FI-Net: Identification of Cancer Driver Genes by Using Functional Impact Prediction Neural Network

The Clinical and Molecular Characterization of Gastric Cancer Patients in Qinghai-Tibetan Plateau

GEOlimma: Differential Expression Analysis and Feature Selection Using Pre-Existing Microarray Data

Contact Info

Product

Resources

About