Comprehensive Characterization of Cancer Driver Genes and Mutations.

Identifying molecular cancer drivers is critical for precision oncology. Multiple advanced algorithms to identify drivers now exist, but systematic attempts to combine and optimize them on large datasets are few. We report a PanCancer and PanSoftware analysis spanning 9,423 tumor exomes (comprising all 33 of The Cancer Genome Atlas projects) and using 26 computational tools to catalog driver genes and mutations. We identify 299 driver genes with implications regarding their anatomical sites and cancer/cell types. Sequence- and structure-based analyses identified >3,400 putative missense driver mutations supported by multiple lines of evidence. Experimental validation confirmed 60%-85% of predicted mutations as likely drivers. We found that >300 MSI tumors are associated with high PD-1/PD-L1, and 57% of tumors analyzed harbor putative clinically actionable events. Our study represents the most comprehensive discovery of cancer genes and mutations to date and will serve as a blueprint for future biological and clinical endeavors.

PhenoDriver: interpretable framework for studying personalized phenotype-associated driver genes in breast cancer.

Identifying personalized cancer driver genes and further revealing their oncogenic mechanisms is critical for understanding the mechanisms of cell transformation and aiding clinical diagnosis. Almost all existing methods primarily focus on identifying driver genes at the cohort or individual level but fail to further uncover their underlying oncogenic mechanisms. To fill this gap, we present an interpretable framework, PhenoDriver, to identify personalized cancer driver genes, elucidate their roles in cancer development and uncover the association between driver genes and clinical phenotypic alterations. By analyzing 988 breast cancer patients, we demonstrate the outstanding performance of PhenoDriver in identifying breast cancer driver genes at the cohort level compared to other state-of-the-art methods. Otherwise, our PhenoDriver can also effectively identify driver genes with both recurrent and rare mutations in individual patients. We further explore and reveal the oncogenic mechanisms of some known and unknown breast cancer driver genes (e.g. TP53, MAP3K1, HTT, etc.) identified by PhenoDriver, and construct their subnetworks for regulating clinical abnormal phenotypes. Notably, most of our findings are consistent with existing biological knowledge. Based on the personalized driver profiles, we discover two existing and one unreported breast cancer subtypes and uncover their molecular mechanisms. These results intensify our understanding for breast cancer mechanisms, guide therapeutic decisions and assist in the development of targeted anticancer therapies.

DRdriver: identifying drug resistance driver genes using individual-specific gene regulatory network.

Drug resistance is one of principal limiting factors for cancer treatment. Several mechanisms, especially mutation, have been validated to implicate in drug resistance. In addition, drug resistance is heterogeneous, which makes an urgent need to explore the personalized driver genes of drug resistance. Here, we proposed an approach DRdriver to identify drug resistance driver genes in individual-specific network of resistant patients. First, we identified the differential mutations for each resistant patient. Next, the individual-specific network, which included the genes with differential mutations and their targets, was constructed. Then, the genetic algorithm was utilized to identify the drug resistance driver genes, which regulated the most differentially expressed genes and the least non-differentially expressed genes. In total, we identified 1202 drug resistance driver genes for 8 cancer types and 10 drugs. We also demonstrated that the identified driver genes were mutated more frequently than other genes and tended to be associated with the development of cancer and drug resistance. Based on the mutational signatures of all driver genes and enriched pathways of driver genes in brain lower grade glioma treated by temozolomide, the drug resistance subtypes were identified. Additionally, the subtypes showed great diversity in epithelial-mesenchyme transition, DNA damage repair and tumor mutation burden. In summary, this study developed a method DRdriver for identifying personalized drug resistance driver genes, which provides a framework for unlocking the molecular mechanism and heterogeneity of drug resistance.

Exploring gene-patient association to identify personalized cancer driver genes by linear neighborhood propagation.

BACKGROUND: Driver genes play a vital role in the development of cancer. Identifying driver genes is critical for diagnosing and understanding cancer. However, challenges remain in identifying personalized driver genes due to tumor heterogeneity of cancer. Although many computational methods have been developed to solve this problem, few efforts have been undertaken to explore gene-patient associations to identify personalized driver genes. RESULTS: Here we propose a method called LPDriver to identify personalized cancer driver genes by employing linear neighborhood propagation model on individual genetic data. LPDriver builds personalized gene network based on the genetic data of individual patients, extracts the gene-patient associations from the bipartite graph of the personalized gene network and utilizes a linear neighborhood propagation model to mine gene-patient associations to detect personalized driver genes. The experimental results demonstrate that as compared to the existing methods, our method shows competitive performance and can predict cancer driver genes in a more accurate way. Furthermore, these results also show that besides revealing novel driver genes that have been reported to be related with cancer, LPDriver is also able to identify personalized cancer driver genes for individual patients by their network characteristics even if the mutation data of genes are hidden. CONCLUSIONS: LPDriver can provide an effective approach to predict personalized cancer driver genes, which could promote the diagnosis and treatment of cancer. The source code and data are freely available at https://github.com/hyr0771/LPDriver .

Gsw-fi: a GLM model incorporating shrinkage and double-weighted strategies for identifying cancer driver genes with functional impact.

BACKGROUND: Cancer, a disease with high morbidity and mortality rates, poses a significant threat to human health. Driver genes, which harbor mutations accountable for the initiation and progression of tumors, play a crucial role in cancer development. Identifying driver genes stands as a paramount objective in cancer research and precision medicine. RESULTS: In the present work, we propose a method for identifying driver genes using a Generalized Linear Regression Model (GLM) with Shrinkage and double-Weighted strategies based on Functional Impact, which is named GSW-FI. Firstly, an estimating model is proposed for assessing the background functional impacts of genes based on GLM, utilizing gene features as predictors. Secondly, the shrinkage and double-weighted strategies as two revising approaches are integrated to ensure the rationality of the identified driver genes. Lastly, a statistical method of hypothesis testing is designed to identify driver genes by leveraging the estimated background function impacts. Experimental results conducted on 31 The Cancer Genome Altas datasets demonstrate that GSW-FI outperforms ten other prediction methods in terms of the overlap fraction with well-known databases and consensus predictions among different methods. CONCLUSIONS: GSW-FI presents a novel approach that efficiently identifies driver genes with functional impact mutations using computational methods, thereby advancing the development of precision medicine for cancer.

Unmutated RRAS2 emerges as a key oncogene in post-partum-associated triple negative breast cancer.

BACKGROUND: Breast cancer (BC) is the most common cancer in women, with triple negative BC (TNBC) accounting for 20% of cases. While early detection and targeted therapies have improved overall life expectancy, TNBC remains resistant to current treatments. Although parity reduces the lifetime risk of developing BC, pregnancy increases the risk of developing TNBC for years after childbirth. Although numerous gene mutations have been associated with BC, no single gene alteration has been identified as a universal driver. RRAS2 is a RAS-related GTPase rarely found mutated in cancer. METHODS: Conditional knock-in mice were generated to overexpress wild type human RRAS2 in mammary epithelial cells. A human sample cohort was analyzed by RT-qPCR to measure RRAS2 transcriptional expression and to determine the frequency of both a single-nucleotide polymorphism (SNP rs8570) in the 3'UTR region of RRAS2 and of genomic DNA amplification in tumoral and non-tumoral human BC samples. RESULTS: Here we show that overexpression of wild-type RRAS2 in mice is sufficient to develop TNBC in 100% of females in a pregnancy-dependent manner. In human BC, wild-type RRAS2 is overexpressed in 68% of tumors across grade, location, and molecular type, surpassing the prevalence of any previously implicated alteration. Still, RRAS2 overexpression is notably higher and more frequent in TNBC and young parous patients. The increased prevalence of the alternate C allele at the SNP position in tumor samples, along with frequent RRAS2 gene amplification in both tumors and blood of BC patients, suggests a cause-and-effect relationship between RRAS2 overexpression and breast cancer. CONCLUSIONS: Higher than normal expression of RRAS2 not bearing activating mutations is a key driver in the majority of breast cancers, especially those of the triple-negative type and those linked to pregnancy.

Comprehensive evaluation of computational methods for predicting cancer driver genes.

Optimal methods could effectively improve the accuracy of predicting and identifying candidate driver genes. Various computational methods based on mutational frequency, network and function approaches have been developed to identify mutation driver genes in cancer genomes. However, a comprehensive evaluation of the performance levels of network-, function- and frequency-based methods is lacking. In the present study, we assessed and compared eight performance criteria for eight network-based, one function-based and three frequency-based algorithms using eight benchmark datasets. Under different conditions, the performance of approaches varied in terms of network, measurement and sample size. The frequency-based driverMAPS and network-based HotNet2 methods showed the best overall performance. Network-based algorithms using protein-protein interaction networks outperformed the function- and the frequency-based approaches. Precision, F1 score and Matthews correlation coefficient were low for most approaches. Thus, most of these algorithms require stringent cutoffs to correctly distinguish driver and non-driver genes. We constructed a website named Cancer Driver Catalog (http://159.226.67.237/sun/cancer_driver/), wherein we integrated the gene scores predicted by the foregoing software programs. This resource provides valuable guidance for cancer researchers and clinical oncologists prioritizing cancer driver gene candidates by using an optimal tool.

Two-stage-vote ensemble framework based on integration of mutation data and gene interaction network for uncovering driver genes.

Identifying driver genes, exactly from massive genes with mutations, promotes accurate diagnosis and treatment of cancer. In recent years, a lot of works about uncovering driver genes based on integration of mutation data and gene interaction networks is gaining more attention. However, it is in suspense if it is more effective for prioritizing driver genes when integrating various types of mutation information (frequency and functional impact) and gene networks. Hence, we build a two-stage-vote ensemble framework based on somatic mutations and mutual interactions. Specifically, we first represent and combine various kinds of mutation information, which are propagated through networks by an improved iterative framework. The first vote is conducted on iteration results by voting methods, and the second vote is performed to get ensemble results of the first poll for the final driver gene list. Compared with four excellent previous approaches, our method has better performance in identifying driver genes on $33$ types of cancer from The Cancer Genome Atlas. Meanwhile, we also conduct a comparative analysis about two kinds of mutation information, five gene interaction networks and four voting strategies. Our framework offers a new view for data integration and promotes more latent cancer genes to be admitted.

Contrastive learning-based computational histopathology predict differential expression of cancer driver genes.

MOTIVATION: Digital pathological analysis is run as the main examination used for cancer diagnosis. Recently, deep learning-driven feature extraction from pathology images is able to detect genetic variations and tumor environment, but few studies focus on differential gene expression in tumor cells. RESULTS: In this paper, we propose a self-supervised contrastive learning framework, HistCode, to infer differential gene expression from whole slide images (WSIs). We leveraged contrastive learning on large-scale unannotated WSIs to derive slide-level histopathological features in latent space, and then transfer it to tumor diagnosis and prediction of differentially expressed cancer driver genes. Our experiments showed that our method outperformed other state-of-the-art models in tumor diagnosis tasks, and also effectively predicted differential gene expression. Interestingly, we found the genes with higher fold change can be more precisely predicted. To intuitively illustrate the ability to extract informative features from pathological images, we spatially visualized the WSIs colored by the attention scores of image tiles. We found that the tumor and necrosis areas were highly consistent with the annotations of experienced pathologists. Moreover, the spatial heatmap generated by lymphocyte-specific gene expression patterns was also consistent with the manually labeled WSIs.

Mutations in cancer-relevant genes are ubiquitous in histologically normal endometrial tissue.

OBJECTIVE: Endometrial cancer (EndoCA) is the most common gynecologic cancer and incidence and mortality rate continue to increase. Despite well-characterized knowledge of EndoCA-defining mutations, no effective diagnostic or screening tests exist. To lay the foundation for testing development, our study focused on defining the prevalence of somatic mutations present in non-cancerous uterine tissue. METHODS: We obtained ≥8 uterine samplings, including separate endometrial and myometrial layers, from each of 22 women undergoing hysterectomy for non-cancer conditions. We ultra-deep sequenced (>2000× coverage) samples using a 125 cancer-relevant gene panel. RESULTS: All women harbored complex mutation patterns. In total, 308 somatic mutations were identified with mutant allele frequencies ranging up to 96.0%. These encompassed 56 unique mutations from 24 genes. The majority of samples possessed predicted functional cancer mutations but curiously no growth advantage over non-functional mutations was detected. Functional mutations were enriched with increasing patient age (p = 0.045) and BMI (p = 0.0007) and in endometrial versus myometrial layers (68% vs 39%, p = 0.0002). Finally, while the somatic mutation landscape shared similar mutation prevalence in key TCGA-defined EndoCA genes, notably PIK3CA, significant differences were identified, including NOTCH1 (77% vs 10%), PTEN (9% vs 61%), TP53 (0% vs 37%) and CTNNB1 (0% vs 26%). CONCLUSIONS: An important caveat for future liquid biopsy/DNA-based cancer diagnostics is the repertoire of shared and distinct mutation profiles between histologically unremarkable and EndoCA tissues. The lack of selection pressure between functional and non-functional mutations in histologically unremarkable uterine tissue may offer a glimpse into an unrecognized EndoCA protective mechanism.

RB1 Mutations Induce Smoking-Related Bladder Cancer by Modulating the Cytochrome P450 Pathway.

Cigarette smoking causes multiple cancers by directly influencing mutation burden of driver mutations. However, the mechanism between somatic mutation caused by cigarette smoking and bladder tumorigenesis remains elusive. Smoking-related mutation profile of bladder cancer was characterized by The Cancer Genome Atlas cohort. Integraticve OncoGenomics database was utilized to detect the smoking-related driver genes, and its biological mechanism predictions were interpreted based on bulk transcriptome and single-cell transcriptome, as well as cell experiments. Cigarette smoking was associated with an increased tumor mutational burden under 65 years old (p = 0.031), and generated specific mutational signatures in smokers. RB1 was identified as a differentially mutated driver gene between smokers and nonsmokers, and the mutation rate of RB1 increased twofold after smoking (p = 0.008). RB1 mutations and the 4-aminobiphenyl interference could significantly decrease the RB1 expression level and thus promote the proliferation, invasion, and migration ability of bladder cancer cells. Enrichment analysis and real-time quantitative PCR (RT-qPCR) data showed that RB1 mutations inhibited cytochrome P450 pathway by reducing expression levels of UGT1A6 and AKR1C2. In addition, we also observed that the component of immunological cells was regulated by RB1 mutations through the stronger cell-to-cell interactions between epithelial scissor+ cells and immune cells in smokers. This study highlighted that RB1 mutations could drive smoking-related bladder tumorigenesis through inhibiting cytochrome P450 pathway and regulating tumor immune microenvironment.

Chromosome instability region analysis and identification of the driver genes of the epithelial ovarian cancer cell lines A2780 and SKOV3.

Epithelial ovarian cancer (EOC) is one of the most prevalent gynaecological cancers worldwide. The molecular mechanisms of serous ovarian cancer (SOC) remain unclear and not well understood. SOC cases are primarily diagnosed at the late stage, resulting in a poor prognosis. Advances in molecular biology techniques allow us to obtain a better understanding of precise molecular mechanisms and to identify the chromosome instability region and key driver genes in the carcinogenesis and progression of SOC. Whole-exome sequencing was performed on the normal ovarian cell line IOSE80 and the EOC cell lines SKOV3 and A2780. The single-nucleotide variation burden, distribution, frequency and signature followed the known ovarian mutation profiles, without chromosomal bias. Recurrently mutated ovarian cancer driver genes, including LRP1B, KMT2A, ARID1A, KMT2C and ATRX were also found in two cell lines. The genome distribution of copy number alterations was found by copy number variation (CNV) analysis, including amplification of 17q12 and 4p16.1 and deletion of 10q23.33. The CNVs of MED1, GRB7 and MIEN1 located at 17q12 were found to be correlated with the overall survival of SOC patients (MED1: p = 0.028, GRB7: p = 0.0048, MIEN1: p = 0.0051), and the expression of the three driver genes in the ovarian cell line IOSE80 and EOC cell lines SKOV3 and A2780 was confirmed by western blot and cell immunohistochemistry.

Network embedding framework for driver gene discovery by combining functional and structural information.

Comprehensive analysis of multiple data sets can identify potential driver genes for various cancers. In recent years, driver gene discovery based on massive mutation data and gene interaction networks has attracted increasing attention, but there is still a need to explore combining functional and structural information of genes in protein interaction networks to identify driver genes. Therefore, we propose a network embedding framework combining functional and structural information to identify driver genes. Firstly, we combine the mutation data and gene interaction networks to construct mutation integration network using network propagation algorithm. Secondly, the struc2vec model is used for extracting gene features from the mutation integration network, which contains both gene's functional and structural information. Finally, machine learning algorithms are utilized to identify the driver genes. Compared with the previous four excellent methods, our method can find gene pairs that are distant from each other through structural similarities and has better performance in identifying driver genes for 12 cancers in the cancer genome atlas. At the same time, we also conduct a comparative analysis of three gene interaction networks, three gene standard sets, and five machine learning algorithms. Our framework provides a new perspective for feature selection to identify novel driver genes.

Interactions between driver genes shape the signaling pathway landscape and direct hepatocellular carcinoma therapy.

Hepatocellular carcinoma (HCC) is one of the most lethal malignancies, whose initiation and development are driven by alterations in driver genes. In this study, we identified four driver genes (TP53, PTEN, CTNNB1, and KRAS) that show a high frequency of somatic mutations or copy number variations (CNVs) in patients with HCC. Four different spontaneous HCC mouse models were constructed to screen for changes in various kinase signaling pathways. The sgTrp53 + sgPten tumor upregulated mTOR and noncanonical nuclear factor-κB signaling, which was shown to be strongly inhibited by rapamycin (an mTOR inhibitor) in vitro and in vivo. The JAK-signal transducer and activator of transcription (STAT) signaling was activated in Ctnnb1mut + sgPten tumor, the proliferation of which was strongly inhibited by napabucasin (a STAT3 inhibitor). Additionally, mTOR, cytoskeleton, and AMPK signaling were upregulated while rapamycin and ezrin inhibitors exerted potent antiproliferative effects in sgPten + KrasG12D tumor. We found that JAK-STAT, MAPK, and cytoskeleton signaling were activated in sgTrp53 + KrasG12D tumor and the combination of sorafenib and napabucasin led to the complete inhibition of tumor growth in vivo. In patients with HCC who had the same molecular classification as our mouse models, the downstream signaling pathway landscapes associated with genomic alterations were identical. Our research provides novel targeted therapeutic options for the clinical treatment of HCC, based on the presence of specific genetic alterations within the tumor.

A greedy approach for mutual exclusivity analysis in cancer study.

The main challenge in cancer genomics is to distinguish the driver genes from passenger or neutral genes. Cancer genomes exhibit extensive mutational heterogeneity that no two genomes contain exactly the same somatic mutations. Such mutual exclusivity (ME) of mutations has been observed in cancer data and is associated with functional pathways. Analysis of ME patterns may provide useful clues to driver genes or pathways and may suggest novel understandings of cancer progression. In this article, we consider a probabilistic, generative model of ME, and propose a powerful and greedy algorithm to select the mutual exclusivity gene sets. The greedy method includes a pre-selection procedure and a stepwise forward algorithm which can significantly reduce computation time. Power calculations suggest that the new method is efficient and powerful for one ME set or multiple ME sets with overlapping genes. We illustrate this approach by analysis of the whole-exome sequencing data of cancer types from TCGA.

Heterogeneity in the immune microenvironment of bone metastasis in driver-positive non-small cell lung cancer.

Mutations in epidermal growth factor receptor and anaplastic lymphoma kinase are common driver events in non-small cell lung cancer (NSCLC), which are associated with a high frequency of bone metastases (BMs). While the bone marrow represents a specialized immune microenvironment, the immune repertoire of BMs remains unknown. Considering the higher incidence of BMs in driver gene-positive NSCLCs, and the unique biology of the bone, herein, we assessed the infiltrating immune cells and T cell receptor (TCR) profile of BMs in driver-positive NSCLCs. Immune profile of BMs in driver gene-positive NSCLC were assessed in 10 patients, where 6 had driver gene-positive mutation. TCR and bulk RNA sequencing were performed on malignant bone samples. The diversity and clonality of the TCR repertoire were analyzed. The cellular components were inferred from bulk gene expression profiles computationally by CIBERSORT. Although BMs were generally regarded as immune-cold tumors, immune cell composition analyses showed co-existence of cytotoxic and suppressor immune cells in driver-positive BM samples, as compared to primary lung. Analysis of the TCR repertoire indicated a trend of higher diversity and similar clonality in the driver-positive compared with the driver-negative subsets. In addition, we identified two cases that showed the opposite response to immune checkpoint blockade. A comparison of these two patients' BM samples showed more highly amplified clones, fewer M2 macrophages and more activated natural killer cells in the responder. In summary, BMs in NSCLC are heterogeneous in their immune microenvironment, which might be related to differential clinical outcomes to immune checkpoint blockade.

The methylation level of a single cancer risk marker gene reflects methylation burden in gastric mucosa.

BACKGROUND: Gastric cancer risk can be accurately predicted by measuring the methylation level of a single marker gene in gastric mucosa. However, the mechanism is still uncertain. We hypothesized that the methylation level measured reflects methylation alterations in the entire genome (methylation burden), induced by Helicobacter pylori (H. pylori) infection, and thus cancer risk. METHODS: Gastric mucosa of 15 healthy volunteers without H. pylori infection (G1), 98 people with atrophic gastritis (G2), and 133 patients with gastric cancer (G3) after H. pylori eradication were collected. Methylation burden of an individual was obtained by microarray analysis as an inverse of the correlation coefficient between the methylation levels of 265,552 genomic regions in the person's gastric mucosa and those in an entirely healthy mucosa. RESULTS: The methylation burden significantly increased in the order of G1 (n = 4), G2 (n = 18), and G3 (n = 19) and was well correlated with the methylation level of a single marker gene (r = 0.91 for miR124a-3). The average methylation levels of nine driver genes tended to increase according to the risk levels (P = 0.08 between G2 vs G3) and was also correlated with the methylation level of a single marker gene (r = 0.94). Analysis of more samples (14 G1, 97 G2, and 131 G3 samples) yielded significant increases of the average methylation levels between risk groups. CONCLUSIONS: The methylation level of a single marker gene reflects the methylation burden, which includes driver gene methylation, and thus accurately predicts cancer risk.

m6Acancer-Net: Identification of m6A-mediated cancer driver genes from gene-site heterogeneous network.

N6-methyladenosine (m6A) is the most abundant eukaryotic modification internal mRNA, which plays the crucial roles in the occurrence and development of cancer. However, current knowledge about m6A-mediated functional circuit and key genes targeted by m6A methylation in cancer is mostly elusive. Thus, here we proposed a novel network-based approach (called m6Acancer-Net) to identify m6A-mediated driver genes and their associated network in specific type of cancer, such as acute myeloid leukemia. m6A-mediated cancer driver genes are defined as genes mediated by m6A methylation, significantly mutated, and functionally interacted in cancer. m6Acancer-Net identified the m6A-mediated cancer driver genes by combining gene functional interaction network with RNA methylation, gene expression and mutation information. A cancer-specific gene-site heterogeneous network was firstly constructed by connecting the m6A site co-methylation network with the functional interaction pruned gene co-expression network generated from large scale gene expression profile of specific cancer. Then, the functional m6A-mediated genes were identified by selecting the m6A regulators as seed genes to perform the random walk with restart algorithm on the gene-site heterogeneous network. Finally, m6A-mediated cancer driver gene subnetworks were constructed by performing the heat diffusion of mutation frequency for functional m6A-mediated genes in protein-protein interaction networks. The experimental results of m6Acancer-Net on the acute myeloid leukemia (AML) and glioblastoma multiforme (GBM) data from TCGA project show that the m6A-mediated caner driver genes identified by m6Acancer-Net are targeted by m6A regulators, and mediate significant cancer-related pathways. They play crucial roles in development and prognostic stratification of cancer. Moreover, 15 m6A-mediated cancer driver genes identified in AML are validated by literatures to mediate AML progress, and 14 m6A-mediated cancer driver genes identified in GBM are validated by literatures to participate in development of GBM. m6Acancer-Net is reliable to identify the functionally significant m6A-mediated driver genes in specific cancer, and it can effectively facilitate the understanding of regulatory and therapeutic mechanism of cancer driver genes in epitranscriptome layer.

A radiomics nomogram prediction for survival of patients with "driver gene-negative" lung adenocarcinomas (LUAD).

BACKGROUND: To study the role of computed tomography (CT)-derived radiomics features and clinical characteristics on the prognosis of "driver gene-negative" lung adenocarcinoma (LUAD) and to explore the potential molecular biological which may be helpful for patients' individual postoperative care. METHODS: A total of 180 patients with stage I-III "driver gene-negative" LUAD in the First Affiliated Hospital of Sun Yat-Sen University from September 2003 to June 2015 were retrospectively collected. The Least Absolute Shrinkage and Selection Operator (LASSO) Cox regression model was used to screen radiomics features and calculated the Rad-score. The prediction performance of the nomogram model based on radiomics features and clinical characteristics was validated and then assessed with respect to calibration. Gene set enrichment analysis (GSEA) was used to explore the relevant biological pathways. RESULTS: The radiomics and the clinicopathological characteristics were combined to construct a nomogram resulted in better performance for the estimation of OS (C-index: 0.815; 95% confidence interval [CI]: 0.756-0.874) than the clinicopathological nomogram (C-index: 0.765; 95% CI: 0.692-0.837). Decision curve analysis demonstrated that in terms of clinical usefulness, the radiomics nomogram outperformed the traditional staging system and the clinicopathological nomogram. The clinical prognostic risk score of each patient was calculated based on the radiomics nomogram and divided by X-tile into high-risk (> 65.28) and low-risk (≤ 65.28) groups. GSEA results showed that the low-risk score group was directly related to amino acid metabolism, and the high-risk score group was related to immune and metabolism pathways. CONCLUSIONS: The radiomics nomogram was promising to predict the prognosis of patients with "driver gene-negative" LUAD. The metabolism and immune-related pathways may provide new treatment orientation for this genetically unique subset of patients, which may serve as a potential tool to guide individual postoperative care for those patients.

Accurate Prediction of Cancer Prognosis by Exploiting Patient-Specific Cancer Driver Genes.

Accurate prediction of the prognoses of cancer patients and identification of prognostic biomarkers are both important for the improved treatment of cancer patients, in addition to enhanced anticancer drugs. Many previous bioinformatic studies have been carried out to achieve this goal; however, there remains room for improvement in terms of accuracy. In this study, we demonstrated that patient-specific cancer driver genes could be used to predict cancer prognoses more accurately. To identify patient-specific cancer driver genes, we first generated patient-specific gene networks before using modified PageRank to generate feature vectors that represented the impacts genes had on the patient-specific gene network. Subsequently, the feature vectors of the good and poor prognosis groups were used to train the deep feedforward network. For the 11 cancer types in the TCGA data, the proposed method showed a significantly better prediction performance than the existing state-of-the-art methods for three cancer types (BRCA, CESC and PAAD), better performance for five cancer types (COAD, ESCA, HNSC, KIRC and STAD), and a similar or slightly worse performance for the remaining three cancer types (BLCA, LIHC and LUAD). Furthermore, the case study for the identified breast cancer and cervical squamous cell carcinoma prognostic genes and their subnetworks included several pathways associated with the progression of breast cancer and cervical squamous cell carcinoma. These results suggested that heterogeneous cancer driver information may be associated with cancer prognosis.