scholarly journals Providing an optimized model to detect driver genes from heterogeneous cancer samples using restriction in subspace learning

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Ali Reza Ebadi ◽  
Ali Soleimani ◽  
Abdulbaghi Ghaderzadeh
Keyword(s):  
Subspace Learning ◽  
Driver Gene ◽  
Controversial Issues ◽  
Learning Method ◽  
Driver Genes ◽  
Gene Group ◽  
Optimized Model ◽  
Cancer Studies ◽  
Degree Of Overlap ◽  
Better Than

AbstractExtracting the drivers from genes with mutation, and segregation of driver and passenger genes are known as the most controversial issues in cancer studies. According to the heterogeneity of cancer, it is not possible to identify indicators under a group of associated drivers, in order to identify a group of patients with diseases related to these subgroups. Therefore, the precise identification of the related driver genes using artificial intelligence techniques is still considered as a challenge for researchers. In this research, a new method has been developed using the subspace learning method, unsupervised learning, and with more constraints. Accordingly, it has been attempted to extract the driver genes with more precision and accurate results. The obtained results show that the proposed method is more to predict the driver genes and subgroups of driver genes which have the highest degree of overlap due to p-value with known driver genes in valid databases. Driver genes are the benchmark of MsigDB which have more overlap compared to them as selected driver genes. In this article, in addition to including the driver genes defined in previous work, introduce newer driver genes. The minister will define newer groups of driver genes compared to other methods the p-value of the proposed method was 9.21e-7 better than previous methods for 200 genes. Due to the overlap and newer driver genes and driver gene group and subgroups. The results show that the p value of the proposed method is about 2.7 times less than the driver sub method due to overlap, indicating that the proposed method can identify driver genes in cancerous tumors with greater accuracy and reliability.

scholarly journals Providing An Optimized Model to Detect Driver Genes From Heterogeneous Cancer Samples, Using Restriction in Subspace Learning

2020 ◽  
Author(s):  
Ali Reza EBADI ◽  
Ali Soleimani ◽  
ABDULBAGHI GHADERZADEH3
Keyword(s):  
Artificial Intelligence ◽  
Unsupervised Learning ◽  
Subspace Learning ◽  
P Value ◽  
Controversial Issues ◽  
Learning Method ◽  
Driver Genes ◽  
Optimized Model ◽  
Cancer Studies ◽  
Better Than

Abstract Extracting the drivers from genes with mutation, and segregation of driver and passenger genes are known as the most controversial issues in cancer studies. According to the heterogeneity of cancer, it is not possible to identify indicators under a group of associated drivers, in order to identify a group of patients with diseases related to these subgroups. Therefore, the precise identification of the related driver genes using artificial intelligence techniques is still considered as a challenge for researchers. In this research, a new method has been developed using the subspace learning method, unsupervised learning, and with more constraints. Accordingly, it has been attempted to extract the driver genes with more precision and accurate results. The obtained results show that the proposed method is more efficient for more genes compared to other methods. The p-value of the proposed method was 9.21e-7 better than previous methods for 200 genes. The results show that the p. value of the proposed method is about 2.7 times less than the driver sub method, indicating that the proposed method can identify driver genes in cancerous tumors with greater accuracy and reliability.

scholarly journals Inferring subgroup-specific driver genes from heterogeneous cancer samples via subspace learning with subgroup indication

2019 ◽  
Author(s):  
Jianing Xi ◽  
Xiguo Yuan ◽  
Minghui Wang ◽  
Ao Li ◽  
Xuelong Li ◽  
...  
Keyword(s):  
Ground Truth ◽  
Subspace Learning ◽  
Detection Methods ◽  
Supplementary Information ◽  
Driver Gene ◽  
Key Factors ◽  
Gene Detection ◽  
Driver Genes ◽  
Learning Framework ◽  
Mutation Data

AbstractMotivationDetecting driver genes from gene mutation data is a fundamental task for tumorigenesis research. Due to the fact that cancer is a heterogeneous disease with various subgroups, subgroup-specific driver genes are the key factors in the development of precision medicine for heterogeneous cancer. However, the existing driver gene detection methods are not designed to identify subgroup specificities of their detected driver genes, and therefore cannot indicate which group of patients is associated with the detected driver genes, which is difficult to provide specifically clinical guidance for individual patients.ResultsBy incorporating the subspace learning framework, we propose a novel bioinformatics method called DriverSub, which can efficiently predict subgroup-specific driver genes in the situation where the subgroup annotations are not available. When evaluated by simulation datasets with known ground truth and compared with existing methods, DriverSub yields the best prediction of driver genes and the inference of their related subgroups. When we apply DriverSub on the mutation data of real heterogeneous cancers, we can observe that the predicted results of DriverSub are highly enriched for experimentally validated known driver genes. Moreover, the subgroups inferred by DriverSub are significantly associated with the annotated molecular subgroups, indicating its capability of predicting subgroup-specific driver genes.Availability and implementationThe source code is publicly available at https://github.com/JianingXi/DriverSub.Supplementary informationSupplementary data are available at Bioinformatics online.

scholarly journals Simulation and Nonlinearity Optimization of a High-Pressure Sensor

Sensors ◽  
2020 ◽  
Vol 20 (16) ◽  
pp. 4419
Author(s):  
Ting Li ◽  
Haiping Shang ◽  
Weibing Wang
Keyword(s):  
High Pressure ◽  
Pressure Sensor ◽  
Pressure Sensors ◽  
Original Model ◽  
Ansys Software ◽  
Nonlinear Error ◽  
Sensor Model ◽  
Optimized Model ◽  
Simulation Results ◽  
Better Than

A pressure sensor in the range of 0–120 MPa with a square diaphragm was designed and fabricated, which was isolated by the oil-filled package. The nonlinearity of the device without circuit compensation is better than 0.4%, and the accuracy is 0.43%. This sensor model was simulated by ANSYS software. Based on this model, we simulated the output voltage and nonlinearity when piezoresistors locations change. The simulation results showed that as the stress of the longitudinal resistor (RL) was increased compared to the transverse resistor (RT), the nonlinear error of the pressure sensor would first decrease to about 0 and then increase. The theoretical calculation and mathematical fitting were given to this phenomenon. Based on this discovery, a method for optimizing the nonlinearity of high-pressure sensors while ensuring the maximum sensitivity was proposed. In the simulation, the output of the optimized model had a significant improvement over the original model, and the nonlinear error significantly decreased from 0.106% to 0.0000713%.

scholarly journals driveR: a novel method for prioritizing cancer driver genes using somatic genomics data

2021 ◽  
Vol 22 (1) ◽  
Author(s):  
Ege Ülgen ◽  
O. Uğur Sezerman
Keyword(s):  
Biological Knowledge ◽  
Driver Gene ◽  
Driver Genes ◽  
Cancer Driver ◽  
Prior Biological Knowledge ◽  
Wilcoxon Rank Sum Test ◽  
Cancer Genomes ◽  
Novel Method ◽  
Cancer Driver Genes ◽  
Batch Analysis

Abstract Background Cancer develops due to “driver” alterations. Numerous approaches exist for predicting cancer drivers from cohort-scale genomics data. However, methods for personalized analysis of driver genes are underdeveloped. In this study, we developed a novel personalized/batch analysis approach for driver gene prioritization utilizing somatic genomics data, called driveR. Results Combining genomics information and prior biological knowledge, driveR accurately prioritizes cancer driver genes via a multi-task learning model. Testing on 28 different datasets, this study demonstrates that driveR performs adequately, achieving a median AUC of 0.684 (range 0.651–0.861) on the 28 batch analysis test datasets, and a median AUC of 0.773 (range 0–1) on the 5157 personalized analysis test samples. Moreover, it outperforms existing approaches, achieving a significantly higher median AUC than all of MutSigCV (Wilcoxon rank-sum test p < 0.001), DriverNet (p < 0.001), OncodriveFML (p < 0.001) and MutPanning (p < 0.001) on batch analysis test datasets, and a significantly higher median AUC than DawnRank (p < 0.001) and PRODIGY (p < 0.001) on personalized analysis datasets. Conclusions This study demonstrates that the proposed method is an accurate and easy-to-utilize approach for prioritizing driver genes in cancer genomes in personalized or batch analyses. driveR is available on CRAN: https://cran.r-project.org/package=driveR.

scholarly journals ZRSR2 overexpression is a frequent and early event in castration-resistant prostate cancer development

2021 ◽  
Author(s):  
Haiqing He ◽  
Jun Hao ◽  
Xin Dong ◽  
Yu Wang ◽  
Hui Xue ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Cell Cycle Progression ◽  
Locally Advanced ◽  
Patient Treatment ◽  
Early Event ◽  
Driver Gene ◽  
Castration Resistant Prostate Cancer ◽  
Driver Genes ◽  
Castration Resistant ◽  
Pdx Models

Abstract Background Androgen deprivation therapy (ADT) remains the leading systemic therapy for locally advanced and metastatic prostate cancers (PCa). While a majority of PCa patients initially respond to ADT, the durability of response is variable and most patients will eventually develop incurable castration-resistant prostate cancer (CRPC). Our research objective is to identify potential early driver genes responsible for CRPC development. Methods We have developed a unique panel of hormone-naïve PCa (HNPC) patient-derived xenograft (PDX) models at the Living Tumor Laboratory. The PDXs provide a unique platform for driver gene discovery as they allow for the analysis of differentially expressed genes via transcriptomic profiling at various time points after mouse host castration. In the present study, we focused on genes with expression changes shortly after castration but before CRPC has fully developed. These are likely to be potential early drivers of CRPC development. Such genes were further validated for their clinical relevance using data from PCa patient databases. ZRSR2 was identified as a top gene candidate and selected for further functional studies. Results ZRSR2 is significantly upregulated in our PDX models during the early phases of CRPC development after mouse host castration and remains consistently high in fully developed CRPC PDX models. Moreover, high ZRSR2 expression is also observed in clinical CRPC samples. Importantly, elevated ZRSR2 in PCa samples is correlated with poor patient treatment outcomes. ZRSR2 knockdown reduced PCa cell proliferation and delayed cell cycle progression at least partially through inhibition of the Cyclin D1 (CCND1) pathway. Conclusion Using our unique HNPC PDX models that develop into CRPC after host castration, we identified ZRSR2 as a potential early driver of CRPC development.

NIMG-52. RADIOGENOMICS SIGNATURES IN KEY DRIVER GENES IN GLIOBLASTOMA EVALUATED WITH AND WITHOUT THE PRESENCE OF CO-OCCURRING MUTATIONS

2021 ◽  
Vol 23 (Supplement_6) ◽  
pp. vi141-vi141
Author(s):  
Anahita Fathi Kazerooni ◽  
Hamed Akbari ◽  
Spyridon Bakas ◽  
Erik Toorens ◽  
Chiharu Sako ◽  
...  
Keyword(s):  
Gabor Wavelet ◽  
Egfr Mutations ◽  
Driver Gene ◽  
Significant Heterogeneity ◽  
Driver Genes ◽  
Targeted Next Generation Sequencing ◽  
Promising Tool ◽  
Key Driver ◽  
In Vivo Characterization

Abstract PURPOSE Glioblastomas display significant heterogeneity on the molecular level, typically harboring several co-occurring mutations, which likely contributes to failure of molecularly targeted therapeutic approaches. Radiogenomics has emerged as a promising tool for in vivo characterization of this heterogeneity. We derive radiogenomic signatures of four mutations via machine learning (ML) analysis of multiparametric MRI (mpMRI) and evaluate them in the presence and absence of other co-occurring mutations. METHODS We identified a retrospective cohort of 359 IDH-wildtype glioblastoma patients, with available pre-operative mpMRI (T1, T1Gd, T2, T2-FLAIR) scans and targeted next generation sequencing (NGS) data. Radiomic features, including morphologic, histogram, texture, and Gabor wavelet descriptors, were extracted from the mpMRI. Multivariate predictive models were trained using cross-validated SVM with LASSO feature selection to predict mutation status in key driver genes, EGFR, PTEN, TP53, and NF1. ML models and spatial population atlases of genetic mutations were generated for stratification of the tumors (1) with co-occurring mutations versus wildtypes, (2) with exclusive mutations in each driver gene versus the tumors without any mutations in the pathways associated with these genes. RESULTS ML models yielded AUCs of 0.75 (95%CI:0.62-0.88) / 0.87 (95%CI:0.70-1) for co-occurring / exclusive EGFR mutations, 0.69 (95%CI:0.58-0.80) / 0.80 (95%CI:0.61-0.99) for co-occurring / exclusive PTEN mutations, and 0.77 (95%CI:0.65-0.88) / 0.86 (95%CI:0.69-1) for co-occurring / exclusive TP53 cases. Spatial atlases revealed a predisposition of left temporal lobe for NF1 and right frontotemporal region for TP53 in mutually exclusive tumors, which was not observed in the co-occurring mutation atlases. CONCLUSION Our results suggest the presence of distinct radiogenomic signatures of several glioblastoma mutations, which become even more pronounced when respective mutations do not co-occur with other mutations. These in vivo signatures can contribute to pre-operative stratification of patients for molecular targeted therapies, and potentially longitudinal monitoring of mutational changes during treatment.

scholarly journals Synstable Fusion: A Network-Based Algorithm for Estimating Driver Genes in Fusion Structures

Molecules ◽  
2018 ◽  
Vol 23 (8) ◽  
pp. 2055 ◽  
Author(s):  
Mingzhe Xu ◽  
Zhongmeng Zhao ◽  
Xuanping Zhang ◽  
Aiqing Gao ◽  
Shuyan Wu ◽  
...  
Keyword(s):  
Gene Networks ◽  
Gene Fusion ◽  
Fusion Gene ◽  
Driver Gene ◽  
Clinical Practices ◽  
Driver Genes ◽  
Multiple Networks ◽  
Fusion Data ◽  
Evaluation Algorithm ◽  
Chromosomal Mutations

Gene fusion structure is a class of common somatic mutational events in cancer genomes, which are often formed by chromosomal mutations. Identifying the driver gene(s) in a fusion structure is important for many downstream analyses and it contributes to clinical practices. Existing computational approaches have prioritized the importance of oncogenes by incorporating prior knowledge from gene networks. However, different methods sometimes suffer different weaknesses when handling gene fusion data due to multiple issues such as fusion gene representation, network integration, and the effectiveness of the evaluation algorithms. In this paper, Synstable Fusion (SYN), an algorithm for computationally evaluating the fusion genes, is proposed. This algorithm uses network-based strategy by incorporating gene networks as prior information, but estimates the driver genes according to the destructiveness hypothesis. This hypothesis balances the two popular evaluation strategies in the existing studies, thereby providing more comprehensive results. A machine learning framework is introduced to integrate multiple networks and further solve the conflicting results from different networks. In addition, a synchronous stability model is established to reduce the computational complexity of the evaluation algorithm. To evaluate the proposed algorithm, we conduct a series of experiments on both artificial and real datasets. The results demonstrate that the proposed algorithm performs well on different configurations and is robust when altering the internal parameter settings.

Pure-Tone Thresholds and Word-Recognition Abilities of Hearing-Impaired Children

1974 ◽  
Vol 17 (2) ◽  
pp. 194-202 ◽  
Author(s):  
Norman P. Erber
Keyword(s):  
Word Recognition ◽  
Pure Tone ◽  
Hearing Impaired ◽  
Pure Tone Average ◽  
Recognition Ability ◽  
Impaired Children ◽  
Degree Of Overlap ◽  
Better Than ◽  
Hearing Impaired Children

A recorded list of 25 spondaic words was administered monaurally through earphones to 72 hearing-impaired children to evaluate their comprehension of “easy” speech material. The subjects ranged in age from eight to 16 years, and their average pure-tone thresholds (500-1000-2000 Hz) ranged in level from 52 to 127 dB (ANSI, 1969). Most spondee-recognition scores either were high (70 to 100* correct) or low (0 to 30% correct). The degree of overlap in thresholds between the high-scoring and the low-scoring groups differed as a function of the method used to describe the audiogram. The pure-tone average of 500-1000-2000 Hz was a good, but not perfect, predictor of spondee-recognition ability. In general, children with average pure-tone thresholds better than about 85 dB HTL (ANSI, 1969) scored high, and those with thresholds poorer than about 100 dB scored low. Spondee-recognition scores, however, could not be predicted with accuracy for children whose audiograms fell between 85 and 100 dB HTL.

Weighted multi-view common subspace learning method

2021 ◽  
Author(s):  
Jing An ◽  
Xiaoxia Liu ◽  
Mei Shi ◽  
Jun Guo ◽  
Xiaoqing Gong ◽  
...  
Keyword(s):  
Subspace Learning ◽  
Learning Method

Pengaruh Metode Pembelajaran dan Kecerdasan Linguistik Terhadap Kemampuan Bahasa Arab Siswa Kelas II SDIT Anak Sholeh

2016 ◽  
Vol 18 (2) ◽  
pp. 77
Author(s):  
Ayif Royidi
Keyword(s):  
Hypothesis Testing ◽  
Experimental Methods ◽  
Arabic Language ◽  
Learning Ability ◽  
Learning Method ◽  
Tukey Test ◽  
Student Ability ◽  
And Linguistics ◽  
Better Than ◽  
Arabic Students

The purpose of this research is to find out the influence of Three-ber method and linguistic intelligence implementation on Arabic students learning Ability of Arabic language. The research is comparative quantitative with the experimental methods and 2 x 2 by level design .A test is the instrument, used to gather the linguistics data intelligence and student Ability of Arabic language. ANAVA is applied for hypothesis testing two lanes continued to Tukey Test .The results of the study (1) .The Students who learn Arabic trough Three-ber method achieve better than the students who is being taught conventionally(2) There is an interaction between learning method and linguistics intelligence(3)The students whose high linguistic intelligence and learn using Three-ber method achieve better than the students who learn conventionally(4). Arabic students learning Ability of Arabic language whose low linguistic intelligence and learn using Three-ber method achieve lower than student who is being taught conventionally.

Sign in / Sign up

Export Citation Format

Share Document