Predicting Parkinson's Disease Genes Based on Node2vec and Autoencoder

Peng, Jiajie; Guan, Jiaojiao; Shang, Xuequn

doi:10.3389/fgene.2019.00226

Cited by 91 publications

(79 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Random forest as a decision tree-based algorithm, the number of decision tree and predictor variable at each decision split have an important impact on prediction performance. Therefore, the prediction performance of the constructed model was optimized based on the grid search strategy, in which change the tree number from 100 to 1000 with interval 100 and feature number from 2 1 , 2 2 , …, to 2 5 . In addition, a default value (i.e.…”

Section: Resultsmentioning

confidence: 99%

Seq-SymRF: a random forest model predicts potential miRNA-disease associations based on information of sequences and clinical symptoms

Chen

Huang

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Increasing evidence indicates that miRNAs play a vital role in biological processes and are closely related to various human diseases. Research on miRNA-disease associations is helpful not only for disease prevention, diagnosis and treatment, but also for new drug identification and lead compound discovery. A novel sequence- and symptom-based random forest algorithm model (Seq-SymRF) was developed to identify potential associations between miRNA and disease. Features derived from sequence information and clinical symptoms were utilized to characterize miRNA and disease, respectively. Moreover, the clustering method by calculating the Euclidean distance was adopted to construct reliable negative samples. Based on the fivefold cross-validation, Seq-SymRF achieved the accuracy of 98.00%, specificity of 99.43%, sensitivity of 96.58%, precision of 99.40% and Matthews correlation coefficient of 0.9604, respectively. The areas under the receiver operating characteristic curve and precision recall curve were 0.9967 and 0.9975, respectively. Additionally, case studies were implemented with leukemia, breast neoplasms and hsa-mir-21. Most of the top-25 predicted disease-related miRNAs (19/25 for leukemia; 20/25 for breast neoplasms) and 15 of top-25 predicted miRNA-related diseases were verified by literature and dbDEMC database. It is anticipated that Seq-SymRF could be regarded as a powerful high-throughput virtual screening tool for drug research and development. All source codes can be downloaded from https://github.com/LeeKamlong/Seq-SymRF.

show abstract

Section: Resultsmentioning

confidence: 99%

Seq-SymRF: a random forest model predicts potential miRNA-disease associations based on information of sequences and clinical symptoms

Chen

Huang

et al. 2020

Sci Rep

View full text Add to dashboard Cite

show abstract

“…We have set out to construct a network that is comprised of these non-coding RNAs, genes and drugs. We hope that the next step will be to provide an online analysis tool (such as Peng et al, 2019a;Peng et al, 2019c) to provide further personalized analysis. We will gather these resources into the database in the next version, and we anticipate that the database will help promote the analysis of cancer and the identification of valuable drug targets.…”

Section: Discussionmentioning

confidence: 99%

CHG: A Systematically Integrated Database of Cancer Hallmark Genes

et al. 2020

View full text Add to dashboard Cite

Background: The analysis of cancer diversity based on a logical framework of hallmarks has greatly improved our understanding of the occurrence, development and metastasis of various cancers. Methods: We designed Cancer Hallmark Genes (CHG) database which focuses on integrating hallmark genes in a systematic, standard way and annotates the potential roles of the hallmark genes in cancer processes. Following the conceptual criteria description of hallmark function the keywords for each hallmark were manually selected from the literature. Candidate hallmark genes collected were derived from 301 pathways of KEGG database by Lucene and manually corrected. Results: Based on the variation data, we finally identified the hallmark genes of various types of cancer and constructed CHG. And we also analyzed the relationships among hallmarks and potential characteristics and relationships of hallmark genes based on the topological structures of their networks. We manually confirm the hallmark gene identified by CHG based on literature and database. We also predicted the prognosis of breast cancer, glioblastoma multiforme and kidney papillary cell carcinoma patients based on CHG data. Conclusions: In summary, CHG, which was constructed based on a hallmark feature set, provides a new perspective for analyzing the diversity and development of cancers.

show abstract

“…The Proposed works are evaluated on real-time dataset features. There are many medical based and ML existing techniques available to detect PD [16] [17] [18].…”

Section: Unitsmentioning

confidence: 99%

Parkinson Data Analysis and Prediction System Using Multi-Variant Stacked Auto Encoder

Nagasubramanian

Sankayya²,

Al‐Turjman³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Parkinson Disease (PD) is a kind of neural disorder that affects a range of people. This disease has continuously growing stages to halt entire neural activities of any people. There are many techniques proposed to detect and predict PD using medical symptoms and measurements. The medical measurements provided by different experiments must be effectively handled to produce concrete results on the detection of PD. This saves many people from PD at earlier stage itself. Recent technologies focus on Machine Learning (ML) and Deep Learning (DL) techniques for effective PD data analysis for making efficient prediction system. They are concentrating to build complex artificial neural systems using effective learning functions. However, the existing systems are lacking to attain multi-attribute and multivariant data analysis to predict PD. To attain multi-variant Parkinson symptom analysis, the artificial neural systems must be equipped with more characteristics. In this regard, the Proposed system is developed using Multi-Variant Stacked Auto Encoder (MVSAE). The MVSAE based PD Prediction System (MSAEPD) helps to analyze more PD symptoms than existing systems. This article provides four different variants of SAE construction procedures to predict PD symptoms. The MSAEPD is implemented and compared with existing works such as MANN, GAE and UMLBD. This comparison shows the MSAEPD system gives 5% to 10% better results than existing works.

show abstract

Predicting Parkinson's Disease Genes Based on Node2vec and Autoencoder

Cited by 91 publications

References 29 publications

Seq-SymRF: a random forest model predicts potential miRNA-disease associations based on information of sequences and clinical symptoms

Seq-SymRF: a random forest model predicts potential miRNA-disease associations based on information of sequences and clinical symptoms

CHG: A Systematically Integrated Database of Cancer Hallmark Genes

Parkinson Data Analysis and Prediction System Using Multi-Variant Stacked Auto Encoder

Contact Info

Product

Resources

About