A Novel Method for miRNA-Disease Association Prediction based on Space Projection and Label Propagation (SPLPMDA)
[ X ]
Tarih
2022
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Kırıkkale Üniversitesi
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
miRNAs, a subclass of non-coding small RNAs, are about 18-22 nucleotides long. It has been revealed that miRNAs are responsible many diseases such as cancer. Therefore, great efforts have been made recently by researchers to explore possible relationships between miRNAs and diseases. Experimental studies to identify new disease-associated miRNAs are very expensive and at the same time a long process. Therefore, to determine the relationships between miRNA and disease many computational methods have been developed. In this paper, a new method for the identification of miRNA-disease associations based on space projection and label propagation (SPLPMDA) is proposed. The forecast the precision of SPLPMDA was demonstrated using 5-fold cross-validation and LOOCV techniques. Values of 0.9333 in 5-fold cross validation and 0.9441 in LOOCV were obtained. Moreover, case studies on breast neoplasms and lymphoma were performed to further confirm the predictive reliability of SPLPMDA.
miRNAs, a subclass of non-coding small RNAs, are about 18-22 nucleotides long. It has been revealed that miRNAs are responsible many diseases such as cancer. Therefore, great efforts have been made recently by researchers to explore possible relationships between miRNAs and diseases. Experimental studies to identify new disease-associated miRNAs are very expensive and at the same time a long process. Therefore, to determine the relationships between miRNA and disease many computational methods have been developed. In this paper, a new method for the identification of miRNA-disease associations based on space projection and label propagation (SPLPMDA) is proposed. The forecast the precision of SPLPMDA was demonstrated using 5-fold cross-validation and LOOCV techniques. Values of 0.9333 in 5-fold cross validation and 0.9441 in LOOCV were obtained. Moreover, case studies on breast neoplasms and lymphoma were performed to further confirm the predictive reliability of SPLPMDA.
miRNAs, a subclass of non-coding small RNAs, are about 18-22 nucleotides long. It has been revealed that miRNAs are responsible many diseases such as cancer. Therefore, great efforts have been made recently by researchers to explore possible relationships between miRNAs and diseases. Experimental studies to identify new disease-associated miRNAs are very expensive and at the same time a long process. Therefore, to determine the relationships between miRNA and disease many computational methods have been developed. In this paper, a new method for the identification of miRNA-disease associations based on space projection and label propagation (SPLPMDA) is proposed. The forecast the precision of SPLPMDA was demonstrated using 5-fold cross-validation and LOOCV techniques. Values of 0.9333 in 5-fold cross validation and 0.9441 in LOOCV were obtained. Moreover, case studies on breast neoplasms and lymphoma were performed to further confirm the predictive reliability of SPLPMDA.
Açıklama
Anahtar Kelimeler
miRNA, disease, miRNA-disease association, space projection, label propagation, miRNA, disease, miRNA-disease association, space projection, label propagation, Engineering
Kaynak
Uluslararası Mühendislik Araştırma ve Geliştirme Dergisi
WoS Q Değeri
Scopus Q Değeri
Cilt
1
Sayı
3-234
