Limits...
Phenome-driven disease genetics prediction toward drug discovery.

Chen Y, Li L, Zhang GQ, Xu R - Bioinformatics (2015)

Bottom Line: Our approach achieved significantly improved performance over a baseline method, which used only one phenotype data source.We also found literature evidence to support a number of drugs among the top 200 candidates.In summary, we demonstrated that a novel strategy combining unique disease phenotype data with system approaches can lead to rapid drug discovery. nlp. edu/public/data/DMN

View Article: PubMed Central - PubMed

Affiliation: Department of Electrical Engineering and Computer Science, Department of Epidemiology and Biostatistics and Department of Family Medicine and Community Health, Case Western Reserve University, Cleveland, OH 44106, USA.

Show MeSH

Related in: MedlinePlus

The ROC curves for each disease class in de novo gene prediction. We compared the top part of ROC curves and AUC scores based on the top 100 genes in each validation run
© Copyright Policy - creative-commons
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4542779&req=5

btv245-F4: The ROC curves for each disease class in de novo gene prediction. We compared the top part of ROC curves and AUC scores based on the top 100 genes in each validation run

Mentions: We evaluated the approach for nine disease classes. In the leave-one-out cross-validation, 93.4% retained genes was ranked within top 100, and the AUCs for all disease classes are close and above 90%. But the ranks of the retained genes vary up and down within the top 100 for different disease classes. Figure 4 shows the top part of ROC curves for each disease class. The corresponding AUC is the highest for ‘congenital malformations and deformations’, and lowest for ‘mental diseases’ and ‘malignant neoplasms’. Table 2 (the column of ‘All diseases’) compares the success ratio for all diseases between disease classes, and shows that our approach ranked 78% retained genes for congenital malformations and deformations in top 1, while prioritized 26% and 27% retained genes for malignant neoplasms and mental diseases, respectively.Fig. 4.


Phenome-driven disease genetics prediction toward drug discovery.

Chen Y, Li L, Zhang GQ, Xu R - Bioinformatics (2015)

The ROC curves for each disease class in de novo gene prediction. We compared the top part of ROC curves and AUC scores based on the top 100 genes in each validation run
© Copyright Policy - creative-commons
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4542779&req=5

btv245-F4: The ROC curves for each disease class in de novo gene prediction. We compared the top part of ROC curves and AUC scores based on the top 100 genes in each validation run
Mentions: We evaluated the approach for nine disease classes. In the leave-one-out cross-validation, 93.4% retained genes was ranked within top 100, and the AUCs for all disease classes are close and above 90%. But the ranks of the retained genes vary up and down within the top 100 for different disease classes. Figure 4 shows the top part of ROC curves for each disease class. The corresponding AUC is the highest for ‘congenital malformations and deformations’, and lowest for ‘mental diseases’ and ‘malignant neoplasms’. Table 2 (the column of ‘All diseases’) compares the success ratio for all diseases between disease classes, and shows that our approach ranked 78% retained genes for congenital malformations and deformations in top 1, while prioritized 26% and 27% retained genes for malignant neoplasms and mental diseases, respectively.Fig. 4.

Bottom Line: Our approach achieved significantly improved performance over a baseline method, which used only one phenotype data source.We also found literature evidence to support a number of drugs among the top 200 candidates.In summary, we demonstrated that a novel strategy combining unique disease phenotype data with system approaches can lead to rapid drug discovery. nlp. edu/public/data/DMN

View Article: PubMed Central - PubMed

Affiliation: Department of Electrical Engineering and Computer Science, Department of Epidemiology and Biostatistics and Department of Family Medicine and Community Health, Case Western Reserve University, Cleveland, OH 44106, USA.

Show MeSH
Related in: MedlinePlus