Lncident

Lncident classifies long noncoding RNAs (lncRNAs) and discriminates them from messenger RNAs using sequence intrinsic composition and open reading frame (ORF) features to support studies of lncRNA functions in biological processes and disease.

Key Features:

• Sequence intrinsic composition and ORF features: Uses sequence intrinsic composition features together with open reading frame (ORF) information to characterize transcripts.
• Support vector machine model: Applies a support vector machine (SVM) classifier to distinguish lncRNAs from mRNAs.
• Benchmark comparisons: Performance was compared with Coding-Potential Calculator, Coding-Potential Assessment Tool, Coding-Noncoding Index, and PLEK.
• Performance evaluation: Model performance was assessed using 10-fold cross-validation and receiver operating characteristic (ROC) curves.
• Organismal versatility: Demonstrated performance on human datasets and microorganisms.
• Custom training capability: Supports retraining with user-collected datasets to create tailored models.

Scientific Applications:

• Identification for functional studies: Rapid identification of lncRNAs to facilitate exploration of their roles in biological processes.
• Disease mechanism investigation: Enables study of lncRNA associations with disease mechanisms.
• Comparative and cross-organism genomics: Applicable to human and microbial datasets for comparative genomic analyses.

Methodology:

Integrates sequence intrinsic composition features and open reading frame (ORF) information into a support vector machine (SVM) classifier; performance was evaluated using 10-fold cross-validation and receiver operating characteristic (ROC) curve analysis.