CaLecPred

CaLecPred predicts cancerlectins from protein sequence data to enable identification of lectins involved in tumor cell differentiation.

Key Features:

• Sequence-based classification: Uses g-gap dipeptide composition derived from protein sequences to represent candidate lectins.
• Feature selection: Applies analysis of variance (ANOVA) to select an optimal subset of g-gap dipeptide features.
• Validation and performance: Employs jackknife cross-validation and achieved a jackknife accuracy of 75.19%.
• Prediction objective: Distinguishes cancerlectins from non-cancerlectins based on sequence-derived features.

Scientific Applications:

• Cancerlectin identification: Enables computational identification of cancerlectins from sequence data to support investigation of lectins implicated in tumor cell differentiation.
• Experimental prioritization: Provides predictions to guide and prioritize experimental validation of candidate cancerlectins.
• Resource-efficient screening: Serves as a computational alternative to wet-experimental methods, helping to reduce time and financial costs for cancerlectin studies.
• Therapeutic research: Supports studies of cancerlectin roles that may inform therapeutic targeting strategies.

Methodology:

Represents sequences using g-gap dipeptide composition, selects features with analysis of variance (ANOVA), and evaluates model performance via jackknife cross-validation.