Predicting cancerlectins by the optimal g-gap dipeptides.

Area of Science:

• Biochemistry
• Computational Biology
• Oncology

Background:

• Cancerlectins are vital for tumor cell differentiation, influencing cancer therapy strategies.
• Traditional experimental methods for identifying cancerlectins are costly and time-intensive.
• Developing efficient computational tools is essential for advancing cancerlectin research.

Purpose of the Study:

• To develop a sequence-based computational method for identifying cancerlectins.
• To discriminate between cancerlectins and non-cancerlectins using bioinformatics approaches.
• To provide a user-friendly web server for cancerlectin prediction.

Main Methods:

• A sequence-based approach was employed to differentiate cancerlectins from non-cancerlectins.
• Analysis of Variance (ANOVA) was utilized to select optimal features from g-gap dipeptide composition.
• Jackknife cross-validation was performed to assess the method's performance.

Main Results:

• The developed method achieved a prediction accuracy of 75.19% for identifying cancerlectins.
• The proposed computational approach demonstrated superior performance compared to existing methods.
• An online web server, CaLecPred, was established for public access and use.

Conclusions:

• CaLecPred is an effective and efficient computational tool for identifying cancerlectins.
• The tool can aid researchers in studying cancerlectin functions and planning experimental validations.
• This work contributes to the advancement of cancer therapy through improved understanding of cancerlectins.