In-silico drug screening method based on the protein-compound affinity matrix using the factor selection technique.

Area of Science:

• Computational chemistry
• Drug discovery
• Bioinformatics

Background:

• In-silico drug screening is crucial for identifying potential drug candidates.
• Existing docking score index (DSI) methods require optimization for enhanced accuracy and efficiency.
• Principal Component Analysis (PCA) offers a powerful dimensionality reduction technique applicable to complex datasets.

Purpose of the Study:

• To develop and validate a modified in-silico drug screening method.
• To improve the selection of principal component axes for enhanced database enrichment.
• To evaluate the efficacy of the proposed method across 12 diverse target proteins.

Main Methods:

• Development of a modified docking score index (DSI) method utilizing a protein-compound docking affinity matrix.
• Application of Principal Component Analysis (PCA) to convert docking scores into docking score indexes.
• Projection of compounds into a PCA space for analysis and selection of principal component axes.
• Evaluation of database enrichment for 12 target proteins using the developed method.

Main Results:

• The proposed method successfully enhances database enrichment by identifying new active compounds or hits.
• Compounds identified by the method are positioned close to known active compounds in the PCA space.
• The method demonstrates effectiveness across a panel of 12 target proteins, indicating broad applicability.

Conclusions:

• The modified in-silico drug screening method, incorporating PCA, significantly improves the identification of potential drug candidates.
• This approach offers a valuable tool for accelerating drug discovery pipelines by enhancing hit identification and database enrichment.
• The method's ability to group known and novel active compounds provides insights into structure-activity relationships.