ACFIS 2.0

ACFIS 2.0 integrates a dynamic fragment growing strategy and dynamic simulations to predict and optimize fragment-protein binding for fragment-based drug discovery (FBDD).

Key Features:

• Dynamic Fragment Growing Strategy: Incorporates a dynamic fragment growing strategy that accounts for protein flexibility during screening to improve prediction of binding modes and affinities.
• Enhanced Accuracy in Hit Compound Identification: Demonstrates increased hit identification accuracy from 75.4% to 88.5% when tested on the same dataset.
• Improved Binding Mode Rationality: Provides improved rationalization of protein-fragment binding modes, yielding more reliable insights into fragment interactions with target proteins.
• Expanded Fragment Libraries and Structural Diversity: Features expanded fragment libraries that increase structural diversity among screened candidates to broaden exploration of chemical space.
• Comprehensive Molecular Property Prediction: Includes functionality for predicting various molecular properties to support lead optimization.

Scientific Applications:

• Parkinson's Disease: Identification of novel compounds with potential therapeutic effects.
• Cancer: Discovery of promising candidates targeting specific oncogenic pathways.
• Major Depressive Disorder: Development of lead molecules aimed at modulating relevant biological targets.

Methodology:

Employs a combination of computational techniques including a dynamic fragment growing strategy and dynamic simulations that consider protein flexibility to simulate and predict interactions, binding modes, and binding affinities between chemical fragments and protein targets.