RosettaEvolutionaryLigand (REvoLd)

RosettaEvolutionaryLigand (REvoLd) implements an evolutionary algorithm that searches combinatorial make-on-demand chemical space efficiently without enumerating all molecules for protein-ligand docking with full ligand and receptor flexibility.

Key Features:

• Evolutionary Algorithm: The algorithm optimizes and explores ultra-large make-on-demand libraries through an evolutionary approach rather than exhaustive enumeration.
• Make-on-Demand Library Exploitation: The tool exploits the construction of make-on-demand compound libraries from lists of substrates and chemical reactions to navigate combinatorial chemical space.
• Full Receptor and Ligand Flexibility: Protein-ligand docking incorporates full flexibility of both the ligand and the receptor through RosettaLigand.
• Hit Rate Enrichment: Benchmarking on five drug targets demonstrated improvements in hit rates by factors between 869 and 1622 compared to random selections.

Scientific Applications:

• Ultra-Large Library Screening: REvoLd enables efficient screening of compound libraries containing billions of readily available compounds for in-silico drug discovery.
• Drug Discovery in Vast Chemical Spaces: The algorithm accelerates identification of promising compounds in ultra-large chemical spaces where exhaustive screening is computationally prohibitive.

Methodology:

REvoLd formulates an evolutionary algorithm for optimization and exploration of ultra-large make-on-demand libraries, exploiting that these libraries are constructed from lists of substrates and chemical reactions to search combinatorial chemical space without enumerating all molecules, with protein-ligand docking performed through RosettaLigand.