Fragment and torsion biasing algorithms for construction of small organic molecules in proteins using DOCK

The computational construction of small organic molecules (de novo
design), directly in a protein binding site, is an effective means for
generating novel ligands tailored to fit the pocket environment. In this
work, we present two new methods, which aim to improve de novo design
outcomes using (1) biasing algorithms to prioritize selection and/or
acceptance of fragments and torsions during growth, and (2) parallel‐based
clustering and pruning algorithms to remove duplicate molecules as
candidate fragment are added. Large‐scale testing encompassing thousands
of simulations were employed to interrogate the methods in terms of
multiple metrics which include numbers of duplicate molecules generated,
pairwise‐similarity, focused library reconstruction rates, fragment and
torsion frequencies, fragment and torsion rank scores, interaction energy
and drug‐likeness scores, and 3D pose comparisons. The biasing algorithms,
particularly those that include fragment and torsion components
simultaneously, led to molecules that more closely mimicked the
distributions of fragments and torsions found in drug‐like libraries. The
new parallel‐based clustering and pruning algorithms, compared with the
existing serial approach, also led to larger ensembles comprised of
topologically unique molecules with much greater efficiency by removing
redundant growth paths.