The structure of the most variable antibody hypervariable loop, CDR-H3
, has been predicted from amino acid sequence alone, In contrast to ot
her approaches predictions are made for loop lengths up to 17 residues
, The predictions have been achieved using artificial neural networks
which are trained on a large set of loops from the Brookhaven Protein
Databank which have structures similar to CDR-H3, The loop structures
are described by the two backbone dihedral angles phi and psi for each
residue, For 21 CDR-H3 loops unique to the neural network, the predic
tion of dihedral angles leads to an average root mean square deviation
in the Cartesian coordinates of 2.65 Angstrom. The present method, wh
en combined with existing modelling protocols, provides an important a
ddition to the structural prediction of the complementarity determinin
g regions of antibodies.