Table 1. Machine learning predictions of the impact of RBD mutations in current and former CDC Variants of Concern on ACE2 affinity and human serum antibody escape.

Variant	RBD Mutations	Predicted ACE2 affinity (KA app, M)	Predicted antibody escape (%)
Wild type		1.00 x 1011	3.4
Alpha	N501Y	1.48 x 10 11	2.5
Beta	K417N, E484K, N501Y	4.32 x 1010	7.2
Epsilon	L452R	2.54 x 10 11	5.5
Gamma	K417T, E484K, N501Y	9.76 x 1010	7.7
Delta	L452R, T478K	4.37 x 10 11	6.3

Predictions of increased ACE2 affinity or human serum antibody escape or both relative to wild-type SARS-CoV-2 are indicated by bold values. ACE2 affinities are reported as apparent values because the experimental datasets were obtained using bivalent ACE2 (ACE2-Fc), which results in much higher apparent affinities than those observed for monovalent ACE2.