Sequences were designed via Synthyra's protein design environment. It is similar to an already established method on ProteinBase, DSM Synteract, but leverages more oracles. It works by generating a large amount of protein variants and ranking them via models: predicting PPI probability, binding affinity, foldability, thermostability, and optimal embedding distances. Promising variants are further optimized via a monte carlo scheme.
id: frozen-crow-cedar

Nipah Virus Glycoprotein G
None
73.20
False
26.8 kDa
241
id: rough-ox-opal

Nipah Virus Glycoprotein G
None
76.39
False
26.4 kDa
239
id: noble-moth-cypress

Nipah Virus Glycoprotein G
None
75.24
False
26.7 kDa
240
id: violet-ibis-reed

Nipah Virus Glycoprotein G
None
74.89
True
26.7 kDa
241
id: pale-lynx-fern

Nipah Virus Glycoprotein G
None
74.66
False
26.5 kDa
240
id: soft-quail-vine

Nipah Virus Glycoprotein G
None
74.07
True
26.7 kDa
241
id: golden-falcon-stone

Nipah Virus Glycoprotein G
0.84
73.48
--
26.7 kDa
240
id: steady-crow-ember

Nipah Virus Glycoprotein G
0.82
74.67
--
26.7 kDa
241
id: azure-heron-reed

Nipah Virus Glycoprotein G
0.59
76.74
--
26.3 kDa
240
id: vast-bison-cedar

Nipah Virus Glycoprotein G
0.85
75.59
--
26.2 kDa
238