Pipeline
Description
Pro-1 is a fully open source reasoning model (8b and 70b) trained using GRPO towards a physics based reward function for protein stability. It takes in a protein sequence + text description of the protein + past mutagenesis results, reasons over the information given, and proposes modifications to improve the stability of the given sequence.
Proteins (20)
id: swift-cobra-birch
FGF R1
None
--
True
17.4 kDa
155
id: scarlet-raven-snow
No preview available
FGF R1
None
--
True
N/A
305
id: amber-ram-thorn
FGF R1
None
--
True
17.4 kDa
155
id: small-otter-sand
FGF R1
None
--
False
17.8 kDa
156
id: steady-moth-lotus
FGF R1
Medium
5.7e-8 M
True
17.5 kDa
155
id: rough-otter-birch
FGF R1
None
--
False
17.4 kDa
155
id: amber-goat-onyx
FGF R1
Medium
1.0e-7 M
True
17.5 kDa
155
id: radiant-shark-iron
No preview available
FGF R1
Strong
3.0e-8 M
True
N/A
311
id: gentle-cobra-ice
FGF R1
Strong
2.1e-8 M
True
17.5 kDa
155
id: rough-lion-opal
FGF R1
Strong
1.2e-8 M
True
17.5 kDa
155
id: small-deer-rose
FGF R1
None
--
True
17.5 kDa
155
id: brisk-deer-flint
FGF R1
Strong
2.7e-8 M
True
17.4 kDa
155
id: bright-cobra-leaf
FGF R1
Strong
2.1e-8 M
True
17.5 kDa
155
id: amber-cobra-lotus
FGF R1
None
--
True
17.5 kDa
155
id: steady-gecko-onyx
FGF R1
None
--
True
17.4 kDa
155
id: lunar-yak-flint
FGF R1
None
--
True
17.5 kDa
156
id: noble-zebra-ash
FGF R1
None
--
True
17.3 kDa
155
id: hollow-ox-topaz
FGF R1
None
--
True
17.4 kDa
155
id: lunar-gecko-opal
FGF R1
None
--
False
17.2 kDa
154
id: frozen-bison-pine
FGF R1
None
--
True
17.4 kDa
155