Research → Design protein binders.

(A) Design of proteins scaffolding immunogenic epitopes on RSV protein F (site II: PDB ID 3IXT chain P residues 254 to 277; site V: PDB ID 5TPN chain A residues 163 to 181). Comparisons of the RF hallucinated models to AF2 structure predictions from the design sequence are in fig. S9; here, because of space constraints, we show only the AF2 model (the two are very close in all cases). Here and in the following figures, we assess the extent of success in designing sequences that fold to structures harboring the desired motif through two metrics computed on the AF2 predictions: prediction confidence (AF pLDDT) and the accuracy of recapitulation of the original scaffolded motif (motif AF-RMSD). For RSV-F designs, these metrics are rsvf_ii_141 (85.0, 0.53 Å), rsvf_ii_158 (82.9, 0.51 Å), rsvf_ii_171 (88.4, 0.69 Å), rsvfv_hal_1 (82, 0.7 Å), rsvfv_hal_2 (88, 0.64 Å), and rsvfv_hal_3 (86, 0.65 Å). (B) Design of COVID-19 receptor trap based on ACE2 interface helix (PDB ID 6VW1 chain A residues 24 to 42). Design metrics: ace2_76 (89.1, 0.55 Å), ace2_1157 (80.4, 0.47 Å), and ace2_1007 (83.3, 0.57 Å). Colors: native protein scaffold, light yellow; native functional motif, orange; hallucinated scaffold, gray; hallucinated motif, purple; and binding partner, blue. See table S2 for additional metrics on each design. From doi: 10.1126/science.abn2100

https://colab.research.google.com/github/martinpacesa/BindCraft/blob/main/notebooks/BindCraft.ipynb

https://github.com/martinpacesa/BindCraft

References

1. Scaffolding protein functional sites using deep learning. Wang J, Lisanza S, Juergens D, Tischer D, Watson JL, Castro KM, Ragotte R, Saragovi A, Milles LF, Baek M, Anishchenko I, Yang W, Hicks DR, Expòsit M, Schlichthaerle T, Chun JH, Dauparas J, Bennett N, Wicky BIM, Muenks A, DiMaio F, Correia B, Ovchinnikov S, Baker D. Science. 2022 Jul 22;377(6604):387-394. doi: 10.1126/science.abn2100.