Back

Computational design of intrinsically disordered protein regions by matching bulk molecular properties

Strome, B.; Elemam, K.; Pritisanac, I.; Forman-Kay, J. D.; Moses, A. M.

2023-04-29 synthetic biology
10.1101/2023.04.28.538739 bioRxiv
Show abstract

Algorithms for computational protein design usually begin with a 3D structure and design an amino acid sequence that will fold into that structure. Since intrinsically disordered protein regions lack stable 3D structures, strategies for their design have been limited. Here we describe and validate a general computational strategy for design of intrinsically disordered regions (IDRs). Our algorithm designs synthetic IDRs by minimizing the distance of an initially random amino acid sequence to a known IDR in a high-dimensional space of molecular properties, such as repeat content, charge and hydrophobicity. We tested a handful of IDRs designed to target proteins to mitochondria and heat-induced condensates, and several showed the expected patterns in cells. One sentence summaryWe design synthetic mitochondrial targeting signals and condensate forming intrinsically disordered regions

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.