iiinova — where your digital self keeps evolving

We're super excited by the method. We think it can help to rapidly produce binders to small molecules for sensors, antidotes, delivery vehicles, even enzymes. Let us know what you think and please try it out! Finally, shout out to Ben and Kaia for making this all happen!!! 🤩

Reposted by Ben Fry

Lastly, Kaia checked to see if EPIC and its higher affinity mutant are able to protect exatecan from hydrolysis, which is not something serum albumin can do. For a drug that normally hydrolyzes in a few hours, EPIC was able to stabilize the lactone form for days! ✅

absorbance data showing that epic protect exatecan from hydrolysis

Reposted by Ben Fry

Since EPIC and exatecan aren't in the PDB, we wanted to see how co-structure predictors do on it. They each get the backbone right but differ at the ligand. The pose is correct but the modeling of the conformer is wonky. AF3 does the best. AF3 is also able to rank affinities via pLDDT of ligand! 😱

co-structure predictors agree with crystal structure but differ at ligand

Reposted by Ben Fry

Kaia was able to crystalize EPIC and determine its structure to 2.0 Å resolution. It agreed pretty well with the LASEr design! RFAA had a hard time modeling the lactone ring of the drug, so there is some disagreement there. The lactone is buried as intended, and the goal was to hide it from water 👍

crystal structure of EPIC agrees with design

Reposted by Ben Fry

Ben didn't stop there. He wanted to improve affinity of EPIC for exatecan using computation alone. He used LASErMPNN to "proofread" EPIC's sequence using a predicted co-structure as input. LASEr suggested two mutations. Kaia verified that each improved binding 10x. 100x when combined (1 nM Kd)!

example of neural proofreading to improve affinity

Reposted by Ben Fry

Kaia Slaw (no bluesky) experimentally tested 4 designs from NISE and 16 from COMBS. All 4 NISE designs bound! The highest affinity binder- which Ben and Kaia call "EPIC" - was pretty tight (0.1 uM Kd). Compared to COMBS (3 of 16 bound, tightest was 10 uM), NISE and LASErMPNN did a much better job!

Reposted by Ben Fry

Ben used NISE and LASErMPNN to design binders to exatecan, an anticancer drug prone to inactivation by hydrolysis. We also used a more "traditional" approach using COMBS and Rosetta to design binders. We could compare the methods head to head.

image of exatecan drug and design pipelines using COMBS and NISE

Reposted by Ben Fry

With the new co-structure predictors like RFAA, Boltz-1, and AF3, we can now extend self-consistency into the ligand dimension. And Ben's NISE algorithm maximizes this. Code repo here: github.com/polizzilab/N...

two proteins that have good predicted structures but only one has a self consistent ligand position

Reposted by Ben Fry

We all know in protein design about the goal of self consistency. That is, we want the predicted structure to look like the structure for which we designed the sequence.

protein sequence design and structure prediction showing some designs agree with the intended structure

Reposted by Ben Fry

Ben used LASErMPNN in combination with a protein-ligand co-structure predictor, RFAA, in an iterative algorithm called NISE that refines designs. NISE optimizes the sequence, structure, and ligand conformer together to improve the confidence of both models. It's a neural-network-only algorithm

the NISE design algorithm iteratively optimizes a starting model through many rounds of sequence design and structure prediction

Reposted by Ben Fry

Ben Fry (@benf549.bsky.social) was excited when proteinMPNN came out, which motivated him to train a new gNN called LASErMPNN to design sequences given protein-ligand co-structure. LASErMPNN does pretty well at this! The repo is available and even has the training code! github.com/polizzilab/L...

scatter plot of sequence recovery on a test set showing lasermpnn improves slightly over ligandmpnn

131

Reposted by Ben Fry