Protein discovery and synthesis accelerated by AI

[funkervogt]

Overall, Baker’s team estimates that they have about a 15% success rate with such designs, which is far, far above where things were just two or three years ago. And that rate may have already improved. The bottleneck is making and testing the proteins themselves; these techniques are spitting out so many plausible hits that it’s hard to keep up.

https://www.science.org/content/blog-po ... ign-ai-way

[caltrek]

AI Tool Predicts Function of Unknown Proteins
February 14, 2024

Introduction:

(Eurekalert) A new artificial intelligence (AI) tool that draws logical inferences about the function of unknown proteins promises to help scientists unravel the inner workings of the cell.

Developed by KAUST bioinformatics researcher Maxat Kulmanov and colleagues, the tool outperforms existing analytical methods for forecasting protein functions and is even able to analyze proteins with no clear matches in existing datasets.

The model, termed DeepGO-SE, takes advantage of large language models similar to those used by generative AI tools such as Chat-GPT. It then employs logical entailment to draw meaningful conclusions about molecular functions based on general biological principles about the way proteins work.

It essentially empowers computers to logically process outcomes by constructing models of part of the world — in this case, protein function — and inferring the most plausible scenario based on common sense and reasoning about what should happen in these world models.

“This method has many applications,” says Robert Hoehndorf, head of the KAUST Bio-Ontology Research Group, who supervised this research, “especially when it is necessary to reason over data and hypotheses generated by a neural network or another machine learning model,” he adds.

Read more of the Eurekalert article here: https://www.eurekalert.org/news-releases/1034251

For a technical description of DeepGO-SE as published in Nature : https://www.nature.com/articles/s42256-024-00795-w

[caltrek]

A Deep Learning Pipeline for Controlling Protein Interactions
January 16, 2025

Introduction:

(Eurekalert) In 2023, scientists in the joint School of Engineering and School of Life Sciences Laboratory of Protein Design and Immunoengineering (LPDI), led by Bruno Correia, published in Nature a deep-learning pipeline for designing new proteins to interact with therapeutic targets. MaSIF can rapidly scan millions of proteins to identify optimal matches between molecules based on their chemical and geometric surface properties, enabling scientists to engineer novel protein-protein interactions that play key roles in cell regulation and therapeutics.

A year and a half later, the team has reported – again in Nature – an exciting advancement of this technology. They have used MaSIF to design novel protein binders to interact with known protein complexes involving small molecules like therapeutic drugs or hormones. Because these bound small molecules induce subtle changes in the surface properties (‘neosurfaces’) of these protein-drug complexes, they can act as ‘on’ or ‘off’ switches for the fine control of cellular functions like DNA transcription or protein degradation.

“Our idea was to engineer an interaction in which a small molecule causes two proteins to come together. Some approaches have focused on screening for such small molecules, but we wanted to design a novel protein that would bind to a defined protein-drug complex,” says LPDI scientist and co-first author Anthony Marchand.

Remarkably, the team showed that MaSIF could seamlessly apply protein surface representations (‘fingerprints’) that had been trained only on proteins to neosurfaces emerging from protein-drug complexes. While most learning-based protein design systems work only on amino acid building blocks from nature, MaSIF’s sensitivity and generalizability to small molecules means it could be used to design chemically induced protein interactions in engineered cells for drug-controlled cell-based therapies or biosensors.

Small but powerful

While protein binding may seem as simple as fitting puzzle pieces together, in reality, protein surface variations make it hard to predict how and where binding events will occur. As in their previous study, the team designed novel protein binders by using MaSIF to generate ‘fingerprints’ for surface features like positive and negative charge, hydrophobicity, shape, etc. Then they identified complementary surfaces from a database, digitally grafted protein fragments onto larger scaffolds, and selected binders predicted to fit best with their target

Read more here: https://www.eurekalert.org/news-releases/1070697