Using genetic programming to predict and optimize protein function

Miralavy, Iliya; Bricco, Alexander R.; Gilad, Assaf A.; Banzhaf, Wolfgang

doi:10.7717/peerj-pchem.24

Cited by 7 publications

(12 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…POET uses mutational operators that modify the weights and motifs of the model tables. Across 5,000 to 50,000 iterations of this algorithm (Figure , arrow), the motif-weight pairs that are most important and accurate at predicting the training data set are maintained, and those that are poor at improving the training data set are discarded, causing the model to develop in an analogous manner to Darwinian evolution …”

Section: Resultsmentioning

confidence: 99%

A Genetic Programming Approach to Engineering MRI Reporter Genes

Bricco

Miralavy

et al. 2023

ACS Synth. Biol.

Self Cite

View full text Add to dashboard Cite

Here we develop a mechanism of protein optimization using a computational approach known as “genetic programming”. We developed an algorithm called Protein Optimization Engineering Tool (POET). Starting from a small library of literature values, the use of this tool allowed us to develop proteins that produce four times more MRI contrast than what was previously state-of-the-art. Interestingly, many of the peptides produced using POET were dramatically different with respect to their sequence and chemical environment than existing CEST producing peptides, and challenge prior understandings of how those peptides function. While existing algorithms for protein engineering rely on divergent evolution, POET relies on convergent evolution and consequently allows discovery of peptides with completely different sequences that perform the same function with as good or even better efficiency. Thus, this novel approach can be expanded beyond developing imaging agents and can be used widely in protein engineering.

show abstract

Section: Resultsmentioning

confidence: 99%

A Genetic Programming Approach to Engineering MRI Reporter Genes

Bricco

Miralavy

et al. 2023

ACS Synth. Biol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Consequently, this burden on metabolism reduces the reporter protein’s cellular concentration, leading to a decrease in overall contrast. To remedy this issue, we developed a machine learning algorithm that evolved peptides to optimize their CEST contrast while diversifying the amino acid residues in their sequences 40,43 . Having generated a wide range of 12 amino acid long peptides, questions about their expression in cells still existed.…”

Section: Resultsmentioning

confidence: 99%

“…To remedy this issue, we developed a machine learning algorithm that evolved peptides to optimize their CEST contrast while diversifying the amino acid residues in their sequences 40,43 .…”

Section: -Design Of Synthetic Genes -Supercestidesmentioning

confidence: 99%

Development of a Synthetic Biosensor for Chemical Exchange MRI UtilizingIn SilicoOptimized Peptides

Fillion

Bricco

Lee

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Chemical Exchange Saturation Transfer (CEST) magnetic resonance imaging (MRI) has been identified as a novel alternative to classical diagnostic imaging. Over the last several decades, many studies have been conducted to determine possible CEST agents, such as endogenously expressed compounds or proteins, that can be utilized to produce contrast with minimally invasive procedures and reduced or non-existent levels of toxicity. In recent years there has been an increased interest in the generation of genetically engineered CEST contrast agents, typically based on existing proteins with CEST contrast or modified to produce CEST contrast. We have developed an in-silico method for the evolution of peptide sequences to optimize CEST contrast and showed that these peptides could be combined to create de novo biosensors for CEST MRI. A single protein, superCESTide 2.0, was designed to be 198 amino acids. SuperCESTide 2.0 was expressed in E. coli and purified with size-exclusion chromatography. The magnetic transfer ratio asymmetry (MTRasym) generated by superCESTide 2.0 was comparable to levels seen in previous CEST reporters, such as protamine sulfate (salmon protamine, SP), Poly-L-Lysine (PLL), and human protamine (hPRM1). This data shows that novel peptides with sequences optimized in silico for CEST contrast that utilizes a more comprehensive range of amino acids can still produce contrast when assembled into protein units expressed in complex living environments.

show abstract

“…This burden on metabolism reduces the reporter protein's cellular concentration, leading to a decrease in overall contrast. To remedy this issue, we developed a machine learning algorithm that evolved peptides to optimize their CEST contrast while diversifying the amino acid residues in their sequences 36,42 . Having generated a wide range of 12 amino acid long peptides, questions about their expression in cells still existed.…”

Section: Resultsmentioning

confidence: 99%

“…To remedy this issue, we developed a machine learning algorithm that evolved peptides to optimize their CEST contrast while diversifying the amino acid residues in their sequences. 36,42 Having generated a wide range of 12 amino acid long peptides, questions about their expression in cells still existed. While these de novo peptides produced relatively high CEST contrast when suspended in solution, it was unknown if they would still create detectable contrast once expressed as a single genetic unit in a complex organism.…”

Section: Design Of Synthetic Genes-supercestidesmentioning

confidence: 99%

Development of a synthetic biosensor for chemical exchange MRI utilizing in silico optimized peptides

et al. 2023

View full text Add to dashboard Cite

Chemical exchange saturation transfer (CEST) MRI has been identified as a novel alternative to classical diagnostic imaging. Over the last several decades, many studies have been conducted to determine possible CEST agents, such as endogenously expressed compounds or proteins, that can be utilized to produce contrast with minimally invasive procedures and reduced or non‐existent levels of toxicity. In recent years there has been an increased interest in the generation of genetically engineered CEST contrast agents, typically based on existing proteins with CEST contrast or modified to produce CEST contrast. We have developed an in silico method for the evolution of peptide sequences to optimize CEST contrast and showed that these peptides could be combined to create de novo biosensors for CEST MRI. A single protein, superCESTide, was designed to be 198 amino acids. SuperCESTide was expressed in E. coli and purified with size exclusion chromatography. The magnetic transfer ratio asymmetry generated by superCESTide was comparable to levels seen in previous CEST reporters, such as protamine sulfate (salmon protamine) and human protamine. These data show that novel peptides with sequences optimized in silico for CEST contrast that utilize a more comprehensive range of amino acids can still produce contrast when assembled into protein units expressed in complex living environments.

show abstract

Using genetic programming to predict and optimize protein function

Cited by 7 publications

References 54 publications

A Genetic Programming Approach to Engineering MRI Reporter Genes

A Genetic Programming Approach to Engineering MRI Reporter Genes

Development of a Synthetic Biosensor for Chemical Exchange MRI UtilizingIn SilicoOptimized Peptides

Development of a synthetic biosensor for chemical exchange MRI utilizing in silico optimized peptides

Contact Info

Product

Resources

About