Sequence optimization

Generating optimized protein or nucleic acid sequence with an improved function over the target sequence using a machine learning model configured to receive the target protein sequence or a nucleic acid sequence, and to generate therefrom optimized sequences. The machine learning model has been tra...

Full description

Saved in:
Bibliographic Details
Main Authors Diana Ikasalaite, Donatas Repecka, Irmantas Rokaitis, Vykintas Jauniskis, Laurynas Karpus
Format Patent
LanguageEnglish
Published 26.06.2024
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTEDFOR SPECIFIC APPLICATION FIELDS
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:Generating optimized protein or nucleic acid sequence with an improved function over the target sequence using a machine learning model configured to receive the target protein sequence or a nucleic acid sequence, and to generate therefrom optimized sequences. The machine learning model has been trained on a set of training data comprising native or engineered protein or nucleic acid sequences, and additionally, at least a subset of the sequences comprising one or more masked portions and/or at least a subset of the sequences comprising one or more mutations introduced therein. The likelihood of substitutions with a pre-defined set of proteinogenic amino acids at positions of the protein target sequence, and bases in the acid sequence. Improved function may be thermostability, pH, ionic strength, solvent, stability, specificity, resistance to chaotropic agent, ionic detergent, shelf life, expressibility and adsorption into plastic.
Bibliography:Application Number: GB20220003714