Similar to natural languages, proteins have a language that can be rearranged and assembled to create different functional proteins.
Like words and phrases in human language, protein sequences can be computationally broken down to identify how segments of amino acid sequences determine a protein’s function.
Our platform distills this knowledge from natural protein sequence databases to capture the evolutionary, structural, and functional properties of proteins.
This knowledge is then used to train our ML models to derive novel proteins that fit within the design constraints of naturally occurring proteins.
With your datasets, we further tune our models for your objectives and generate novel variants