Methods, systems, and software for identifying functional biomolecules

A computer program product comprising tangible machine readable medium medium on which is provided program code for identifying nucleotides for variation in nucleic acids encoding a protein variant library in order to impact a desired activity, said program code comprising:

• (a) code for receiving data characterizing a training set of a protein variant library, wherein the data comprises activity and a nucleotide sequence for each protein variant in the training set;
• (b) code for developing, from the data, a sequence activity model for predicting activity as a function of independent variables each specifying the presence or absence of a nucleotide, identity of said nucleotide, and position of said nucleotide in a nucleotide sequence;
• (c) code for using the sequence activity model to rank positions in the reference nucleotide sequence and nucleotide types at the ranked positions in the reference nucleotide sequence in order of impact on the desired activity;
• (d) code for using the ranking to identify one or more nucleotides, in the reference nucleotide sequence, that are to be varied or fixed in order to impact the desired activity, wherein the nucleotides to be varied include codons encoding particular amino acids;
• and
• (e) code for defining a new protein variant library containing one or more new protein variants having amino acid sequences encoded by nucleic acids in which the identified nucleotides are varied or fixed in order to impact the desired activity.