A method for selecting and synthesizing a variant of a protein having a desired fitness, the method comprising:
- encoding an amino acid sequence of each of a plurality of variants of the protein to be evaluated for having the desired fitness into a numerical sequence according to an index of biochemical or physico-chemical property values in a protein database, wherein the protein database includes a plurality of indices of said property values for each amino acid in each of the plurality of variants to be evaluated such that the numerical sequence comprises a property value for each amino acid of the sequence of each of the plurality of variants to be evaluated, said plurality of indices comprising an index selected from the group consisting of D Normalized frequency of extended structure, D Electron-ion interaction potential values, D SD of amino acid composition of total proteins, D pK-C and D Weights from the interfacial hydrophobicity (IFH) scale
- calculating a protein spectrum according to the numerical sequence for each of said plurality of variants to be evaluated by applying a Fourier transform to the numerical sequence such that each protein spectrum verifies the following equation:
-
- f
- j
-
- =
-
- ∑
- k
- =
- 0
- N
- -
- 1
-
- x
- k
-
- exp
-
- (
- -
- 2
-
- i
-
-
- π
- N
-
- jk
- )
-
- where j is an index-number of the protein spectrum |fj|;
- the numerical sequence includes N value(s) denoted xk, with 0≤k≤N−1 and N≥1;
- and
- i defining the imaginary number such that i2=−1;
- determining a protein spectra database according to learning data comprising a plurality of protein spectrum values for each of a plurality of pre-existing variants other than the variants to be evaluated that have been experimentally tested in a wet lab for their biochemical or physico-chemical property values, such that each of said protein spectrum values of said pre-existing variants corresponds to a value of protein fitness
- comparing the calculated protein spectrum for each variant to be evaluated with protein spectrum values of the predetermined database;
- predicting a value of said fitness according to the comparison step for each of said variants to be evaluated by determining the protein spectrum value in the protein spectra database that is the closest to the protein spectrum of each variant to be evaluated;
- selecting the variant of the protein from the plurality of variants to be evaluated that has the predicted value of said fitness closest to the desired fitness value;
- and
- synthesizing the selected variant of the protein.