# US 11,749,377 B2 · Method and electronic system for predicting at least one fitness value of a protein, related computer program product

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 11,749,377 B2
- Document ID: US11749377B2
- Status: Granted
- Kind: B2
- Application number: 15/565,893
- Filed: 2016-04-14
- Published: 2018-04-05
- Granted: 2023-09-05
- Earliest claimed: 2015-04-14
- Assignees: Peaccel
- Applicants: Peaccel
- Inventors: Nicolas Fontaine; Frédéric Cadet
- Web page: https://patentgrep.com/patent/US11749377B2

## CPC

- G16B 30/00: ICT specially adapted for sequence analysis involving nucleotides or amino acids
- C07K 2/00: Peptides of undefined number of amino acids; Derivatives thereof
- G06F 17/14: Fourier, Walsh or analogous domain transformations {, e.g. Laplace, Hilbert, Karhunen-Loeve, transforms (for correlation function computation G06F17/156; spectrum analysers G01R23/16)}
- G16B 20/00: ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
- G16B 20/50: Mutagenesis
- C12N 15/1089: {Design, preparation, screening or analysis of libraries using computer algorithms}
- C40B 40/10: Libraries containing peptides or polypeptides, or derivatives thereof
- G16B: BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- C07K: PEPTIDES (peptides in foodstuffs A23; obtaining protein compositions for foodstuffs, working-up proteins for foodstuffs A23J; preparations for medicinal purposes A61K; peptides containing beta-lactam rings C07D; cyclic dipeptides not having in their molecule any other peptide link than those which form their ring, e.g. piperazine-2,5-diones, C07D; ergot alkaloids of the cyclic peptide type C07D519/02; macromolecular compounds having statistically distributed amino acid units in their molecules, i.e. when the preparation does not provide for a specific; but for a random sequence of the amino acid units, homopolyamides and block copolyamides derived from amino acids C08G69/00; macromolecular products derived from proteins C08H1/00; preparation of glue or gelatine C09H; single cell proteins, enzymes C12N; genetic engineering processes for obtaining peptides C12N15/00; compositions for measuring or testing processes involving enzymes C12Q; investigation or analysis of biological material G01N33/00)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- C12N: MICROORGANISMS OR ENZYMES; COMPOSITIONS THEREOF; PROPAGATING, PRESERVING, OR MAINTAINING MICROORGANISMS; MUTATION OR GENETIC ENGINEERING; CULTURE MEDIA (microbiological testing media C12Q1/00)
- C40B: COMBINATORIAL CHEMISTRY; LIBRARIES, e.g. CHEMICAL LIBRARIES (in silico combinatorial libraries of nucleic acids, proteins or peptides G16B35/00; in silico combinatorial chemistry G16C20/60)

## Abstract

A method for predicting at least one fitness value of a protein is implemented on a computer and includes the following steps: encoding the amino acid sequence of the protein into a numerical sequence according to a protein database, the numerical sequence comprising a value for each amino acid of the sequence; calculating a protein spectrum according to the numerical sequence; and for each fitness: comparing the calculated protein spectrum with protein spectrum values of a predetermined database, said database containing protein spectrum values for different values of said fitness, predicting a value of said fitness according to the comparison step.

## Claims

### Claim 1

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.

### Claim 2 (depends on 1)

The method according to claim 1, wherein the calculated protein spectrum includes at least one frequency value and the calculated protein spectrum is compared with said protein spectrum values for each frequency value.

### Claim 3 (depends on 1)

The method according to claim 1, wherein, during the encoding step, the protein database includes several indexes of property values; and
wherein the method further includes a step of:
selecting the best index based on a comparison of measured fitness values for sample proteins with predicted fitness values previously obtained for said sample proteins according to each index;
the encoding step being then performed using the selected index.

### Claim 4 (depends on 3)

The method according to claim 3, wherein, during the selection step, the selected index is the index with the smallest root mean square error,
wherein the root mean square error for each index verifies the following equation:
RMSE
Index
⁢
_
⁢
j
=
∑
i
=
1
S
⁢
(
y
i
-
y
^
i
,
j
)
2
S
where yi is the measured fitness of the ith sample protein,
ŷi,j is the predicted fitness of the ith sample protein with the jth index, and
S the number of sample proteins.

### Claim 5 (depends on 3)

The method according to claim 3, wherein, during the selection step, the selected index is the index with the coefficient of determination nearest to 1,
wherein the coefficient of determination for each index verifies the following equation:
R
Index
⁢
_
⁢
j
2
=
(
∑
i
=
1
S
⁢
(
y
i
-
y
_
)
⁢
(
y
^
i
,
j
-
y
^
_
)
)
2
∑
i
=
1
S
⁢
(
y
i
-
y
_
)
2
⁢
∑
i
=
1
S
⁢
(
y
^
i
,
j
-
y
^
_
)
2
where yi is the measured fitness of the ith sample protein,
ŷi,j is the predicted fitness of the ith sample protein with the jth index,
S the number of sample proteins,
y is an average of the measured fitness for the S sample proteins, and
ŷ is an average of the predicted fitness for the S sample proteins.

### Claim 6 (depends on 1)

The method according to claim 1, wherein the method further includes, after the encoding step and before the protein spectrum calculation step, the following step:
normalizing the numerical sequence obtained via the encoding step, by subtracting to each value of the numerical sequence a mean of the numerical sequence values;
the protein spectrum calculation step being then performed on the normalized numerical sequence.

### Claim 7 (depends on 1)

The method according to claim 1, wherein the method further includes, after the encoding step and before the protein spectrum calculation step, the following step:
zero padding the numerical sequence obtained via the encoding step, by adding M zeros at one end of said numerical sequence, with M equal to (N−P) where N is a predetermined integer and P is the number of values in said numerical sequence;
the protein spectrum calculation step being then performed on the numerical sequence obtained further to the zero padding step.

### Claim 8 (depends on 1)

The method according to claim 1, wherein the comparison step comprises determining, in the predetermined database of protein spectrum values for different values of said fitness, the protein spectrum value which is the closest to the calculated protein spectrum according to a predetermined criterion,
the predicted value of said fitness being then equal to the fitness value which is associated in said database with the determined protein spectrum value.

### Claim 9 (depends on 1)

The method according to claim 1, wherein, during the protein spectrum calculation step, several protein spectra are calculated for said protein according to several frequency ranges, and
wherein, during the prediction step, an intermediate value of the fitness is estimated for each protein spectrum according to the comparison step, and the predicted value of the fitness is then computed using the intermediate fitness values.

### Claim 10 (depends on 1)

The method according to claim 1, wherein the method includes a step of:
analysis of the protein according to the calculated protein spectrum, for screening of mutants libraries.

### Claim 11 (depends on 1)

The method of claim 1, further comprising testing the selected variant that is synthesized in a wet laboratory to confirm the desired fitness.

### Claim 12 (depends on 10)

The method of claim 10, wherein the analysis comprises analyzing each protein in a wet lab library of mutants comprising a plurality of mutant proteins according to the calculated protein spectrum.

### Claim 13 (depends on 1)

The method of claim 1, further comprising testing the selected variant in a wet lab to obtain an actual value of said fitness of said selected variant to confirm the fitness of the selected variant.

### Claim 14

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 the selected 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;
selecting the best index based on a comparison of measured fitness values for sample proteins with predicted fitness values previously obtained for said sample proteins according to each index;
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:
❘
"\[LeftBracketingBar]"
f
j
❘
"\[RightBracketingBar]"
=
❘
"\[LeftBracketingBar]"
∑
k
=
0
N
-
1
x
k
⁢
exp
⁡
(
-
2
⁢
i
⁢
π
N
⁢
jk
)
❘
"\[RightBracketingBar]"
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.