# US 2021/0343369 A1 · Mathematical processes for determination of peptidase cleavage

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

- Number: US 2021/0343369 A1
- Document ID: US20210343369A1
- Status: Published application
- Kind: A1
- Application number: 17/376,739
- Filed: 2021-07-15
- Published: 2021-11-04
- Earliest claimed: 2013-06-10
- Assignees: Iogenetics, LLC
- Applicants: Iogenetics, LLC
- Inventors: Robert D. Bremel
- Web page: https://patentgrep.com/patent/US20210343369A1

## CPC

- G16B 20/30: Detection of binding sites or motifs
- G06N 3/0499: Feedforward networks
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G16B 5/00: ICT specially adapted for modelling or simulations in systems biology, e.g. gene-regulatory networks, protein interaction networks or metabolic networks
- G16B 20/00: ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
- G16B 40/00: ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
- G16B: BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

This invention relates to the identification of peptidase cleavage sites in proteins and in particular to identification protease cleavage by the endopeptidases. The present invention utilizes a bioinformatic methodology for prediction of peptidase cleavage sites based on principal component analysis and based on training sets obtained by experimental protein cleavage. This invention is not limited to training sets derived from CSL approaches, nor to any other experimental determination of cleavage site.

## Claims

### Claim 1

A computer implemented process for providing desired peptidase cleavage sites in a synthetic polypeptide comprising:
a) obtaining an amino acid sequence for a target polypeptide;
b) deriving an ensemble of peptidase cleavage prediction equations for each possible cleavage site dimer by:
(i) assembling experimentally derived data comprising a multiplicity of measurements of amino acid physicochemical properties;
(ii) producing a correlation matrix of the experimentally derived data;
(iii) deriving by Principal Component Analysis multiple uncorrelated dimensionless, weighted and ranked proxy descriptors to describe at least 80% of the variance in said physicochemical properties of individual amino acids,
(iv) using said proxy descriptors to describe individual amino acids in a set of peptides each of which comprises a specific cleavage site dimer experimentally determined to be cleaved, and to describe the individual amino acids in a set of peptides each of which comprises the same cleavage site dimer experimentally determined to be uncleaved;
(v) comparing, via probabilistic modeling, the amino acid descriptors of said peptides comprising said experimentally determined cleaved and uncleaved cleavage site dimers to derive a cleavage prediction equation for said specific cleavage site dimer based on that peptide set;
(vi) repeating the steps of (iv) and (v) multiple times, each time with a different set of peptides that comprise the same cleavage site dimer and are experimentally determined to be cleaved or not cleaved, thereby deriving an ensemble of independently derived peptidase cleavage prediction equations for said specific cleavage site dimer;
(vii) repeating the process of (iv) to (vi) to derive ensembles of independently derived prediction equations for every possible cleavage site dimer up to a total of 400 such ensembles;
(viii) storing said ensembles of independently derived prediction equations on a non-transitory computer readable medium;
(c) in-putting said amino acid sequence from said target polypeptide into a computer;
(d) applying said proxy descriptors from said Principal Component Analysis to describe individual amino acids in said target polypeptide sequence;
(e) deriving vectors to describe a plurality of peptides of defined length in said target polypeptide;
(f) via said computer processor applying said up to 400 ensembles of independently derived peptidase cleavage prediction equations to said plurality of peptides of defined length from said target polypeptide to predict a plurality of peptidase cleavage sites in said target polypeptide;
(g) identifying, by consensus of the ensembles of prediction equations, the probability of cleavage at any given cleavage site dimer in said target polypeptide;
(h) defining amino acids subsets in said target polypeptide that are predicted to be cleaved by a peptidase;
(i) substituting one or more amino acids in the target polypeptide to change the probability of peptidase cleavage;
(j) synthesizing a synthetic polypeptide comprising the substituted amino acids; and
(k) administering said synthetic polypeptide to a subject.

### Claim 2 (depends on 1)

The process of claim 1, wherein said probabilistic modeling is by a probabilistic neural net or a support vector machine.

### Claim 3 (depends on 2)

The process of claim 2, wherein said probabilistic neural net comprises a multi-layer perceptron neural network regression process wherein the output is the probability of cleavage by a particular peptidase within a particular cleavage site dimer within a particular amino acid sequence.

### Claim 4 (depends on 3)

The process of claim 3, wherein said probabilistic neural net predicts a peptidase cleavage site with greater than about 70, 80, 90, or 95% accuracy.

### Claim 5 (depends on 4)

The process of claim 4, further comprising utilizing a number of hidden nodes in said multi-layer perceptron that correlates to the number of amino acids in the cleavage site octomer.

### Claim 6 (depends on 1)

The process of claim 1, wherein said amino acid subset in said protein of interest is from about 4 to about 50 amino acids in length.

### Claim 7 (depends on 1)

The process of claim 1, wherein said peptide of defined length is 8 amino acids in length.

### Claim 8 (depends on 1)

The process of claim 1, wherein said subsets of amino acid sequences begin at n-terminus of the amino acid sequence, wherein n is the first amino acid of the sequence and c is the last amino acid in the sequence, and the sets comprise each peptide of 8 amino acids in length starting from n and the next peptide in the set is n+1 until n+1 ends at c for the given length of the peptides selected.

### Claim 9 (depends on 1)

The process of claim 1, wherein said physicochemical properties of individual amino acids are selected from the group consisting of polarity, optimized matching hydrophobicity, hydropathicity, hydropathcity expressed as free energy of transfer to surface in kcal/mole, hydrophobicity scale based on free energy of transfer in kcal/mole, hydrophobicity expressed as ΔG ½ cal, hydrophobicity scale derived from 3D data, hydrophobicity scale represented as π−r, molar fraction of buried residues, proportion of residues 95% buried, free energy of transfer from inside to outside of a globular protein, hydration potential in kcal/mol, membrane buried helix parameter, mean fractional area loss, average area buried on transfer from standard state to folded protein, molar fraction of accessible residues, hydrophilicity, normalized consensus hydrophobicity scale, average surrounding hydrophobicity, hydrophobicity of physiological L-amino acids, hydrophobicity scale represented as (π−r)2, retension coefficient in HFBA, retention coefficient in HPLC pH 2.1, hydrophobicity scale derived from HPLC peptide retention times, hydrophobicity indices at pH 7.5 determined by HPLC, retention coefficient in TFA, retention coefficient in HPLC pH 7.4, hydrophobicity indices at pH 3.4 determined by HPLC, mobilities of amino acids on chromatography paper, hydrophobic constants derived from HPLC peptide retention times, and combinations thereof.

### Claim 10 (depends on 1)

The process of claim 1, wherein said contribution of the physical properties of each amino acids in said subsets to the peptidase cleavage site is weighted according to the amino acid and its position in each peptide in said set of peptides

### Claim 11 (depends on 1)

The process of claim 1, wherein said process is applied sequentially to determine cleavage by two or more peptidases.

### Claim 12 (depends on 1)

The process of claim 1, wherein said peptidase is a eukaryotic, prokaryotic, viral or synthetic peptidase.

### Claim 13 (depends on 1)

The process of claim 1, wherein said peptidase is an endopeptidase drawn from the group comprising a serine peptidase, a cysteine peptidase, an aspartic peptidase, a glutamic peptidase, an asparagine peptidase, a threonine peptidase, or a metallo-peptidase.

### Claim 14 (depends on 1)

The process of claim 1, wherein said peptidase is a cathepsin.

### Claim 15 (depends on 1)

The process of claim 1 wherein said change in the probability of peptidase cleavage is an increased probability of cleavage.

### Claim 16 (depends on 1)

The process of claim 1 wherein said change in the probability of peptidase cleavage is a decreased probability of cleavage.

### Claim 17 (depends on 1)

The process of claim 1 wherein said synthetic polypeptide is a biopharmaceutical polypeptide or protein.

### Claim 18 (depends on 17)

The process of claim 17 wherein said biopharmaceutical polypeptide or protein is drawn from the group comprising enzymes, clotting factors, monoclonal antibodies and antibody fusions.

### Claim 19 (depends on 17)

The process of claim 17 wherein said biopharmaceutical polypeptide or protein is an immunogen.

### Claim 20 (depends on 1)

The process of claim 1 wherein said target polypeptide is an allergen.

### Claim 21 (depends on 1)

The process of claim 1 wherein said target polypeptide elicits an autoimmune reaction.

### Claim 22 (depends on 1)

The process of claim 1 further comprising:
determining if the target polypeptide comprises a predicted B cell epitope or a predicted T cell epitope peptide and
substituting said one or more amino acids in the target polypeptide to change the probability of peptidase cleavage to cleave said predicted B or T cell epitope peptide, thereby removing its immunogenicity.

### Claim 23 (depends on 1)

The process of claim 1, wherein said peptidase is in an antigen presenting cell.

### Claim 24 (depends on 23)

The process of claim 23, wherein said peptidase is secreted

### Claim 25 (depends on 23)

The process of claim 23, wherein said peptidase is membrane associated

### Claim 26 (depends on 23)

The process of claim 23, wherein said peptidase functions in digestion.

### Claim 27 (depends on 23)

The process of claim 23, wherein said peptidase functions in cell signaling.

### Claim 28 (depends on 23)

The process of claim 23, wherein said peptidase functions in immune processing.

### Claim 29 (depends on 1)

A host cell comprising a nucleic acid encoding a polypeptide identified in step (i) of claim 1.