# US 2026/0227383 A1 · Systems and methods for determining a cosmetic formula

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

- Number: US 2026/0227383 A1
- Document ID: US20260227383A1
- Status: Published application
- Kind: A1
- Application number: 19/042,273
- Filed: 2025-01-31
- Published: 2026-08-06
- Earliest claimed: 2025-01-31
- Assignees: L’oréAl
- Applicants: L’Oreal
- Inventors: Xue LIU; Jyotsna PATURI; Janet WANGARI OLIVERO
- Web page: https://patentgrep.com/patent/US20260227383A1

## CPC

- G01N 33/5008: {for testing or evaluating the effect of chemical or biological compounds, e.g. drugs, cosmetics}
- G16H 20/00: ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q)
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

Systems, apparatuses, methods, and computer program products are disclosed for determining cosmetic ingredients and/or efficacy of each. In embodiments, methods may include receiving a biological sample from one or more subjects corresponding to an area applied with a cosmetic. The method may include performing multi-omics analysis on the biological sample, thereby to generate cell characteristics of the biological sample for the cosmetic. The method may include determining a difference between the cell characteristics of the biological sample and one or more of (i) an untreated biological sample from the one or more subjects or (ii) a standard. The method may include scoring the cell characteristics of each biological sample based on determined difference. The method may include determining one or more of (i) one or more new ingredients or (ii) one or more new amounts of ingredients in the cosmetic based on the score for the cell characteristics.

## Claims

### Claim 1

A method for determining cosmetic ingredient efficacy and selection, the method comprising:
(a) receiving a biological sample from one or more subjects corresponding to an area applied with a cosmetic;
(b) performing multi-omics analysis on the biological sample, thereby to generate cell characteristics of the biological sample for the cosmetic;
(c) determining a difference between the cell characteristics of the biological sample and one or more of (i) an untreated biological sample from the one or more subjects or (ii) a standard;
(d) scoring the cell characteristics of each biological sample based on determined difference; and
(e) determining one or more of (i) one or more new ingredients or (ii) one or more new amounts of ingredients in the cosmetic based on the score for the cell characteristics.

### Claim 2 (depends on 1)

The method of claim 1, further comprising iteratively performing steps (a) and (b) with a plurality of cosmetics each with at least one formulaic difference from a previously analyzed cosmetic.

### Claim 3 (depends on 2)

The method of claim 2, wherein the determined difference is further based on the difference between each cell characteristics and cell characteristics of each other sample treated with the plurality of cosmetics.

### Claim 4 (depends on 1)

The method of claim 1, wherein the multi-OMICS analysis comprises one or more of overlaying spatial gene expressions with histology images; performing differential expression analysis between the biological sample and a control; analyzing gene ontology and pathway enrichment; or integrating transcriptomics, proteomics, and clinical data.

### Claim 5 (depends on 1)

The method of claim 1, wherein determination of the one or more of (i) one or more new ingredients or (ii) one or more new amounts of ingredients in the cosmetic comprises:
applying the score for the cell characteristics, the cell characteristics, ingredients of the cosmetic, and amounts of ingredients in the cosmetic to a trained machine learning model.

### Claim 6 (depends on 5)

The method of claim 5, wherein an output of the trained machine learning model comprises data indicative of the one or more of (i) one or more new ingredients or (ii) one or more new amounts of ingredients in the cosmetic.

### Claim 7

An apparatus for determining cosmetic ingredient efficacy and selection, the apparatus comprising:
a multi-omics testing circuitry configured to:
receive biological samples from one or more subjects corresponding to an area applied with a corresponding one of a plurality of cosmetics over a selected time, each of the plurality of cosmetics varying by at least one ingredient from each other of the plurality of cosmetics,
execute multi-omics testing on the biological samples to generate multi-omics data for each of the biological samples; and
a scoring circuitry configured to:
apply the multi-omics data to one or more of (a) one or more analysis algorithms or (b) a trained machine learning model, thereby to generate cell characteristics for each of the biological samples,
determine a difference between the cell characteristics of each of the biological samples,
score each of the cell characteristics of the biological samples based on (a) the cell characteristics of the biological sample and (b) the difference, the score indicating efficacy of the cosmetic, and
determine one or more of (a) one or more new ingredients or (b) one or more new amounts of ingredients in the cosmetic based on each score of each of the cell characteristics thereby to increase cosmetic efficacy.

### Claim 8 (depends on 7)

The apparatus of claim 7, wherein the score indicates an efficacy of the cosmetic in comparison to a control.

### Claim 9 (depends on 7)

The apparatus of claim 7, wherein the difference is further based on differences between the cell characteristics and a control.

### Claim 10 (depends on 9)

The apparatus of claim 9, wherein the control comprises one or more of an untreated sample, a standard, or a comparable standard.

### Claim 11 (depends on 7)

The apparatus of claim 7, wherein each of the cell characteristics correlate to selected cellular attributes, and wherein the cellular attributes comprise one or more of lipid metabolism, extracellular matrix organization, cellular stress response, cellular detoxification, immune responses, or inflammatory response.

### Claim 12 (depends on 7)

The apparatus of claim 7, wherein each of the cell characteristics correlate to selected cellular attributes, and wherein the cellular attributes comprise one or more of lipid metabolism, extracellular matrix organization, cellular stress response, cellular detoxification, immune responses, or inflammatory response.

### Claim 13

A computer program product for determining cosmetic ingredient efficacy, the computer program product comprising a non-transitory machine-readable storage medium storing software instructions that, when executed, cause an apparatus to:
execute multi-OMICS testing on a biological sample from a subject corresponding to an application of a cosmetic treatment, thereby to generate multi-OMICS data; and
apply the multi-OMICS data to one or more analysis instructions, thereby to generate cell characteristics of the biological sample,
determine a difference between the cell characteristics of the biological sample and cell characteristics of an untreated sample, control, or standard,
score the cell characteristics of the biological sample based on (a) the cell characteristics of the biological sample and (b) the difference, and
determine efficacy of ingredients in the cosmetic based on the score of each of the cell characteristics.

### Claim 14 (depends on 13)

The computer program product of claim 13, wherein the one or more analysis instructions comprise one or more of (a) multi-OMICS analysis algorithms or (b) a trained machine learning algorithm.
