# US 2026/0018249 A1 · Peptide manufacturability determination

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

- Number: US 2026/0018249 A1
- Document ID: US20260018249A1
- Status: Published application
- Kind: A1
- Application number: 18/725,548
- Filed: 2024-05-30
- Published: 2026-01-15
- Earliest claimed: 2023-05-31
- Assignees: Amazon Technologies, Inc.
- Applicants: Amazon Technologies, Inc.
- Inventors: Anta IMATA SAFO; Samuel Anthony DANZIGER; Gil SADEH; Layne Christopher PRICE; Frank Wilhelm SCHMITZ; David HECKERMAN; Haibao TANG; Alena HARLEY
- Web page: https://patentgrep.com/patent/US20260018249A1

## CPC

- G16B 15/20: Protein or domain folding
- 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 40/20: Supervised data analysis
- G16B: BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY

## Abstract

Approaches for predicting manufacturability of a peptide are provided. A request for information related to manufacturability of a peptide can be received. A determination as to whether the peptide is predicted to be synthesizable can be made, such as by using a machine learning model. The machine learning model can be trained on data including manufacturer specifications and descriptions associated with a peptide and features for peptides. A second determination can be made as to whether the peptide is predicted to be soluble, using the same or different machine learning model trained with solubility data for peptides. If the peptide is predicted to be soluble and synthesizable, a manufacturability score for the peptide can be determined. The manufacturability score can correspond to or be indicative of a chance of successfully manufacturing the peptide.

## Claims

### Claim 1

A computer-implemented method, comprising:
receiving a request for information related to manufacturability of a peptide;
determining whether the peptide is predicted to be synthesizable;
determining whether the peptide is predicted to be soluble; and
determining, based at least in part on whether the peptide is predicted to be synthesizable and soluble, whether the peptide is manufacturable using a trained machine learning model.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, further comprising:
determining whether the peptide is predicted to pass a quality control check; and
determining, based at least in part on whether the peptide is predicted to be synthesizable, soluble, and pass the quality control check, whether the peptide is manufacturable.

### Claim 3 (depends on 1)

The computer-implemented method of claim 1, further comprising:
calculating a manufacturability score for the peptide, the manufacturability score indicative of a probability of successfully manufacturing the peptide; and
using the manufacturability score to determine whether the peptide is manufacturable.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, wherein the machine learning model is trained, at least in part, on peptide data, peptide feature data, manufacturer specification and descriptor data, or manufacturability data.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, wherein a result of whether the peptide was successfully manufactured is used to further train the machine learning model.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein the determining whether the peptide is predicted to be synthesizable and determining whether the peptide is predicted to be soluble are each performed using models trained specifically for each determination.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, further comprising:
selecting the peptide for manufacture based on the determination whether the peptide is manufacturable.

### Claim 8

A computing system, comprising:
a computing device processor; and
a memory device including instructions that, when executed by the computing device processor, enable the computing system to:
receive a request for information related to manufacturability of a peptide;
determine whether the peptide is predicted to be synthesizable;
determine whether the peptide is predicted to be soluble; and
determine, based at least in part on whether the peptide is synthesizable and soluble, whether the peptide is manufacturable using a trained machine learning model.

### Claim 9 (depends on 8)

The computing system of claim 8, wherein the instructions that, when executed by the computing device processor, enable the computing system to further:
determine whether the peptide is predicted to pass a quality control check; and
determine, based at least in part on whether the peptide is predicted to be synthesizable, soluble, and pass the quality control check, whether the peptide is manufacturable.

### Claim 10 (depends on 8)

The computing system of claim 8, wherein the instructions that, when executed by the computing device processor, enable the computing system to further:
calculate a manufacturability score for the peptide, the manufacturability score indicative of a probability of successfully manufacturing the peptide; and
use the manufacturability score to determine whether the peptide is manufacturable.

### Claim 11 (depends on 8)

The computing system of claim 8, wherein the machine learning model is trained, at least in part, on peptide data, peptide feature data, manufacturer specification and descriptor data, or manufacturability data.

### Claim 12 (depends on 8)

The computing system of claim 8, wherein a result of whether the peptide was successfully manufactured is used to further train the machine learning model.

### Claim 13 (depends on 8)

The computing system of claim 8, wherein the determining whether the peptide is predicted to be synthesizable and determining whether the peptide is predicted to be soluble are each performed using models trained specifically for each determination.

### Claim 14 (depends on 8)

The computing system of claim 8, wherein the determining whether the peptide is predicted to be synthesizable and the determining whether the peptide is predicted to be soluble is determined as part of using the trained machine learning model to determine whether the peptide is manufacturable.

### Claim 15 (depends on 8)

The computing system of claim 8, wherein the instructions that, when executed by the computing device processor, enable the computing system to further:
determine a solubility score for the peptide;
determine a synthesizability score for the peptide; and
predict a likelihood of manufacturability for the peptide based, at least in part, on the solubility score or the synthesizability score.

### Claim 16

A non-transitory computer-readable medium comprising instructions stored thereon, that when executed on a processor, perform the steps of:
receiving a request for information related to manufacturability of a peptide;
determining whether the peptide is predicted to be synthesizable;
determining whether the peptide is predicted to be soluble; and
determining, based at least in part on whether the peptide is predicted to be synthesizable and soluble, whether the peptide is manufacturable using a trained machine learning model.

### Claim 17 (depends on 16)

The non-transitory computer-readable medium of claim 16, wherein the instructions that, when executed on the processor, additionally perform the steps of:
determining whether the peptide is predicted to pass a quality control check; and
determining, based at least in part on whether the peptide is predicted to be synthesizable, soluble, and pass the quality control check, whether the peptide is manufacturable.

### Claim 18 (depends on 16)

The non-transitory computer-readable medium of claim 16, wherein the instructions that, when executed on the processor, additionally perform the steps of:
determining a solubility score for the peptide;
determine a synthesizability score for the peptide; and
predicting a likelihood of manufacturability for the peptide based, at least in part, on the solubility score or the synthesizability score.

### Claim 19 (depends on 16)

The non-transitory computer-readable medium of claim 16, wherein the machine learning model is trained, at least in part, on peptide data, peptide feature data, manufacturer specification and descriptor data, or manufacturability data.

### Claim 20 (depends on 16)

The non-transitory computer-readable medium of claim 16, wherein a result of whether the peptide was successfully manufactured is used to further train the machine learning model.
