Official websites use .gov

A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS

A lock ( 🔒 ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Need Help

Artificial intelligence-enhanced prediction of neuropeptides

Award Number: R21LM015107
ORGANIZATION: NATIONAL LIBRARY OF MEDICINE
OPDIV: NIH
AWARD CLASS: DISCRETIONARY
AWARD ACTIVITY TYPE: SCIENTIFIC/HEALTH RESEARCH (INCLUDES SURVEYS)
PERIOD OF PERFORMANCE START DATE: 09/23/2026
PERIOD OF PERFORMANCE END DATE: 08/31/2028

Group Awards By:

View Award Description

Artificial intelligence-enhanced prediction of neuropeptides - Neuropeptides play a crucial role in regulating central nervous system processes such as reward, food intake, and pain sensation. These signaling molecules have become vital in treating conditions like diabetes, obesity, migraines, and substance abuse. However, one key challenge in developing neuropeptide-based therapies is the variability in their sequences, caused by complex cleavage of prohormone proteins. This variability complicates their detection, especially using sequence-reliant methods like mass spectrometry. Our team has been a leader in mapping the prohormone and neuropeptide landscapes across species and conditions. Through the NIH-funded portal, we offer a curated neuropeptide database and cleavage prediction tools, including machine learning models. This portal has become an essential resource, widely cited for the repository of sequences and tools applying standards to ensure accessibility and reusability. Advances in single-cell proteomics and transcriptomics and AI-driven approaches, provide us with an opportunity to model complex cleavage processes more accurately. However, prior attempts at integrating AI have been hindered by sequence constraints and oversimplified assumptions. We propose an innovative AI-driven approach to tackle these challenges and improve neuropeptide detection, thus advancing detection and characterization. This strategy leverages our extensive sequence repository, along with deep learning and traditional AI models that incorporate primary and secondary structure data. By integrating comprehensive datasets, spanning human, primate, and model organism sequences, including alternative splicing and SNPs, we aim to significantly enhance prediction accuracy and reproducibility. In aim 1 AI-assisted neuropeptide prediction will be enhanced using variant-augmented datasets. In aim 2, the incorporation of bond information in AI models for more accurate cleavage prediction. These advancements address current limitations in prediction accuracy and reproducibility. Preliminary results show significant improvements in sensitivity while maintaining specificity. The algorithms are computationally efficient, fast, and use open-source tools, making the system adaptable for public use. This work supports a growing body of research focused on neuropeptide detection and study for therapeutic uses.


Issue Date FY	Funding FY	Legal Entity Name	Legal Entity Address	Legal Entity City	Legal Entity State	Legal Entity Zip Code	Legal Entity COUNTY	Legal Entity COUNTRY	Assistance Listing	Award Code	Budget Year	Action Date	Action Type	Action Amount

Issue Date FY: 2026 ( Subtotal = $210,258 )
2026	2026	UNIVERSITY OF ILLINOIS	506 S WRIGHT ST	URBANA	IL	61801	CHAMPAIGN	USA	Medical Library Assistance	000	1	9/18/2026	NEW	$210,258
2026	2026	UNIVERSITY OF ILLINOIS	506 S WRIGHT ST	URBANA	IL	61801	CHAMPAIGN	USA	Medical Library Assistance	001	1	9/24/2026	NEW	$0
														Subtotal = $210,258

Grand Total All Awards = $210,258

Top

All Categories

About

Search

Reports

Data Submission

Award Information

Artificial intelligence-enhanced prediction of neuropeptides

Award Number: R21LM015107

ORGANIZATION: NATIONAL LIBRARY OF MEDICINE

OPDIV: NIH

AWARD CLASS: DISCRETIONARY

AWARD ACTIVITY TYPE: SCIENTIFIC/HEALTH RESEARCH (INCLUDES SURVEYS)

PERIOD OF PERFORMANCE START DATE: 09/23/2026

PERIOD OF PERFORMANCE END DATE: 08/31/2028

Federal Websites

Department of Health & Human Services

HHS Operating Divisions

HHS Staff Divisions

Download A Document Viewer