2409105
Project Grant
Overview
Grant Description
SBIR Phase I: Development of an AI-driven humanized and developable single-domain library design platform for accelerated drug discovery.
The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project is to address major technical and commercial limitations in protein drug discovery.
Drug discovery is currently a slow and expensive process, taking an average of 10 years and $2.6B per drug.
In 2021 the US pharma industry spent almost $100B on drug research and development (R&D) efforts, with ~10% dedicated to protein drugs.
Although some Artificial Intelligence (AI) solutions exist to support this process, fundamental problems exist: no current system optimizes multiple protein functions simultaneously, existing models rely heavily on predicting protein structures, and there is a lack of transparency in the models.
This proposal supports the development of an AI system to improve the identification of small, highly specialized antibodies.
The proposed technology could enhance the speed of identifying lead molecules while also reducing the cost through technical innovations.
Therefore, this work has enormous clinical and commercial potential.
This Small Business Innovation Research (SBIR) Phase I project is intended to support the creation of an AI model to improve the identification of highly developable single-domain antibodies.
These molecules have accepted advantages for therapeutic use (strong binding affinity, good thermal stability and chemostability, and less steric hindrance than conventional antibodies).
However, they are typically obtained through a time- and cost-intensive process that involves immunizing a camelid or screening a large synthetic library.
This proposal will support the development and validation of an AI model specifically intended to quickly identify effective and highly developable single-domain antibody leads against a given target.
In order to accomplish this goal, the proposed work encompasses training a multimodal AI model that is able to recognize key features and residues of single-domain antibodies, then produce libraries of sufficient depth and quality to generate stable, safe leads with strong binding affinities.
After the study period, the model and developed workflows will be evaluated for their ability to rapidly identify lead molecules.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the foundation's intellectual merit and broader impacts review criteria.
Subawards are planned for this award.
The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project is to address major technical and commercial limitations in protein drug discovery.
Drug discovery is currently a slow and expensive process, taking an average of 10 years and $2.6B per drug.
In 2021 the US pharma industry spent almost $100B on drug research and development (R&D) efforts, with ~10% dedicated to protein drugs.
Although some Artificial Intelligence (AI) solutions exist to support this process, fundamental problems exist: no current system optimizes multiple protein functions simultaneously, existing models rely heavily on predicting protein structures, and there is a lack of transparency in the models.
This proposal supports the development of an AI system to improve the identification of small, highly specialized antibodies.
The proposed technology could enhance the speed of identifying lead molecules while also reducing the cost through technical innovations.
Therefore, this work has enormous clinical and commercial potential.
This Small Business Innovation Research (SBIR) Phase I project is intended to support the creation of an AI model to improve the identification of highly developable single-domain antibodies.
These molecules have accepted advantages for therapeutic use (strong binding affinity, good thermal stability and chemostability, and less steric hindrance than conventional antibodies).
However, they are typically obtained through a time- and cost-intensive process that involves immunizing a camelid or screening a large synthetic library.
This proposal will support the development and validation of an AI model specifically intended to quickly identify effective and highly developable single-domain antibody leads against a given target.
In order to accomplish this goal, the proposed work encompasses training a multimodal AI model that is able to recognize key features and residues of single-domain antibodies, then produce libraries of sufficient depth and quality to generate stable, safe leads with strong binding affinities.
After the study period, the model and developed workflows will be evaluated for their ability to rapidly identify lead molecules.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the foundation's intellectual merit and broader impacts review criteria.
Subawards are planned for this award.
Awardee
Funding Goals
THE GOAL OF THIS FUNDING OPPORTUNITY, "NSF SMALL BUSINESS INNOVATION RESEARCH (SBIR)/ SMALL BUSINESS TECHNOLOGY TRANSFER (STTR) PROGRAMS PHASE I", IS IDENTIFIED IN THE LINK: HTTPS://WWW.NSF.GOV/PUBLICATIONS/PUB_SUMM.JSP?ODS_KEY=NSF23515
Grant Program (CFDA)
Awarding / Funding Agency
Place of Performance
Sacramento,
California
95825-1474
United States
Geographic Scope
Single Zip Code
Deepseq.Ai was awarded
Project Grant 2409105
worth $274,797
from National Science Foundation in July 2024 with work to be completed primarily in Sacramento California United States.
The grant
has a duration of 1 year and
was awarded through assistance program 47.084 NSF Technology, Innovation, and Partnerships.
The Project Grant was awarded through grant opportunity NSF Small Business Innovation Research / Small Business Technology Transfer Phase I Programs.
SBIR Details
Research Type
SBIR Phase I
Title
SBIR Phase I: Development of an AI-Driven Humanized and Developable Single-Domain Library Design Platform for Accelerated Drug Discovery
Abstract
The broader impact /commercial potential of this Small Business Innovation Research (SBIR) Phase I project is to address major technical and commercial limitations in protein drug discovery. Drug discovery is currently a slow and expensive process, taking an average of 10 years and $2.6B per drug. In 2021 the US pharma industry spent almost $100B on drug research and development (R&D) efforts, with ~10% dedicated to protein drugs. Although some artificial intelligence (AI) solutions exist to support this process, fundamental problems exist: no current system optimizes multiple protein functions simultaneously, existing models rely heavily on predicting protein structures, and there is a lack of transparency in the models. This proposal supports the development of an AI system to improve the identification of small, highly specialized antibodies. The proposed technology could enhance the speed of identifying lead molecules while also reducing the cost through technical innovations. Therefore, this work has enormous clinical and commercial potential.
This Small Business Innovation Research (SBIR) Phase I project is intended to support the creation of an AI model to improve the identification of highly developable single-domain antibodies. These molecules have accepted advantages for therapeutic use (strong binding affinity, good thermal stability and chemostability, and less steric hindrance than conventional antibodies). However, they are typically obtained through a time- and cost-intensive process that involves immunizing a camelid or screening a large synthetic library. This proposalwill support the development and validation of an AI model specifically intended to quickly identify effective and highly developable single-domain antibody leads against a given target. In order to accomplish this goal, the proposed work encompasses training a multimodal AI model that is able to ecognize key features and residues of single-domain antibodies, then produce libraries of sufficient depth and quality to generate stable, safe leads with strong binding affinities. After the study period, the model and developed workflows will be evaluated for their ability to rapidly identify lead molecules.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
Topic Code
DH
Solicitation Number
NSF 23-515
Status
(Complete)
Last Modified 7/23/24
Period of Performance
7/15/24
Start Date
6/30/25
End Date
Funding Split
$274.8K
Federal Obligation
$0.0
Non-Federal Obligation
$274.8K
Total Obligated
Activity Timeline
Additional Detail
Award ID FAIN
2409105
SAI Number
None
Award ID URI
SAI EXEMPT
Awardee Classifications
Small Business
Awarding Office
491503 TRANSLATIONAL IMPACTS
Funding Office
491503 TRANSLATIONAL IMPACTS
Awardee UEI
EZXQZQPMRY43
Awardee CAGE
None
Performance District
CA-06
Senators
Dianne Feinstein
Alejandro Padilla
Alejandro Padilla
Modified: 7/23/24