Identifying Novel Kinases for Approved Drugs using a Convolutional Neural Network Autoencoder and AlphaFold
CSEF · 2023 Biochemistry/ Molecular Biology Second Award
Overview
Today, it takes >14 years, $2B to develop a new drug. A faster, cheaper way to inhibit newly-discovered disease targets would greatly benefit patients. The purpose of this project is to test whether FDA-approved, small-molecule drugs may be repurposed against novel targets. The hypothesis is that if a novel kinase has a 3D-binding pocket similar to that of a known kinase for which there is already an approved drug, then this medicine may also be therapeutically useful against the novel kinase. Training/Testing Datasets were established to create 2D- contact matrices from 3D-structures of kinases from both ProteinDataBank (experimentally-derived; known/bound-to-inhibitors) and AlphaFold (AI- predicted; novel/unbound). A cosine similarity matrix between kinases was created using a CNN autoencoder. To-date, four novel kinases were identified (including a novel G protein-coupled receptor kinase) that fit approved drugs. This innovative, machine learning-based methodology supports the repurposing of medicines against novel protein targets and may accelerate future treatments.
Source coverage
This record comes from a published award list, not a complete project archive. Its abstract comes from CSEF's public project showcase as archived by the Internet Archive before judging (https://web.archive.org/web/20230401224130/https://ca-csef.zfairs.com/showcase/ShowcaseInfo?f=838e60b7-ea75-46e8-865c-fde4864244b3); the version presented may differ.
Awards (2)
- Category Award: 2
- Sponsored Award: Junior Division Biochemistry/Molecular Biology Award
Competition history
- CSEF 2023
Resources
Related projects
ISEF · 2021
Using Machine Learning to Repurpose FDA-Approved Drugs to Treat Cancers and Inflammatory Diseases
ISEF · 2023
Using Artificial Intelligence Neural Networks to Repurpose Pre-Existing Drugs and Analyze Drug Relationships, Year 3
ISEF · 2026
AI-Driven Graph Neural Networks for Dual-Target AChE and BACE1 Drug Repurposing in Alzheimer’s Disease
ISEF · 2021
A Novel Computational Approach to Drug Discovery Through Drug Repositioning
ISEF · 2022
Using Artificial Intelligence Graph Neural Networks To Repurpose Pre-existing Drugs and Analyze Drug Relationships: Year 2
ISEF · 2025
A Novel Computational Generative Model That Identifies Ligands: A Potential Way to Reduce Cost & Time in Identifying Promising Drug Candidates
ISEF · 2020
DeepChem: Using Generative Adversarial Networks to Develop Novel Inhibitors of Carcinomas
ISEF · 2021
Novel Evolutionary Artificial Intelligence Methods for De Novo Drug Design
Closest projects by meaning, across every fair and year in the corpus.
Browse more like this
Source: California Science & Engineering Fair public projects