A Low-Cost Biocomputational Framework for Identifying Novel Malaria Inhibitors Targeting Plasmodium Falciparum
JSHS · 2025
Overview
Malaria is the third deadliest disease with around 249 million cases annually, particularly in tropical regions. Malaria is caused by Plasmodium parasites transmitted through the bite of Anopheles mosquitoes and is a global health burden. Malaria remains d ifficult to treat due to growing drug resistance. Malaria drug discovery is a costly and lengthy process, requiring over a decade and approximately $3 billion before a compound reaches approval. To combat this issue, I created AutoFilter, a low -cost and no vel biocomputational framework that combines machine learning (ML) and screening tools to streamline the filtering of large chemical databases for better drug discovery. AutoFilter sequentially: (i) screens compounds violating basic chemical filters such a s Lipinski’s Rule of 5, Vebers, and PAINS, (ii) docks each compound in the cleaned database and analyzes post-docking interactions. Following docking, AutoFilter conducts ADME filtration to identify compounds with favorable drug -like properties. Then, Auto Filter uses an ML model to predict the toxicity and synthetic accessibility of the compounds. The final step is molecular dynamics, which further refines the selected compounds for stability. I applied AutoFilter to screen the ChEMBL database, a chemical database with 2.4 million bioactive drugs, to identify malaria inhibitors targeting Plasmodium Falciparum apPOL. The five final selected compounds have high inhibition performance and favorable drug -like properties and are undergoing in vitro synthesis. Aut oFilter is the first integrated biocomputational framework for screening chemical databases and is expandable for all diseases. It efficiently identifies inhibitors, reducing current costs and time by 50%, and saving many lives globally.
Competition history
- JSHS 2025
Resources
Related projects
ISEF · 2025
Computational Analysis of Known HIV-1 Protease Inhibitors to Investigate Their Therapeutic Potential for Fatal Malaria Prevention
ISEF · 2023
Using Machine Learning to Discover Novel Drug Combinations Against Malaria
ISEF · 2021
Novel Evolutionary Artificial Intelligence Methods for De Novo Drug Design
ISEF · 2014
Antimalarials: Modeling the Next Generation Inhibitors
ISEF · 2019
Fighting Zika: Computational Discovery of New Drugs to Inhibit the NS2B-NS3 Protease of the Zika Virus
ISEF · 2015
Rethinking Drug Discovery: New Algorithms for Virtual Drug Screening
CWSF · 2026
Evaluating and Improving In Silico Drug Candidate Prediction for Preventing Toxoplasmic Encephalitis
ISEF · 2026
Cost-Effective MalariaX: An AI-Optomechatronic System Decoding Expert Reasoning Into a Sub-Micron, Pan-Species Clinically Traceable Pipeline
Closest projects by meaning, across every fair and year in the corpus.