SMILES Encoding and Deep Learning to Predict Quantitative Efficacy of Structurally Distinct Molecules for Antibiotics
CSEF · 2023 Microbiology (General) Honorable_mention Award
Overview
Background: Antibiotics have become a vital part of our society with many individuals relying on them for medical usage and building immunity within our bodies. However, due to the adaptability of bacteria and antimicrobial resistance, professionals estimate an additional 10 million deaths per year by 2050. Current screening methods for new antibiotic ingredients consist of natural product discovery (shown to detect similar structures repeatedly) and scanning synthetic chemical libraries (containing millions of hard-to-parse molecules). Research Purpose/Methods: This novel approach to antibiotic discovery aims to identify compounds inhibiting the development of bacteria through machine learning. By analyzing the past data of molecular structures and extracting useful data from a SMILE format such as the features of individual atoms and bonds, this artificial intelligence model finds which structures would be most optimal at restricting the growth of a certain bacteria. Specifically, this approach utilizes a Graph Neural Network architecture built upon other available metadata through a transfer-learning approach. The rapid output of this program allows for the development of robust antibiotics on a limited timetable. Conclusion/Discussion: By utilizing an R^2 test (test of linearity among predicted results vs actual results), the program performed with a score of 0.94649, greater than comparative research. Through this research, the time of testing a certain molecule for Echestria Coli inhibition is reduced to seconds and corporations can further optimize research costs.
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 (1)
- Category Award: HM
Competition history
- CSEF 2023
Resources
Related projects
ISEF · 2022
Synthesis and Motif Discovery of Novel Antibacterial Molecules and Orally Active Drugs via Sequence-Based Machine Learning
CSEF · 2019
Using Machine Learning and Surface Enhanced Raman Spectroscopy to Analyze the Effects of Antibiotics on P. aeruginosa
ISEF · 2020
Improving Hazard Characterization in Bacterial Pathogens: Predicting Efficiency of Antibiotics Using Machine Learning
ISEF · 2017
Using Artificial Neural Networks to Predict Minimum Inhibitory Concentration of Candidate Antibiotics against E. coli and X. alfalfae
AJAS · 2025
Molecular Image-Based Explainable AI Framework Identifies Novel Candidate Antibiotics
ISEF · 2026
Beyond the Mutation: Evolution-Aware Antibiotic Discovery Through a Novel Resistance-Robust Computational Framework
AJAS · 2020
Development of an Antimicrobial Peptide Activity Detector Using Machine Learning
ISEF · 2018
Battling Superbugs: A Machine Learning Framework for Identifying Novel Antibiotic Resistance Factors
Closest projects by meaning, across every fair and year in the corpus.
Browse more like this
Source: California Science & Engineering Fair public projects