APTAi: De Novo Aptamer Design for Proteomic Biomarker Detection Using a Physics-Informed AI Model
CWSF · 2026 Disease & Illness Platinum Award
Overview
Sepsis claims 11 million lives annually, but current diagnostics are costly and often ineffective. Aptamers are single-stranded DNA or RNA sequences that are promising for detecting proteomic biomarkers like Procalcitonin. However, their discovery is bottlenecked by the expensive and labor-intensive SELEX process. APTAi is a novel computational pipeline that utilizes a Conditional Variational Autoencoder (CVAE) and Monte-Carlo Tree Search (MCTS) to generate these high-affinity sequences in-silico. By mapping biomarker features onto a 423-dimensional Riemannian manifold, APTAi navigates the target’s unique surface topography. Integrating physics-based validation, including ΔG thermodynamics, molecular docking, and toxicity assessment, ensures stable binding and manufacturability. This de novo approach replaces months of research with a rapid, generalizable solution for the future of disease diagnostics.
Awards (5)
- Platinum Award
- Challenge Award
- Special Award
- Gold Medal
- Selected for CWSF 2026
Competition history
- CWSF 2026
Related projects
CWSF · 2026
AptaBind AI: Using Artificial Intelligence to predict aptamer target binding.
ISEF · 2025
TETRA-C: Accelerating Cancer Therapy Through AI-Optimized Telomerase Inhibition, Enzymatic Targeting, and the Suppression of Metastasis
ISEF · 2026
POCKET: A Multiplexing Point-of-Care Kinetic Electrochemical Test Using Aptamers for Accessible, Rapid Diagnostics
ISEF · 2017
Developing a Nanoscale DLD Array Using Immunosignature-Derived Aptamers to Effectively Separate and Analyze Tumor Exosomes
Closest projects by meaning, across every fair and year in the corpus.