Institution profile

Mayo Clinic

Academic institutionnorthamerica · us
Official website
Research library170linked papers
Opportunities0open roles
Selected work

Representative Papers

MatchMiner-AI: An Open-Source Solution for Cancer Clinical Trial Matching

Dec 23, 2024arXiv.org

To address the critical challenges of insufficient patient recruitment in oncology clinical trials and low efficiency of manual eligibility screening, this paper proposes TrialSpace: an interpretable, AI-assisted matching framework grounded in semantic embeddings. Methodologically, it introduces a novel decoupled matching paradigm—jointly modeling patient electronic health records and trial protocols within a disease-specific semantic space. Clinical BERT is fine-tuned to extract domain-aware features, followed by vector-based candidate retrieval and a lightweight binary classifier for eligibility verification. Key contributions include: (1) the first open-source clinical trial matching toolkit and a synthetically generated benchmark dataset; (2) strong performance (Top-5 recall >92% on synthetic data), model interpretability, and clinical deployability; and (3) a publicly available interactive demo, along with full source code and pre-trained model weights. TrialSpace significantly enhances physician screening efficiency while supporting evidence-based decision-making—not replacing clinicians, but augmenting their expertise.

6 citationsRead paper

Conditioned Generative Modeling of Molecular Glues: A Realistic AI Approach for Synthesizable Drug-like Molecules

Jun 01, 2025Biomolecules

This study addresses the challenge of developing highly specific, synthetically accessible small-molecule degraders for intracellular toxic Aβ-42 protein in Alzheimer’s disease by proposing a molecular glue design strategy leveraging the ubiquitin–proteasome system. The authors innovatively integrate conditional information of E3 ligases (CRBN, VHL, and MDM2) into a generative model, constructing a Ligase-Conditioned Junction Tree Variational Autoencoder (LC-JT-VAE) that combines protein sequence embeddings with torsion-aware molecular graphs. The framework further incorporates structural docking and ADMET filtering to prioritize viable candidates. This approach successfully generates novel, chemically synthesizable, and ligase-selective molecular glues capable of mediating ternary complex formation between Aβ-42 and E3 ligases, demonstrating promising potential for promoting Aβ-42 degradation and offering a new therapeutic paradigm for neurodegenerative diseases.

4 citationsRead paper
Recent publications

Latest Papers