AI for Science
Molecular dynamics and scientific machine learning projects for understanding complex molecular systems.
Home
Photo
Avelyn Jing
Student Researcher
Understanding, Predicting, and Engineering Complicated Systems.
Research
Current Research
Cybersecurity
Applied AI projects for detecting, explaining, and managing online security risks.
Publications
Publications
A Physics-Informed Machine Learning Framework for Screening Antifungal Resistance-Mediating ABC Transporter Pocket Stability
A Jing · 2026 48th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Feasibility of Risk-Calibrated Early-Termination for Molecular Dynamics Screening of Antifungal Resistance-Mediating ABC Transporters
A Jing · The 17th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics
Mechanism-Aware GNN Framework for Predicting Pocket Dynamics in ABC Transporters Mediating Antifungal Resistance
A Jing · 2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
Structure-Guided Framework for Characterizing Drug Resistance-Mediating ABC Transporters in Coccidioides immitis
A Jing · 2025 IEEE EMBS International Conference on Biomedical and Health Informatics
Cited by 1
Personal Interests
Speech & Debate
Public speaking, argumentation, and structured discussion.
Book Reading
Reading across science, technology, history, and literature.
Article Writing
Writing short-form reflections on science, technology, and ideas.
News
New updates on publications and ongoing collaborations will appear here.
Contact
For research discussions, collaborations, or speaking inquiries, reach out at avelynjing29@gmail.com.
GitHub: github.com/aiscihub
Research Learning
A working syllabus
A curated path through the ideas and tools behind my research.
Why these topics
My work asks how molecular systems move, how those motions shape transport and resistance, and how machine learning can help us study them. OpenMM is the simulation framework at the center of this path, from physical principles to research-ready analysis.
01
Molecular Dynamics Foundations
Build an intuition for how atomic motion is computed and what a simulation can—and cannot—tell us.
- Force fields
- Integrators
- Ensembles
- Periodic boundaries
02
From Structure to Trajectory
Learn the practical workflow: prepare a system, add solvent and ions, minimize, equilibrate, and run production dynamics.
- System setup
- Solvation
- Equilibration
- Quality checks
03
Reading Molecular Motion
Turn trajectories into evidence using structural, contact-based, and collective-motion analyses.
- RMSD & RMSF
- Contacts
- PCA
- Convergence
04
Free Energy & Enhanced Sampling
Explore rare transitions and rugged energy landscapes that conventional simulation timescales may miss.
- Collective variables
- Umbrella sampling
- Metadynamics
- Reweighting
05
Machine Learning for Molecular Systems
Connect OpenMM simulations with learned representations, neural potentials, and data-driven dynamics.
- Molecular graphs
- Neural potentials
- OpenMM-ML
- Learned forces
Research Toolkit
Useful links from the research workflow
Structure prediction, pocket detection, docking, and interaction analysis tools used across Avelyn's work.