Research · Build · DiscoverComputational Science & Engineering

Computational research & software

Research · Build · Discover

Computational Science & Engineering

I explore problems in complex systems, build computational and experimental tools to understand them, and turn ideas into open-source software products.

I am interested in making the assumptions behind a computational decision visible, so that a prediction can be examined rather than simply accepted.

  • Molecular simulation
  • AI for science
  • Scientific software
  • Privacy

Selected Projects

Featured research

Do molecular-dynamics simulations of drug candidates need to run to the end?

PocketStop uses early molecular motion to flag unpromising simulation runs. Calibrated decisions help preserve runs that may still pass the screening endpoint.

Held-out milbemycin evaluation · 106 historical 100 ns runs · screening at 8 ns · 10% false-stop target

Endpoint-passing runs preserved
95.0%
38 of 40 runs
Later failures identified
60.6%
40 of 66 runs
Simulation time saved
34.7%
vs. all 106 runs to 100 ns

A retrospective replay of completed simulations, with held-out proteins excluded from model fitting and threshold calibration. The policy has not yet been tested on new screens.

As sole author, I defined the problem, ran the simulations and machine-learning analyses, and released the software.

PocketStopOpen-source research software

Recognition: 2027 Top 100 Emerging Innovators — Emerging Innovator Awards · Honoree

Recognition: International AI Innovation Olympiad 2026 — AI for Science · Remote Session · Rank 2, Silver

Can a successful login still leave its session cookie insecure?

CookieGuard AI helps build trust in AI browser agents by independently checking how their login cookies are protected. It also supports browser tests, CI, and interactive Chrome scans. 1,852 reported downloads across 6 npm and PyPI packages (through Nov 5, 2026; 1 package awaiting its first report; includes recorded snapshot).

I built the Chrome extension and expanded the project into tools for browser agents, automated tests, and CI.

CookieGuard AIChrome extension · Developer toolkit

Recognition: 2027 Top 100 Emerging Innovators — Emerging Innovator Awards · Honoree

Recognition: Girls Who Code Challenge 2026 — Winner

Explore the project
Two AirWater AI panels for Phoenix in July on a blue background. The daily operating plan for an example hot, dry day: relative humidity and temperature by hour, with the material adsorbing overnight and releasing around midday; daily average humidity 26%, temperature 93.7 °F, peak solar availability 935 W/m². The top recommendation: Al-Fumarate, high confidence, passing climate match, heat feasibility and evidence-aware ranking, with its crystal structure.

Can we tell whether pulling water from the air will work before building the system?

AirWater AI uses climate and material data to screen sites and operating schedules. It flags cases with weak evidence.

Phoenix in July with a 3 L/day target: an hour-by-hour capture-and-release plan and the top-ranked material, Al-Fumarate, at an estimated 3.47–4.50 L/day-equivalent before device losses. For the same site in January, the application answers Do not deploy.

I built it as a functional proof of concept: the isotherm dataset, the uptake model, the ranking and scheduling logic, and the web app.

AirWater AIPublic web application

Recognition: International Youth AI Competition 2026 (Fall) — Gold Award

Explore the project
Two BenefitStep screens on a green background. The side panel at its first step: Prepare your benefits application package, with the steps Quick check, Document, Review and Application, and a choice between a new application and a renewal or periodic report. The last step: Your preparation package is ready, with a button to generate the CalFresh package (CF285).

Can a family prepare a CalFresh or Medi-Cal application from the documents they already have, without sending those documents anywhere?

BenefitStep reads pay stubs, bills and receipts on the user's own computer, links each detail to its source, and fills in unsigned drafts of California's official forms.

The extension's first and last steps, from choosing an application to generating the draft forms. In a test of its document reader on 26 fictional files written for the project, 66 of 68 filled-in values matched the document.

I researched the problem, designed the workflow, and directed AI-assisted implementation and testing.

BenefitStepPublished Chrome extension

Explore the project

More research

View all projects

Selected Publications

  1. 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 ·

  2. Feasibility of Risk-Calibrated Early-Termination for Molecular Dynamics Screening of Antifungal Resistance-Mediating ABC Transporter Pockets

    A. Jing · The 17th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics ·

  3. 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) ·

View all publications