Research · Build · DiscoverComputational Science & Engineering

AI for Science

PocketStop

Risk-aware decisions from early molecular-dynamics data.

Can early simulation data identify runs that are not worth continuing without discarding too many runs that would later meet the study's endpoint?

PocketStop uses early ligand- and pocket-motion features to make risk-calibrated stop-or-continue recommendations for molecular-dynamics screening.

The primary retrospective study evaluates 106 completed 100 ns milbemycin trajectories using protein-held-out testing, with held-out proteins excluded from both model fitting and threshold calibration.

Key Results

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

Endpoint-passing runs preserved
95.0%
Proportion of runs that would have met the endpoint and were not stopped (38 of 40)
Later failures identified
60.6%
Proportion of runs that did not meet the endpoint and were correctly stopped (40 of 66)
Simulation time saved
34.7%
Planned simulation time avoided through correct stops, relative to completing all 106 runs to 100 ns

How It Works

The user sets the false-stop target; calibration determines the stopping threshold.

  1. Early trajectory

    Only the first 8–12 ns of a planned 100 ns simulation is used.

  2. Ligand + pocket motion

    Seven features describe how the ligand changes shape and how the pocket around it moves.

  3. Predictive model

    Logistic regression combines the features into one stop score; a higher score favors stopping.

  4. Risk calibration

    The cutoff is set to catch the most failures while keeping false stops within the target.

  5. Decision

    A frozen policy applies the cutoff to proteins it has never seen.

Check at 8 ns, then decide. Two simulations of the same held-out protein, at the 8 ns checkpoint with a 10% false-stop target.

pocket 3Fungal transporter CDR1
Molecular-dynamics snapshot at 8 ns: the small molecule, in orange, inside pocket 3 of the CDR1 transporter, in blue
8 ns checkpoint100 ns planned
Stop score at 8 ns0.519cutoff 0.692

Decision at 8 ns: ContinueResult at 100 ns: Pass

pocket 14Fungal transporter CDR1
Molecular-dynamics snapshot at 8 ns: the small molecule, in orange, inside pocket 14 of the CDR1 transporter, in blue
8 ns checkpoint100 ns planned
Stop score at 8 ns0.856cutoff 0.692

Decision at 8 ns: StopResult at 100 ns: Fail

Small molecule (milbemycin)Protein pocketReal molecular-dynamics snapshots. Retrospective replay of two completed simulations, selected as an example; the model saw only the first 8 ns.

Each recommendation records the checkpoint, features, fitted model, threshold, decision rule, and provenance needed to reproduce the decision.

What I Did

I defined the research problem, ran the simulations and machine-learning analyses, analyzed the data, wrote the paper as its sole author, and released PocketStop as open-source software.

  • Designed the evaluation framework
  • Ran MD simulations
  • Implemented machine-learning models
  • Calibrated risk-based decision thresholds
  • Built the analysis pipeline and documentation
  • Wrote the paper and created the open-source release

Open-Source Software

PocketStop repository

View on GitHub

Research Poster

IAI²O research backboard

View poster

PocketStop Research Backboard

View full-size image (opens in a new tab)