rangsimanketkaew

Mitigating the effect of activity cliffs using Triplet Soft Margin (TSM) loss on High-Value Activity Cliff Triplets (HV-ACTs).

Running molecular geometry optimization and molecular dynamics (MD) simulations using ASE and MLIPs.

Generating 3D molecular conformations and preparing input files for quantum chemistry DFT calculations.

Constructing Gaussian output neural networks and training deep ensembles to quantify aleatoric and epistemic uncertainty.

Implementing Delta-ML (residual learning between low and high levels of theory) and model transfer learning.

Optimizing molecular feature weights and performing feature selection via Differentiable Information Imbalance (DII).

Active learning loops for MLIPs using uncertainty-biased configuration selection and DFT query oracle simulation.

Training Machine Learning Interatomic Potentials (MLIP) to predict energies and forces, and wrapping as an ASE Calculator.

Add a new quantum chemistry (QM) software or tool as a SCINE calculator. Use when implementing a new external QM code (e.g., ORCA, Turbomole, Gaussian, CP2K, MRCC, or any custom QM tool) as a calculator in SCINE Utils (C++) and/or Puffin (Python). Covers the full workflow: C++ class hierarchy, settings, file I/O parsers, output parsers, module registration, CMake, Python bindings, Puffin program class, Puffin job class, and config registration.

Add a new machine learning (ML) model as a calculator in the SCINE Parrot module. Use when integrating a new ML potential or interatomic potential (e.g., MACE, ANI, M3GNet, LMLP, NequIP, or any custom ML model) into scine_parrot. Covers creating the calculator class, registering in the calculator registry, adding CLI support, writing unit tests, and updating documentation.