Skip to content

README.md

Latest commit

 

History

History
153 lines (112 loc) · 3.12 KB

README.md

File metadata and controls

153 lines (112 loc) · 3.12 KB

MAchine-learning Potential for Landscape Exploration (MAPLE)

MAPLE Concept

MAPLE is a machine-learning-potential-native computational chemistry toolkit for geometry optimization, transition-state search, reaction-path analysis, molecular dynamics, and related post-processing workflows.

Core Capabilities

Category Methods
Optimization L-BFGS, RFO, SD, CG, SD-CG, GDIIS
Transition State NEB, CI-NEB, P-RFO, Dimer, String/GSM, AutoNEB
Reaction Path IRC with GS, LQA, HPC, EulerPC
Dynamics NVE, NVT, NPT
Analysis Frequency, PES Scan, Single Point
ML Potentials ANI, AIMNet2, MACE, MACEPol, UMA
Extras D4 dispersion, GBSA solvation, PBC, restart files, DCD output

Installation

Requirements

  • Python >= 3.9
  • PyTorch >= 2.0
  • CUDA-capable GPU recommended for production workloads

Install MAPLE

git clone https://github.com/ClickFF/MAPLE.git
cd MAPLE
pip install -e .

Install Dependencies

# Core scientific stack
pip install numpy scipy matplotlib ase

# PyTorch example: CUDA 11.8
pip install torch --index-url https://download.pytorch.org/whl/cu118

# CPU-only PyTorch
pip install torch --index-url https://download.pytorch.org/whl/cpu

# ML potentials
pip install fairchem-core

Quick Start

Command Line

maple input.inp
maple input.inp output.out
maple --version
maple md nve

Minimal Example

#model=uma(size=uma-s-1p2)
#opt(method=lbfgs)
#device=gpu0

C   -0.748   0.014   0.025
C    0.748  -0.014  -0.025
O    1.170   0.016   1.330
H   -1.155  -0.888  -0.460
H   -1.096   0.888  -0.530
H   -1.155   0.049   1.065
H    1.148  -0.912   0.457
H    1.096   0.869   0.513
H    0.802   0.842   1.742

Input Overview

Header Keywords

#model=<model>
#<task>(options)
#device=<device>

Common Tasks

Header Description
#opt(method=lbfgs) Geometry optimization
#sp Single-point energy
#ts(method=neb) Transition-state search
#freq Frequency analysis
#irc(method=gs) Intrinsic reaction coordinate
#scan(method=lbfgs) PES scan
#md(ensemble=nvt,mdp=nvt.mdp) Molecular dynamics

Coordinates

Inline coordinates:

#model=uma
#sp

C   0.000   0.000   0.000
H   1.089   0.000   0.000
...

External coordinates:

XYZ /path/to/molecule.xyz

Multi-structure jobs such as NEB accept multiple XYZ records.

Documentation

Citation

https://github.com/ClickFF/MAPLE

Contributing

  1. Fork the repository.
  2. Create a feature branch.
  3. Make changes with clear commits.
  4. Open a pull request.

Acknowledgments

Version: 0.1.2
Status: Active Development
Updated: April 2026