Merge branch 'duartegroup:main' into autode-update

.github/dependabot.yml

@@ -0,0 +1,12 @@
+---
+version: 2
+updates:
+  # Maintain dependencies for GitHub Actions
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "monthly"
+    groups:
+      gha-dependencies:
+        patterns:
+          - '*'

.github/workflows/pre-commit.yml

@@ -4,6 +4,9 @@ on:
   push:
   pull_request:
 
+env:
+  FORCE_COLOR: 1
+
 jobs:
   pre-commit:
     env:
@@ -15,4 +18,4 @@ jobs:
         uses: actions/checkout@v4
 
       - name: Run pre-commit
-        uses: pre-commit/action@v3.0.0
+        uses: pre-commit/action@v3.0.1

.github/workflows/pytest.yml

@@ -6,25 +6,28 @@ on:
     branches: [main]
   pull_request:
 
+env:
+  FORCE_COLOR: 1
+
 jobs:
   test:
     name: GAP (${{ matrix.python-version }}, ${{ matrix.os }})
     runs-on: ${{ matrix.os }}
-    
+
     strategy:
       fail-fast: true
       matrix:
-        os: ["ubuntu-latest"]
+        os: ["ubuntu-22.04"]
         python-version: ["3.9"]
-      
+
     defaults:
       run:
         shell: bash -l {0}
-        
+
     steps:
     - uses: actions/checkout@v4
-        
-    - uses: mamba-org/setup-micromamba@v1
+
+    - uses: mamba-org/setup-micromamba@v2
       with:
         # the create command looks like this:
         # `micromamba create -n test-env python=3.9 -f environment.yml`
@@ -38,34 +41,75 @@ jobs:
       run: ./install_gap.sh
 
     - name: Test basic install
-      run: pytest --cov
+      run: pytest --cov=mlptrain -k "not test_openmm"
 
     - name: Upload coverage reports to Codecov
-      uses: codecov/codecov-action@v4
+      uses: codecov/codecov-action@v5
       with:
           flags: python-${{ matrix.python-version }}
           token: ${{ secrets.CODECOV_TOKEN }}
           slug: duartegroup/mlp-train
 
+  test-ace:
+    name: ACE (${{ matrix.python-version }}, ${{ matrix.os }})
+    runs-on: ${{ matrix.os }}
+
+    strategy:
+      fail-fast: true
+      matrix:
+        os: ["ubuntu-22.04"]
+        python-version: ["3.9"]
+
+    defaults:
+      run:
+        shell: bash -l {0}
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - uses: julia-actions/setup-julia@v2
+      with:
+        version: '1.6'
+
+    - uses: mamba-org/setup-micromamba@v2
+      with:
+        environment-file: environment_ace.yml
+        environment-name: gha-test-env
+        cache-environment: true
+        create-args: >-
+          python=${{ matrix.python-version }}
+
+    - name: ACE install
+      run: ./install_ace.sh
+
+    - name: Test ACE
+      run: pytest --cov=mlptrain -k "not test_openmm"
+
+    - name: Upload coverage reports to Codecov
+      uses: codecov/codecov-action@v5
+      with:
+          flags: python-${{ matrix.python-version }}-ace
+          token: ${{ secrets.CODECOV_TOKEN }}
+          slug: duartegroup/mlp-train
 
   test-mace:
     name: MACE (${{ matrix.python-version }}, ${{ matrix.os }})
     runs-on: ${{ matrix.os }}
-    
+
     strategy:
       fail-fast: true
       matrix:
-        os: ["ubuntu-latest"]
+        os: ["ubuntu-22.04"]
         python-version: ["3.9"]
-      
+
     defaults:
       run:
         shell: bash -l {0}
-        
+
     steps:
     - uses: actions/checkout@v4
-        
-    - uses: mamba-org/setup-micromamba@v1
+
+    - uses: mamba-org/setup-micromamba@v2
       with:
         environment-file: environment_mace.yml
         environment-name: gha-test-env
@@ -77,10 +121,10 @@ jobs:
       run: ./install_mace.sh
 
     - name: Test MACE install
-      run: pytest --cov
+      run: pytest --cov=mlptrain
 
     - name: Upload coverage reports to Codecov
-      uses: codecov/codecov-action@v4
+      uses: codecov/codecov-action@v5
       with:
           flags: python-${{ matrix.python-version }}-mace
           token: ${{ secrets.CODECOV_TOKEN }}

.pre-commit-config.yaml

@@ -8,9 +8,10 @@ repos:
       - id: no-commit-to-branch
       - id: check-executables-have-shebangs
       - id: check-shebang-scripts-are-executable
+        exclude: examples/WTMetaD_paper/r2/free_energy/wtmetad_ib/accumulated_bias/bias_after_iter_15.dat
       - id: check-added-large-files
         args: ['--maxkb=500', '--enforce-all']
-        exclude: mlptrain/sampling/tests/data.zip
+        exclude: tests/data/data.zip
       - id: check-yaml
       - id: check-toml
 

README.md

@@ -1,9 +1,9 @@
+[![DOI](https://img.shields.io/badge/doi-10.6084/m9.figshare.25816864.v1-blue.svg?style=flat&labelColor=whitesmoke&logo=data%3Aimage%2Fpng%3Bbase64%2CiVBORw0KGgoAAAANSUhEUgAAAB8AAAAfCAYAAAAfrhY5AAAJsklEQVR42qWXd1DTaRrHf%2BiB2Hdt5zhrAUKz4IKEYu9IGiGFFJJQ0gkJCAKiWFDWBRdFhCQUF3UVdeVcRQEBxUI3yY9iEnQHb3bdW1fPubnyz%2F11M7lvEHfOQee2ZOYzPyDv%2B3yf9%2Fk95YX4fx%2BltfUt08GcFEuPR4U9hDDZ%2FVngIlhb%2FSiI6InkTgLzgDcgfvtnovhH4BzoVlrbwr55QnhCtBW4QHXnFrZbPBaQoBh4%2FSYH2EnpBEtqcDMVzB93wA%2F8AFwa23XFGcc8CkT3mxz%2BfXWtq9T9IQlLIXYEuHojudb%2BCM7Hgdq8ydi%2FAHiBXyY%2BLjwFlAEnS6Jnar%2FvnQVhvdzasad0eKvWZKe8hvDB2ofLZ%2FZEcWsh%2BhyIuyO5Bxs2iZIE4nRv7NWAb0EO8AC%2FWPxjYAWuOEX2MSXZVgPxzmRL3xKz3ScGpx6p6QnOx4mDIFqO0w6Q4fEhO5IzwxlSwyD2FYHzwAW%2BAZ4fEsf74gCumykwNHskLM7taQxLYjjIyy8MUtraGhTWdkfhkFJqtvuVl%2F9l2ZquDfEyrH8B0W06nnpH3JtIyRGpH1iJ6SfxDIHjRXHJmdQjLpfHeN54gnfFx4W9QRnovx%2FN20aXZeTD2J84hn3%2BqoF2Tqr14VqTPUCIcP%2B5%2Fly4qC%2BUL3sYxSvNj1NwsVYPsWdMUfomsdkYm3Tj0nbV0N1wRKwFe1MgKACDIBdMAhPE%2FwicwNWxll8Ag40w%2BFfhibJkGHmutjYeQ8gVlaN%2BjO51nDysa9TwNUFMqaGbKdRJZFfOJSp6mkRKsv0rRIpEVWjAvyFkxNOEpwvcAVPfEe%2Bl8ojeNTx3nXLBcWRrYGxSRjDEk0VlpxYrbe1ZmaQ5xuT0u3r%2B2qe5j0J5uytiZPGsRL2Jm32AldpxPUNJ3jmmsN4x62z1cXrbedXBQf2yvIFCeZrtyicZZG2U2nrrBJzYorI2EXLrvTfCSB43s41PKEvbZDEfQby6L4JTj%2FfIwam%2B4%2BwucBu%2BDgNK05Nle1rSt9HvR%2FKPC4U6LTfvUIaip1mjIa8fPzykii23h2eanT57zQ7fsyYH5QjywwlooAUcAdOh5QumgTHx6aAO7%2FL52eaQNEShrxfhL6albEDmfhGflrsT4tps8gTHNOJbeDeBlt0WJWDHSgxs6cW6lQqyg1FpD5ZVDfhn1HYFF1y4Eiaqa18pQf3zzYMBhcanlBjYfgWNayAf%2FASOgklu8bmgD7hADrk4cRlOL7NSOewEcbqSmaivT33QuFdHXj5sdvjlN5yMDrAECmdgDWG2L8P%2BAKLs9ZLZ7dJda%2BB4Xl84t7QvnKfvpXJv9obz2KgK8dXyqISyV0sXGZ0U47hOA%2FAiigbEMECJxC9aoKp86re5O5prxOlHkcksutSQJzxZRlPZmrOKhsQBF5zEZKybUC0vVjG8PqOnhOq46qyDTDnj5gZBriWCk4DvXrudQnXQmnXblebhAC2cCB6zIbM4PYgGl0elPSgIf3iFEA21aLdHYLHUQuVkpgi02SxFdrG862Y8ymYGMvXDzUmiX8DS5vKZyZlGmsSgQqfLub5RyLNS4zfDiZc9Edzh%2FtCE%2BX8j9k%2FqWB071rcZyMImne1SLkL4GRw4UPHMV3jjwEYpPG5uW5fAEot0aTSJnsGAwHJi2nvF1Y5OIqWziVCQd5NT7t6Q8guOSpgS%2Fa1dSRn8JGGaCD3BPXDyQRG4Bqhu8XrgAp0yy8DMSvvyVXDgJcJTcr1wQ2BvFKf65jqhvmxXUuDpGBlRvV36XvGjQzLi8KAKT2lYOnmxQPGorURSV0NhyTIuIyqOmKTMhQ%2BieEsgOgpc4KBbfDM4B3SIgFljvfHF6cef7qpyLBXAiQcXvg5l3Iunp%2FWv4dH6qFziO%2BL9PbrimQ9RY6MQphEfGUpOmma7KkGzuS8sPUFnCtIYcKCaI9EXo4HlQLgGrBjbiK5EqMj2AKWt9QWcIFMtnVvQVDQV9lXJJqdPVtUQpbh6gCI2Ov1nvZts7yYdsnvRgxiWFOtNJcOMVLn1vgptVi6qrNiFOfEjHCDB3J%2BHDLqUB77YgQGwX%2Fb1eYna3hGKdlqJKIyiE4nSbV8VFgxmxR4b5mVkkeUhMgs5YTi4ja2XZ009xJRHdkfwMi%2BfocaancuO7h%2FMlcLOa0V%2FSw6Dq47CumRQAKhgbOP8t%2BMTjuxjJGhXCY6XpmDDFqWlVYbQ1aDJ5Cptdw4oLbf3Ck%2BdWkVP0LpH7s9XLPXI%2FQX8ws%2Bj2In63IcRvOOo%2BTTjiN%2BlssfRsanW%2B3REVKoavBOAPTXABW4AL7e4NygHdpAKBscmlDh9Jysp4wxbnUNna3L3xBvyE1jyrGIkUHaqQMuxhHElV6oj1picvgL1QEuS5PyZTEaivqh5vUCKJqOuIgPFGESns8kyFk7%2FDxyima3cYxi%2FYOQCj%2F%2B9Ms2Ll%2Bhn4FmKnl7JkGXQGDKDAz9rUGL1TIlBpuJr9Be2JjK6qPzyDg495UxXYF7JY1qKimw9jWjF0iV6DRIqE%2B%2FeWG0J2ofmZTk0mLYVd4GLiFCOoKR0Cg727tWq981InYynvCuKW43aXgEjofVbxIqrm0VL76zlH3gQzWP3R3Bv9oXxclrlO7VVtgBRpSP4hMFWJ8BrUSBCJXC07l40X4jWuvtc42ofNCxtlX2JH6bdeojXgTh5TxOBKEyY5wvBE%2BACh8BtOPNPkApjoxi5h%2B%2FFMQQNpWvZaMH7MKFu5Ax8HoCQdmGkJrtnOiLHwD3uS5y8%2F2xTSDrE%2F4PT1yqtt6vGe8ldMBVMEPd6KwqiYECHDlfbvzphcWP%2BJiZuL5swoWQYlS%2Br7Yu5mNUiGD2retxBi9fl6RDGn4Ti9B1oyYy%2BMP5G87D%2FCpRlvdnuy0PY6RC8BzTA40NXqckQ9TaOUDywkYsudxJzPgyDoAWn%2BB6nEFbaVxxC6UXjJiuDkW9TWq7uRBOJocky9iMfUhGpv%2FdQuVVIuGjYqACbXf8aa%2BPeYNIHZsM7l4s5gAQuUAzRUoT51hnH3EWofXf2vkD5HJJ33vwE%2FaEWp36GHr6GpMaH4AAPuqM5eabH%2FhfG9zcCz4nN6cPinuAw6IHwtvyB%2FdO1toZciBaPh25U0ducR2PI3Zl7mokyLWKkSnEDOg1x5fCsJE9EKhH7HwFNhWMGMS7%2BqxyYsbHHRUDUH4I%2FAheQY7wujJNnFUH4KdCju83riuQeHU9WEqNzjsJFuF%2FdTDAZ%2FK7%2F1WaAU%2BAWymT59pVMT4g2AxcwNa0XEBDdBDpAPvgDIH73R25teeuAF5ime2Ul0OUIiG4GpSAEJeYW9wDTf43wfwHgHLKJoPznkwAAAABJRU5ErkJggg%3D%3D)](https://doi.org/10.6084/m9.figshare.25816864.v1)
 [![pytest CI](https://github.com/duartegroup/mlp-train/actions/workflows/pytest.yml/badge.svg?event=push)](https://github.com/duartegroup/mlp-train/actions/workflows/pytest.yml)
 [![codecov](https://codecov.io/gh/duartegroup/mlp-train/branch/main/graph/badge.svg)](https://codecov.io/gh/duartegroup/mlp-train)
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit)](https://github.com/pre-commit/pre-commit)
 [![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
 [![License](https://img.shields.io/badge/License-MIT%202.0-blue.svg)](https://opensource.org/licenses/mit)
-[![GitHub issues](https://img.shields.io/github/issues/duartegroup/mlp-train.svg)](https://github.com/duartegroup/mlp-train/issues)
 
 # mlp-train
 General machine learning potentials (MLP) training for molecular systems in gas phase and solution
@@ -16,7 +16,7 @@ Available models:
 
 ## Install
 
-Each model is installed into individual conda environment:
+Each model is installed into an individual conda environment:
 
 ```
 # Install GAP
@@ -33,14 +33,19 @@ Each model is installed into individual conda environment:
 
 - Units are: distance (Å), energy (eV), force (eV Å$`^{-1}`$), time (fs)
 
-## Using with OpenMM (Experimental!)
+## Using with OpenMM
 
 The OpenMM backend only works with MACE at the moment. The necessary dependencies are installed automatically via conda:
 
-```console
+```
 ./install_mace.sh
 ```
 
+Depending on your machine, you might need to prefix the command above with something like `CONDA_OVERRIDE_CUDA="11.2"` in two scenarios:
+
+- To ensure an environment that is compatible with your CUDA driver.
+- To force CUDA builds to be installed, even if the installation is being done from a CPU-only machine. This is typical in a situation where you are installing from a head node without GPUs but intend to run on GPUs and want to install the CUDA builds.
+
 You should now be able to run `water_openmm.py` in `./examples` or run the jupyter notebook on Google Colab [`water_openmm_colab.ipynb`](./examples/water_openmm_colab.ipynb).
 
 You can use OpenMM during active learning by passing the keyword argument `md_program="OpenMM"` to the `al_train` method.

environment.yml

@@ -13,7 +13,7 @@ dependencies:
   - cython
   - dscribe=2.0
   - matplotlib-base
-  - numpy
+  - numpy<2
   - pytest=8
   - pytest-cov=5
   - py-plumed

environment_ace.yml

@@ -13,7 +13,7 @@ dependencies:
   - cython
   - dscribe=2.0
   - matplotlib-base
-  - numpy
+  - numpy<2
   - pytest=8
   - pytest-cov=5
   - py-plumed

environment_mace.yml

@@ -21,20 +21,11 @@ dependencies:
   - scipy
   - xtb
   - scikit-learn
-  - openmm
-  - openmm-torch
+  - openmm=8.1.2
+  - openmm-torch=1.4
   - nnpops
-  # MACE dependencies
-  - pytorch=2.0
-  - torchvision
-  - torchaudio
-  - torch-ema
-  # TODO: You might also need CUDA-specific libraries,
-  # but that depends on CUDA version
-  # https://pytorch.org/get-started/locally/
-  # - pytorch-cuda=11.8
-  # - pytorch-cuda=12.1
+  - openmm-ml=1.2
+  - git
   - pip:
-    - mace-torch
-    - openmmml@git+https://github.com/openmm/openmm-ml.git@main
     - ase@git+https://gitlab.com/ase/ase.git@f2615a6e9a # For PLUMED
+    - mace-torch==0.3.6

examples/WTMetaD_paper/README.md

@@ -0,0 +1,9 @@
+#  Active learning meets metadynamics: Automated workflow for reactive machine learning potentials
+
+This folder contains codes and initial files for various computational tasks discussed in the paper "Active learning meets metadynamics: Automated workflow for reactive machine learning potentials" ([https://chemrxiv.org/engage/chemrxiv/article-details/671fe54b98c8527d9ea7647a]).
+
+The manuscript demonstrates three reactions: the SN2 reaction in implicit solvent (referred to as r1), rearrangement reaction in the gas phase (r2), and glycosylation reaction in explicit solvent (r3). Python scripts for each reaction can be found in the corresponding folders.
+
+For r1 and r2, active learning (AL) was utilised with both WTMetaD-IB and downhill sampling methods to train the potential. Input geometries (as *.xyz files) and training script are located within folders named after the training methods, such as al_downhill.
+
+In the case of r2, free energy calculations were performed using different enhanced sampling methods. All scripts can be found in the free_energy folder within the r2 directory. Within the free_energy folder, each enhanced sampling method is organised in separate folders containing Python scripts and necessary configuration files.

examples/WTMetaD_paper/r1/al_downhill/r1_ts.xyz

@@ -0,0 +1,8 @@
+6
+Coordinates from ORCA-job sn2_nebts_NEB-CI_converged
+  C   0.02394151244587     -0.02273675265530      0.05167818806821
+  F   -0.65299103371021      0.72656624059729     -1.73488992550113
+  Cl  0.68562794924814     -0.78844305036752      1.89308430540763
+  H   0.99880860408280      0.16036474652930     -0.38536247269303
+  H   -0.52740777250600      0.82166542425637      0.44671920342826
+  H   -0.52797925956060     -0.89741660836014     -0.27122929870995

examples/WTMetaD_paper/r1/al_downhill/training.py

@@ -0,0 +1,31 @@
+import mlptrain as mlt
+
+mlt.Config.n_cores = 30
+mlt.Config.orca_keywords = ['PBE0', 'def2-SVP', 'EnGrad', 'CPCM(Water)']
+
+if __name__ == '__main__':
+    # Initialise the system
+    system = mlt.System(mlt.Molecule('r1_ts.xyz', charge=-1, mult=1), box=None)
+
+    # Define CV and attach an upper wall
+    avg_r = mlt.PlumedAverageCV(name='avg_r', atom_groups=((0, 1), (0, 2)))
+    avg_r.attach_upper_wall(location=2.5, kappa=1000)
+
+    # Define CVs for extra information
+    r_f = mlt.PlumedAverageCV(name='r_f', atom_groups=(0, 1))
+    r_cl = mlt.PlumedAverageCV(name='r_cl', atom_groups=(0, 2))
+
+    # Initialise PlumedBias
+    bias = mlt.PlumedBias(cvs=(avg_r, r_f, r_cl))
+
+    # Define the potential and train using Downhill AL (fix_init_config=True)
+    ace = mlt.potentials.ACE('r1_downhill', system=system)
+    ace.al_train(
+        method_name='orca',
+        temp=500,
+        n_configs_iter=5,
+        max_active_iters=50,
+        min_active_iters=20,
+        fix_init_config=True,
+        bias=bias,
+    )

examples/WTMetaD_paper/r1/al_wtmetad/ch3cl_f.xyz

@@ -0,0 +1,8 @@
+6
+
+C          0.11150        0.23091        0.58288
+F         -0.88850        1.32101       -2.02704
+Cl         0.64512       -0.39439        2.08233
+H          1.02099        0.50449       -0.09172
+H         -0.45901        1.13911        0.74042
+H         -0.45901       -0.53348        0.04182

examples/WTMetaD_paper/r1/al_wtmetad/training.py

@@ -0,0 +1,39 @@
+import mlptrain as mlt
+
+mlt.Config.n_cores = 20
+mlt.Config.orca_keywords = ['PBE0', 'def2-SVP', 'EnGrad', 'CPCM(Water)']
+
+if __name__ == '__main__':
+    system = mlt.System(
+        mlt.Molecule('ch3cl_f.xyz', charge=-1, mult=1), box=None
+    )
+
+    # Define CV and attach an upper wall
+    avg_r = mlt.PlumedAverageCV(name='avg_r', atom_groups=((0, 1), (0, 2)))
+    avg_r.attach_upper_wall(location=2.5, kappa=1000)
+
+    # Define CVs for extra information
+    r_f = mlt.PlumedAverageCV(name='r_f', atom_groups=(0, 1))
+    r_cl = mlt.PlumedAverageCV(name='r_cl', atom_groups=(0, 2))
+
+    # Define CV for WTMetaD AL (r_cl - r_f)
+    diff_r = mlt.PlumedDifferenceCV(
+        name='diff_r', atom_groups=((0, 2), (0, 1))
+    )
+
+    # Initialise PlumedBias for WTMetaD AL
+    bias = mlt.PlumedBias(cvs=(avg_r, r_f, r_cl, diff_r))
+    bias.initialise_for_metad_al(width=0.05, cvs=diff_r, biasfactor=100)
+
+    # Define the potential and train using WTMetaD AL (inherit_metad_bias=True)
+    ace = mlt.potentials.ACE('r1_wtmetad', system=system)
+    ace.al_train(
+        method_name='orca',
+        temp=300,
+        n_init_configs=5,
+        n_configs_iter=5,
+        max_active_iters=50,
+        min_active_iters=30,
+        inherit_metad_bias=True,
+        bias=bias,
+    )

examples/WTMetaD_paper/r2/al_downhill/al_downhill.py

@@ -0,0 +1,35 @@
+import autode as ade
+import mlptrain as mlt
+
+# ORCA PATH (change accordingly)
+ade.Config.ORCA.path = '/usr/local/orca_5_0_3/orca'
+
+mlt.Config.n_cores = 10
+mlt.Config.orca_keywords = ['PBE0', 'D3BJ', 'def2-SVP', 'EnGrad']
+
+if __name__ == '__main__':
+    system = mlt.System(mlt.Molecule('ts_r2.xyz', charge=0, mult=1), box=None)
+
+    # Define CVs for extra information
+    avg_r = mlt.PlumedAverageCV(name='avg_r', atom_groups=((14, 11), (14, 10)))
+    r_1 = mlt.PlumedAverageCV(name='r_1', atom_groups=(14, 11))
+    r_2 = mlt.PlumedAverageCV(name='r_2', atom_groups=(14, 10))
+    diff_r = mlt.PlumedDifferenceCV(
+        name='diff_r', atom_groups=((14, 11), (14, 10))
+    )
+
+    # Initialise PlumedBias
+    bias = mlt.PlumedBias(cvs=(avg_r, r_1, r_2, diff_r))
+
+    # Define the potential and train using Downhill AL (fix_init_config=True)
+    ace = mlt.potentials.ACE('r2_downhill', system=system)
+    ace.al_train(
+        method_name='orca',
+        temp=500,
+        n_init_configs=10,
+        n_configs_iter=10,
+        max_active_iters=50,
+        min_active_iters=20,
+        fix_init_config=True,
+        bias=bias,
+    )