# Use ANI potentials

**You will learn:** how to run an NNP/MM simulation using the ANI family of neural-network potentials [^smith2020] [^devereux2020] instead of AceFF.

**Prerequisites:**

- ACEMD installed with NNP support.
- A classically built system (see [Run an NNP/MM simulation](run-an-nnp-mm-simulation.md) for the setup).

ANI is one of the earliest publicly available NNP families and is still used as a benchmark. The `torchani` package downloads the weights on first use and caches them; no checkpoint file management is needed — set `nnp.name` to an ANI variant and ACEMD does the rest.

```{warning}
ANI models cannot correctly describe molecules with a total charge different from zero. For charged species, use [AceFF](obtain-aceff-models.md) instead.
```

## Setup

```{code-block} yaml
:caption: input.yaml

barostat: true
thermostat: true
thermostattemperature: 300
velocities: 300
structure: structure.prmtop
coordinates: structure.pdb
boxsize: [22.66, 25.397, 25.982]
minimize: 500
timestep: 2
run: 2ns
nnp:
  name: ANI-2x
  sel: "resname BEN"
  type: torch
```

Note that **`file` is omitted** — ANI models are auto-downloaded. The only thing that selects between variants is `name`.

## Available ANI variants

- `ANI-2x` — most general, recommended starting point.
- `ANI-1x` — older variant; H, C, N, O only.
- `ANI-1ccx` — coupled-cluster reference data; H, C, N, O only.
- `ANI-2xr`, `ANI-2dr`, `snnANI-2xr` — ANI-2x-derived variants with repulsion (`r`) / dispersion+repulsion (`dr`) corrections for a smoother potential-energy surface. These are still bonded-only (non-reactive) models trained on the ANI-2x element set. Unlike `ANI-2x`, they do not benefit from NNPOps acceleration and run on the slower pure-PyTorch path.

Model names are case-insensitive and dashes are ignored, so `ANI-2x`, `ani2x`, and `ANI2X` all select the same model.

## Run

```bash
acemd
```

The first run downloads the ANI weights; subsequent runs reuse the cached copy.

## Gotchas

- **Zero total charge only.** If your `sel` covers atoms whose total charge isn't zero, switch to AceFF.
- **`timestep: 2`.** Same stability constraint as AceFF — see [Run an NNP/MM simulation](run-an-nnp-mm-simulation.md).

## See also

- [Run an NNP/MM simulation](run-an-nnp-mm-simulation.md)
- [NNP options reference](../reference/nnp-options.md)
- [NNP and NNP/MM concepts](../explanation/nnp-and-nnp-mm.md)

[^smith2020]: J. S. Smith et al., *Sci. Data* **7**, 134 (2020). [doi:10.1038/s41597-020-0473-z](https://doi.org/10.1038/s41597-020-0473-z)

[^devereux2020]: C. Devereux et al., *J. Chem. Theory Comput.* **16**(7), 4192–4202 (2020). [doi:10.1021/acs.jctc.0c00121](https://doi.org/10.1021/acs.jctc.0c00121)