From d68e471b0a0738cde9b41047dcb99f84d7cc091d Mon Sep 17 00:00:00 2001 From: Finlay Clark Date: Thu, 9 Jul 2026 14:26:33 +0100 Subject: [PATCH 1/4] Add citation.cff and cite preprint in README and docs --- CITATION.cff | 119 +++++++++++++++++++++++++++++++++++++++++++++++++ README.md | 8 ++++ docs/citing.md | 28 ++++++++++++ mkdocs.yml | 1 + 4 files changed, 156 insertions(+) create mode 100644 CITATION.cff create mode 100644 docs/citing.md diff --git a/CITATION.cff b/CITATION.cff new file mode 100644 index 0000000..a5650a9 --- /dev/null +++ b/CITATION.cff @@ -0,0 +1,119 @@ +cff-version: 1.2.0 +title: presto +message: >- + If you use presto in your work, please cite the article + below. +type: software +authors: + - given-names: Finlay + family-names: Clark + orcid: 'https://orcid.org/0000-0003-0474-5475' + - given-names: Thomas + family-names: Pope + orcid: 'https://orcid.org/0000-0001-7552-9812' + - given-names: Sarah + family-names: Maier + orcid: 'https://orcid.org/0000-0002-3817-1476' + - given-names: Simon + family-names: Boothroyd + orcid: 'https://orcid.org/0000-0002-3456-1872' + - given-names: Joshua T. + family-names: Horton + orcid: 'https://orcid.org/0000-0001-8694-7200' + - given-names: Kevin + family-names: Ryczko + orcid: 'https://orcid.org/0000-0001-6933-3856' + - given-names: Andrea + family-names: Bortolato + orcid: 'https://orcid.org/0000-0002-1631-6363' + - given-names: Daniel J. + family-names: Cole + orcid: 'https://orcid.org/0000-0003-2933-0719' +identifiers: + - type: doi + value: 10.26434/chemrxiv.15004169/v2 + description: ChemRxiv Pre-Print +repository-code: 'https://github.com/cole-group/presto' +url: 'https://cole-group.github.io/presto/' +abstract: >- + Molecular mechanics force fields enable the thorough + sampling required for applications such as alchemical + binding free energy calculations for computer-aided drug + design. However, parameters from transferable molecular + mechanics force fields can be unreliable, and training + accurate molecule-specific parameters against quantum + mechanical (QM) reference data is slow. Here, we present + presto (https://github.com/cole-group/presto), a Python + package for fast training of bespoke SMIRKS-Native Open + Force Field (SMIRNOFF) format force fields. presto + generates training data using high-temperature molecular + dynamics with well-tempered metadynamics. It iteratively + fits all valence parameters to energies and forces from + transferable machine learning potentials (MLPs). By + leveraging fast MLP evaluations and training on the GPU + using PyTorch (via the packages smee and descent), the + fully-automated workflow completes in around 15 minutes + for a 50-atom molecule on a single GPU. presto reduces + torsion scan errors by a factor of three relative to Open + Force Field Sage 2.3.0 on 400 molecules from TorsionNet500. + It also achieves torsion scan performance comparable to + direct QM fitting on a benchmark dataset of fragmented + drug-like molecules, and relative conformer energies of + 510 molecules from the set of Folmsbee and Hutchison are + significantly improved compared to both Sage and espaloma. + presto allows simultaneous fitting of congeneric series + with partially shared parameters. It produces comparable + relative binding free energy performance to OpenFF 1.3.1 + (Parsley) on systems where Parsley already performs well, + and may improve performance in cases where initial + parameters are particularly poor. +keywords: + - force field + - free energy + - molecular mechanics + - machine learning potential + - openff + - smirnoff + - smee + - descent +license: MIT + +preferred-citation: + type: article + title: >- + Fast Training of Bespoke SMIRNOFF-format Molecular + Mechanics Force Fields Using Machine Learning Potentials + authors: + - given-names: Finlay + family-names: Clark + orcid: 'https://orcid.org/0000-0003-0474-5475' + - given-names: Thomas + family-names: Pope + orcid: 'https://orcid.org/0000-0001-7552-9812' + - given-names: Sarah + family-names: Maier + orcid: 'https://orcid.org/0000-0002-3817-1476' + - given-names: Simon + family-names: Boothroyd + orcid: 'https://orcid.org/0000-0002-3456-1872' + - given-names: Joshua T. + family-names: Horton + orcid: 'https://orcid.org/0000-0001-8694-7200' + - given-names: Kevin + family-names: Ryczko + orcid: 'https://orcid.org/0000-0001-6933-3856' + - given-names: Andrea + family-names: Bortolato + orcid: 'https://orcid.org/0000-0002-1631-6363' + - given-names: Daniel J. + family-names: Cole + orcid: 'https://orcid.org/0000-0003-2933-0719' + identifiers: + - type: doi + value: 10.26434/chemrxiv.15004169/v2 + description: ChemRxiv Pre-Print + doi: "10.26434/chemrxiv.15004169/v2" + journal: "ChemRxiv" + year: 2026 + publisher: + name: ChemRxiv diff --git a/README.md b/README.md index 0c17f81..49edea9 100644 --- a/README.md +++ b/README.md @@ -70,6 +70,14 @@ presto train --param-settings.molecule-input-type sdf --param-settings.molecules For more details on the theory and implementation, please see the [documentation](https://cole-group.github.io/presto/latest/). +## Citation + +If you use `presto` in your work, please cite: + +> Clark, F.; Pope, T.; Maier, S.; Boothroyd, S.; Horton, J. T.; Ryczko, K.; Bortolato, A.; Cole, D. J. *Fast Training of Bespoke SMIRNOFF-format Molecular Mechanics Force Fields Using Machine Learning Potentials.* ChemRxiv **2026**. [doi:10.26434/chemrxiv.15004169/v2](https://doi.org/10.26434/chemrxiv.15004169/v2) + +A `CITATION.cff` file is provided in the repository, and GitHub will generate formatted citations (including BibTeX) from the *Cite this repository* link on the project page. + ## Copyright Copyright (c) 2025-2026, Finlay Clark, Newcastle University, UK diff --git a/docs/citing.md b/docs/citing.md new file mode 100644 index 0000000..40699e9 --- /dev/null +++ b/docs/citing.md @@ -0,0 +1,28 @@ +# Citing presto + +If you use `presto` in your work, please cite the following article: + +> Clark, F.; Pope, T.; Maier, S.; Boothroyd, S.; Horton, J. T.; Ryczko, K.; Bortolato, A.; Cole, D. J. +> *Fast Training of Bespoke SMIRNOFF-format Molecular Mechanics Force Fields Using Machine Learning Potentials.* +> ChemRxiv **2026**. [doi:10.26434/chemrxiv.15004169/v2](https://doi.org/10.26434/chemrxiv.15004169/v2) + +## BibTeX + +```bibtex +@article{clark2026presto, + title = {Fast Training of Bespoke {SMIRNOFF}-format Molecular Mechanics Force Fields Using Machine Learning Potentials}, + author = {Clark, Finlay and Pope, Thomas and Maier, Sarah and Boothroyd, Simon and Horton, Joshua T. and Ryczko, Kevin and Bortolato, Andrea and Cole, Daniel J.}, + journal = {ChemRxiv}, + year = {2026}, + doi = {10.26434/chemrxiv.15004169/v2}, + url = {https://doi.org/10.26434/chemrxiv.15004169/v2}, + publisher = {ChemRxiv} +} +``` + +## CITATION.cff + +The repository also ships a [`CITATION.cff`](https://github.com/cole-group/presto/blob/main/CITATION.cff) +file. On GitHub, use the **Cite this repository** button on the +[project page](https://github.com/cole-group/presto) to generate a formatted +citation (APA or BibTeX) automatically. diff --git a/mkdocs.yml b/mkdocs.yml index 5cf1e1b..d281848 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -56,6 +56,7 @@ nav: - Contributing: development/contributing.md - Building the docs: development/docs.md - Releasing: development/releasing.md +- Citing presto: citing.md - Changelog: changelog.md theme: From 58e968e2e04deb11d4ff9efc2e1a9931eccd440c Mon Sep 17 00:00:00 2001 From: Finlay Clark Date: Thu, 9 Jul 2026 14:31:33 +0100 Subject: [PATCH 2/4] Also point to OpenFF citations --- README.md | 2 ++ docs/citing.md | 4 ++++ 2 files changed, 6 insertions(+) diff --git a/README.md b/README.md index 49edea9..fa11e11 100644 --- a/README.md +++ b/README.md @@ -76,6 +76,8 @@ If you use `presto` in your work, please cite: > Clark, F.; Pope, T.; Maier, S.; Boothroyd, S.; Horton, J. T.; Ryczko, K.; Bortolato, A.; Cole, D. J. *Fast Training of Bespoke SMIRNOFF-format Molecular Mechanics Force Fields Using Machine Learning Potentials.* ChemRxiv **2026**. [doi:10.26434/chemrxiv.15004169/v2](https://doi.org/10.26434/chemrxiv.15004169/v2) +Because `presto` builds on the Open Force Field ecosystem, please also cite the relevant OpenFF publications listed at [openforcefield.org/science/how-to-cite](https://openforcefield.org/science/how-to-cite/). + A `CITATION.cff` file is provided in the repository, and GitHub will generate formatted citations (including BibTeX) from the *Cite this repository* link on the project page. ## Copyright diff --git a/docs/citing.md b/docs/citing.md index 40699e9..0014688 100644 --- a/docs/citing.md +++ b/docs/citing.md @@ -6,6 +6,10 @@ If you use `presto` in your work, please cite the following article: > *Fast Training of Bespoke SMIRNOFF-format Molecular Mechanics Force Fields Using Machine Learning Potentials.* > ChemRxiv **2026**. [doi:10.26434/chemrxiv.15004169/v2](https://doi.org/10.26434/chemrxiv.15004169/v2) +Because `presto` builds on the Open Force Field ecosystem, please also cite the +relevant OpenFF publications listed at +[openforcefield.org/science/how-to-cite](https://openforcefield.org/science/how-to-cite/). + ## BibTeX ```bibtex From d663a856b412a24111cdcff75e148832bedfa49f Mon Sep 17 00:00:00 2001 From: Finlay Clark Date: Thu, 9 Jul 2026 14:36:16 +0100 Subject: [PATCH 3/4] Change software author list to the contributors --- CITATION.cff | 25 +------------------------ 1 file changed, 1 insertion(+), 24 deletions(-) diff --git a/CITATION.cff b/CITATION.cff index a5650a9..0eaa3ca 100644 --- a/CITATION.cff +++ b/CITATION.cff @@ -5,30 +5,7 @@ message: >- below. type: software authors: - - given-names: Finlay - family-names: Clark - orcid: 'https://orcid.org/0000-0003-0474-5475' - - given-names: Thomas - family-names: Pope - orcid: 'https://orcid.org/0000-0001-7552-9812' - - given-names: Sarah - family-names: Maier - orcid: 'https://orcid.org/0000-0002-3817-1476' - - given-names: Simon - family-names: Boothroyd - orcid: 'https://orcid.org/0000-0002-3456-1872' - - given-names: Joshua T. - family-names: Horton - orcid: 'https://orcid.org/0000-0001-8694-7200' - - given-names: Kevin - family-names: Ryczko - orcid: 'https://orcid.org/0000-0001-6933-3856' - - given-names: Andrea - family-names: Bortolato - orcid: 'https://orcid.org/0000-0002-1631-6363' - - given-names: Daniel J. - family-names: Cole - orcid: 'https://orcid.org/0000-0003-2933-0719' + - name: The presto Contributors identifiers: - type: doi value: 10.26434/chemrxiv.15004169/v2 From 4c7aef850a776d8a6c211631f6cd96b4cea10369 Mon Sep 17 00:00:00 2001 From: Finlay Clark Date: Thu, 9 Jul 2026 14:37:36 +0100 Subject: [PATCH 4/4] Update changelog --- docs/changelog.md | 1 + 1 file changed, 1 insertion(+) diff --git a/docs/changelog.md b/docs/changelog.md index cd8fdb5..0f23f1f 100644 --- a/docs/changelog.md +++ b/docs/changelog.md @@ -4,6 +4,7 @@ ### Documentation +- Add a `CITATION.cff` file and cite the presto preprint in the README and docs, and point users to the OpenFF publications to cite, in [#76](https://github.com/cole-group/presto/pull/76). - Document installing `presto` from `conda-forge` as `presto-fit` (note this comes without the MLP dependencies, which must be installed separately) in [#70](https://github.com/cole-group/presto/pull/70). ## 0.8.1