Find research datasets worth reusing

opencc-by-4.0Oct 2024View details →

Supporting data for "Raising awareness of potential biases in medical machine learning: Experience from a Datathon"

This archive contains files from a Datathon held virtually in February 2024 to introduce clinicians and data scientists to the challenge of reviewing a clinical dataset for potential biases.

opencc-by-4.0Dec 2022View details →

Data and software: Heat flux for semi-local machine-learning potentials

This repository contains data, code, and related artefacts supporting the following publication: "Heat flux for semi-local machine-learning potentials" by Marcel F. Langer, Florian Knoop, Christian Carbogno, Matthias Scheffler, and Matthias Rupp arXiv: TBD doi: TBD   More details can be found in the main README.md file, and the README.md files in the subfolders. For any further questions, feel free to contact mail@marcel.science, @marceldotsci on Twitter, or @marcel@sigmoid.social.

opencc-by-4.0Dec 2022View details →

Data and code for "Phase transitions in inorganic halide perovskites from machine learning potentials: The impact of size, rate, and the underlying exchange-correlation functional"

This record contains databases with data from density functional theory calculations used for training a series of neuroevolution potentials (NEPs), which are also included here. Information is also included for how to access the databases and run the NEP models. Databases The <code>*.db</code> files are databases with the results from density functional theory (DFT) calculations. These are sqlite databases in ase format, see <a href="https://wiki.fysik.dtu.dk/ase/tutorials/tut06_database/database.html">here</a> for more information. The <code>demo-database-access.py</code> script illustrates the most basic access. Models The neuroevolution potential (NEP) models described in the publication can be found in the <code>nep-*.txt</code> files. They can be used in conjunction with the <a href="https://gpumd.org">GPUMD package</a>. The <a href="https://calorine.materialsmodeling.org">calorine package</a> provides a Python interface to GPUMD. Primitive structures Several primitive structures in extended xyz format can be found in the <code>*.xyz</code> files. These structures have been relaxed using the NEP models included here. The <code>demo-for-using-structures-and-models.py</code> script illustrates how to access the structures and models.

opencc-by-4.0Oct 2023View details →

Ensemble Machine Learning Prediction of Potential FAPAR: Monthly time-series 2021 and Long-Term Comparison with Actual FAPAR

General Description The dataset contains composites at 250 m spatial resolution of (1)  monthly potential FAPAR for the year 2021 from ensemble ML model predictions, (2) the model deviance for each prediction, (3) the yearly average of potential FAPAR, (4) the yearly average of actual FAPAR and (5) the yearly average of the difference between actual and potential (actual minus potential) FAPAR. The dataset is based on the <a href="https://zenodo.org/record/8392976">95th percentile of the monthly aggregated FAPAR</a> derived from <a href="http://glass.umd.edu/Overview.html">250 m 8 d GLASS V6 FAPAR</a>. Potential FAPAR was predicted by fitting an ensemble ML model using globally distributed training points (cca 3 Mio) and a set of 52 biophysical covariates including several layers related to human pressure. The code for modeling potential FAPAR is openly available at <a href="http://github.com/Open-Earth-Monitor/Global_FAPAR_250m">https://github.com/Open-Earth-Monitor/Global_FAPAR_250m</a>. The dataset can be used in many applications like land degradation modeling, land productivity mapping, and land potential mapping.  Data Details <ul> <li>Time period: January 2021 - December 2021</li> <li>Type of data: Fraction of Absorbed Photosynthetically Active Radiation (FAPAR)</li> <li>How the data was collected or derived: Derived from 250m 8 d GLASS V6 FAPAR</li> <li>Statistical methods used: Ensemble machine learning</li> <li>Limitations or exclusions in the data: The dataset does not include data for Antarctica.</li> <li>Coordinate reference system: EPSG:4326</li> <li>Bounding box (Xmin, Ymin, Xmax, Ymax): (-180.00000, -62.0008094, 179.9999424, 87.37000)</li> <li>Spatial resolution: 1/480 d.d. = 0.00208333 (250m)</li> <li>Image size: 172,800 x 71,698</li> <li>File format: Cloud Optimized Geotiff (COG) format.</li> </ul> Support If you discover a bug, artifact, or inconsistency, or if you have a question please raise a GitHub issue: <a href="https://github.com/Open-Earth-Monitor/Global_FAPAR_250m/issues">https://github.com/Open-Earth-Monitor/Global_FAPAR_250m/issues</a> Reference Hackländer, J., Parente, L., Ho, Y.-F., Hengl, T., Simoes, R., Consoli, D., Şahin, M., Tian, X., Herold, M., Jung, M., Duveiller, G., Weynants, M., Wheeler, I., (2023?) "Land potential assessment and trend-analysis using 2000–2021 FAPAR monthly time-series at 250 m spatial resolution", submitted to PeerJ, preprint available at: <a href="https://doi.org/10.21203/rs.3.rs-3415685/v1">https://doi.org/10.21203/rs.3.rs-3415685/v1</a>   Name convention To ensure consistency and ease of use across and within the projects, we follow the standard Open-Earth-Monitor file-naming convention. The convention works with 10 fields that describes important properties of the data. In this way users can search files, prepare data analysis etc, without needing to open files. The fields are: <ol> <li>generic variable name: pot.fapar = Potential Fraction of Absorbed Photosynthetically Active Radiation</li> <li>variable procedure combination: eml = ensemble machine learning</li> <li>Position in the probability distribution / variable type: m = mean</li> <li>Spatial support: 250m</li> <li>Depth reference: s = surface</li> <li>Time reference begin time: 20210101 = 2021-01-01</li> <li>Time reference end time: 20211231 = 2021-12-31</li> <li>Bounding box: go = global (without Antarctica)</li> <li>EPSG code: epsg.4326 = EPSG:4326</li> <li>Version code: v20230924 = 2023-09-24 (creation date)</li> </ol>

opencc-by-4.0Sep 2022View details →

Datasets from "Electrostatic Embedding of Machine Learning Potentials"

Data required to reproduce results in "Electrostatic Embedding of Machine Learning Potentials" <a href="https://doi.org/10.26434/chemrxiv-2022-rknwt">article</a>. See <a href="https://github.com/emedio/embedding">https://github.com/emedio/embedding</a> for details. <ul> <li>QM7_B3LYP_cc-pVTZ.tgz - outputs of single point B3LYP/cc-pVTZ calculations of structures in <a href="http://quantum-machine.org/data/qm7.mat">QM7 dataset</a> with ORCA 5. Include molecular dipolar polarizabilities.</li> <li>QM7_B3LYP_cc-pVTZ_horton.tgz - MBIS partitioning of the B3LYP/cc-pVTZ densities with <a href="https://github.com/theochem/horton">Horton 2.1.0</a>.</li> <li>mpro_xyz.tgz - coordinates of the ligand and surrounding point charges from 100 snapshots of SARS-CoV-2 Mpro complex with PF-00835231.</li> <li>mpro_*.tgz - DFT and semiempirical single point calculations with ORCA 5 for the coordinates from mpro_xyz.tgz, in vacuo and in presence of point charges.</li> <li>mlmm.mat - learned parameters and SOAP feature vectors of reference atomic environments</li> </ul>

opencc-by-4.0Nov 2021View details →

Network Theme: The potential of machine learning and AI for blood based investigations - Professor Jeremy Frey (University of Southampton)

This video is the sixth talk from our Future Blood Testing Network Plus Launch that took place on the 23/11/2021. Network Theme: The potential of machine learning and AI for blood based investigations - Professor Jeremy Frey (University of Southampton) Bio: Prof Jeremy Frey Professor of Physical Chemistry, Head of Computational Systems Chemistry, University of Southampton (UoS). He is PI of AI for Scientific Discovery Network+, and co_I on the Internet of Food Things Digital Economy Network+ and has had considerable involvement in the UK e-Science and Digital Economy programmes for many years (e.g., PI of the Digital Economy IT as a Utility Network+. He is a strong proponent of interdisciplinary research and the use of digital technology and ideas to enhance methods of scientific research & development. His own research involves activities across the physical land life sciences, from the application of novel mathematical analysis (e.g., Topological Data Analysis), laser spectroscopy and imagining techniques to chemical and biological problems, with the development of sensors and imagining systems such as the novel soft x-ray microscope. In parallel he works on the integration of these techniques with full provenance environment into laboratory systems using semantic web technologies. Further details on this event can be found at: https://futurebloodtesting.org/event/23-11-21-future-blood-testing-network-launch/ This video is an output from the Future Blood Testing Network which is funded by EPSRC under Grant Number EP/W000652/1 YouTube Link: https://youtu.be/eNORwfMy5cE

opencc-by-4.0Oct 2024View details →

Supporting data for "The Operando Nature of Isobutene in H–SSZ–13 Unraveled by Machine Learning Potentials Beyond DFT Accuracy"

Supporting data for "The Operando Nature of Isobutene in H–SSZ–13 Unraveled by Machine Learning Potentials Beyond DFT Accuracy" by M. Bocus, S. Vandenhaute and V. Van Speybroeck. This dataset contains examples of input files, submission and analysis scripts, in addition to the molecular dynamics trajectories used to obtain the results reported in the main manuscript. A more detailed description of the dataset content is provided in the README files therein.

opencc-by-4.0Jul 2021View details →

Molecular dynamics simulation of tricaproin in gas phase using machine-learning potential ANI2x

Tricaproin (Glycerol trihexanoate) is an example of a triglyceride molecule with very short alkyl tails attached to the glycerol moiety, and this deposit contains a 10 ns long simulation of tricaproin in a gas phase. The model chemistry (a.k.a. interaction potential or force field) is the machine-learning potential ANI2x implemented in python package torchANI, which has a close-to-DFT accuracy, yet low cost compared to DFT or other electronic structure theories. Molecular dynamics were run using ASE with Langevin integrator at a constant temperature of 310 K. The resulting trajectory was written every 1 ps ("traj.h5", can be viewed in ASEgui), and gathered every 10 ps in a XTC format ("traj.xtc", open in MDAnalysis, VMD, UnityMol, GROMACS tools ...).   Detailed simulation settings are in the python script.   This simulation was performed for the purpose of building a coarse grained Martini 3 model of this molecule.   ANI2x https://doi.org/10.26434/chemrxiv.11819268.v1 torchANI https://aiqm.github.io/torchani/index.html ASE https://wiki.fysik.dtu.dk/ase/tutorials/md/md.html#constant-temperature-md

opencc-by-4.0Apr 2023View details →

DIETxPOSOME - Selection of potentially useful papers from literature mining and machine learning protocols

DIETxPOSOME database concerning literature selection of potentially useful papers retrieved from PubMed search API, concerning contaminants quantification in food items of worldwide highest supply and using FoodMine code (text matching filter) and machine learning (ML) protocols. A list of 2,442 papers that potentially contained relevant information, covering the period between 2000 and 2022, was compiled from an initial number of 1,932,345 papers.

opencc-by-4.0Aug 2022View details →

Molecular simulations and machine learning potentials for graphene on liquid copper

Dataset for the paper: Gao, H. et al. Graphene at Liquid Copper Catalysts: Atomic-Scale Agreement of Experimental and First-Principles Adsorption Height. Advanced Science 9, 2204684 (2022). (DOI: 10.1002/advs.202204684)   zenodo/dataset/: Training and test sets for MTP zenodo/md/: Initial atomic models of the Gr-Cu interface, input files and resulting trajectories of MD simulations zenodo/potentials/: Trained MTP potential files

opencc-by-4.0Aug 2023View details →

Data related to the publication "Efficient molecular dynamics simulations of deep eutectic solvents with first-principles accuracy using machine learning interatomic potentials"

The training data sets, the trained machine learning models, and input scripts for the training and molecular dynamics simulations.

opencc-by-4.0Nov 2023View details →

Dataset for "Mo-Si alloys studied by atomistic computer simulations using a novel machine-learning interatomic potential: Thermodynamics and interface phenomena"

This dataset was used to fit a general purpose machine-learning interatomic potential for Mo-Si alloys based on the Atomic Cluster Expansion (ACE) formalism. It supports the paper "Mo-Si alloys studied by atomistic computer simulations using a novel machine-learning interatomic potential: Thermodynamics and interface phenomena".

opencc-by-4.0Oct 2021View details →

Dataset for: Anniés et al., "Accessing structural, electronic, transport and mesoscale properties of Li-GICs via a complete DFTB-model with machine-learned repulsion potential"

GPrep training data, GPrep jupyter notebook, .skf files. The GPrep code is available at https://doi.org/10.5281/zenodo.3697913

opencc-by-4.0Jul 2021View details →

An automated system for inspecting rock faces and detecting potential rock falls using machine learning

Rockfall is a hazard in mountainous areas threatening infrastructure and human lives. Rockfall hazards are often mitigated by manual inspections using pry bars. The inspector must access the rock face, hit the rock surface, detect, and remove the loose rocks. This method is very labor demanding, unsafe, and challenging. This research presents a method that automatize the inspection of rock blocks that are prone to rockfall events. A robot is developed to replace the manual hammer tap process and collect the sound data remotely; subsequently, the sound signal is used to identify different types of the discontinuity in rocks in controlled laboratory environment. Machine learning is used to train the method to discriminate between intact rock and rock that may be prone to fall. This methodology was successfully applied to laboratory tests on rock. Finally, the research involves the implementation of this system in field to understand the potential and limitations of the proposing system in automatizing the rock inspections. This research enables the inspectors to collect data remotely, detect loose rocks, and save data for future references.

opencc-by-4.0Jun 2024View details →

Trained Potentials for Article "Computationally Efficient Machine-Learned Model for GST Phase Change Materials via Direct and Indirect Learning"

We provide 8 files here to get started using our trained potentials: 1) *.yaml files for each trained potential. These are the outputs of the PACE training process. 2) *.yace files for each trained potential. These are read by LAMMPS to use the trained potential. They can be obtained from the *.yaml files using the command line command: "pace_yaml2yace *.yaml". 3) GST_config.data   --   a starting configuration of GST to be read by LAMMPS. This configuration contains 504 atoms at density 5.85 g/cm^3. 4) sample.inp   --   a sample LAMMPS input file using the trained potentials. This currently uses "ACE-Indir2.yace" to run the starting configuration "GST_config.data" for 10 ps at 1200 K. When run, it outputs a log file "test.log" and a dump file "test.dump". The choice of trained potential can be changed in the "pair_coeff" section.

opencc-by-4.0Sep 2024View details →

Research data for "Exploring the energy landscape of aluminas through machine learning interatomic potential"

This dataset supports the paper "Exploring the energy landscape of aluminas through machine learning interatomic potential". The paper is online here: The following folders are provided: <ul> <li>classical_potential_files: Contains all the empirical potentials used in this study.</li> </ul>   <ul> <li>crystal_structure_file: Contains structural files of aluminas with various crystal structures, which can be distinguished by their respective filenames. Configurations of alumina with partially occupied cation sites can be obtained from the references provided in the supplementary materials of our article.</li> </ul>   <ul> <li>lowest_E-config: The files named <code>poscar_{0..19}</code> represent the 20 structure files identified through our developed structural search workflow in conjunction with the final NEP of Aluminas. These structures exhibit different distributions of Al cation occupancy sites. The suffix numbers in the file names indicate that these 20 structures are arranged in ascending order based on their corresponding energy values after structural relaxation using the NEP. In other words, <code>poscar_0</code>, after structural optimization, has the lowest energy among these 20 configurations. Additionally, we have included the CIF files for the crystal structures with partial occupancies provided by the Smrcok model in this folder.</li> </ul>   <ul> <li>the_final-dataset_alumina: This folder contains all the relevant files for training the final NEP of Aluminas, including the final training dataset named <code>train.xyz</code>, the training parameter file <code>nep.in</code>, and log files. The file <code>nep.txt</code> refers to the final NEP of Aluminas. </li> </ul>   <ul> <li>various_test-datasets: This folder provides all the test datasets used for testing the final NEP of Aluminas. We have categorized them into four types based on composition: clusters, amorphous structures, crystals, and datasets with physically unallowed configurations that exhibit nearest-neighbor cation occupancy according to the Smrcok model.</li> </ul> Additionally, for ease of retrieval, we have placed the file for the final NEP of aluminas in the main directory and named it <code>nep_3335.txt</code>, where the suffix indicates that the final training dataset <code>train.xyz</code> contains 3,335 structures. This file is identical to the file named <code>nep.txt</code> located in the folder <code>the_final-dataset_alumina</code>.

opencc-by-4.0Oct 2022View details →

Supporting data for "Nuclear quantum effects on zeolite proton hopping kinetics explored with machine learning potentials and path integral molecular dynamics"

Supporting data for "<a href="https://www.nature.com/articles/s41467-023-36666-y">Nuclear quantum effects on zeolite proton hopping kinetics explored with machine learning potentials and path integral molecular dynamics</a>" by M. Bocus, R. Goeminne, A. Lamaire, M. Cools-Ceuppens, T. Verstraelen and V. Van Speybroeck, Nature Communications, 2023, 14, 1008. This dataset contains examples of input files, submission and analysis scripts to train and use a machine learning potential based on the Schnet architecture for the proton hopping reaction in the H-CHA zeolite. The complete DFT training set, obtained by unbiasing the forces printed by CP2K (with PLUMED coupling), is stored as extended xyz files in the folders DFT/A-B/training_data.xyz where A=1-3 and A<B<5. More details on the folder architecture can be found in the README.md file.