/tools
tools tagged “benchmark”
SUPERChem_eval
catalystforyou/SUPERChem_eval
SUPERChem is a multimodal reasoning benchmark designed to evaluate the chemical reasoning capabilities of large language models. It includes a dataset of 500 expert-curated problems and provides tools for evaluation and analysis of model performance in chemistry.
ichor
popelier-group/ichor
Ichor is a Python package designed to simplify data management from computational chemistry programs and support machine learning force field development. It provides interfaces for various computational chemistry software, flexible data structures for managing large datasets, and tools for benchmarking molecular dynamics simulations.
holo-bench
prescient-design/holo-bench
HoloBench is a benchmarking tool for discrete sequence optimization algorithms, specifically designed for biophysical applications. It allows users to optimize sequences using evolutionary strategies, making it relevant for protein design and optimization tasks.
EvalRetro
OptiMaL-PSE-Lab/EvalRetro
EvalRetro is a repository designed for evaluating single-step retrosynthesis algorithms. It allows users to test their own retrosynthetic predictions against benchmark datasets, facilitating the development and assessment of molecular generation models.
GPCNDTA
LiZhang30/GPCNDTA
GPCNDTA is a tool designed for predicting drug-target binding affinity using cross-attention networks enhanced with graph features and pharmacophores. It includes benchmark datasets for training and evaluation, making it suitable for drug discovery applications.
Uni-Dock-Benchmarks
dptech-corp/Uni-Dock-Benchmarks
Uni-Dock-Benchmarks is a repository that contains a curated collection of datasets and benchmarking tests for assessing the performance and accuracy of the Uni-Dock docking system. It includes prepared structures and input files for both molecular docking and virtual screening, making it a valuable resource for researchers in computational chemistry.
VenusX
ai4protein/VenusX
VenusX is a benchmark tool designed for fine-grained functional annotation of proteins, focusing on tasks such as residue-level classification and fragment-level classification. It includes a comprehensive dataset with over 878,000 samples, facilitating the evaluation of protein models and their functional understanding.
mongo-rdkit
rdkit/mongo-rdkit
Mongo-rdkit is a project that integrates RDKit, a cheminformatics toolkit, with MongoDB to facilitate the creation and manipulation of a chemically-intelligent database. It provides methods for performing high-performance searches, including similarity and substructure searches, making it useful for molecular property analysis.
syntharena
ischemist/syntharena
SynthArena is an interactive platform designed for visualizing and comparing retrosynthetic routes generated by AI models. It facilitates the evaluation of these models through standardized benchmarks and provides features for side-by-side comparison of synthetic routes.
ibenchmark
ci-lab-cz/ibenchmark
iBenchmark is a collection of datasets and performance metrics for evaluating the structural interpretation of QSAR models. It includes synthetic datasets designed for regression and classification tasks, focusing on the contributions of atoms in molecular structures.
laplaciannb
rdkit/laplaciannb
LaplacianNB is a Python module for a Laplacian-modified Naive Bayes classifier optimized for binary/boolean molecular data. It integrates with RDKit for molecular fingerprint conversion and includes features for performance benchmarking and large-scale processing of molecular datasets.
LAMBench
deepmodeling/LAMBench
LAMBench provides a comprehensive suite of benchmarks to evaluate the performance of machine learning interatomic potentials across various atomic systems. It aims to facilitate the understanding of model generalizability and performance in real-world applications.
AutoGraph
BorgwardtLab/AutoGraph
AutoGraph is a scalable autoregressive model designed for generating molecular graphs by flattening them into sequences. It achieves state-of-the-art performance on various molecular benchmarks and supports both unconditional and substructure-conditioned generation.
integrator-benchmark
choderalab/integrator-benchmark
This repository provides code for evaluating numerical methods used in Langevin dynamics simulations. It systematically enumerates different integrators and measures their error in sampling distributions, contributing to the field of molecular dynamics.
dualbind
NVIDIA-Digital-Bio/dualbind
DualBind is a deep learning model designed for accurate and fast prediction of protein-ligand binding affinities. It includes a benchmark dataset, ToxBench, which provides a large-scale collection of protein-ligand complexes and their binding free energies.
ActiveLearning_BindingAffinity
meyresearch/ActiveLearning_BindingAffinity
This repository benchmarks active learning protocols for predicting ligand binding affinities using various datasets corresponding to different protein targets. It evaluates the performance of machine learning models in identifying top binders, providing valuable insights for computational drug discovery.
CASP15
Bhattacharya-Lab/CASP15
The CASP15 repository benchmarks various state-of-the-art protein structure prediction methods, including AlphaFold2 and RoseTTAFold. It provides generated protein structures and metrics for evaluating their predictive performance, making it a valuable resource for researchers in molecular biology and computational chemistry.
TopoteinWorkshop
ZW471/TopoteinWorkshop
TopoteinWorkshop is a topological deep learning extension to the ProteinWorkshop framework, designed for protein structure representation learning. It incorporates novel geometric topological neural network architectures and provides benchmarking capabilities for evaluating these models against existing ones.
lammps-testing
lammps/lammps-testing
The LAMMPS Test Suite repository contains utilities for testing the LAMMPS molecular dynamics code. It allows users to run compilation, regression, and unit tests to ensure the accuracy and reliability of molecular simulations.
HP35
moldyn/HP35
This repository contains scripts and methodologies for selecting features and performing Markov state modeling on protein folding data. It includes tools for analyzing molecular trajectories and clustering, which are essential for understanding protein dynamics.
RosettaSilentToolbox
jaumebonet/RosettaSilentToolbox
RosettaSilentToolbox is a Python library designed for the analysis and management of large populations of protein or nucleotide decoys. It is particularly useful for protein designers and developers looking to benchmark their methods against existing protocols.
BOOM
FLASK-LLNL/BOOM
BOOM is a tool designed for data-driven molecule discovery, focusing on out-of-distribution predictions of molecular properties. It includes benchmarks for evaluating various machine learning models on their ability to generalize to unseen molecular properties.
Matcha
LigandPro/Matcha
Matcha is a molecular docking tool that utilizes multi-stage flow matching to enhance the accuracy and physical validity of docking predictions. It includes features for benchmarking and supports various datasets for evaluating docking performance.
chemprop_benchmark_v2
chemprop/chemprop_benchmark_v2
Chemprop benchmarking scripts and data for v2 provide tools for evaluating the performance of molecular property prediction models. The repository includes various datasets and benchmarks related to molecular properties, facilitating research in computational chemistry and machine learning.