Molecular Property Prediction

MoleculeNet is a large scale benchmark for molecular machine learning. MoleculeNet curates multiple public datasets, establishes metrics for evaluation, and offers high quality open-source implementations of multiple previously proposed molecular featurization and learning algorithms (released as part of the DeepChem open source library). MoleculeNet benchmarks demonstrate that learnable representations are powerful tools for molecular machine learning and broadly offer the best performance.

QM9 provides quantum chemical properties (at DFT level) for a relevant, consistent, and comprehensive chemical space of small organic molecules. This database may serve the benchmarking of existing methods, development of new methods, such as hybrid quantum mechanics/machine learning, and systematic identification of structure-property relationships. Source: QM9 Dataset Image Source: https://pubs.acs.org/doi/pdf/10.1021/ci300415d

The Tox21 data set comprises 12,060 training samples and 647 test samples that represent chemical compounds. There are 801 "dense features" that represent chemical descriptors, such as molecular weight, solubility or surface area, and 272,776 "sparse features" that represent chemical substructures (ECFP10, DFS6, DFS8; stored in Matrix Market Format ). Machine learning methods can either use sparse or dense data or combine them. For each sample there are 12 binary labels that represent the outcome (active/inactive) of 12 different toxicological experiments. Note that the label matrix contains many missing values (NAs). The original data source and Tox21 challenge site is https://tripod.nih.gov/tox21/challenge/. Source: Tox21 Machine Learning Data Set Image Source: https://www.frontiersin.org/articles/10.3389/fenvs.2015.00080/full

The BBBP dataset comes from a study focused on modeling and predicting the permeability of the blood-brain barrier. The BBBP dataset contains binary labels indicating whether a compound can penetrate the blood-brain barrier (BBB) or not. Researchers use this dataset to develop and evaluate machine learning methods for predicting BBB permeability. It’s a critical task because understanding which compounds can cross the BBB is essential for drug discovery and designing therapeutics for neurological conditions. Check https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8708321/

ESOL is a water solubility prediction dataset consisting of 1128 samples.

The FreeSolv database offers a curated collection of experimental and calculated hydration-free energies for small molecules in water. It includes both experimental values obtained from prior literature and calculated values based on simulations. The goal is to provide accurate hydration-free energy data, which is essential for understanding solvation properties and interactions of molecules in aqueous environments.

QM7 dataset is a subset of the GDB-13 database. GDB-13 contains nearly 1 billion stable and synthetically accessible organic molecules. In the QM7 subset, only molecules with up to 23 atoms are included. These atoms consist of carbon ©, nitrogen (N), oxygen (O), and sulfur (S). The total number of molecules in the QM7 dataset is 7165. Each molecule is represented using the Coulomb matrix, which captures the interactions between atoms.

The BACE dataset focuses on inhibitors of human beta-secretase 1 (BACE-1). It includes both quantitative (IC50 values) and qualitative (binary labels) binding results. The dataset comprises small molecule inhibitors across a wide range of affinities, spanning three orders of magnitude (from nanomolar to micromolar IC50 values). Specifically, it provides: 154 BACE inhibitors for affinity prediction. 20 BACE inhibitors for pose prediction. 34 BACE inhibitors for free energy prediction.

The HIV dataset was introduced by the Drug Therapeutics Program (DTP) AIDS Antiviral Screen, which tested the ability to inhibit HIV replication for over 40,000 compounds. Screening results were evaluated and placed into three categories: confirmed inactive (CI), confirmed active (CA), and confirmed moderately active (CM). Check https://link.springer.com/chapter/10.1007/978-3-540-89689-0_33

Using conservation of energy -- a fundamental property of closed classical and quantum mechanical systems -- we develop an efficient gradient-domain machine learning (GDML) approach to construct accurate molecular force fields using a restricted number of samples from ab initio molecular dynamics (AIMD) trajectories. The GDML implementation is able to reproduce global potential energy surfaces of intermediate-sized molecules with an accuracy of 0.3 kcal $\text{mol}^{-1}$ for energies and 1 kcal $\text{mol}^{-1}$ $\text{\AA}^{-1}$ for atomic forces using only 1000 conformational geometries for training. We demonstrate this accuracy for AIMD trajectories of molecules, including benzene, toluene, naphthalene, ethanol, uracil, and aspirin. The challenge of constructing conservative force fields is accomplished in our work by learning in a Hilbert space of vector-valued functions that obey the law of energy conservation. The GDML approach enables quantitative molecular dynamics simulations for molecules at a fraction of cost of explicit AIMD calculations, thereby allowing the construction of efficient force fields with the accuracy and transferability of high-level ab initio methods.

The ClinTox dataset compares drugs approved by the FDA and drugs that have failed clinical trials for toxicity reasons. The dataset includes two classification tasks for 1491 drug compounds with known chemical structures: (1) clinical trial toxicity (or absence of toxicity) and (2) FDA approval status.

SIDER contains information on marketed medicines and their recorded adverse drug reactions. The information is extracted from public documents and package inserts. The available information include side effect frequency, drug and side effect classifications as well as links to further information, for example drug–target relations. Source: Side Effect Resource Image Source: http://sideeffects.embl.de/drugs/2756/

Molecule3D is a new benchmark that includes a dataset with precise ground-state geometries of approximately 4 million molecules derived from density functional theory (DFT). It also provides a set of software tools for data processing, splitting, training, and evaluation, etc.

ToxCast is an initiative by the U.S. Environmental Protection Agency (EPA) aimed at predicting the potential toxicity of various chemical compounds. It involves high-throughput screening assays that evaluate thousands of chemicals across multiple biological endpoints. These endpoints cover a wide range of effects, including cell cycle disruptions, interactions with steroid receptors, and cytotoxicity.

The Maximum Unbiased Validation (MUV) dataset is a benchmark dataset selected from PubChem BioAssay. It was created by applying a refined nearest-neighbor analysis. The MUV dataset is specifically designed for the validation of virtual screening techniques.

QM8 dataset is a collection of molecular data used for studying quantum mechanical calculations of electronic spectra and excited state energy of small molecules. The QM8 dataset consists of approximately 7,165 molecules. These molecules are a subset of the GDB-13 database, which contains nearly 1 billion stable and synthetically accessible organic molecules. The subset includes all molecules with up to 23 atoms, including 7 heavy atoms (C, N, O, and S).

Benchmark for de novo molecular design

DrivAerNet is a large-scale, high-fidelity CFD dataset of 3D industry-standard car shapes designed for data-driven aerodynamic design. It comprises 4000 high-quality 3D car meshes and their corresponding aerodynamic performance coefficients, alongside full 3D flow field information. It includes: - CFD Simulation Data: The raw dataset, including full 3D pressure, velocity fields, and wall-shear stresses, computed using 8-16 million mesh elements has a total size of $\sim$ 16TB. - Curated CFD Simulations: For ease of access and use, a streamlined version of the CFD simulation data is provided, refined to include key insights and data, reducing the size to $\sim$ 1TB. - 3D Car Meshes: A total of 4000 designs, showcasing a variety of conventional car shapes and emphasizing the impact of minor geometric modifications on aerodynamic efficiency. The 3D meshes and aerodynamic coefficients $\sim$ 84GB. - 2D slices include the car's wake in the $x$-direction and the symmetry plane in the $y$-direction $\sim$ 12GB.

PCBA dataset 11 is a collection of high-quality dose-response data, formulated as a multitask learning benchmark from 128 high-throughput screening (HTS) assays.

A benchmark for molecular machine learning where improvements in model performance can be immediately observed in the throughput of promising molecules synthesized in the lab. Photoswitches are a versatile class of molecule for medical and renewable energy applications where a molecule's efficacy is governed by its electronic transition wavelengths. Source: The Photoswitch Dataset: A Molecular Machine Learning Benchmark for the Advancement of Synthetic Chemistry

This dataset is a multi-labelled SMILES odor dataset with 138 odor descriptors. This dataset was created for replicating the paper: A principal odor map unifies diverse tasks in olfactory perception. The complete replication of the paper (dataset curation + model) can be found in the OpenPOM GitHub repository. The dataset contains 4983 molecules, each described by multiple odor labels (e.g. creamy, grassy), was made by combining the GoodScents and Leffingwell PMP 2001 datasets each containing odorant molecules and corresponding odor descriptors.

A.2.1 AN OPEN, LARGE-SCALE DATASET FOR ZERO-SHOT DRUG DISCOVERY DERIVED FROM PUBCHEM We constructed a large public dataset extracted from PubChem (Kim et al., 2019; Preuer et al., 2018), an open chemistry database, and the largest collection of readily available chemical data. We take assays ranging from 2004 to 2018-05. It initially comprises 224,290,250 records of molecule-bioassay activity, corresponding to 2,120,854 unique molecules and 21,003 unique bioassays. We find that some molecule-bioassay pairs have multiple activity records, which may not all agree. We reduce every molecule-bioassay pair to exactly one activity measurement by applying majority voting. Molecule-bioassay pairs with ties are discarded. This step yields our final bioactivity dataset, which features 223,219,241 records of molecule-bioassay activity, corresponding to 2,120,811 unique molecules and 21,002 unique bioassays ranging from AID 1 to AID 1259411. Molecules range up to CID 132472079. The dataset has 3 different splitting schemes.