Molecular-Representation

Computational Chemistry
Bar chart comparing LLM, DeBERTa, GCN, and GIN performance on three OGB molecular classification benchmarks

Benchmarking LLMs for Molecular Property Prediction

Benchmarks large language models on six molecular property prediction datasets, finding that LLMs lag behind GNNs but can augment ML models when used collaboratively.

Predictive Chemistry
Bar chart comparing fixed molecular representations (RF, SVM, XGBoost) against learned representations (MolBERT, GROVER) across six property prediction benchmarks under scaffold split

Benchmarking Molecular Property Prediction at Scale

This study trains over 62,000 models to systematically evaluate molecular representations and models for property prediction, finding that traditional ML on fixed descriptors often outperforms deep learning approaches.

Computational Chemistry
Hierarchical pyramid showing ChemEval's four evaluation levels from basic knowledge QA to scientific knowledge deduction

ChemEval: Fine-Grained LLM Evaluation for Chemistry

ChemEval is a four-level, 62-task benchmark for evaluating LLMs across chemical knowledge, literature understanding, molecular reasoning, and scientific deduction, revealing that general LLMs excel at comprehension while chemistry-specific models perform better on domain tasks.

Molecular Generation
Stylized visualization of protein-ligand docking and benchmark performance bars across five drug targets

DOCKSTRING: Docking-Based Benchmarks for Drug Design

DOCKSTRING bundles an AutoDock Vina wrapper, a 260K-molecule docking dataset across 58 protein targets, and pharmaceutically relevant benchmarks for regression, virtual screening, and de novo design.

Predictive Chemistry
Scatter plot showing molecules ranked by perplexity score with color coding for task-relevant (positive delta) versus pretraining-biased (negative delta) generations

Perplexity for Molecule Ranking and CLM Bias Detection

This study applies perplexity, a model-intrinsic metric from NLP, to rank de novo molecular designs generated by SMILES-based chemical language models and introduces a delta score to detect pretraining bias in transfer-learned CLMs.

Molecular Generation
Sample efficiency curves showing different molecular optimization algorithm families converging at different rates under a fixed oracle budget

PMO: Benchmarking Sample-Efficient Molecular Design

A large-scale benchmark of 25 molecular optimization methods on 23 oracles under constrained oracle budgets, showing that sample efficiency is a critical and often neglected dimension of evaluation.

Molecular Representations
Taxonomy of molecular representation learning foundation models organized by input modality

Review of Molecular Representation Learning Models

A comprehensive survey classifying molecular representation learning foundation models by input modality (sequence, graph, 3D, image, multimodal) and analyzing four pretraining paradigms for drug discovery tasks.

Molecular Generation
Visualization of STONED algorithm generating a local chemical subspace around a seed molecule through SELFIES string mutations, with a chemical path shown between two endpoints

STONED: Training-Free Molecular Design with SELFIES

STONED introduces simple string manipulation algorithms on SELFIES for molecular design, achieving competitive results with deep generative models while requiring no training data or GPU resources.

Predictive Chemistry
QSPR surface roughness comparison across molecular representations, showing smooth fingerprint surfaces versus rougher pretrained model surfaces

ROGI-XD: Roughness of Pretrained Molecular Representations

This paper introduces ROGI-XD, a reformulation of the ROuGhness Index that enables fair comparison of QSPR surface roughness across molecular representations of different dimensionalities. Evaluating VAE, GIN, ChemBERTa, and ChemGPT representations, the authors show that pretrained chemical models do not produce smoother structure-property landscapes than simple molecular fingerprints or descriptors.

Molecular Generation
Taxonomy diagram showing the three axes of MolGenSurvey: molecular representations (1D string, 2D graph, 3D geometry), generative methods (deep generative models and combinatorial optimization), and eight generation tasks (1D/2D and 3D)

MolGenSurvey: Systematic Survey of ML for Molecule Design

MolGenSurvey systematically reviews ML models for molecule design, organizing the field by molecular representation (1D/2D/3D), generative method (deep generative models vs. combinatorial optimization), and task type (8 distinct generation/optimization tasks). It catalogs over 100 methods, unifies task definitions via input/output/goal taxonomy, and identifies key challenges including out-of-distribution generation, oracle costs, and lack of unified benchmarks.

Molecular Representations
BARTSmiles ablation study summary showing impact of pre-training strategies on downstream task performance

BARTSmiles: BART Pre-Training for Molecular SMILES

BARTSmiles pre-trains a BART-large model on 1.7 billion SMILES strings from ZINC20 and achieves the best reported results on 11 classification, regression, and generation benchmarks.

Predictive Chemistry
Three distribution plots showing RNN language models closely matching training distributions across peaked, multi-modal, and large-scale molecular generation tasks while graph models fail

Language Models Learn Complex Molecular Distributions

This study benchmarks RNN-based chemical language models against graph generative models on three challenging tasks: high penalized LogP distributions, multi-modal molecular distributions, and large-molecule generation from PubChem. The LSTM language models consistently outperform JTVAE and CGVAE.