Sultan et al. review 16 sequence-based transformer models for molecular property prediction, systematically analyzing seven design decisions (database selection, chemical language, tokenization, positional encoding, model size, pre-training objectives, and fine-tuning strategy) and identifying a critical need for standardized evaluation practices.
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.
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.
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.
This paper benchmarks 24 machine and deep learning methods on activity cliff compounds (structurally similar molecules with large potency differences) across 30 macromolecular targets. Traditional ML with molecular fingerprints consistently outperforms graph neural networks and SMILES-based transformers on these challenging cases, especially in low-data regimes.
Battaglia et al. argue that combinatorial generalization requires structured representations, systematically analyze the relational inductive biases in standard deep learning architectures (MLPs, CNNs, RNNs), and present the graph network as a unifying framework that generalizes and extends prior graph neural network approaches.
Tay et al. systematically compare scaling laws across ten diverse architectures (Transformers, Switch Transformers, Performers, MLP-Mixers, and others), finding that the vanilla Transformer has the best scaling coefficient and that the best-performing architecture changes across compute regions.
This systematization paper traces the history of OCSR, comparing early rule-based systems like OSRA with modern deep learning approaches like DECIMER. It highlights the shift from image classification to image captioning and identifies critical gaps in dataset standardization and evaluation metrics.
This paper reviews three decades of OCSR development, transitioning from rule-based heuristics to early deep learning approaches. It includes a benchmark study comparing the performance of three open-source tools (OSRA, Imago, MolVec) on four diverse datasets.
This 1994 handbook chapter serves as a practical user guide for the Embedded-Atom Method (EAM). It details the theoretical derivation from density-functional theory, synthesizes related methods like the Glue Model, and provides a complete tutorial on fitting potentials, illustrated with a specific implementation for the Ni-Al-B system.
This 1993 review systematizes the Embedded-Atom Method (EAM) as a practical semi-empirical approach for metallic systems. It synthesizes theory, applications, and connections to related methods while addressing the limitations of pair potentials.
This paper established the three-domain classification system (Bacteria, Archaea, Eucarya) based on molecular evidence from ribosomal RNA sequences, arguing that the prokaryote-eukaryote dichotomy obscures the deep evolutionary divergence of Archaea from Bacteria.