MaCBench evaluates frontier vision language models across 1,153 chemistry and materials science tasks spanning data extraction, experimental execution, and data interpretation, uncovering fundamental limitations in spatial reasoning and cross-modal integration.
MolBERT pre-trains a BERT model on SMILES strings using masked language modeling, SMILES equivalence, and physicochemical property prediction as auxiliary tasks, achieving state-of-the-art results on virtual screening and QSAR benchmarks.
MolPMoFiT applies ULMFiT-style transfer learning to QSAR modeling, pre-training an AWD-LSTM on one million ChEMBL molecules and fine-tuning for property prediction on small datasets.
nach0 unifies natural language and SMILES-based chemical tasks in a single encoder-decoder model, achieving competitive results across molecular property prediction, reaction prediction, molecular generation, and biomedical NLP benchmarks.
This paper applies character-level CNN and LSTM encoder-decoder networks to translate chemical names between English and Chinese, comparing them against an existing rule-based tool.
Hocky and White argue that NLP models capable of generating code from natural language prompts will fundamentally alter how chemists interact with scientific software, reducing barriers to computational research and reshaping programming pedagogy.
PASITHEA adapts deep dreaming from computer vision to molecular design, directly optimizing SELFIES-encoded molecules for target chemical properties via gradient-based inversion of a trained regression network.
PrefixMol prepends learnable condition vectors to a GPT transformer for SMILES generation, enabling joint control over binding pocket targeting and chemical properties like QED, SA, and LogP.
Applies the Transformer architecture to generate drug-like molecules conditioned on protein amino acid sequences, treating target-specific de novo drug design as a sequence-to-sequence translation problem.
An extensive benchmark showing that training RNN generative models with randomized (non-canonical) SMILES strings yields more uniform, complete, and closed molecular output domains than canonical SMILES.
A critical reassessment of the PMO benchmark for de novo molecule generation, showing that adding molecular weight, LogP, and diversity filters substantially re-ranks generative models, with Augmented Hill-Climb emerging as the top method.
Overview of REINVENT 4, an open-source generative molecular design framework from AstraZeneca that unifies RNN and transformer generators within reinforcement learning, transfer learning, and curriculum learning optimization algorithms.