The Grammar VAE replaces character-level decoding with context-free grammar production rules, using a stack-based masking mechanism to guarantee that all generated SMILES strings are syntactically valid. Applied to molecular optimization and symbolic regression, it learns smoother latent spaces and finds better molecules than character-level baselines.
LatentGAN decouples molecular generation from SMILES syntax by training a Wasserstein GAN on latent vectors from a pretrained heteroencoder, enabling de novo design of drug-like and target-biased compounds.
LlaSMol fine-tunes Mistral, Llama 2, and other open-source LLMs on SMolInstruct, a 3.3M-sample instruction tuning dataset covering 14 chemistry tasks. The Mistral-based model outperforms GPT-4 and Claude 3 Opus across all tasks.
Ertl et al. train a character-level LSTM on 509K bioactive ChEMBL SMILES and generate one million novel, diverse molecules whose physicochemical properties, substructure features, and predicted bioactivity closely match the training distribution.
Introduces a memory unit that modifies the RL reward function to penalize previously explored chemical scaffolds, substantially increasing the diversity of generated molecules while maintaining relevance to known active ligands.
Proposes MolecularRNN, a graph recurrent model that generates molecular graphs atom-by-atom with 100% validity via valency-based rejection sampling, then shifts property distributions using policy gradient reinforcement learning.
MolFM pre-trains a multimodal encoder that fuses 2D molecular graphs, biomedical text, and knowledge graph entities through fine-grained cross-modal attention, achieving strong gains on cross-modal retrieval, molecule captioning, text-based generation, and property prediction.
MoMu pre-trains dual graph and text encoders on 15K molecule graph-text pairs using contrastive learning, enabling cross-modal retrieval, molecule captioning, zero-shot text-to-graph generation, and improved molecular property prediction.
This 2016 paper first proposed treating organic reaction prediction as a neural machine translation problem, using a GRU-based sequence-to-sequence model with attention to translate reactant SMILES strings into product SMILES strings.
Proposes ORGAN, a framework that extends SeqGAN with domain-specific reward functions via reinforcement learning, enabling tunable generation of molecules optimized for druglikeness, solubility, and synthesizability while maintaining sample diversity.
PharmaGPT is a suite of domain-specific LLMs (13B and 70B parameters) built on LLaMA with continued pretraining on biopharmaceutical and chemical data, achieving strong results on NAPLEX and Chinese pharmacist exams.
PharMolixFM proposes a unified framework for all-atom foundation models using three multi-modal generative approaches (diffusion, flow matching, BFN) and demonstrates competitive docking accuracy with fast inference.