Molecule Captioning

Molecular description generation entails the creation of a detailed textual depiction illuminating the structure, properties, biological activity, and applications of a molecule based on its molecular descriptors. It furnishes chemists and biologists with a swift conduit to essential molecular information, thus efficiently guiding their research and experiments.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 11–20 of 25 papers

Title	Date	Tasks	Status	Hype
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations	Oct 11, 2023	Drug DiscoveryMolecule Captioning	CodeCode Available	1
From Artificially Real to Real: Leveraging Pseudo Data from Large Language Models for Low-Resource Molecule Discovery	Sep 11, 2023	DescriptiveDomain Adaptation	CodeCode Available	1
GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text	Aug 14, 2023	Drug DiscoveryImage Captioning	CodeCode Available	1
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective	Jun 11, 2023	In-Context LearningMolecule Captioning	CodeCode Available	1
Unifying Molecular and Textual Representations via Multi-task Language Modelling	Jan 29, 2023	Language ModellingMolecule Captioning	CodeCode Available	1
A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language	Sep 12, 2022	Contrastive LearningCross-Modal Retrieval	CodeCode Available	1
Graph-based Molecular Representation Learning	Jul 8, 2022	Graph Learningmolecular representation	CodeCode Available	1
Translation between Molecules and Natural Language	Apr 25, 2022	Drug DiscoveryMolecule Captioning	CodeCode Available	1
XMolCap: Advancing Molecular Captioning through Multimodal Fusion and Explainable Graph Neural Networks	May 23, 2025	Drug DiscoveryMolecule Captioning	CodeCode Available	0
Automatic Annotation Augmentation Boosts Translation between Molecules and Natural Language	Feb 10, 2025	Drug DiscoveryMolecule Captioning	CodeCode Available	0

Show:10 25 50

← PrevPage 2 of 3Next →

All datasets ChEBI-20 L+M-24

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	Mol-LLM (Mistral-Instruct-v0.2)	BLEU-2	73.2	—	Unverified
2	Mol-LLM (LLaMA2-Chat)	BLEU-2	72.7	—	Unverified
3	MolReFlect	BLEU-2	67.6	—	Unverified
4	BioT5+	BLEU-2	66.6	—	Unverified
5	BioT5	BLEU-2	63.5	—	Unverified
6	Text+Chem T5-augm-Base	BLEU-2	62.5	—	Unverified
7	MolCA, Galac1.3B	BLEU-2	62	—	Unverified
8	XMolCap	BLEU-2	62	—	Unverified
9	MolCA, Galac125M	BLEU-2	61.6	—	Unverified
10	Mol2Lang-VLM	BLEU-2	61.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Mol2Lang-VLM	BLEU-2	77.7	—	Unverified
2	XMolCap	BLEU-2	77.4	—	Unverified
3	MolT5-Large	BLEU-2	76.9	—	Unverified
4	Nach0	BLEU-2	73.81	—	Unverified
5	MolT5-Base	BLEU-2	73.8	—	Unverified
6	MolT5-Small	BLEU-2	70.9	—	Unverified