InstructMol: Multi-Modal Integration for Building a Versatile and
Reliable Molecular Assistant in Drug Discovery
- URL: http://arxiv.org/abs/2311.16208v1
- Date: Mon, 27 Nov 2023 16:47:51 GMT
- Title: InstructMol: Multi-Modal Integration for Building a Versatile and
Reliable Molecular Assistant in Drug Discovery
- Authors: He Cao, Zijing Liu, Xingyu Lu, Yuan Yao, Yu Li
- Abstract summary: Large Language Models (LLMs) offer promise in reshaping interactions with complex molecular data.
Our novel contribution, InstructMol, effectively aligns molecular structures with natural language via an instruction-tuning approach.
InstructMol showcases substantial performance improvements in drug discovery-related molecular tasks.
- Score: 19.870192393785043
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The rapid evolution of artificial intelligence in drug discovery encounters
challenges with generalization and extensive training, yet Large Language
Models (LLMs) offer promise in reshaping interactions with complex molecular
data. Our novel contribution, InstructMol, a multi-modal LLM, effectively
aligns molecular structures with natural language via an instruction-tuning
approach, utilizing a two-stage training strategy that adeptly combines limited
domain-specific data with molecular and textual information. InstructMol
showcases substantial performance improvements in drug discovery-related
molecular tasks, surpassing leading LLMs and significantly reducing the gap
with specialized models, thereby establishing a robust foundation for a
versatile and dependable drug discovery assistant.
Related papers
- MolX: Enhancing Large Language Models for Molecular Learning with A Multi-Modal Extension [34.586861881519134]
Large Language Models (LLMs) with their strong task-handling capabilities have shown remarkable advancements across a spectrum of fields.
This study seeks to enhance the ability of LLMs to comprehend molecules by designing and equipping them with a multi-modal external module, namely MolX.
In particular, instead of directly using a SMILES string to represent a molecule, we utilize specific encoders to extract fine-grained features from both SMILES string and 2D molecular graph representations.
arXiv Detail & Related papers (2024-06-10T20:25:18Z) - Data-Efficient Molecular Generation with Hierarchical Textual Inversion [48.816943690420224]
We introduce Hierarchical textual Inversion for Molecular generation (HI-Mol), a novel data-efficient molecular generation method.
HI-Mol is inspired by the importance of hierarchical information, e.g., both coarse- and fine-grained features, in understanding the molecule distribution.
Compared to the conventional textual inversion method in the image domain using a single-level token embedding, our multi-level token embeddings allow the model to effectively learn the underlying low-shot molecule distribution.
arXiv Detail & Related papers (2024-05-05T08:35:23Z) - Instruction Multi-Constraint Molecular Generation Using a Teacher-Student Large Language Model [50.756644656847165]
We introduce a multi-constraint molecular generation large language model, TSMMG, akin to a student.
To train TSMMG, we construct a large set of text-molecule pairs by extracting molecular knowledge from these 'teachers'
We experimentally show that TSMMG remarkably performs in generating molecules meeting complex, natural language-described property requirements.
arXiv Detail & Related papers (2024-03-20T02:15:55Z) - Bridging Text and Molecule: A Survey on Multimodal Frameworks for Molecule [16.641797535842752]
In this paper, we present the first systematic survey on multimodal frameworks for molecules research.
We begin with the development of molecular deep learning and point out the necessity to involve textual modality.
Furthermore, we delves into the utilization of large language models and prompting techniques for molecular tasks and present significant applications in drug discovery.
arXiv Detail & Related papers (2024-03-07T03:03:13Z) - MolTC: Towards Molecular Relational Modeling In Language Models [28.960416816491392]
We propose a novel framework for Molecular inTeraction prediction following Chain-of-Thought (CoT) theory termed MolTC.
Our experiments, conducted across various datasets involving over 4,000,000 molecular pairs, exhibit the superiority of our method over current GNN and LLM-based baselines.
arXiv Detail & Related papers (2024-02-06T07:51:56Z) - From molecules to scaffolds to functional groups: building context-dependent molecular representation via multi-channel learning [10.025809630976065]
This paper introduces a novel pre-training framework that learns robust and generalizable chemical knowledge.
Our approach demonstrates competitive performance across various molecular property benchmarks.
arXiv Detail & Related papers (2023-11-05T23:47:52Z) - Interactive Molecular Discovery with Natural Language [69.89287960545903]
We propose the conversational molecular design, a novel task adopting natural language for describing and editing target molecules.
To better accomplish this task, we design ChatMol, a knowledgeable and versatile generative pre-trained model, enhanced by injecting experimental property information.
arXiv Detail & Related papers (2023-06-21T02:05:48Z) - Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective [53.300288393173204]
Large Language Models (LLMs) have shown remarkable performance in various cross-modal tasks.
In this work, we propose an In-context Few-Shot Molecule Learning paradigm for molecule-caption translation.
We evaluate the effectiveness of MolReGPT on molecule-caption translation, including molecule understanding and text-based molecule generation.
arXiv Detail & Related papers (2023-06-11T08:16:25Z) - Towards Unified AI Drug Discovery with Multiple Knowledge Modalities [5.232382666884214]
We propose KEDD, a unified, end-to-end, and multimodal deep learning framework.
It optimally incorporates both structured and unstructured knowledge for vast AI drug discovery tasks.
Our framework achieves a deeper understanding of molecule entities, brings significant improvements over state-of-the-art methods.
arXiv Detail & Related papers (2023-04-17T13:15:16Z) - Implicit Geometry and Interaction Embeddings Improve Few-Shot Molecular
Property Prediction [53.06671763877109]
We develop molecular embeddings that encode complex molecular characteristics to improve the performance of few-shot molecular property prediction.
Our approach leverages large amounts of synthetic data, namely the results of molecular docking calculations.
On multiple molecular property prediction benchmarks, training from the embedding space substantially improves Multi-Task, MAML, and Prototypical Network few-shot learning performance.
arXiv Detail & Related papers (2023-02-04T01:32:40Z) - A Molecular Multimodal Foundation Model Associating Molecule Graphs with
Natural Language [63.60376252491507]
We propose a molecular multimodal foundation model which is pretrained from molecular graphs and their semantically related textual data.
We believe that our model would have a broad impact on AI-empowered fields across disciplines such as biology, chemistry, materials, environment, and medicine.
arXiv Detail & Related papers (2022-09-12T00:56:57Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.