A Large Encoder-Decoder Family of Foundation Models For Chemical Language

• URL: http://arxiv.org/abs/2407.20267v1
• Date: Wed, 24 Jul 2024 20:30:39 GMT
• Title: A Large Encoder-Decoder Family of Foundation Models For Chemical Language
• Authors: Eduardo Soares, Victor Shirasuna, Emilio Vital Brazil, Renato Cerqueira, Dmitry Zubarev, Kristin Schmidt,
• Abstract summary: This paper introduces a large encoder-decoder chemical foundation models pre-trained on a curated dataset of 91 million SMILES samples sourced from PubChem. Our experiments across multiple benchmark datasets validate the capacity of the proposed model in providing state-of-the-art results for different tasks.
• Score: 1.1073864511426255
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large-scale pre-training methodologies for chemical language models represent a breakthrough in cheminformatics. These methods excel in tasks such as property prediction and molecule generation by learning contextualized representations of input tokens through self-supervised learning on large unlabeled corpora. Typically, this involves pre-training on unlabeled data followed by fine-tuning on specific tasks, reducing dependence on annotated datasets and broadening chemical language representation understanding. This paper introduces a large encoder-decoder chemical foundation models pre-trained on a curated dataset of 91 million SMILES samples sourced from PubChem, which is equivalent to 4 billion of molecular tokens. The proposed foundation model supports different complex tasks, including quantum property prediction, and offer flexibility with two main variants (289M and $8\times289M$). Our experiments across multiple benchmark datasets validate the capacity of the proposed model in providing state-of-the-art results for different tasks. We also provide a preliminary assessment of the compositionality of the embedding space as a prerequisite for the reasoning tasks. We demonstrate that the produced latent space is separable compared to the state-of-the-art with few-shot learning capabilities.

Related papers

• Pre-trained Molecular Language Models with Random Functional Group Masking [54.900360309677794]
  We propose a SMILES-based underlineem Molecular underlineem Language underlineem Model, which randomly masking SMILES subsequences corresponding to specific molecular atoms. This technique aims to compel the model to better infer molecular structures and properties, thus enhancing its predictive capabilities.
  arXiv  Detail & Related papers  (2024-11-03T01:56:15Z)
• Smirk: An Atomically Complete Tokenizer for Molecular Foundation Models [0.0]
  We systematically evaluate thirteen chemistry-specific tokenizers for their coverage of the SMILES language. We introduce two new tokenizers, i>smirk/i> and i>smirk-gpe/i>, which can represent the entirety of the OpenSMILES specification.
  arXiv  Detail & Related papers  (2024-09-19T02:36:04Z)
• ScholarChemQA: Unveiling the Power of Language Models in Chemical Research Question Answering [54.80411755871931]
  Question Answering (QA) effectively evaluates language models' reasoning and knowledge depth. Chemical QA plays a crucial role in both education and research by effectively translating complex chemical information into readily understandable format. This dataset reflects typical real-world challenges, including an imbalanced data distribution and a substantial amount of unlabeled data that can be potentially useful. We introduce a QAMatch model, specifically designed to effectively answer chemical questions by fully leveraging our collected data.
  arXiv  Detail & Related papers  (2024-07-24T01:46:55Z)
• MoleculeCLA: Rethinking Molecular Benchmark via Computational Ligand-Target Binding Analysis [18.940529282539842]
  We construct a large-scale and precise molecular representation dataset of approximately 140,000 small molecules. Our dataset offers significant physicochemical interpretability to guide model development and design. We believe this dataset will serve as a more accurate and reliable benchmark for molecular representation learning.
  arXiv  Detail & Related papers  (2024-06-13T02:50:23Z)
• Instruction Multi-Constraint Molecular Generation Using a Teacher-Student Large Language Model [49.64512917330373]
  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)
• Learning Invariant Molecular Representation in Latent Discrete Space [52.13724532622099]
  We propose a new framework for learning molecular representations that exhibit invariance and robustness against distribution shifts. Our model achieves stronger generalization against state-of-the-art baselines in the presence of various distribution shifts.
  arXiv  Detail & Related papers  (2023-10-22T04:06:44Z)
• 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)
• Tyger: Task-Type-Generic Active Learning for Molecular Property Prediction [121.97742787439546]
  How to accurately predict the properties of molecules is an essential problem in AI-driven drug discovery. To reduce annotation cost, deep Active Learning methods are developed to select only the most representative and informative data for annotating. We propose a Task-type-generic active learning framework (termed Tyger) that is able to handle different types of learning tasks in a unified manner.
  arXiv  Detail & Related papers  (2022-05-23T12:56:12Z)
• Improving VAE based molecular representations for compound property prediction [0.0]
  We propose a simple method to improve chemical property prediction performance of machine learning models. We show the relation between the performance of property prediction models and the distance between property prediction dataset and the larger unlabeled dataset.
  arXiv  Detail & Related papers  (2022-01-13T12:57:11Z)
• Do Large Scale Molecular Language Representations Capture Important Structural Information? [31.76876206167457]
  We present molecular embeddings obtained by training an efficient transformer encoder model, referred to as MoLFormer. Experiments show that the learned molecular representation performs competitively, when compared to graph-based and fingerprint-based supervised learning baselines.
  arXiv  Detail & Related papers  (2021-06-17T14:33:55Z)
• Predicting Chemical Properties using Self-Attention Multi-task Learning based on SMILES Representation [0.0]
  In this study, we explore the structural differences of the transformer-variant model and proposed a new self-attention based model. The representation learning performance of the self-attention module was evaluated in a multi-task learning environment using imbalanced chemical datasets.
  arXiv  Detail & Related papers  (2020-10-19T09:46:50Z)

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.