HELM-BERT: A Transformer for Medium-sized Peptide Property Prediction

• URL: http://arxiv.org/abs/2512.23175v1
• Date: Mon, 29 Dec 2025 03:29:54 GMT
• Title: HELM-BERT: A Transformer for Medium-sized Peptide Property Prediction
• Authors: Seungeon Lee, Takuto Koyama, Itsuki Maeda, Shigeyuki Matsumoto, Yasushi Okuno,
• Abstract summary: We present HELM-BERT, the first encoder-based peptide language model trained on HELM notation.<n>The model is pre-trained on a curated corpus of 39,079 chemically diverse peptides spanning linear and cyclic structures.<n>It significantly outperforms state-of-the-art SMILES-based language models in downstream tasks, including cyclic peptide membrane permeability prediction and peptide-protein interaction prediction.
• Score: 0.5510752448348083
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Therapeutic peptides have emerged as a pivotal modality in modern drug discovery, occupying a chemically and topologically rich space. While accurate prediction of their physicochemical properties is essential for accelerating peptide development, existing molecular language models rely on representations that fail to capture this complexity. Atom-level SMILES notation generates long token sequences and obscures cyclic topology, whereas amino-acid-level representations cannot encode the diverse chemical modifications central to modern peptide design. To bridge this representational gap, the Hierarchical Editing Language for Macromolecules (HELM) offers a unified framework enabling precise description of both monomer composition and connectivity, making it a promising foundation for peptide language modeling. Here, we propose HELM-BERT, the first encoder-based peptide language model trained on HELM notation. Based on DeBERTa, HELM-BERT is specifically designed to capture hierarchical dependencies within HELM sequences. The model is pre-trained on a curated corpus of 39,079 chemically diverse peptides spanning linear and cyclic structures. HELM-BERT significantly outperforms state-of-the-art SMILES-based language models in downstream tasks, including cyclic peptide membrane permeability prediction and peptide-protein interaction prediction. These results demonstrate that HELM's explicit monomer- and topology-aware representations offer substantial data-efficiency advantages for modeling therapeutic peptides, bridging a long-standing gap between small-molecule and protein language models.

Related papers

• Morphology-Specific Peptide Discovery via Masked Conditional Generative Modeling [0.0]
  PepMorph is an end-to-end peptide discovery pipeline.<n>It generates sequences prone to aggregate but self-assemble into a specified fibrillar or spherical morphology.
  arXiv  Detail & Related papers  (2025-09-02T07:58:12Z)
• Molecular Fingerprints Are Strong Models for Peptide Function Prediction [0.0]
  Long-range molecular interactions are often assumed to require modeling complex graph neural networks and pretrained transformers.<n>We investigate if simple, domain-specific molecular fingerprints can capture peptide function without these assumptions.<n>Our results challenge the presumed necessity of long-range interaction modeling and highlight molecular fingerprints as efficient, interpretable, and computationally lightweight alternatives for peptide prediction.
  arXiv  Detail & Related papers  (2025-01-29T10:05:27Z)
• MeToken: Uniform Micro-environment Token Boosts Post-Translational Modification Prediction [65.33218256339151]
  Post-translational modifications (PTMs) profoundly expand the complexity and functionality of the proteome. Existing computational approaches predominantly focus on protein sequences to predict PTM sites, driven by the recognition of sequence-dependent motifs. We introduce the MeToken model, which tokenizes the micro-environment of each acid, integrating both sequence and structural information into unified discrete tokens.
  arXiv  Detail & Related papers  (2024-11-04T07:14:28Z)
• 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)
• Structure Language Models for Protein Conformation Generation [66.42864253026053]
  Traditional physics-based simulation methods often struggle with sampling equilibrium conformations.<n>Deep generative models have shown promise in generating protein conformations as a more efficient alternative.<n>We introduce Structure Language Modeling as a novel framework for efficient protein conformation generation.
  arXiv  Detail & Related papers  (2024-10-24T03:38:51Z)
• DPLM-2: A Multimodal Diffusion Protein Language Model [75.98083311705182]
  We introduce DPLM-2, a multimodal protein foundation model that extends discrete diffusion protein language model (DPLM) to accommodate both sequences and structures. DPLM-2 learns the joint distribution of sequence and structure, as well as their marginals and conditionals. Empirical evaluation shows that DPLM-2 can simultaneously generate highly compatible amino acid sequences and their corresponding 3D structures.
  arXiv  Detail & Related papers  (2024-10-17T17:20:24Z)
• Multi-Peptide: Multimodality Leveraged Language-Graph Learning of Peptide Properties [5.812284760539713]
  Multi-Peptide is an innovative approach that combines transformer-based language models with Graph Neural Networks (GNNs) to predict peptide properties. Evaluations on hemolysis and nonfouling datasets demonstrate Multi-Peptide's robustness, achieving state-of-the-art 86.185% accuracy in hemolysis prediction. This study highlights the potential of multimodal learning in bioinformatics, paving the way for accurate and reliable predictions in peptide-based research and applications.
  arXiv  Detail & Related papers  (2024-07-02T20:13:47Z)
• Diffusion Language Models Are Versatile Protein Learners [75.98083311705182]
  This paper introduces diffusion protein language model (DPLM), a versatile protein language model that demonstrates strong generative and predictive capabilities for protein sequences. We first pre-train scalable DPLMs from evolutionary-scale protein sequences within a generative self-supervised discrete diffusion probabilistic framework. After pre-training, DPLM exhibits the ability to generate structurally plausible, novel, and diverse protein sequences for unconditional generation.
  arXiv  Detail & Related papers  (2024-02-28T18:57:56Z)
• Efficient Prediction of Peptide Self-assembly through Sequential and Graphical Encoding [57.89530563948755]
  This work provides a benchmark analysis of peptide encoding with advanced deep learning models. It serves as a guide for a wide range of peptide-related predictions such as isoelectric points, hydration free energy, etc.
  arXiv  Detail & Related papers  (2023-07-17T00:43:33Z)
• 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)

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.