SpecMER: Fast Protein Generation with K-mer Guided Speculative Decoding

• URL: http://arxiv.org/abs/2509.21689v1
• Date: Thu, 25 Sep 2025 23:26:04 GMT
• Title: SpecMER: Fast Protein Generation with K-mer Guided Speculative Decoding
• Authors: Thomas Walton, Darin Tsui, Aryan Musharaf, Amirali Aghazadeh,
• Abstract summary: SpecMER (Speculative Decoding via k-mer Guidance) is a novel framework that incorporates biological, structural, and functional priors.<n>It achieves 24-32% speedup over standard autoregressive decoding, along with higher acceptance rates and improved sequence likelihoods.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Autoregressive models have transformed protein engineering by enabling the generation of novel protein sequences beyond those found in nature. However, their sequential inference introduces significant latency, limiting their utility in high-throughput protein screening. Speculative decoding accelerates generation by employing a lightweight draft model to sample tokens, which a larger target model then verifies and refines. Yet, in protein sequence generation, draft models are typically agnostic to the structural and functional constraints of the target protein, leading to biologically implausible outputs and a shift in the likelihood distribution of generated sequences. We introduce SpecMER (Speculative Decoding via k-mer Guidance), a novel framework that incorporates biological, structural, and functional priors using k-mer motifs extracted from multiple sequence alignments. By scoring candidate sequences in parallel and selecting those most consistent with known biological patterns, SpecMER significantly improves sequence plausibility while retaining the efficiency of speculative decoding. SpecMER achieves 24-32% speedup over standard autoregressive decoding, along with higher acceptance rates and improved sequence likelihoods.

Related papers

• Self Distillation Fine-Tuning of Protein Language Models Improves Versatility in Protein Design [61.2846583160056]
  Supervised fine-tuning (SFT) is a standard approach for adapting large language models to specialized domains.<n>This is in part because high-quality annotated data are far more difficult to obtain for proteins than for natural language.<n>We present a simple and general recipe for fast SFT of PLMs, designed to improve the fidelity, reliability, and novelty of generated protein sequences.
  arXiv  Detail & Related papers  (2025-12-10T05:34:47Z)
• ProteinAE: Protein Diffusion Autoencoders for Structure Encoding [64.77182442408254]
  We introduce ProteinAE, a novel and streamlined protein diffusion autoencoder.<n>ProteinAE directly maps protein backbone coordinates from E(3) into a continuous, compact latent space.<n>We demonstrate that ProteinAE achieves state-of-the-art reconstruction quality, outperforming existing autoencoders.
  arXiv  Detail & Related papers  (2025-10-12T14:30:32Z)
• Guide your favorite protein sequence generative model [1.5914835340090132]
  We present ProteinGuide, a principled and general method for conditioning protein generative models.<n>We demonstrate the applicability of ProteinGuide by guiding two protein generative models, ProteinMPNN and ESM3, to generate amino acid and structure token sequences.<n>We also used ProteinGuide with inverse folding models and our own experimental assay to design adenine base editor sequences for high activity.
  arXiv  Detail & Related papers  (2025-05-07T21:56:50Z)
• Regulatory DNA sequence Design with Reinforcement Learning [56.20290878358356]
  We propose a generative approach that leverages reinforcement learning to fine-tune a pre-trained autoregressive model.<n>We evaluate our method on promoter design tasks in two yeast media conditions and enhancer design tasks for three human cell types.
  arXiv  Detail & Related papers  (2025-03-11T02:33:33Z)
• GENERator: A Long-Context Generative Genomic Foundation Model [66.46537421135996]
  We present GENERator, a generative genomic foundation model featuring a context length of 98k base pairs (bp) and 1.2B parameters.<n>Trained on an expansive dataset comprising 386B bp of DNA, the GENERator demonstrates state-of-the-art performance across both established and newly proposed benchmarks.<n>It also shows significant promise in sequence optimization, particularly through the prompt-responsive generation of enhancer sequences with specific activity profiles.
  arXiv  Detail & Related papers  (2025-02-11T05:39:49Z)
• 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)
• Protein Sequence and Structure Co-Design with Equivariant Translation [19.816174223173494]
  Existing approaches generate both protein sequence and structure using either autoregressive models or diffusion models. We propose a new approach capable of protein sequence and structure co-design, which iteratively translates both protein sequence and structure into the desired state. Our model consists of a trigonometry-aware encoder that reasons geometrical constraints and interactions from context features. All protein amino acids are updated in one shot in each translation step, which significantly accelerates the inference process.
  arXiv  Detail & Related papers  (2022-10-17T06:00:12Z)
• Reprogramming Pretrained Language Models for Antibody Sequence Infilling [72.13295049594585]
  Computational design of antibodies involves generating novel and diverse sequences, while maintaining structural consistency. Recent deep learning models have shown impressive results, however the limited number of known antibody sequence/structure pairs frequently leads to degraded performance. In our work we address this challenge by leveraging Model Reprogramming (MR), which repurposes pretrained models on a source language to adapt to the tasks that are in a different language and have scarce data.
  arXiv  Detail & Related papers  (2022-10-05T20:44:55Z)
• Unsupervisedly Prompting AlphaFold2 for Few-Shot Learning of Accurate Folding Landscape and Protein Structure Prediction [28.630603355510324]
  We present EvoGen, a meta generative model, to remedy the underperformance of AlphaFold2 for poor MSA targets. By prompting the model with calibrated or virtually generated homologue sequences, EvoGen helps AlphaFold2 fold accurately in low-data regime.
  arXiv  Detail & Related papers  (2022-08-20T10:23:17Z)
• Diversifying Design of Nucleic Acid Aptamers Using Unsupervised Machine Learning [54.247560894146105]
  Inverse design of short single-stranded RNA and DNA sequences (aptamers) is the task of finding sequences that satisfy a set of desired criteria. We propose to use an unsupervised machine learning model known as the Potts model to discover new, useful sequences with controllable sequence diversity.
  arXiv  Detail & Related papers  (2022-08-10T13:30:58Z)
• Generative power of a protein language model trained on multiple sequence alignments [0.5639904484784126]
  Computational models starting from large ensembles of evolutionarily related protein sequences capture a representation of protein families. Protein language models trained on multiple sequence alignments, such as MSA Transformer, are highly attractive candidates to this end. We propose and test an iterative method that directly uses the masked language modeling objective to generate sequences using MSA Transformer.
  arXiv  Detail & Related papers  (2022-04-14T16:59:05Z)
• Guided Generative Protein Design using Regularized Transformers [5.425399390255931]
  We introduce Regularized Latent Space Optimization (ReLSO), a deep transformer-based autoencoder which is trained to jointly generate sequences and predict fitness. We explicitly model the underlying sequence-function landscape of large labeled datasets and optimize within latent space using gradient-based methods.
  arXiv  Detail & Related papers  (2022-01-24T20:55:53Z)
• Fast differentiable DNA and protein sequence optimization for molecular design [0.0]
  Machine learning models that accurately predict biological fitness from sequence are becoming a powerful tool for molecular design. Here, we build on a previously proposed straight-through approximation method to optimize through discrete sequence samples. The resulting algorithm, which we call Fast SeqPropProp, achieves up to 100-fold faster convergence compared to previous versions.
  arXiv  Detail & Related papers  (2020-05-22T17:03:55Z)

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.