Accelerating inference in genomic and proteomic foundation models via speculative decoding
Clicks: 7
ID: 323130
2026
Article Quality & Performance Metrics
Overall Quality
Not rated
Combines reader engagement with the AI quality analysis. This
article has not been analysed, so there is no overall score —
reader engagement is measured and shown alongside.
Reader Engagement
Emerging Content
1.8
/100
7 views
2 readers
AI Quality Assessment
Not analyzed
Readership in this journal
EmergingRanked #176 of 829 articles by views in BMC Bioinformatics
Most read
Least read
Bar heights use a square-root scale. Only the 120 most-read articles are drawn; the journal has 829 in total.
Mint this article as an NFT
Not yet mintedCreate a permanent, verifiable on-chain record of this article on the Scimatic Network. The NFT is held in your Journament account, and you can withdraw it to your own wallet at any time.
5
SUSD
one-off · no wallet required
Abstract
Abstract Motivation Genomic and protein foundation models (GFMs and PFMs) have demonstrated strong performance in learning the language of DNA and proteins, but their use in large-scale sequence generation is limited by the latency of autoregressive decoding. Because every token triggers a forward pass of a large Transformer, whose inference is relatively slow, long-sequence generation quickly becomes costly. Results In this work we adapt speculative decoding to a representative GFM: the DNA model DNAGPT and two representative PFMs: ProGen2 and ProtGPT2. We implement a probabilistic variant of speculative decoding, in which a lightweight draft model proposes short token spans and a larger target model verifies or corrects them in parallel, while preserving the target model’s sampling distribution. Across all three models we systematically study the effect of speculation window length, temperature, draft architecture and prompt length, and we benchmark tokens per second over multiple runs per configuration. Speculative decoding yields consistent speedups over standard key-value cached decoding, with maximum observed speedup reaching 100% increase, while average gains across models ranging between 20% and 40% (e.g. 1.2x–1.4×), without changing the underlying target model predictions. Our results show that speculative decoding is a practical and model-agnostic strategy for accelerating genomic and proteomic sequence generation without sacrificing prediction quality. Availability and implementation All code and results are freely available at https://github.com/Georgakopoulos-Soares-lab/BioSpecDec. Supplementary information Supplementary data are available at Bioinformatics online.
| Reference Key |
openalex_W7172005527
Use this key to autocite in the manuscript while using
SciMatic Manuscript Manager or Thesis Manager
|
|---|---|
| Authors | Kimonas Provatas, Aris Karatzikos, Charalampos Koilakos, Michail Patsakis, Alexandros Tzanakakis, Akshatha Nayak, Georgios A. Pavlopoulos, Ioannis Mouratidis, Evangelos Avgoulas, Ilias Georgakopoulos‐Soares |
| Journal | BMC Bioinformatics |
| Year | 2026 |
| DOI |
10.1093/bioinformatics/btag579
|
| URL | |
| Keywords | Keywords not found |
Citations
No citations found. To add a citation, contact the admin at info@scimatic.org
Comments
No comments yet. Be the first to comment on this article.