A RISC-V Accelerator for Sequence Decoding in Mobile DNA Sequencers
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Modern nanopore sequencers generate raw signal data at high speed, demanding low-latency and energy-efficient basecalling pipelines to enable fully portable genomic analysis. In this work, we present a hardware accelerator for the Viterbi-based connectionist temporal classification (CTC) decoding stage of basecalling—a key bottleneck in translating neural network outputs into deoxyribonucleic acid (DNA) sequences. Our design is the first pipelined CTC Viterbi decoder architecture tailored for nanopore sequencing and is implemented on a Xilinx Virtex-7 (VC707) FPGA within a Linux-capable reduced instruction set computer-fifth generation (RISC-V) system-on-chip (SoC). The accelerator processes over 23 000 DNA bases per second at 100 MHz with about <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$4.3~\boldsymbol {\mu }$</tex-math> </inline-formula>s per-sample latency and only 0.43-W overhead power. This corresponds to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\textbf {5.3}\times \mathbf {10^{4}}$</tex-math> </inline-formula> bases/J (<inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$19~\boldsymbol {\mu }$</tex-math> </inline-formula>J/base) and yields approximately 7x end-to-end speedup over a CPU baseline, while reserving the baseline read-identity accuracy. For the same CTC task, the accelerator delivers 29x higher throughput than a recent FPGA beam-search decoder. These results demonstrate the viability of dedicated decoding accelerators for real time, on-device genomic processing in power-constrained environments.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it