Research preview · computational biology

Drop-in speedups for scientific toolkits, produced by autonomous research.

AutoZyme combines automated experiment search with expert review to rewrite the slow paths inside widely used scientific packages — without changing their public API. Every shipped patch clears a strict output-concordance gate.

See the benchmarks → Suggest a toolkit

Preprint coming soon · arXiv:TBD Current releases: SeuratTurbo · R / ScanpyTurbo · Python

By the numbers

Aggregated across all tracked benchmarks

—

Benchmarks

—

Datasets

—

Methods

—

Median speedup

—

Peak speedup

Benchmarks at a glance

Per-method speedup & concordance across datasets

AutoZyme benchmark figure: per-method speedup and concordance for Seurat (panel A) and Scanpy (panel B), across four dataset sizes — Figure 1 Per-method wall-clock speedup (left), before/after timings, peak memory, and output concordance, for Seurat (A) and Scanpy (B) at 4 threads on an AMD Ryzen 9 7950X.
Download PDF ↓

Top speedups

Best wall-clock ratio per method

Install

Drop-in — no API changes to your existing pipelines

R · SeuratTurbo Seurat v5.x

# Install from GitHub (CRAN release coming)
remotes::install_github("ElliotXie/seurat-turbo")

library(Seurat)
library(SeuratTurbo)   # activates patches

# Use Seurat exactly as you normally would —
# NormalizeData / RunPCA / FindClusters / etc.
# are transparently accelerated.

Requires R ≥ 4.0, Seurat ≥ 5.0

Python · ScanpyTurbo Scanpy v1.11.x

# Install from GitHub (PyPI release coming)
pip install git+https://github.com/ElliotXie/scanpy-turbo.git

import scanpy as sc
import scanpy_turbo   # activates patches

# Use Scanpy exactly as you normally would —
# pp.normalize_total / tl.leiden / etc.
# are transparently accelerated.

Requires Python ≥ 3.10, Scanpy ≥ 1.11

Currently optimized

Packages & methods shipped to date

Seurat · R

SeuratTurbo

Drop-in patches for Seurat v5.x

NormalizeData · FindVariableFeatures · ScaleData · RunPCA · FindNeighbors · FindClusters (Louvain / Leiden) · RunUMAP · FindAllMarkers · SCTransform · IntegrateData (CCA)

ElliotXie/seurat-turbo →

Scanpy · Python

ScanpyTurbo

Drop-in patches for Scanpy v1.11.x

normalize_total · highly_variable_genes · scale · pca · neighbors · leiden · umap · rank_genes_groups

ElliotXie/scanpy-turbo →

How AutoZyme works

Under the hood, AutoZyme runs an autonomous research loop: candidate optimizations are generated, benchmarked against the upstream baseline on real datasets, and filtered on both speed and output concordance — ARI for clusterings, correlations for embeddings, Jaccard for marker lists, and so on. Only patches that preserve scientific output within tight tolerance are shipped.

You can nominate the next package for optimization on the Suggest & Vote page. We periodically review the top-voted entries and pick one to work on next.

How to cite

@misc{autozyme2026,
  title  = {AutoZyme: Autonomous-Research-Driven Speedups for Scientific Toolkits},
  author = {The AutoZyme Team},
  year   = {2026},
  note   = {Manuscript in preparation}
}