R Observatory: Metrics for mLLMCelltype version 2.0.8

Balamuta, James Joseph

doi:10.5281/zenodo.21843040

mLLMCelltype

2.0.8Package record

Cell Type Annotation Using Large Language Models

0packages depend

3.1Kdownloads / year

82.7%test coverage

13/13flavors OK

Overview

About

Maintained by Chen YangCRAN page ↗GitHub ↗Website ↗Issues ↗

Automated cell type annotation for single-cell RNA sequencing data using consensus predictions from multiple large language models. Integrates with Seurat objects and provides uncertainty quantification for annotations. Supports various LLM providers including OpenAI, Anthropic, and Google. For details see Yang et al. (2026) doi:10.1038/s42003-026-10420-8.

Changes in 2.0.8

Bug Fixes

Disabled DeepSeek V4 thinking mode for cell-type annotation requests. DeepSeek V4 enables thinking by default, which could consume the 4,096-token response budget before producing final annotation text and lead to an invalid-response error.
Increased the default R API request timeout from 30 to 120 seconds so slower non-streaming model responses, including DeepSeek V4 Pro annotations, are not aborted before completion. Set options(mLLMCelltype.api_timeout = 300) to override the timeout when a longer response window is needed.

Maintenance

Unified marker and tissue prompt preparation across plain and structured reasoning annotations so both modes stay consistent as prompt behavior evolves.

From NEWS.md in the release

Install

R (CRAN)pak (dev)Ubuntu (r2u)Fedora (COPR)openSUSE (OBS)

install.packages("mLLMCelltype", repos = "https://cloud.r-project.org/")

Installs the current CRAN release. Prebuilt binaries on Windows and macOS.

if (!requireNamespace("pak", quietly = TRUE))
  install.packages("pak", repos = "https://cloud.r-project.org/")
pak::pak("cafferychen777/mLLMCelltype")

Development version from cafferychen777/mLLMCelltype. Installs pak first if it is not already available.

Release

# enable cranapt (r2u) if it is not already set up, then install
grep -rqs r2u.stat.illinois.edu /etc/apt/sources.list /etc/apt/sources.list.d/ \
  || curl -fsSL https://raw.githubusercontent.com/eddelbuettel/r2u/master/inst/scripts/add_cranapt_noble.sh | sudo bash
sudo apt install -y r-cran-mllmcelltype

Fast Ubuntu binaries via r2u (no compilation). The cranapt setup runs once and is skipped when it is already enabled. We list this channel from recorded r2u download activity rather than from a live index of the repository, so treat it as last known rather than guaranteed.

bspm (used by r2u) also needs make: sudo apt install make

# enable the iucar/cran COPR if it is not already present, then install
ls /etc/yum.repos.d/*iucar*cran*.repo >/dev/null 2>&1 \
  || sudo dnf copr enable -y iucar/cran
sudo dnf install -y R-CRAN-mLLMCelltype

RPMs from the iucar/cran COPR, rebuilt from CRAN.

For install.packages() integration in R, also: sudo dnf install R-CoprManager

# add the autoCRAN OBS repo (Tumbleweed) if it is missing, then install
zypper -q lr | grep -qi autoCRAN \
  || sudo zypper addrepo https://download.opensuse.org/repositories/devel:/languages:/R:/autoCRAN/openSUSE_Tumbleweed/devel:languages:R:autoCRAN.repo
sudo zypper install -y R-mLLMCelltype

RPMs auto-built from CRAN on openSUSE OBS (Tumbleweed). We list this channel from recorded autoCRAN download activity rather than from a live index of the repository, so treat it as last known rather than guaranteed.

Health

CRAN checks

13OK

CRAN check page ↗

Slowest check: 2.5 min · r-oldrel-windows-x86_64

Status changes

OK13 OK2026-08-05
NOTE12 OK, 1 NOTE2026-08-01
OK14 OK2026-03-10

Advisories

none known

How this is measured·How advisories are found

Documentation

In release 2.0.8

READMENoVignettesYes · 12 · dynamicNEWSYes · 100% structured · mentions 2.0.8Citation fileYes · cites a publicationWebsiteYes

Help pages: 65 (35 internal)includes a package overview page
Examples that run: 17%1 run in a plain check · 5 never run
Exported functions with examples: 20%
Documented parameters: 98%
Return-value docs: 43%
Help pages citing references: 0%

Vignettes (12)

mLLMCelltype: Overview and Quick Reference HTML
Advanced Features & Case Studies HTML
Consensus Annotation Principles HTML
Consensus vs Single-Agent: A Methodology Comparison HTML
Contributing Guide HTML
Frequently Asked Questions HTML
Getting Started with mLLMCelltype HTML
Installation Guide HTML
Introduction to mLLMCelltype HTML
Usage Tutorial HTML

Show 2 moreHide 2 vignettes

How these are measured

Downloads

3.1K

CRAN downloads in the past year

Rank #13,945 · ~8/day · ~255/mo

Releases R versions

Daily download trend is not available in this view yet.

24930 days

85290 days

3.1K1 year

Compare downloads with other packages →

Also on86 r2u4 autocran

How downloads are counted

Repository

cafferychen777/mllmcelltype ↗Account: cafferychen777

661Stars

59Forks

5Open issues

4Open PRs

10Releases

525Commits

3Commit identities

bioinformaticscell-type-annotationconsensus-algorithmlarge-language-modelsllmscanpyseuratsingle-cell

License file reads as MIT · 525 commits · Last activity 2026-09-24 · -0.2% stars, 30d · Discussions: 2 posts

Responsiveness

How these are sampled

PRs merged (all time): 97%
Median days to close, 50 most recently updated closed issues: 433
Median days to close, 50 most recently updated closed PRs: 0

Stars over time

2026-07-21 · 6522026-10-08 · 661

How these are measured

PracticesBeta

11 development-tooling and community-health practices detected across 6 families in the upstream repository

Checks run against github.com/cafferychen777/mllmcelltype on 2026-10-25.

Continuous integration (1)

GitHub Actions

Governance and community (5)

Code of conductContributing guideIssue templatesPR templateFunding

Funding links: buymeacoffee.com, patreon.com

Docs source (2)

GitHub Pages site last deployed 2026-09-01 · The repository has a site deploy workflow

Research and citation (1)

CITATION.cff

Show all practicesHide 2 practices

Automation and maintenance (1)

Dependabot

Git structural (1)

.gitattributes

How this is detected·Detection ruleset v4 (2026-10-20)

AI coding toolsBeta

This repository shows signs of AI coding tools.

Claude Codefirst seen 2025-06-14
Named in .gitignore: CLAUDE.md
Commits: at least 76 crediting it in the message
Codexfirst seen 2026-08-18
Named in .gitignore: .codex

Shared conventions any agent may read, so they name no particular tool.

Seen in the repository: AGENTS.md

Models named in its commits

Claude Opus 4.11 commit · Aug 2025
Claude Opus 4.61 commit · Jun 2026
Claude Opus 4.81 commit · Jul 2026

Counts are commits, not lines of code. Commits by a tool's accounts count once across all of its accounts. Commits crediting it are the largest count among its credit lines, a minimum.How this is detected·Detection ruleset v4 (updated 2026-09-27)

Dependencies

Declared dependencies

8 external dependencies (excludes base and recommended)

Installing mLLMCelltype adds 9 packages (7 with compiled code, 3.2 MB of source tarballs). Heaviest: openssl 1.1 MB, jsonlite 1.0 MB, curl 714 KB.

Depends (0)

none

Imports (7)

httr jsonlite R6 digeststatstoolsutils

LinkingTo (0)

none

Suggests (4)

knitr rmarkdown Seurat testthat

Enhances (0)

none

Dependency license breakdown →

Reverse dependencies

0direct

0indirect

Nothing depends on this yet.

How these are counted

Code & Tests

Datasets

People & History

People (1)

Chen Yang

Releases (5)

Pick two releases to compare their code metrics.

2.0.8Latest
record
2026-09-01 · current release · diff ↗
unarchivedReturned to CRAN
2026-07-21
2.0.7
record
2026-07-21 · diff ↗ ·
added 2 exports
KimiProcessor, create_reasoning_annotation_prompt
archivedRemoved from CRAN
2026-06-29
issues were not corrected in time
2.0.5
record
2026-05-11 · diff ↗ ·
removed 1 export
.qwen_endpoint_cache

added 1 export
QwenProcessor
R
R 4.6.0 released · 2026-04-24
2.0.0
record
2026-02-08 · diff ↗ ·
removed 1 export
QwenProcessor

added 3 exports
.qwen_endpoint_cache, mllmcelltype_cache_dir, mllmcelltype_clear_cache
1.3.2
record
2025-09-02
R
R 4.5.0 released · 2025-04-11

Package metadata

First published: 2025-09-02
Total releases: 5 / 1 yrs
License: MIT + file LICENSE OSI
Download size: 538 KB

Cite

Cite this package

Run in R for the authors' entry:

citation("mLLMCelltype")

The package provides a citation file, so citation() returns the authors' own entry.

It points to 10.1038/s42003-026-10420-8.

The repository also keeps a CITATION.cff.

Cite the R Observatory

For a number measured here: a download total, a coverage figure, an archival date.

Format

APA

Balamuta, J. J. (2026). R Observatory: Metrics for mLLMCelltype version 2.0.8 [Data set]. HJJB, LLC. Data release v2026-10-26. https://doi.org/10.5281/zenodo.21843040

From data release v2026-10-26, which the citation names so these numbers can be found later. More on citing and the projects behind them.

Report a problem with this page →