跳到正文
FunCoding

scgpt

Embed and annotate single-cell expression data with scGPT, a foundation model for single-cell biology. Use this skill when: (1) Producing cell embeddings from an AnnData for clustering/integration, (2) Zero-shot or fine-tuned cell-type annotation, (3) Gene-level representation for perturbation/GRN tasks. For probabilistic single-cell models (scVI etc.), use the scvi-tools library.

Star
2,593
分类
科研
最近提交
2026年8月30日

skills/claude-science/scgpt/SKILL.md

在 GitHub 上查看

scGPT — Single-Cell Foundation Model

Prerequisites

RequirementMinimumRecommended
Python3.10+3.11
CUDA12.1+12.4+
GPU VRAM16 GB24 GB+

How to run

Loading the vocabulary and checkpoint

scGPT checkpoints are raw directories (args.json, best_model.pt, vocab.json) — not Hugging Face hub repos. Point at the directory, not an HF repo id.

from scgpt.tokenizer.gene_tokenizer import GeneVocab
gv = GeneVocab.from_file("/path/to/scgpt-human/vocab.json")
print(len(gv))   # 60697 for the released human checkpoint

Embedding an AnnData

import anndata as ad
from scgpt.tasks import embed_data

adata = ad.read_h5ad("dataset.h5ad")        # var must contain a gene-name column
emb = embed_data(
    adata,
    model_dir="/path/to/scgpt-human",
    gene_col="feature_name",
    use_fast_transformer=False,             # see Gotchas
)
# emb is an AnnData with .obsm["X_scGPT"]

Output format

embed_data returns an AnnData whose .obsm["X_scGPT"] is the per-cell embedding (n_cells × emb_dim, 512 by default). Downstream: feed to scanpy.pp.neighbors / scanpy.tl.umap.

Remote compute

Needs ≥24 GB VRAM and the released human checkpoint (~200 MB: args.json, best_model.pt, vocab.json). Read compute_details({provider, mode:'read'}) for an environment with scgpt and a pre-cached checkpoint directory, then:

c = host.compute.create(provider)
job = c.submit_job(
    intent="scGPT embed 50k cells — 1×GPU, ~5 min",
    inputs=[
        {"src": "dataset.h5ad", "dst_filename": "dataset.h5ad"},
        {"src": "embed.py", "dst_filename": "embed.py"},
    ],
    command="python3 embed.py",
    environment=...,   # env name from compute_details
    outputs=["embedded.h5ad"],
    timeout_seconds=1800,
)
print(job.job_id)   # cell ends here — kernel never blocks on compute

Then call the wait_for_notification brain-tool. When the compute_done notification arrives, act on its payload:

save_artifacts(payload["featured_files"])   # paths under hpc/<job_id>/

For the full result dict (output_files, remote_workdir, …), re-enter the kernel and bind the compute handle separately — .close() lives on the handle, not on the job object:

h = host.compute.create(provider)
res = h.attach_job(job_id).result()
h.close()

See the remote-compute-ssh / remote-compute-modal skill for the orchestration details.

In embed.py, pass model_dir= the checkpoint path from compute_details. If flash-attn is unavailable in that environment, set use_fast_transformer=False.

Gotchas

  • use_fast_transformer default is True but resolves to a FlashAttention path that may not import in every env. Pass use_fast_transformer=False unless you've confirmed flash_attn loads cleanly.
  • The package historically depended on torchtext.vocab.Vocab; in environments without torchtext a pure-Python shim provides Vocab — functionally identical for GeneVocab, but if you hit AttributeError: 'Vocab' object has no attribute …, you're on a stale shim.
  • Gene names must match the vocab; unmatched genes are dropped. Set gene_col to the column in adata.var that holds symbols.

Troubleshooting

SymptomFix
flash_attn is not installed warning at importHarmless; pass use_fast_transformer=False
'Vocab' object has no attribute 'vocab'Env has an old torchtext shim — update the env
Nearly all genes droppedWrong gene_col; check adata.var.columns
"scgpt not in manifest" / env-detection misses scGPTThe baked env manifest lists the distribution as scGPT (and flash_attn), pip's canonical casing — normalize manifest keys before lookup: name.lower().replace('-', '_')

Next: cluster/annotate the embedding with the scanpy library (sc.pp.neighbors → sc.tl.leiden / sc.tl.umap), or compare to an scvi-tools latent space on the same data.

相似的 Skill

wiki-query

PApaperclipai/paperclip101k近 7 天新增 2,948 个 star

官方

clinical-case-report

NEnexu-io/open-design101k近 7 天新增 1,126 个 star

systematic-literature-review

BYbytedance/deer-flow84k近 7 天新增 368 个 star

academic-paper-review

BYbytedance/deer-flow84k近 7 天新增 368 个 star

directory-submissions

COcoreyhaines31/marketingskills54k近 7 天新增 958 个 star

academic-paper

IMImbad0202/academic-research-skills52k近 7 天新增 972 个 star