OpenBioMed is an agent platform and toolkit collection for biomedical research and drug discovery, covering areas such as molecular design, protein analysis, and single-cell data analysis. It is intended for researchers and provides the biomedical skills listed in the catalogue as workflows for Claude Code.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add PharMolix/OpenBioMed --skill protein-subcellular-localization-prediction-biot5git clone --depth 1 https://github.com/PharMolix/OpenBioMedWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/pharmolix/openbiomed/protein-subcellular-localization-prediction-biot5)<a href="https://agentmods.dev/skills/pharmolix/openbiomed/protein-subcellular-localization-prediction-biot5"><img src="https://agentmods.dev/badge/skills/pharmolix/openbiomed/protein-subcellular-localization-prediction-biot5/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pharmolix/openbiomed/protein-subcellular-localization-prediction-biot5"><img src="https://agentmods.dev/badge/skills/pharmolix/openbiomed/protein-subcellular-localization-prediction-biot5.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00085 | $0.00894 |
| Opus 5 | $0.00043 | $0.00447 |
| Sonnet 5 | $0.00017 | $0.00179 |
| Haiku 4.5 | $0.00009 | $0.00089 |
Grade A, and why
protein-subcellular-localization-prediction-biot5 scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Protein Subcellular Localization Prediction
Predict subcellular localization for proteins from their amino acid sequences using the BioT5 model.
When to Use
- You have a protein FASTA sequence and need to know its cellular location
- You want to identify if a protein is cytoplasmic, nuclear, membrane-bound, or secreted
- You need quick localization insights without experimental data
- You're characterizing novel or unannotated protein sequences
Workflow
from open_biomed.data import Protein, Text
from open_biomed.core.pipeline import InferencePipeline
# Create protein from FASTA sequence
protein = Protein.from_fasta("YOUR_AMINO_ACID_SEQUENCE")
# Create the question for subcellular localization
question = Text.from_str(
"Please provide information about the subcellular localization of this protein."
)
# Load the BioT5 model for protein question answering
pipeline = InferencePipeline(
task="protein_question_answering",
model="biot5",
model_ckpt="./checkpoints/server/protein_question_answering_biot5.ckpt",
device="cuda:0"
)
# Run inference to get localization prediction
outputs = pipeline.run(protein=protein, text=question)
localization = outputs[0][0].str
print(localization)
See examples/basic_example.py for a complete runnable script.
Expected Outputs
The model returns subcellular localization information:
| Output | Description |
|---|---|
| Cytoplasm | Cytoplasmic proteins, soluble enzymes |
| Nucleus | Nuclear proteins, transcription factors |
| Membrane | Membrane-bound proteins, receptors |
| Secreted | Extracellular proteins, secreted factors |
| Mitochondria | Mitochondrial proteins |
| Peroxisome | Peroxisomal enzymes |
| Endoplasmic reticulum | ER-resident proteins |
| Golgi apparatus | Golgi-localized proteins |
Example Output
Cytoplasm
Input Formats
The skill accepts protein sequences in FASTA format (amino acid string):
# From raw sequence string
protein = Protein.from_fasta("MRVGVIRFPGSNCDRDVHHVLELAGAEPEYVWW...")
# From UniProt (get sequence first)
from open_biomed.tools.tool_registry import TOOLS
tool = TOOLS["protein_uniprot_request"]
protein, _ = tool.run(accession="P00533") # Example: EGFR
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 114 lines · 85 tokens per session scan A 391275240d4c
protein-subcellular-localization-prediction-biot5 is a skill published in the GitHub repository PharMolix/OpenBioMed (1,105 stars, last pushed 1mo ago), licensed MIT. It adds 85 tokens to every session and 894 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
esm
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations). Use this skill when working with protein sequences, structures, or function prediction; designing novel…
Protein Structures — AlphaFold & PDB
Obtain and predict protein 3D structures — fetch AlphaFold predicted models from the AlphaFold DB, experimental structures from the RCSB PDB, or predict a novel sequence with ColabFold — and visualise them in the Mol desktop app.
protein-qc
Quality control metrics and filtering thresholds for protein design. Use this skill when: (1) Evaluating design quality for binding, expression, or structure, (2) Setting filtering thresholds for pLDDT, ipTM, PAE, (3) Checking sequence liabilities (cysteines, deamidation, polybasic clusters), (4) Creating multi-stage…
cell-free-expression
Guidance for cell-free protein synthesis (CFPS) optimization. Use when: (1) Planning CFPS experiments, (2) Troubleshooting low yield or aggregation, (3) Optimizing DNA template design for CFPS, (4) Expressing difficult proteins (disulfide-rich, toxic, membrane).
rfdiffusion
Generate protein backbones using RFdiffusion, a diffusion-based generative model for de novo protein structure generation. Use this skill when: (1) Designing binder scaffolds for a target protein, (2) Generating novel protein backbones from scratch, (3) Scaffolding functional motifs into new proteins, (4) Specifying…
binder-design
Guidance for choosing the right protein binder design tool. Use this skill when: (1) Deciding between BoltzGen, BindCraft, or RFdiffusion, (2) Planning a binder design campaign, (3) Understanding trade-offs between different approaches, (4) Selecting tools for specific target types. For specific tool parameters, use…