Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

RNA-seq Differential Expression Analysis (DESeq2) · FreedomIntelligence | DecimalAI

Scienceby FreedomIntelligence

RNA-seq Differential Expression Analysis (DESeq2)

Production-ready RNA-seq differential expression analysis using PyDESeq2. Performs DESeq2 normalization, dispersion estimation, Wald testing, LFC shrinkage, and result filtering. Handles multi-factor designs, multiple contrasts, batch effects, and integrates with gene enrichment (gseapy) and ToolUniverse annotation tools (UniProt, Ensembl, OpenTargets). Supports CSV/TSV/H5AD input formats and any organism.

Never made a case worse

SkillScore

SkillScore18/100

Test results 18

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

5%18%of test cases passed +14 pts

Without skill1 of 22

With skill4 of 22

3 fixed1 passed either way18 still failing0 broke

Measured on gemini-3.6-flash7/26/2026v121 comparable

Track record

Agent runs: 0; All time

Use this skill

Your agent runs on

Adds every file the skill has, pinned so you can update it. No account needed.

pip install "decimalai>=0.15"
decimalai skills add tooluniverse-rnaseq-deseq2
claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"

The same install from Python, for a notebook or a setup script.

Install

pip install "decimalai>=0.15"

Add the skill

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("tooluniverse-rnaseq-deseq2")
if result.exit_code:
    raise SystemExit(result.problems)

print("Added. Start Claude Code with the command below.")

Start Claude Code with it

claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"

Type these in a Claude Code session. No account or API key. It writes the skill and any files it bundles, and asks first when its safety rating isn't Passed.

Add the DecimalAI plugin, once

/plugin marketplace add decimal-labs/decimalai-claude-plugins
/plugin install decimalai@decimalai

Install this skill

/decimalai:install tooluniverse-rnaseq-deseq2

The plugin needs python3 and curl on your machine.

No Python or account. Claude Code picks it up in its next session.

Save it into your project

curl -fsSL --create-dirs -o .claude/skills/tooluniverse-rnaseq-deseq2/SKILL.md https://app.decimal.ai/s/tooluniverse-rnaseq-deseq2/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/tooluniverse-rnaseq-deseq2/SKILL.md

This gets SKILL.md only. The skill's 12 other files are not included.

Other ways to add it

Claude Code docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[claude-agent-sdk]"
decimalai skills add tooluniverse-rnaseq-deseq2

Add it to your agent

import asyncio

from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

async def main():
    question = "Hello!"
    async with support.run(question) as run:  # one user message, one run
        async for message in run.query(options=ClaudeAgentOptions(max_turns=6)):
            print(message)

# In a notebook or async code: await main()
asyncio.run(main())

Prefer its own loader? ClaudeAgentOptions(plugins=[skills_plugin()], skills="all") reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

The same install from Python, for a notebook or a setup script. agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[claude-agent-sdk]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("tooluniverse-rnaseq-deseq2")
if result.exit_code:
    raise SystemExit(result.problems)

import asyncio

from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

async def main():
    question = "Hello!"
    async with support.run(question) as run:  # one user message, one run
        async for message in run.query(options=ClaudeAgentOptions(max_turns=6)):
            print(message)

# In a notebook or async code: await main()
asyncio.run(main())

Prefer its own loader? ClaudeAgentOptions(plugins=[skills_plugin()], skills="all") reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/tooluniverse-rnaseq-deseq2/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from claude_agent_sdk import ClaudeAgentOptions, query

skill = Path(".agents/skills/tooluniverse-rnaseq-deseq2/SKILL.md").read_text()
options = ClaudeAgentOptions(system_prompt=f"You are a helpful agent.\n\n{skill}", max_turns=6)

async def main():
    async for message in query(prompt="Hello!", options=options):
        print(message)

# In a notebook or async code: await main()
asyncio.run(main())

This gets SKILL.md only. The skill's 12 other files are not included.

Other ways to add it

Claude Agent SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai-agents]"
decimalai skills add tooluniverse-rnaseq-deseq2

Add it to your agent

from agents import Agent, Runner
from decimalai.openai_agents import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    name=support.name,
    instructions=support.instructions,  # your prompt, then the skill list
    tools=[*support.tools],             # your tools, then load_skill
)
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

Using SandboxAgent? capabilities=[Shell(), decimalai.openai_agents.sandbox_skills()] points its own loader at the same folder.

Install

pip install "decimalai[openai-agents]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("tooluniverse-rnaseq-deseq2")
if result.exit_code:
    raise SystemExit(result.problems)

from agents import Agent, Runner
from decimalai.openai_agents import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    name=support.name,
    instructions=support.instructions,  # your prompt, then the skill list
    tools=[*support.tools],             # your tools, then load_skill
)
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

Using SandboxAgent? capabilities=[Shell(), decimalai.openai_agents.sandbox_skills()] points its own loader at the same folder.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/tooluniverse-rnaseq-deseq2/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/tooluniverse-rnaseq-deseq2/SKILL.md").read_text()
agent = Agent(name="support", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

This gets SKILL.md only. The skill's 12 other files are not included.

Other ways to add it

OpenAI Agents docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai]"
decimalai skills add tooluniverse-rnaseq-deseq2

Add it to your agent

import json

from openai import OpenAI
from decimalai.openai import agent_config

client = OpenAI()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your tools, as Chat Completions takes them, and what answers each.
TOOLS = [{"type": "function", "function": {
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters": {"type": "object", "properties": {"order_id": {"type": "string"}},
                   "required": ["order_id"]},
}}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    # run.system is your prompt, then the skill list.
    messages = [{"role": "system", "content": run.system}, run.message]
    while True:
        reply = client.chat.completions.create(
            model="gpt-5.4-mini",
            messages=messages,
            tools=[*TOOLS, *run.tools],  # your tools, then load_skill
        ).choices[0].message
        messages.append(reply)
        if not reply.tool_calls:
            break
        for call in reply.tool_calls:
            # load_skill is answered by the run; your own tools by FUNCTIONS.
            function = FUNCTIONS.get(call.function.name)
            messages.append(run.tool_result(call) or {
                "role": "tool", "tool_call_id": call.id,
                "content": function(**json.loads(call.function.arguments)) if function
                else f"There is no tool named {call.function.name!r}.",
            })
print(reply.content)

# The Responses API takes run.response_tools instead of run.tools.

Install

pip install "decimalai[openai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("tooluniverse-rnaseq-deseq2")
if result.exit_code:
    raise SystemExit(result.problems)

import json

from openai import OpenAI
from decimalai.openai import agent_config

client = OpenAI()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your tools, as Chat Completions takes them, and what answers each.
TOOLS = [{"type": "function", "function": {
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters": {"type": "object", "properties": {"order_id": {"type": "string"}},
                   "required": ["order_id"]},
}}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    # run.system is your prompt, then the skill list.
    messages = [{"role": "system", "content": run.system}, run.message]
    while True:
        reply = client.chat.completions.create(
            model="gpt-5.4-mini",
            messages=messages,
            tools=[*TOOLS, *run.tools],  # your tools, then load_skill
        ).choices[0].message
        messages.append(reply)
        if not reply.tool_calls:
            break
        for call in reply.tool_calls:
            # load_skill is answered by the run; your own tools by FUNCTIONS.
            function = FUNCTIONS.get(call.function.name)
            messages.append(run.tool_result(call) or {
                "role": "tool", "tool_call_id": call.id,
                "content": function(**json.loads(call.function.arguments)) if function
                else f"There is no tool named {call.function.name!r}.",
            })
print(reply.content)

# The Responses API takes run.response_tools instead of run.tools.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/tooluniverse-rnaseq-deseq2/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/tooluniverse-rnaseq-deseq2/SKILL.md").read_text()
reply = client.chat.completions.create(
    model="gpt-5.4-mini",
    messages=[
        {"role": "system", "content": f"You are a helpful agent.\n\n{skill}"},
        {"role": "user", "content": "Hello!"},
    ],
).choices[0].message

This gets SKILL.md only. The skill's 12 other files are not included.

Other ways to add it

OpenAI SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[anthropic]"
decimalai skills add tooluniverse-rnaseq-deseq2

Add it to your agent

import anthropic
from decimalai.anthropic import agent_config

client = anthropic.Anthropic()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

question = "Hello!"
with support.run(question) as run:  # one user message, one run
    answer = client.beta.messages.tool_runner(
        model="claude-haiku-5-5",
        max_tokens=4096,
        system=run.system,     # your prompt, then the skill list
        tools=[*run.tools],    # your tools, then load_skill
        messages=[{"role": "user", "content": question}],
    ).until_done()

Install

pip install "decimalai[anthropic]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("tooluniverse-rnaseq-deseq2")
if result.exit_code:
    raise SystemExit(result.problems)

import anthropic
from decimalai.anthropic import agent_config

client = anthropic.Anthropic()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

question = "Hello!"
with support.run(question) as run:  # one user message, one run
    answer = client.beta.messages.tool_runner(
        model="claude-haiku-5-5",
        max_tokens=4096,
        system=run.system,     # your prompt, then the skill list
        tools=[*run.tools],    # your tools, then load_skill
        messages=[{"role": "user", "content": question}],
    ).until_done()

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/tooluniverse-rnaseq-deseq2/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/tooluniverse-rnaseq-deseq2/SKILL.md").read_text()
reply = client.messages.create(
    model="claude-haiku-5-5",
    max_tokens=4096,
    system=f"You are a helpful agent.\n\n{skill}",
    messages=[{"role": "user", "content": "Hello!"}],
)

This gets SKILL.md only. The skill's 12 other files are not included.

Other ways to add it

Anthropic docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[google-genai]"
decimalai skills add tooluniverse-rnaseq-deseq2

Add it to your agent

from google import genai
from google.genai import types
from decimalai.google_genai import agent_config

client = genai.Client()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your functions, as declarations for the model, and what answers each.
TOOLS = [{"function_declarations": [{
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters_json_schema": {"type": "object", "properties": {"order_id": {"type": "string"}},
                               "required": ["order_id"]},
}]}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    config = types.GenerateContentConfig(
        system_instruction=run.system,     # your prompt, then the skill list
        tools=[*TOOLS, *run.tool_params],  # your functions, then load_skill
    )
    contents = [{"role": "user", "parts": [{"text": run.message}]}]
    while True:
        response = client.models.generate_content(
            model="gemini-3.5-flash", contents=contents, config=config,
        )
        if not response.function_calls:
            break
        contents.append(response.candidates[0].content)
        parts = []
        for call in response.function_calls:
            # load_skill is answered by the run; your own functions by FUNCTIONS.
            # A loop of your own rather than automatic function calling, which
            # raises KeyError when the model asks for a function you did not pass.
            function = FUNCTIONS.get(call.name)
            parts.append(run.tool_result(call) or {"function_response": {
                "name": call.name, "id": call.id,
                "response": {"result": function(**(call.args or {})) if function
                             else f"There is no function named {call.name!r}."},
            }})
        contents.append({"role": "user", "parts": parts})
print(response.text)

Install

pip install "decimalai[google-genai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("tooluniverse-rnaseq-deseq2")
if result.exit_code:
    raise SystemExit(result.problems)

from google import genai
from google.genai import types
from decimalai.google_genai import agent_config

client = genai.Client()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your functions, as declarations for the model, and what answers each.
TOOLS = [{"function_declarations": [{
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters_json_schema": {"type": "object", "properties": {"order_id": {"type": "string"}},
                               "required": ["order_id"]},
}]}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    config = types.GenerateContentConfig(
        system_instruction=run.system,     # your prompt, then the skill list
        tools=[*TOOLS, *run.tool_params],  # your functions, then load_skill
    )
    contents = [{"role": "user", "parts": [{"text": run.message}]}]
    while True:
        response = client.models.generate_content(
            model="gemini-3.5-flash", contents=contents, config=config,
        )
        if not response.function_calls:
            break
        contents.append(response.candidates[0].content)
        parts = []
        for call in response.function_calls:
            # load_skill is answered by the run; your own functions by FUNCTIONS.
            # A loop of your own rather than automatic function calling, which
            # raises KeyError when the model asks for a function you did not pass.
            function = FUNCTIONS.get(call.name)
            parts.append(run.tool_result(call) or {"function_response": {
                "name": call.name, "id": call.id,
                "response": {"result": function(**(call.args or {})) if function
                             else f"There is no function named {call.name!r}."},
            }})
        contents.append({"role": "user", "parts": parts})
print(response.text)

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/tooluniverse-rnaseq-deseq2/SKILL.md

Give it to your agent

from pathlib import Path
from google import genai
from google.genai import types

client = genai.Client()
skill = Path(".agents/skills/tooluniverse-rnaseq-deseq2/SKILL.md").read_text()
response = client.models.generate_content(
    model="gemini-3.5-flash",
    contents="Hello!",
    config=types.GenerateContentConfig(system_instruction=f"You are a helpful agent.\n\n{skill}"),
)

This gets SKILL.md only. The skill's 12 other files are not included.

Other ways to add it

Gemini API docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[langchain]" langchain-openai
decimalai skills add tooluniverse-rnaseq-deseq2

Add it to your agent

from langchain.agents import create_agent
from decimalai.langchain import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = create_agent(
    "openai:gpt-5.4-mini",
    tools=[],                         # your tools; the middleware adds load_skill
    middleware=[support.middleware],  # your prompt, the skill list and load_skill
)
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

Install

pip install "decimalai[langchain]" langchain-openai

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("tooluniverse-rnaseq-deseq2")
if result.exit_code:
    raise SystemExit(result.problems)

from langchain.agents import create_agent
from decimalai.langchain import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = create_agent(
    "openai:gpt-5.4-mini",
    tools=[],                         # your tools; the middleware adds load_skill
    middleware=[support.middleware],  # your prompt, the skill list and load_skill
)
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/tooluniverse-rnaseq-deseq2/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/tooluniverse-rnaseq-deseq2/SKILL.md").read_text()
agent = create_agent("openai:gpt-5.4-mini", tools=[], system_prompt=f"You are a helpful agent.\n\n{skill}")
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

This gets SKILL.md only. The skill's 12 other files are not included.

Other ways to add it

LangChain docs

CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add tooluniverse-rnaseq-deseq2

Add it to your agent

import decimalai.crewai
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                               # your own CrewAI LLM
    skills=decimalai.crewai.skills(),      # the installed folder
    tools=decimalai.crewai.skill_tools(),  # reads a skill's files, runs its scripts
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

The same install from Python, for a notebook or a setup script. CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("tooluniverse-rnaseq-deseq2")
if result.exit_code:
    raise SystemExit(result.problems)

import decimalai.crewai
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                               # your own CrewAI LLM
    skills=decimalai.crewai.skills(),      # the installed folder
    tools=decimalai.crewai.skill_tools(),  # reads a skill's files, runs its scripts
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

No DecimalAI package. CrewAI's own loader reads the folder, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/tooluniverse-rnaseq-deseq2/SKILL.md

Give it to your agent

from pathlib import Path
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                         # your own CrewAI LLM
    skills=[Path(".agents/skills")],
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

This gets SKILL.md only. The skill's 12 other files are not included.

Other ways to add it

CrewAI docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[adk]"
decimalai skills add tooluniverse-rnaseq-deseq2

Add it to your agent

from decimalai.adk import DecimalAIPlugin, agent_config
from google.adk.agents import LlmAgent
from google.adk.apps import App

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = LlmAgent(
    name="support",          # ADK needs a Python identifier
    model="gemini-3.5-flash",
    instruction=support.instruction,  # your prompt, then the skill list
    tools=[*support.tools],           # your tools, then load_skill
)
# DecimalAIPlugin makes each invocation of runners built from this App one trace.
app = App(name="support", root_agent=agent, plugins=[DecimalAIPlugin()])

Prefer ADK's own loader? SkillToolset(skills=decimalai.adk.skills(), ...) reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

Install

pip install "decimalai[adk]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("tooluniverse-rnaseq-deseq2")
if result.exit_code:
    raise SystemExit(result.problems)

from decimalai.adk import DecimalAIPlugin, agent_config
from google.adk.agents import LlmAgent
from google.adk.apps import App

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = LlmAgent(
    name="support",          # ADK needs a Python identifier
    model="gemini-3.5-flash",
    instruction=support.instruction,  # your prompt, then the skill list
    tools=[*support.tools],           # your tools, then load_skill
)
# DecimalAIPlugin makes each invocation of runners built from this App one trace.
app = App(name="support", root_agent=agent, plugins=[DecimalAIPlugin()])

Prefer ADK's own loader? SkillToolset(skills=decimalai.adk.skills(), ...) reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/tooluniverse-rnaseq-deseq2/SKILL.md

Give it to your agent

from pathlib import Path
from google.adk.agents import LlmAgent

skill = Path(".agents/skills/tooluniverse-rnaseq-deseq2/SKILL.md").read_text()
agent = LlmAgent(
    name="support",
    model="gemini-3.5-flash",
    instruction=lambda context: f"You are a helpful agent.\n\n{skill}",
)

This gets SKILL.md only. The skill's 12 other files are not included.

Other ways to add it

Google ADK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[pydantic-ai]"
decimalai skills add tooluniverse-rnaseq-deseq2

Add it to your agent

from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    "openai:gpt-4o-mini",
    name=support.name,
    tools=[],                 # your tools; the capability adds load_skill
    capabilities=[support],   # your prompt, the skill list and load_skill
)
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

On the Pydantic AI harness, decimalai.pydantic_ai_harness.skills(project) uses its own loader instead.

Install

pip install "decimalai[pydantic-ai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("tooluniverse-rnaseq-deseq2")
if result.exit_code:
    raise SystemExit(result.problems)

from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    "openai:gpt-4o-mini",
    name=support.name,
    tools=[],                 # your tools; the capability adds load_skill
    capabilities=[support],   # your prompt, the skill list and load_skill
)
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

On the Pydantic AI harness, decimalai.pydantic_ai_harness.skills(project) uses its own loader instead.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/tooluniverse-rnaseq-deseq2/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/tooluniverse-rnaseq-deseq2/SKILL.md").read_text()
agent = Agent("openai:gpt-4o-mini", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

This gets SKILL.md only. The skill's 12 other files are not included.

Other ways to add it

Pydantic AI docs

Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" deepagents
decimalai skills add tooluniverse-rnaseq-deseq2

Add it to your agent

import decimalai.deepagents
from deepagents import create_deep_agent

agent = create_deep_agent(model=model, **decimalai.deepagents.skills())
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

The default backend reads files but has no shell. To run a skill's scripts, pass skills(backend=LocalShellBackend(...)).

The same install from Python, for a notebook or a setup script. Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" deepagents

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("tooluniverse-rnaseq-deseq2")
if result.exit_code:
    raise SystemExit(result.problems)

import decimalai.deepagents
from deepagents import create_deep_agent

agent = create_deep_agent(model=model, **decimalai.deepagents.skills())
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

The default backend reads files but has no shell. To run a skill's scripts, pass skills(backend=LocalShellBackend(...)).

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/tooluniverse-rnaseq-deseq2/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/tooluniverse-rnaseq-deseq2/SKILL.md").read_text()
agent = create_deep_agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

This gets SKILL.md only. The skill's 12 other files are not included.

Other ways to add it

Deep Agents docs

Its own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" agent-framework
decimalai skills add tooluniverse-rnaseq-deseq2

Add it to your agent

import asyncio

from agent_framework import Agent
from decimalai.agent_framework import skills

agent = Agent(client=client, instructions="You are a helpful agent.", context_providers=[skills()])
asyncio.run(agent.run("Hello!"))

It caches skills by default, so restart the process after decimalai skills update.

The same install from Python, for a notebook or a setup script. Its own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" agent-framework

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("tooluniverse-rnaseq-deseq2")
if result.exit_code:
    raise SystemExit(result.problems)

import asyncio

from agent_framework import Agent
from decimalai.agent_framework import skills

agent = Agent(client=client, instructions="You are a helpful agent.", context_providers=[skills()])
asyncio.run(agent.run("Hello!"))

It caches skills by default, so restart the process after decimalai skills update.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/tooluniverse-rnaseq-deseq2/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/tooluniverse-rnaseq-deseq2/SKILL.md").read_text()
agent = Agent(client=client, instructions=f"You are a helpful agent.\n\n{skill}")
asyncio.run(agent.run("Hello!"))

This gets SKILL.md only. The skill's 12 other files are not included.

Other ways to add it

Microsoft Agent Framework docs

Strands' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" strands-agents
decimalai skills add tooluniverse-rnaseq-deseq2

Add it to your agent

from decimalai.strands import skills
from strands import Agent
from strands.vended_tools import file_editor, shell

agent = Agent(
    model=model,                # always pass one: the default is Amazon Bedrock
    system_prompt="You are a helpful agent.",
    tools=[file_editor, shell],
    plugins=[skills()],
)
agent("Hello!")

Strands loads an agent's skills once, so build the agent again after decimalai skills update.

The same install from Python, for a notebook or a setup script. Strands' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" strands-agents

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("tooluniverse-rnaseq-deseq2")
if result.exit_code:
    raise SystemExit(result.problems)

from decimalai.strands import skills
from strands import Agent
from strands.vended_tools import file_editor, shell

agent = Agent(
    model=model,                # always pass one: the default is Amazon Bedrock
    system_prompt="You are a helpful agent.",
    tools=[file_editor, shell],
    plugins=[skills()],
)
agent("Hello!")

Strands loads an agent's skills once, so build the agent again after decimalai skills update.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/tooluniverse-rnaseq-deseq2/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/tooluniverse-rnaseq-deseq2/SKILL.md").read_text()
agent = Agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent("Hello!")

This gets SKILL.md only. The skill's 12 other files are not included.

Other ways to add it

Strands docs

Adds every file the skill has, pinned so you can update it. Cursor, Copilot, Cline and Warp read this folder by themselves.

pip install "decimalai>=0.15"
decimalai skills add tooluniverse-rnaseq-deseq2

No Python or account. Cursor, Copilot, Cline and Warp read this folder by themselves.

Save it into your project

curl -fsSL --create-dirs -o .agents/skills/tooluniverse-rnaseq-deseq2/SKILL.md https://app.decimal.ai/s/tooluniverse-rnaseq-deseq2/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/tooluniverse-rnaseq-deseq2/SKILL.md

This gets SKILL.md only. The skill's 12 other files are not included.

Other ways to add it

Cursor and other editors docs

Fetch the file and give its text to your model as instructions. No account or package needed.

Get the file

curl -fsSL https://app.decimal.ai/s/tooluniverse-rnaseq-deseq2/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/tooluniverse-rnaseq-deseq2.json

This gets SKILL.md only. The skill's 12 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 7/26/2026
Source: FreedomIntelligence/OpenClaw-Medical-Skills ↗
License: Not recorded

Manage it in DecimalAI

Saved prompts and skills, pinned versions, and traces of this skill in your runs. DecimalAI does not run your agent.

Claude Code reads files from your project, so DecimalAI config does not apply there.

On Claude Agent SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI Agents: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Anthropic: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Gemini API: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On LangChain: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On CrewAI: set DECIMAL_API_KEY and add decimalai.init(crewai=True) to record runs and skill use. The skill version stays in your repo.

On Google ADK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Pydantic AI: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Deep Agents: set DECIMAL_API_KEY and add decimalai.init(langchain=True) to record runs and skill use. The skill version stays in your repo.

On Microsoft Agent Framework: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

On Strands: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

Editors read files from your project, so DecimalAI config does not apply there.

Anywhere else: record a use with decimalai.log_skill_activation() inside a trace.

Use this skill

SKILL.md

RNA-seq Differential Expression Analysis (DESeq2)

Comprehensive differential expression analysis of RNA-seq count data using PyDESeq2, with integrated enrichment analysis (gseapy) and gene annotation via ToolUniverse.

BixBench Coverage: Validated on 53 BixBench questions across 15 computational biology projects covering RNA-seq, miRNA-seq, and differential expression analysis tasks.

Core Principles

Data-first approach - Load and validate count data and metadata BEFORE any analysis
Statistical rigor - Always use proper normalization, dispersion estimation, and multiple testing correction
Flexible design - Support single-factor, multi-factor, and interaction designs
Threshold awareness - Apply user-specified thresholds exactly (padj, log2FC, baseMean)
Reproducible - Set random seeds, document all parameters, output complete results
Question-driven - Parse what the user is actually asking and extract the specific answer
Enrichment integration - Chain DESeq2 results into pathway/GO enrichment when requested
English-first queries - Use English gene/pathway names in all tool calls

When to Use This Skill

Apply when users:

Have RNA-seq count matrices and want differential expression analysis
Ask about DESeq2, DEGs, differential expression, padj, log2FC
Need dispersion estimates or diagnostics
Want enrichment analysis (GO, KEGG, Reactome) on DEGs
Ask about specific gene expression changes between conditions
Need to compare multiple strains/conditions/treatments
Ask about batch effect correction in RNA-seq
Questions mention "count data", "count matrix", "RNA-seq", "transcriptomics"

Required Packages

# Core (MUST be installed)
import pandas as pd
import numpy as np
from pydeseq2.dds import DeseqDataSet
from pydeseq2.ds import DeseqStats

# Enrichment (optional, for GO/KEGG/Reactome)
import gseapy as gp

# ToolUniverse (optional, for gene annotation)
from tooluniverse import ToolUniverse

Installation:

pip install pydeseq2 gseapy pandas numpy scipy anndata

Analysis Workflow

Step 1: Question Parsing

CRITICAL FIRST STEP: Before writing ANY code, parse the question to identify:

Data files: Look for *counts*.csv, *metadata*.csv, *.h5ad
Thresholds: Extract padj (default 0.05), log2FC (default 0), baseMean (default 0)
Design: Identify factors mentioned ("strain", "condition", "batch")
Contrast: Determine comparison ("A vs B", "mutant vs wildtype")
Direction: Check if "upregulated", "downregulated", or both
Enrichment: Look for "GO", "KEGG", "Reactome", "pathway"
Specific genes: Check if asking about individual genes

See references/question_parsing.md for detailed parsing patterns.

Step 1.5: Design Formula Decision Tree ⚠️ CRITICAL

ALWAYS inspect metadata for ALL variables, not just what the question mentions!

Many experiments have hidden batch effects (media conditions, sequencing batches, time points) that MUST be included as covariates. Failing to account for these reduces statistical power and can lead to incorrect results.

Decision process:

List ALL metadata columns (don't skip any!)
Categorize each column:
- Biological interest: The factor you're testing (strain, treatment, genotype, condition)
- Batch/Block: Systematic covariates (media, batch, sequencing_run, time, plate)
- Irrelevant: Sample IDs, notes, file names
Design formula:
- Single factor: ~condition (only if no batch variables exist)
- With covariates: ~batch1 + batch2 + condition (covariates first!)
- Interaction: ~batch + factor1 + factor2 + factor1:factor2

Example (critical real-world case):

Metadata columns: [Strain, Media, Replicate]
Question asks: "strain effects"

❌ WRONG: design="~Strain" (ignores Media!)
✅ CORRECT: design="~Media + Strain" (accounts for media variation)

Why: Even though question doesn't mention media, it systematically
affects expression. DESeq2 must remove media effects to properly test strain.

Rule of thumb: If a column has 2+ levels and represents an experimental condition (not sample ID), include it in design.

Step 2: Data Loading & Validation

Load count matrix and metadata, then validate alignment:

import pandas as pd
from scripts.load_count_matrix import load_count_matrix, validate_inputs

# Load data
counts = load_count_matrix("counts.csv")
metadata = pd.read_csv("metadata.csv", index_col=0)

# Validate and align
counts, metadata, issues = validate_inputs(counts, metadata)

Key considerations:

Ensure samples as rows, genes as columns (PyDESeq2 requirement)
Verify integer counts (round if needed)
Align sample names between counts and metadata
Remove zero-count genes

See references/data_loading.md for detailed data handling.

Step 2.5: Inspect Metadata Structure ⚠️ REQUIRED

Before choosing design formula, ALWAYS inspect metadata to identify all experimental factors:

# Print metadata structure
print("Metadata columns and levels:")
for col in metadata.columns:
    unique_vals = metadata[col].unique()
    print(f"  {col}: {len(unique_vals)} levels → {list(unique_vals)[:5]}")

# Example output:
#   Strain: 4 levels → ['1', '97', '98', '99']
#   Media: 3 levels → ['MMGluFeMinus', 'MMGluFePlus', 'Succinate']
#   Replicate: 3 levels → ['A', 'B', 'C']

# Decision:
#   - Strain: Biological factor (testing)
#   - Media: Batch/covariate (MUST include!)
#   - Replicate: Biological replicate (don't include as factor)
# Design: ~Media + Strain

This step prevents missing hidden batch effects that could invalidate your analysis.

Step 3: Run PyDESeq2

Execute differential expression analysis:

from pydeseq2.dds import DeseqDataSet
from pydeseq2.ds import DeseqStats

# Setup design (set reference level first)
metadata['condition'] = pd.Categorical(
    metadata['condition'],
    categories=['control', 'treatment']  # First = reference
)

# Run DESeq2
dds = DeseqDataSet(
    counts=counts,
    metadata=metadata,
    design="~condition",
    quiet=True
)
dds.deseq2()

# Extract results
stat_res = DeseqStats(dds, contrast=['condition', 'treatment', 'control'], quiet=True)
stat_res.run_wald_test()
stat_res.summary()

# Apply LFC shrinkage (if needed)
stat_res.lfc_shrink(coeff='condition[T.treatment]')

results = stat_res.results_df

Multi-Factor Design (Common Real-World Case)

When metadata has multiple experimental variables (e.g., strain + media conditions), ALWAYS include covariates:

# Inspect metadata (from Step 2.5) showed:
#   - Strain: 4 levels (factor of interest)
#   - Media: 3 levels (batch effect - MUST include!)

# Set reference levels for BOTH factors
metadata['media'] = pd.Categorical(
    metadata['media'],
    categories=['MMGluFeMinus', 'MMGluFePlus', 'Succinate']  # First = reference
)
metadata['strain'] = pd.Categorical(
    metadata['strain'],
    categories=['1', '97', '98', '99']  # First = reference (JBX1)
)

# Include covariate in design formula
dds = DeseqDataSet(
    counts=counts,
    metadata=metadata,
    design="~media + strain",  # Covariate first, then factor!
    quiet=True
)
dds.deseq2()

# Extract strain effect (controlling for media)
stat_res = DeseqStats(dds, contrast=['strain', '98', '1'], quiet=True)
stat_res.run_wald_test()
stat_res.summary()
results = stat_res.results_df

Why this matters: DESeq2 will model media effects separately, removing media-driven variance before testing strain differences. This increases statistical power and prevents false positives/negatives.

When to use what:

Python (PyDESeq2): Use for ALL DESeq2 analysis (normalization, testing, filtering)
ToolUniverse: Use ONLY for gene annotation (ID conversion, pathway context)
gseapy: Use for enrichment analysis (GO/KEGG/Reactome)

See references/pydeseq2_workflow.md for complete PyDESeq2 patterns including batch effects, interaction terms, and complex designs.

Step 4: Filter Results

Apply thresholds from the question:

# Filter DEGs
sig_genes = results[
    (results['padj'] < 0.05) &
    (results['log2FoldChange'].abs() > 0.5) &
    (results['baseMean'] > 10)
]

# Direction-specific filtering
up_genes = sig_genes[sig_genes['log2FoldChange'] > 0]
down_genes = sig_genes[sig_genes['log2FoldChange'] < 0]

Common filtering patterns:

Basic DEG count: len(sig_genes)
Specific gene value: results.loc['GENE_NAME', 'log2FoldChange']
Set operations: Use Python sets for "unique", "shared", "overlap"

See references/result_filtering.md for advanced filtering.

Step 5: Dispersion Analysis (if asked)

Access dispersion estimates:

# Get dispersion data
disp_data = dds.var  # Dispersions stored here

# Common question: "genes below threshold prior to fitting"
genewise = dds.var['genewise_dispersions']
count_below = (genewise < 1e-5).sum()

Dispersion column mapping:

"prior to fitting" → genewise_dispersions
"fitted dispersions" → fitted_dispersions
"after shrinkage" / "MAP" → MAP_dispersions
"final" → dispersions

See references/dispersion_analysis.md for diagnostics.

Step 6: Enrichment Analysis (optional)

Run pathway enrichment on DEGs:

import gseapy as gp

# Prepare gene list
gene_list = sig_genes.index.tolist()

# Run enrichment
enr = gp.enrich(
    gene_list=gene_list,
    gene_sets='GO_Biological_Process_2023',  # or KEGG, Reactome
    background=None,  # or specify background
    outdir=None,
    cutoff=0.05,
    no_plot=True,
    verbose=False
)

# Extract results
top_pathways = enr.results.head(10)

Library selection:

Human GO: GO_Biological_Process_2023
Mouse KEGG: KEGG_2019_Mouse
Human KEGG: KEGG_2021_Human
Reactome: Reactome_2022

See references/enrichment_analysis.md for complete enrichment workflows.

Step 7: Gene Annotation with ToolUniverse (optional)

Use ToolUniverse ONLY for gene annotation, not analysis:

from tooluniverse import ToolUniverse

tu = ToolUniverse()
tu.load_tools()

# Gene ID conversion
result = tu.tools.MyGene_query_genes(query="TP53")

# Gene details
result = tu.tools.ensembl_lookup_gene(
    gene_id="ENSG00000141510",
    species="homo_sapiens"
)

Do NOT use ToolUniverse for:

Differential expression (use PyDESeq2)
Statistical testing (use scipy.stats)
Enrichment analysis (use gseapy)

Output Formatting

Match the question's requested format:

# Numeric precision
round(value, 2)  # "2 decimal points"
f"{value:.2E}"   # "scientific notation"

# Percentages
f"{value * 100:.1f}%"  # "as percentage"

# Counts (no decimals)
int(len(sig_genes))  # "how many genes"

See references/output_formatting.md for all format patterns.

Common BixBench Patterns

Pattern 1: Basic DEG Count

Question: "How many genes show significant DE (padj < 0.05, |log2FC| > 0.5)?"

degs = results[(results['padj'] < 0.05) & (results['log2FoldChange'].abs() > 0.5)]
answer = len(degs)

Pattern 2: Specific Gene Value

Question: "What is the log2FC of gene X?"

answer = round(results.loc['GENE_X', 'log2FoldChange'], 2)

Pattern 3: Direction-Specific

Question: "How many genes are upregulated?"

up_degs = results[(results['padj'] < 0.05) & (results['log2FoldChange'] > 0)]
answer = len(up_degs)

Pattern 4: Set Operations

Question: "How many genes are uniquely DE in condition A?"

degs_A = set(results_A[results_A['padj'] < 0.05].index)
degs_B = set(results_B[results_B['padj'] < 0.05].index)
unique_A = degs_A - degs_B
answer = len(unique_A)

Pattern 5: Dispersion Count

Question: "How many genes have dispersion below 1e-5 prior to fitting?"

genewise = dds.var['genewise_dispersions']
answer = (genewise < 1e-5).sum()

See references/bixbench_examples.md for all 10 patterns with examples.

Error Handling

Error	Solution
"No matching samples"	Check if counts need transposing; strip whitespace
"Dispersion trend did not converge"	Use `fit_type='mean'`
"Contrast not found"	Check `metadata['factor'].unique()` for exact names
"Non-integer counts"	Round to integers OR use t-test for normalized data
"NaN in padj"	Independent filtering removed genes; exclude from counts

See references/troubleshooting.md for complete debugging guide.

Validation Checklist

Every analysis MUST include:

Data Loading:

Count matrix oriented correctly (samples as rows, genes as columns)
Metadata aligned with counts
Integer counts validated

DESeq2 Analysis:

Design formula matches question
Reference level set correctly (first in Categorical)
Correct contrast extracted

Results:

Thresholds match question exactly
Direction filter applied if specified
Answer formatted correctly (decimal places, notation)

Quality Checks:

DEG count is reasonable
P-values between 0 and 1
Log2FC values are finite

Known Limitations

PyDESeq2 vs R DESeq2 Differences

This skill uses PyDESeq2 (Python implementation) for differential expression analysis. While PyDESeq2 faithfully implements the DESeq2 algorithm, numerical differences exist between Python and R implementations:

Dispersion Estimation:

Dispersion estimates may differ from R DESeq2, especially for very low dispersion genes (< 1e-05)
This is due to different numerical optimization methods between Python and R statistical libraries
Results are still statistically valid and biologically meaningful
If you need exact R DESeq2 dispersions for benchmark reproducibility, consider using R DESeq2 directly via rpy2

For Most Analyses: PyDESeq2 provides accurate, publication-quality results. The differences are in numerical precision, not statistical validity.

GO/KEGG Enrichment (gseapy vs clusterProfiler)

Enrichment analysis uses Python gseapy by default. Results may differ from R clusterProfiler due to:

Different enrichment algorithms and statistical tests
Different GO/KEGG database versions
Different term simplification/redundancy removal methods

For R clusterProfiler Compatibility: If you need results matching R clusterProfiler exactly (e.g., for benchmark reproducibility):

# Install rpy2 and R packages first:
# pip install rpy2
# In R: install.packages(c("clusterProfiler", "org.Hs.eg.db", "enrichplot"))

from rpy2.robjects.packages import importr
from rpy2.robjects import pandas2ri, vectors
pandas2ri.activate()

# Load R packages
clusterProfiler = importr('clusterProfiler')
orgdb = importr('org.Hs.eg.db')

# Convert Python gene list to R vector
gene_list = sig_genes.index.tolist()
r_genes = vectors.StrVector(gene_list)

# Run enrichGO (R's clusterProfiler)
enrich_result = clusterProfiler.enrichGO(
    gene=r_genes,
    OrgDb=orgdb.org_Hs_eg_db,
    ont='BP',  # Biological Process
    pAdjustMethod='BH',
    pvalueCutoff=0.05,
    qvalueCutoff=0.2
)

# Apply simplify to remove redundant terms
simplified = clusterProfiler.simplify(enrich_result, cutoff=0.7, by='p.adjust')

# Convert R result back to pandas
results_df = pandas2ri.rpy2py(simplified)

Default behavior: Uses gseapy (no R dependencies required). This is sufficient for most analyses and provides valid enrichment results.

When to use R clusterProfiler:

When exact reproducibility with R-based benchmarks is required
When collaborating with R users who need identical results
When specific clusterProfiler features (GSEA, compareCluster) are needed

References

Detailed documentation for advanced topics:

question_parsing.md - Extract parameters from questions
data_loading.md - Data loading and validation patterns
pydeseq2_workflow.md - Complete PyDESeq2 code examples
result_filtering.md - Advanced filtering and extraction
dispersion_analysis.md - Dispersion diagnostics
enrichment_analysis.md - GO/KEGG/Reactome workflows
output_formatting.md - Format answers correctly
bixbench_examples.md - All 10 question patterns
troubleshooting.md - Common issues and debugging

Utility Scripts

Helper scripts for common tasks:

format_deseq2_output.py - Output formatters
load_count_matrix.py - Data loading utilities

When it activates

Automatically, when a task matches. Use when analyzing RNA-seq count matrices, identifying DEGs, performing differential expre

About this skill

Automatic

Data Analyst pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 7/30/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

FreedomIntelligence / OpenClaw-Medical-Skills

skills/tooluniverse-rnaseq-deseq2/SKILL.md

View on GitHub ↗

Imported 8/1/2026Version v1Bundled 12 files · scripts

Illustrative Want to see what tooluniverse-rnaseq-deseq2 would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

Related skills

Skills that do similar work, with their headline benchmark lift.

From the same source and nearby in the catalogue.

Ready to supercharge your AI agents?

SkillScore

Safety

What it changes

Track record

Use this skill

RNA-seq Differential Expression Analysis (DESeq2)

Core Principles

When to Use This Skill

Required Packages

Analysis Workflow

Step 1: Question Parsing

Step 1.5: Design Formula Decision Tree ⚠️ CRITICAL

Step 2: Data Loading & Validation

Step 2.5: Inspect Metadata Structure ⚠️ REQUIRED

Step 3: Run PyDESeq2

Multi-Factor Design (Common Real-World Case)

Step 4: Filter Results

Step 5: Dispersion Analysis (if asked)

Step 6: Enrichment Analysis (optional)

Step 7: Gene Annotation with ToolUniverse (optional)

Output Formatting

Common BixBench Patterns

Pattern 1: Basic DEG Count

Pattern 2: Specific Gene Value

Pattern 3: Direction-Specific

Pattern 4: Set Operations

Pattern 5: Dispersion Count

Error Handling

Validation Checklist

Known Limitations

PyDESeq2 vs R DESeq2 Differences

GO/KEGG Enrichment (gseapy vs clusterProfiler)

References

Utility Scripts

When it activates

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry