Ready to supercharge your AI agents?

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

Peptide Target Deorphanization · mims-harvard | DecimalAI

Scienceby mims-harvard

Peptide Target Deorphanization

Find the real protein target(s) of a peptide from its sequence — peptide target deorphanization / off-target identification, for ANY target class (GPCR, ion channel, protease, cytokine/growth-factor receptor, enzyme, integrin), not only GPCRs.

Never made a case worseMaintained

SkillScore

SkillScore77/100

Test results 77

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

23%77%of test cases passed +55 pts

Without skill5 of 22

With skill17 of 22

12 fixed5 passed either way5 still failing0 broke

Model 8/2/2026v2 · latest is v319 comparable

This benchmark measured an earlier version of the skill.

A newer attempt on gemini-3.8-flash on 11/1/2026 did not produce a publishable comparison (graded differently). The snapshot above is the previously measured run.

Track record

Agent runs: 0; All time
Forks: 1

See one task, with and without the skill

One test taskA 25-amino-acid peptide isolated from spider venom (sequence: DCLGWFKSCDPKNDKCCKNYTCSRR) shows paralysis in insect assays. When predicting targets, should the search be seeded exclusively with GPCR gene families like GLP1R or ADRB2?

Without the skillMissed

With the skillPassed

Same model, same task. Answers are capped and redacted.

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-peptide-target-deorphanization
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-peptide-target-deorphanization")
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-peptide-target-deorphanization

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-peptide-target-deorphanization/SKILL.md https://app.decimal.ai/s/tooluniverse-peptide-target-deorphanization/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/tooluniverse-peptide-target-deorphanization/SKILL.md

This gets SKILL.md only. The skill's 3 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-peptide-target-deorphanization

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-peptide-target-deorphanization")
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-peptide-target-deorphanization/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-peptide-target-deorphanization/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 3 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-peptide-target-deorphanization

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-peptide-target-deorphanization")
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-peptide-target-deorphanization/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/tooluniverse-peptide-target-deorphanization/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 3 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-peptide-target-deorphanization

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-peptide-target-deorphanization")
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-peptide-target-deorphanization/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/tooluniverse-peptide-target-deorphanization/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 3 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-peptide-target-deorphanization

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-peptide-target-deorphanization")
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-peptide-target-deorphanization/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/tooluniverse-peptide-target-deorphanization/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 3 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-peptide-target-deorphanization

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-peptide-target-deorphanization")
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-peptide-target-deorphanization/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-peptide-target-deorphanization/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 3 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-peptide-target-deorphanization

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-peptide-target-deorphanization")
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-peptide-target-deorphanization/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/tooluniverse-peptide-target-deorphanization/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 3 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-peptide-target-deorphanization

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-peptide-target-deorphanization")
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-peptide-target-deorphanization/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 3 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-peptide-target-deorphanization

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-peptide-target-deorphanization")
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-peptide-target-deorphanization/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/tooluniverse-peptide-target-deorphanization/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 3 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-peptide-target-deorphanization

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-peptide-target-deorphanization")
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-peptide-target-deorphanization/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/tooluniverse-peptide-target-deorphanization/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 3 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-peptide-target-deorphanization

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-peptide-target-deorphanization")
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-peptide-target-deorphanization/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/tooluniverse-peptide-target-deorphanization/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 3 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-peptide-target-deorphanization

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-peptide-target-deorphanization")
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-peptide-target-deorphanization/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/tooluniverse-peptide-target-deorphanization/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 3 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-peptide-target-deorphanization

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-peptide-target-deorphanization")
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-peptide-target-deorphanization/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/tooluniverse-peptide-target-deorphanization/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 3 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-peptide-target-deorphanization

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-peptide-target-deorphanization/SKILL.md https://app.decimal.ai/s/tooluniverse-peptide-target-deorphanization/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/tooluniverse-peptide-target-deorphanization/SKILL.md

This gets SKILL.md only. The skill's 3 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-peptide-target-deorphanization/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/tooluniverse-peptide-target-deorphanization.json

This gets SKILL.md only. The skill's 3 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v3 (v2 tested 8/2/2026)
Source: mims-harvard/ToolUniverse ↗
License: Apache-2.0

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

Peptide Target Deorphanization

Deorphanize a peptide: given a peptide sequence plus an observed phenotype (and often a hypothesized target the peptide does NOT actually bind), find its likely real protein target(s) — using ToolUniverse's keyless characterization, homology, target-family, phenotype, cross-species, and (optional, key-gated) co-folding tools.

The target can be anything, not just a GPCR. A target-class router (GPCR ligand / ion-channel toxin / protease target / cytokine or growth-factor receptor / integrin ligand / antimicrobial / unknown) classifies the peptide up front and adapts the enumeration strategy. GPCRs are the best-trodden case (and the validated control), but the pipeline's spine — homology, motif, phenotype, cross-species, co-fold — is target-class-agnostic, and family enumeration uses HGNC gene-family (general) + InterPro (general) + GPCRdb (GPCR-only cross-check).

Core reasoning: LOOK UP, DON'T GUESS

The failure mode this skill defends against is guessing a target from the peptide's name or its assumed mechanism. A peptide can be phenotypically active yet not bind the hypothesized target — because it hits a paralog, a different family member, or the same receptor in a different species whose binding interface has diverged. So:

Never assert a target from memory. Every candidate must come from a tool result (homology hit, family enumeration, phenotype association, or structural co-fold), with the tool name and accession recorded.
Anchor on PHENOTYPE × STRUCTURE/SEQUENCE plausibility, not on the peptide's reputed mechanism. The real target is the intersection of (a) what the sequence/motif/structure says it could bind and (b) what the phenotype says is biologically relevant. A name-level guess ("it's a GLP-1 analog so it's GLP1R") is exactly what produces off-target errors.
Reconcile across species. "Binds in species A but not B" is usually interface sequence divergence, not a different target. Always pull the ortholog set and align the candidate receptor's ligand-binding interface across the assay species before concluding the peptide "doesn't work."
A non-binding result against the hypothesized target is a clue, not a dead end. It promotes the paralogs and phenotype-shared receptors to the top of the candidate list.

This skill is built on validated, mostly keyless tools (BLAST, ELM/PROSITE, GPCRdb/HGNC/GtoPdb, OpenTargets, EnsemblCompara/Alliance). The single key-gated step is the optional structural confirmation by co-folding (NVIDIA NIM), used only to rank an already-narrowed shortlist.

Automated pipeline (scripts) — the fast path

Two runnable scripts in scripts/ execute the whole pipeline so you don't have to chain the phase calls by hand. Both load ToolUniverse via the SDK and run from the repo root.

`deorphanize_peptide.py` — keyless candidate generation + ranking (Phases 1–4)

No API key. For each peptide it characterizes it (PepCalc/ProtParam), flags non-canonical/cyclic residues, scans PROSITE + ELM signatures, flags protease/degradation liability, classifies the target class (GPCR / channel / protease / cytokine-receptor / integrin / …) and enumerates the candidate target family accordingly, anchors on phenotype (OpenTargets), and — for the top candidates — resolves the ortholog protein sequences and aligns the binding interface across human / assay-species / source-species (the mechanistic "binds in A, not B" step) and suggests a ClusPro-ready PDB structure. Prints a ranked candidate shortlist with evidence tiers.

python3 scripts/deorphanize_peptide.py \
  --sequence <PEPTIDE_SEQ> \             # OR  --fasta peptides.fasta  for BATCH mode
  --hypothesized-target <GENE> \         # optional; seeds family enumeration (e.g. GLP1R). OMIT for SEEDLESS mode
  --phenotype "<disease name>" \         # optional, REPEATABLE; OpenTargets anchor (use the DISEASE node, not a symptom) — pass several to union plausible phenotypes
  --assay-species mus_musculus \         # species of the NEGATIVE binding assay
  --source-species <organism> \          # optional; species where binding WAS observed -> 3-way interface alignment
  [--no-blast] [--out result.json]

Modes:

Seeded (--hypothesized-target GLP1R) — enumerate that gene's family as the candidate panel (cleanest). Even seeded, the sequence-derived candidates (below) are always unioned in, so a wrong hypothesized seed cannot blind the search to the real target's family — exactly the deorphanization premise.
Seedless (omit it) — derive candidate targets from PROSITE and BLAST-homolog keywords × the target-class nouns (e.g. receptor/channel/protease, chosen by the router) via UniProt; degrades to phenotype-only if that resolver is transiently down. No longer receptor-only.
Multi-phenotype — --phenotype is repeatable; pass every plausible disease and the anchor is the union (max score per target). Best when you don't know the single right phenotype.
Batch (--fasta) — one record per FASTA entry, sharing --phenotype/--assay-species.

Extra signals it always reports:

Target class — the router's call (gpcr_ligand / ion_channel_toxin / protease_inhibitor_or_substrate / cytokine_or_growth_factor / integrin_ligand / guanylyl_cyclase_ligand / antimicrobial / unknown) with the evidence that triggered it and the seedless nouns it selected. This is what makes the skill general rather than GPCR-only.
DPP4 / protease liability — a peptide can be assay-negative because it is cleaved, not because it fails to bind. Native GLP-1 (A@P2) is DPP4-LABILE; exendin-4 (G@P2) is resistant. A labile flag triggers a "re-test with a DPP4 inhibitor or protease-resistant analog" note — a key alternative explanation for "works in vitro, not in the mouse assay."
ELM LIG motifs (ranked by rarity) + the Pfam binding domain each engages — low-confidence context for peptides without a named PROSITE family.
Non-canonical / cyclic flag — any residue outside the 20 standard L-amino acids is surfaced, because BLAST/PROSITE/ProtParam silently assume a canonical linear peptide and will mischaracterize a non-ribosomal/cyclic peptide (common for unicellular-organism natural products). Look such peptides up by name with Norine_get_peptide and pass --cyclic to cofold_screen.py.
Cross-species interface alignment (top ≤3 candidates) — resolves each candidate's human + assay-species (+ optional source-species) ortholog sequence (UniProt) and aligns them (EBI_msa_align), reporting per-pair % identity and substitution count. A low human-vs-assay identity flags the ortholog whose binding interface most plausibly diverged — the mechanistic answer to "binds in A, not B". If the source organism is a protist absent from UniProt, it reports insufficient and tells you to supply the partner sequence by hand.
ClusPro-ready PDB (top ≤3 candidates) — PDBeSIFTS_get_best_structures resolves a representative solved PDB id you can feed straight to ClusPro_submit_peptide_docking.

Validated on the control (--sequence HGEGTFTSDLSKQMEEEAVRLFIEWLKNGGPSSGAPPPS --hypothesized-target GLP1R --phenotype "type 2 diabetes mellitus"): recovers the class-B panel {GCGR, GHRHR, GIPR, GLP1R, GLP2R, SCTR}, flags GLP1R as hypothesized (tested negative), and promotes GIPR to Tier 1 (family + phenotype, score 0.674) as the leading real-target hypothesis — exactly the deorphanization re-ranking, produced with zero API keys.

`cofold_screen.py` — structural confirmation (Phase 5, key-gated)

Co-folds the peptide against each shortlisted receptor and ranks by interface confidence (ipTM). Requires NVIDIA_API_KEY; without it, runs a DRY RUN that still resolves every receptor sequence (GPCRdb → UniProt fallback) and prints the co-fold plan, so you can verify inputs before paying for GPU time.

python3 scripts/cofold_screen.py --peptide <SEQ> --candidates GIPR GCGR GLP2R \
  [--backend boltz2|alphafold2_multimer|openfold3] [--assay-species mus_musculus] [--out cofold.json]

Use the scripts for the fast path. When you need to run, debug, or extend a single step by hand, the full per-phase manual reference — every tool call the scripts automate, with exact parameter names, gotchas, fallback chains, runtime notes, and two fully worked examples — lives in references/phases.md. Read it when a script step fails, when you want to drive a phase manually, or when you extend the pipeline to a new tool.

The pipeline at a glance

Six phases; the scripts automate 1–4 (and the Phase-5 dry run). Full detail + exact tool calls + gotchas are in references/phases.md — read it before driving any phase by hand.

Phase	What it does	Key tools
0 Verify	Confirm every tool loads; substitute fallbacks	`tooluniverse.cli run …`
1 Characterize + motif + classify	Properties, non-canonical/cyclic flag, PROSITE/ELM signature → ligand family, target-class router (GPCR/channel/protease/cytokine/integrin/…)	`PepCalc`/`ProtParam`, `ScanProsite`→`PROSITE_get_entry`, `ELM_*`, `ESMFold`
2 Candidate generation	4 independent routes — homology, motif→domain, target-family enumeration (class-aware), phenotype anchor → union	`BLAST`/`EBI_msa_align`, `HGNC`+`InterPro`+`GPCRdb`+`GtoPdb`, `OpenTargets`
3 Cross-species	Resolve "binds in A not B": align the ortholog interface across human / assay / source species	`EnsemblCompara`, `Alliance`, `UniProt`, `EBI_msa_align`
4 Narrow + rank	Score on sequence × phenotype × pharmacology × cross-species → shortlist ≤15	(intersection logic)
5 Structural confirm (optional, key-gated)	Co-fold top candidates, rank by interface ipTM; or academic-free ClusPro docking	`NvidiaNIM_boltz2`/`…`, `ClusPro_submit_peptide_docking`
6 Report	Ranked shortlist with evidence tiers + wet-lab plan	(inline report)

Core intersection rule: the real target is where phenotype-plausible (Route 2D) meets sequence/structure-plausible (Routes 2A–2C). A name-level guess ("it's a GLP-1 analog so it's GLP1R") is exactly what produces off-target errors — never assert a target the union of routes didn't surface.

Output format — ranked shortlist report (return inline, no extra files)

Peptide characterization — length, MW, pI, GRAVY, instability, PROSITE/ELM signature, non-canonical/cyclic flag, fold confidence (if run).
Ranked candidate table — one row per candidate target: gene + accession · target class · evidence tier · routes that surfaced it · OpenTargets phenotype score · known-pharmacology note (GtoPdb peptide ligands?) · cross-species status (ortholog_one2one? interface % identity in the assay species?).
Cross-species reconciliation note — for the lead, the human-vs-assay(-vs-source) interface comparison and what it predicts for "binds A not B."
Recommended wet-lab validation — binding/competition + a class-appropriate functional assay against the top ≤3 candidates and their assay-species orthologs (cAMP/β-arrestin for GPCRs; electrophysiology for channels; enzymatic/inhibition for proteases; reporter for cytokine receptors), with the GtoPdb-listed family antagonist as control where one exists.

Evidence tiers — always state which evidence is keyless/validated vs key-gated (co-fold not run), and flag any candidate that is a negative against the originally hypothesized target so the reader sees the re-ranking:

Tier 1 (strong): ≥2 independent sequence/structure routes AND present in the phenotype anchor AND (if Phase 5 run) top interface ipTM.
Tier 2 (moderate): 1 sequence/structure route + phenotype support, OR ≥2 sequence routes without phenotype.
Tier 3 (weak/hypothesis): single-route only (deep paralog, or a phenotype-only hit not corroborated by sequence/structure).

Peptide Bioactivity Property Databases (supplementary characterization)

Separate from target deorphanization itself, ToolUniverse has 7 small, single-property peptide databases. None of them tell you what a peptide's target is — they each answer a narrower "does this peptide have property X" question, useful as supplementary evidence once a peptide is on your radar (e.g. flagging a candidate as also hemolytic/toxic before recommending it, or checking measured half-life before a stability claim). Query the one matching the property you actually need — searching all 7 for every peptide is wasted effort.

Database	Tools	Property covered	Search fields
DBAASP	`DBAASP_search_peptides`, `DBAASP_get_peptide`	Antimicrobial activity — per-target MIC values, terminus modifications, structure	`sequence`, `name`, `target_species`, `target_group`, `kingdom`, `uniprot`, `dbaasp_id`
AMPSphere	`AMPSphere_search_amps`, `AMPSphere_get_family`, `AMPSphere_get_amp_distributions`, `AMPSphere_get_amp_features`	Antimicrobial peptides predicted from 863K+ prokaryotic metagenomic smORFs — family clustering, geographic/ecological distribution, physicochemical features (MW, pI, charge, molar extinction)	`habitat`, `family`, `microbial_source`, `pep_length_interval`, `mw_interval`, `charge_interval`, or a specific `accession`
ConoServer	`ConoServer_search_conopeptides`, `ConoServer_get_conopeptide`	Cone-snail venom peptides (conotoxins) — sequence, PTMs, cysteine framework, gene superfamily, pharmacological family	`name`, `sequence`, `pharmacological_family`, `gene_superfamily`, `cysteine_framework`, `organism`, or `conoserver_id`
Hemolytik 2.0	`Hemolytik2_search_peptides`	Experimentally validated hemolytic/toxic activity	`dataType` in `{nature, source, seq}` + `dataValue` — no name-based search; use `seq` for a sequence/substring query
CancerPPD 2.0	`CancerPPD2_search_peptides`	Experimentally validated anticancer activity, by cancer type / cell line	`dataType` in `{cancer_type, cell_line, seq}` + `dataValue`
TumorHoPe 2	`TumorHope2_search_peptides`	Tumor-homing peptides used in drug delivery	`source`, `target_tumor`, `name_source`, `conjugate` (all optional filters)
PEPlife 2.0	`PEPlife2_search_peptides`	Experimentally measured half-life / proteolytic stability	`dataType` in `{lin_cyc, org, seq}` + `dataValue` — no name-based search, same pattern as Hemolytik2

Verified live behavior worth knowing before you rely on these:

Hemolytik2 and PEPlife2 both reject a name/dataType value outside their fixed enum ({nature, source, seq} and {lin_cyc, org, seq} respectively) — there is no cross-database "search by peptide name" here except DBAASP, ConoServer, and TumorHope2's name_source. If you only have a name, search DBAASP/TumorHope2 first, or search by seq if you have the sequence.
The seq filter on Hemolytik2/PEPlife2/CancerPPD2 is a loose substring/fragment match, not an exact-sequence lookup — querying a well-known peptide's full sequence can return unrelated peptides that merely share a short subsequence. Always check the returned seq field actually matches before treating a hit as the peptide you queried.
ConoServer_search_conopeptides was found live-broken at the time of writing — the underlying bulk XML download (conoserver.org/download/conoserver_protein.xml.gz) returned HTTP 403 on every attempt (3/3 in tu test, repeated manual retries also failed), and ConoServer_get_conopeptide (which loads the same bulk file) also failed on manual retry after passing once under tu test's cached run. Treat ConoServer as currently unreliable — check its live status with a cheap call before depending on it, and do not fabricate a conopeptide record if it 403s.
The other 6 databases (DBAASP, AMPSphere, Hemolytik2, CancerPPD2, TumorHope2, PEPlife2) were confirmed live and working at the time of writing.

Validation & test set

Validated on the exendin-4 → GLP1R control: recovers the class-B panel {GCGR, GHRHR, GIPR, GLP1R, GLP2R, SCTR}, flags GLP1R as the (negative) hypothesized target, and promotes GIPR to Tier 1 — the deorphanization re-ranking, produced with zero API keys. The full step-by-step (control and the real "binds in the source organism, not in mouse" case) is in references/phases.md.

Reproducible test prompts + checkable assertions are in evals/evals.json (the exendin-4 control, the source-organism/mouse-negative case, and a non-GPCR seedless case). To check the skill still behaves, run a prompt through it and verify the output against that eval's assertions.

When it activates

Only when you call it by name. Your agent never loads it on its own. Use when a peptide has a phenotype but does not bind its hypothesized target, when a peptide binds a target in one species or assay but not another, or to screen candidate targets for an orphan peptide. A target-class router steers a multi-route keyless pi

About this skill

On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.

Research pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v8 — 10/29/2026

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

mims-harvard / ToolUniverse

skills/tooluniverse-peptide-target-deorphanization/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 10/29/2026Version v3Bundled 3 files · scripts

Illustrative Want to see what tooluniverse-peptide-target-deorphanization 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.

mims-harvard/tooluniverse-peptide-target-deorphanizationFind the real protein target(s) of a peptide from its sequence — peptide target deorphanization / off-target identification, for ANY target class (GPCR, ion channel, protease, cytokine/growth-factor receptor, enzyme, integrin), not only GPCRs. Use when a peptide has a phenotype but does not bind its hypothesized target, when a peptide binds a target in one species or assay but not another, or to screen candidate targets for an orphan peptide. A target-class router steers a multi-route keyless piNear-identical description+36 pts pass-rate 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

Peptide Target Deorphanization

Core reasoning: LOOK UP, DON'T GUESS

Automated pipeline (scripts) — the fast path

deorphanize_peptide.py — keyless candidate generation + ranking (Phases 1–4)

cofold_screen.py — structural confirmation (Phase 5, key-gated)

The pipeline at a glance

Output format — ranked shortlist report (return inline, no extra files)

Peptide Bioactivity Property Databases (supplementary characterization)

Validation & test set

When it activates

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry

`deorphanize_peptide.py` — keyless candidate generation + ranking (Phases 1–4)

`cofold_screen.py` — structural confirmation (Phase 5, key-gated)