Mouse Phenome Database

pip install requests pandas matplotlib

import requests

MPD = "https://phenome.jax.org/api"

# 1) Pick a project (Jaxwest1 — cardiovascular phenotyping on inbred panel)
r = requests.get(f"{MPD}/projects/Jaxwest1/strains", timeout=30)
strains = r.json()["strains"]
print(f"Jaxwest1: {len(strains)} strains tested")

# 2) Discover its measures
r = requests.get(f"{MPD}/pheno/measureinfo/Jaxwest1", timeout=30)
measures = r.json()["measures_info"]
print(f"Jaxwest1 measures: {len(measures)}; first: measnum={measures[0]['measnum']} "
      f"varname={measures[0]['varname']}  ({measures[0]['descrip']}, {measures[0]['units']})")

# 3) Pull strain means for heart rate (varname=HR, measnum=15101)
r = requests.get(f"{MPD}/pheno/strainmeans/15101", timeout=30)
sm = r.json()["strainmeans"]
print(f"\nHeart rate strain means: {len(sm)} rows  (one per strain × sex)")
top = sorted(sm, key=lambda x: x["mean"], reverse=True)[:5]
for s in top:
    print(f"  {s['strain']:<20}  sex={s['sex']}  mean={s['mean']:.0f} {s.get('varname','')}  n={s['nmice']}")

import requests, pandas as pd

MPD = "https://phenome.jax.org/api"

# List allowed panel symbols (e.g., BXD, CC, DO)
filters = requests.get(f"{MPD}/project_filters/panelsym", timeout=30).json()
print(f"Available panels ({filters['count']}):", [t['term'] for t in filters['terms']][:10])

# All projects in the BXD recombinant inbred panel
r = requests.get(f"{MPD}/projects", params={"panelsym": "BXD"}, timeout=30)
projects = r.json()["projects"]
print(f"BXD projects: {len(projects)}")
df = pd.DataFrame([{
    "projsym": p["projsym"],
    "pi": p.get("pistring", "")[:40],
    "nstrains": p.get("nstrains"),
    "ages": p.get("ages"),
    "sector": p.get("mpdsector"),
    "title": (p.get("title") or "")[:60],
} for p in projects])
print(df.head(10).to_string(index=False))

# Filter by MPD sector — komp, pheno, qtla, snp, onestrain, phenoarchive
r = requests.get(f"{MPD}/projects", params={"mpdsector": "qtla"}, timeout=30)
qtl_projects = r.json()["projects"]
print(f"QTL-archive projects: {len(qtl_projects)}")
for p in qtl_projects[:5]:
    print(f"  {p['projsym']:<15} panel={p.get('panelsym') or '--':<6} nstrains={str(p.get('nstrains') or '--'):>4}  {(p.get('title') or '')[:55]}")

import requests, io, pandas as pd

MPD = "https://phenome.jax.org/api"

# Full per-animal dataset as CSV (default). Use json=yes for JSON.
r = requests.get(f"{MPD}/projects/Jaxwest1/dataset", timeout=60)
df = pd.read_csv(io.StringIO(r.text))
print(f"Jaxwest1 dataset: {df.shape[0]} animals × {df.shape[1]} columns")
print(df.columns[:12].tolist())
print(df[["strain", "sex", "animal_id", "HR", "QRS", "bw"]].head(5).to_string(index=False))

# Strains tested in a project + publication list
strains = requests.get(f"{MPD}/projects/Jaxwest1/strains", timeout=30).json()
print(f"Jaxwest1 strains ({strains['count']}):")
for s in strains["strains"][:5]:
    print(f"  {s['strainname']:<20}  stock={s['stocknum']}  vendor={s['vendor']}")

pubs = requests.get(f"{MPD}/projects/Jaxwest1/publications", timeout=30).json()
print(f"\nPublications: {pubs['count']}")

import requests, pandas as pd

MPD = "https://phenome.jax.org/api"

# All measures in the Jaxwest1 cardiovascular project
r = requests.get(f"{MPD}/pheno/measureinfo/Jaxwest1", timeout=30)
measures = r.json()["measures_info"]
df = pd.DataFrame([{
    "measnum": m["measnum"],
    "varname": m["varname"],
    "descrip": m["descrip"],
    "units": m.get("units"),
    "sex": m.get("sextested"),
    "age": m.get("ageweeks"),
} for m in measures])
print(f"Jaxwest1 has {len(df)} measures")
print(df.head(10).to_string(index=False))

# Single-measure metadata lookup (protocol + dimensional details)
r = requests.get(f"{MPD}/pheno/measureinfo/15101", timeout=30).json()
m = r["measures_info"][0]
print(f"measnum {m['measnum']} ({m['varname']}): {m['descrip']}")
print(f"  units: {m.get('units')}")
print(f"  project: {m.get('projsym')}  panel: {m.get('panelsym') or m.get('paneldesc')}")
print(f"  sex tested: {m.get('sextested')}  age: {m.get('ageweeks')}")
print(f"  method:  {(m.get('method') or '')[:120]}")

import requests, pandas as pd

MPD = "https://phenome.jax.org/api"

# Strain means for one measure (heart rate, measnum=15101 from Jaxwest1)
r = requests.get(f"{MPD}/pheno/strainmeans/15101", timeout=30)
sm = pd.DataFrame(r.json()["strainmeans"])
print(f"Rows: {len(sm)}  ({sm['strain'].nunique()} strains × {sm['sex'].nunique()} sexes)")

# Rank strains by male HR
male = sm[sm["sex"] == "m"].sort_values("mean", ascending=False)
print(male[["strain", "mean", "sd", "sem", "nmice", "zscore"]].head(8).to_string(index=False))

# Optional: model-adjusted means (lsmeans) account for covariates fit in MPD's models.
# Use lsmeans when comparing strains across cohorts within a project.
r = requests.get(f"{MPD}/pheno/lsmeans/Jaxwest1", timeout=30).json()
print("LS-mean measures available for Jaxwest1:", r.get("ls_measures", [])[:10])

import requests, pandas as pd

MPD = "https://phenome.jax.org/api"

# Per-animal heart rate values
r = requests.get(f"{MPD}/pheno/animalvals/15101", timeout=30)
ad = pd.DataFrame(r.json()["animaldata"])
print(f"Animals measured: {len(ad)}")
print(ad[["animal_id", "strain", "sex", "value", "zscore"]].head(8).to_string(index=False))

# Compare male-only strain distributions
male = ad[ad["sex"] == "m"]
stats = male.groupby("strain")["value"].agg(["mean", "std", "count"]).round(2)
print(f"\nMale HR by strain (top 5 by mean):")
print(stats.sort_values("mean", ascending=False).head(5))

import requests, pandas as pd

MPD = "https://phenome.jax.org/api"

# MP:0001262 = "decreased body weight"
r = requests.get(f"{MPD}/pheno/measures_by_ontology/MP:0001262",
                 params={"omit_baseline": "yes", "collapse_series": "yes"},
                 timeout=30).json()
print(f"Measures mapped to MP:0001262 ('{r['ontology_terms'][0]['descrip']}'): {r['count']}")
if r["count"]:
    df = pd.DataFrame(r["measures"])
    print(df[["measnum", "varname", "descrip", "projsym"]].head(8).to_string(index=False))
else:
    print("(no direct measures; consider a broader parent term)")

import requests

MPD = "https://phenome.jax.org/api"

# Validate C57BL/6J — note `requests` URL-encodes the slash automatically in params
r = requests.get(f"{MPD}/straininfo", params={"name": "C57BL/6J"}, timeout=30).json()
jax = r["jaxinfo"][0]
mpd = r["mpdinfo"][0]
print(f"JAX:  {jax['nomenclature']}  stock={jax['stocknum']}  status={jax['avl_status']}")
print(f"MPD:  longname={mpd['longname']}  type={mpd['straintype']}  "
      f"projects={mpd['nproj']}  snp_projects={mpd['nsnpproj']}  MGI={mpd['mginum']}")

import requests

MPD = "https://phenome.jax.org/api"

r = requests.get(f"{MPD}/geneinfo/Lep", timeout=30).json()
for g in r["gene info"]:
    print(f"{g['descrip']}  chr{g['chrom']}:{g['startbp']:,}–{g['endbp']:,} ({g['strand']})")
    print(f"  type: {g['featuretype']}  MGI: {g['mginum']}  cM: {g['centimorgan']}")

import requests, pandas as pd, time

MPD = "https://phenome.jax.org/api"

# 1) Find candidate projects whose name/description hints at the trait
projects = requests.get(f"{MPD}/projects", timeout=30).json()["projects"]
candidates = [p for p in projects
              if any(kw in (p.get("title") or "").lower()
                     for kw in ["cardiovascular", "heart", "ekg", "ecg"])]
print(f"Candidate cardiovascular projects: {len(candidates)}")
for p in candidates[:5]:
    print(f"  {p['projsym']:<15}  nstrains={str(p.get('nstrains') or '--'):>3}  {(p.get('title') or '')[:60]}")

# 2) Inspect measures for the chosen project
projsym = "Jaxwest1"
mi = requests.get(f"{MPD}/pheno/measureinfo/{projsym}", timeout=30).json()["measures_info"]
hr = next(m for m in mi if m["varname"] == "HR")
print(f"\nPicked: {projsym} measnum={hr['measnum']} varname={hr['varname']} ({hr['descrip']}, {hr['units']})")

# 3) Pull strain means, plot male strains ranked
sm = pd.DataFrame(requests.get(f"{MPD}/pheno/strainmeans/{hr['measnum']}", timeout=30).json()["strainmeans"])
male = sm[sm["sex"] == "m"].sort_values("mean", ascending=False).reset_index(drop=True)
male.to_csv("mpd_strain_means.csv", index=False)
print(f"Strain means (male): {len(male)} strains -> mpd_strain_means.csv")
# Render with the omics-plotting SKILL (`skills/data-visualization/omics-plotting/SKILL.md`) "Box / Violin / Bar" recipe (bar of mean by strain,
# yerr=sem) -> figures/mpd_strain_means.png

import requests, pandas as pd

MPD = "https://phenome.jax.org/api"

measnum = 15101  # heart rate in Jaxwest1
mi = requests.get(f"{MPD}/pheno/measureinfo/{measnum}", timeout=30).json()["measures_info"][0]
ad = pd.DataFrame(requests.get(f"{MPD}/pheno/animalvals/{measnum}", timeout=30).json()["animaldata"])
print(f"measnum {measnum}: {mi['varname']} ({mi['descrip']}, {mi['units']}) — {len(ad)} animals")

# R/qtl2-ready phenotype CSV: rows = individuals, cols = id + covariates + phenotype
out = ad[["animal_id", "strain", "sex", "value"]].rename(
    columns={"animal_id": "id", "value": mi["varname"]}
)
out.to_csv(f"{measnum}_{mi['varname']}_qtl_pheno.csv", index=False)
print(f"Wrote {measnum}_{mi['varname']}_qtl_pheno.csv  ({len(out)} animals)")
print(out.head().to_string(index=False))

import requests, pandas as pd

MPD = "https://phenome.jax.org/api"
projsym = "Jaxwest1"

# Pull all strain means for the project in one call
sm = pd.DataFrame(requests.get(f"{MPD}/pheno/strainmeans/{projsym}", timeout=30).json()["strainmeans"])

# Use the precomputed z-scores; pivot to strain × varname (male only for simplicity)
male = sm[sm["sex"] == "m"]
wide = male.pivot_table(index="strain", columns="varname", values="zscore", aggfunc="mean")
print(f"Shape: {wide.shape}  (strains × measures)")

# Subset to a handful of measures with full coverage
keep = wide.dropna(axis=1, thresh=int(0.8 * len(wide))).columns[:10]
wide = wide[keep].dropna()
print(f"After coverage filter: {wide.shape}")
wide.to_csv("mpd_strain_measure_matrix.csv")
# Render with the omics-plotting SKILL (`skills/data-visualization/omics-plotting/SKILL.md`) "Expression heatmap" recipe (strain x measure z-score,
# RdBu_r, center=0) -> figures/mpd_strain_measure_heatmap.png