Pride Database

pip install requests pandas matplotlib

import requests

PRIDE = "https://www.ebi.ac.uk/pride/ws/archive/v3"

# 1) Free-text search for cancer proteomics projects
projects = requests.get(f"{PRIDE}/search/projects",
                        params={"keyword": "prostate cancer", "pageSize": 5},
                        timeout=30).json()
print(f"Top {len(projects)} projects:")
for p in projects[:3]:
    instr = ", ".join(p.get("instruments", []))[:50]
    print(f"  {p['accession']}  {(p['title'] or '')[:70]}  [{instr}]")

# 2) Drill into one project
acc = projects[0]["accession"]
proj = requests.get(f"{PRIDE}/projects/{acc}", timeout=30).json()
print(f"\n{proj['accession']}: {proj['title'][:70]}")
print(f"  Submitted: {proj.get('submissionDate')}  DOI: {proj.get('doi')}")
print(f"  Organisms: {[o['name'] for o in proj.get('organisms', [])]}")
print(f"  Instruments: {[i['name'] for i in proj.get('instruments', [])]}")

# 3) List files and total size
files = requests.get(f"{PRIDE}/projects/{acc}/files/all", timeout=60).json()
total_mb = sum(f.get("fileSizeBytes", 0) for f in files) / 1e6
print(f"\n  {len(files)} files, {total_mb:.0f} MB total")

import requests, pandas as pd

PRIDE = "https://www.ebi.ac.uk/pride/ws/archive/v3"

def search_projects(keyword=None, organism=None, instrument=None,
                    disease=None, software=None,
                    page_size=25, page=0, sort_field="submission_date",
                    sort_direction="DESC"):
    """Search PRIDE v3 for projects.
    Filter syntax (for the `filter` arg) is `field==value, field==value` using `_facet` field names
    that are discoverable via /facet/projects."""
    filters = []
    if organism:   filters.append(f"organisms_facet=={organism}")
    if instrument: filters.append(f"instruments_facet=={instrument}")
    if disease:    filters.append(f"diseases_facet=={disease}")
    if software:   filters.append(f"softwares_facet=={software}")

    params = {"pageSize": page_size, "page": page,
              "sortFields": sort_field, "sortDirection": sort_direction}
    if keyword: params["keyword"] = keyword
    if filters: params["filter"] = ",".join(filters)

    r = requests.get(f"{PRIDE}/search/projects", params=params, timeout=30)
    r.raise_for_status()
    return r.json()   # plain list[dict]

projects = search_projects(keyword="cancer", organism="Homo sapiens (human)",
                           instrument="Q Exactive", page_size=5)
df = pd.DataFrame([{
    "accession": p["accession"],
    "title": (p.get("title") or "")[:70],
    "submission_date": p.get("submissionDate"),
    "diseases": ", ".join(p.get("diseases", []))[:60],
    "instruments": ", ".join(p.get("instruments", []))[:50],
} for p in projects])
print(df.to_string(index=False))

# Paginate through all matches for a keyword. The API doesn't return total counts inline;
# walk pages until the next one is empty.
def search_all_projects(keyword, page_size=100, max_pages=20):
    all_records, page = [], 0
    while page < max_pages:
        batch = search_projects(keyword=keyword, page_size=page_size, page=page)
        if not batch:
            break
        all_records.extend(batch)
        if len(batch) < page_size:
            break    # last page
        page += 1
    return all_records

results = search_all_projects("phosphoproteomics", page_size=100, max_pages=3)
print(f"Phosphoproteomics projects collected (max 300): {len(results)}")

import requests, pandas as pd

PRIDE = "https://www.ebi.ac.uk/pride/ws/archive/v3"

def get_facets(keyword=None, facet_page_size=20):
    """Return facet counts for projects matching `keyword`. Keys are facet groups
    (instruments, organisms, diseases, softwares, experimentTypes, ...); values are
    dicts of {value: count}."""
    params = {"facetPageSize": facet_page_size}
    if keyword: params["keyword"] = keyword
    r = requests.get(f"{PRIDE}/facet/projects", params=params, timeout=30)
    r.raise_for_status()
    return r.json()

facets = get_facets(keyword="cancer", facet_page_size=10)
print(f"Facet groups: {list(facets.keys())}")
print(f"\nTop instruments for 'cancer':")
for instr, n in sorted(facets.get("instruments", {}).items(), key=lambda kv: -kv[1])[:8]:
    print(f"  {instr:<35} {n}")
print(f"\nTop diseases:")
for d, n in sorted(facets.get("diseases", {}).items(), key=lambda kv: -kv[1])[:6]:
    print(f"  {d:<55} {n}")

import requests

PRIDE = "https://www.ebi.ac.uk/pride/ws/archive/v3"

def get_project(accession):
    r = requests.get(f"{PRIDE}/projects/{accession}", timeout=30)
    r.raise_for_status()
    return r.json()

p = get_project("PXD004131")
print(f"Accession    : {p['accession']}")
print(f"Title        : {p['title'][:80]}")
print(f"Submission   : {p.get('submissionDate')}")
print(f"Publication  : {p.get('publicationDate')}")
print(f"DOI          : {p.get('doi')}")
print(f"License      : {p.get('license')}")
print(f"Type         : {p.get('submissionType')}")
print(f"Organisms    : {[o['name'] for o in p.get('organisms', [])]}")
print(f"Instruments  : {[i['name'] for i in p.get('instruments', [])]}")
print(f"Experiment   : {[e['name'] for e in p.get('experimentTypes', [])]}")
print(f"PIs          : {[pi.get('name') for pi in p.get('labPIs', [])]}")
print(f"References   : {[r.get('doi') for r in p.get('references', [])[:3]]}")

import requests, pandas as pd

PRIDE = "https://www.ebi.ac.uk/pride/ws/archive/v3"

def get_project_files(accession, file_type=None, page_size=100):
    """Walk paginated /files for a project. Optionally filter by category code
    (RAW, PEAK, RESULT, FASTA, OTHER). Returns a DataFrame."""
    rows, page = [], 0
    while True:
        r = requests.get(f"{PRIDE}/projects/{accession}/files",
                         params={"pageSize": page_size, "page": page},
                         timeout=30)
        r.raise_for_status()
        batch = r.json()
        if not batch:
            break
        for f in batch:
            cat = f.get("fileCategory") or {}
            ftp = next((loc["value"] for loc in f.get("publicFileLocations", [])
                        if loc.get("name") == "FTP Protocol"), "")
            asp = next((loc["value"] for loc in f.get("publicFileLocations", [])
                        if loc.get("name") == "Aspera Protocol"), "")
            rows.append({
                "file_name": f.get("fileName"),
                "category": cat.get("value"),     # RAW/PEAK/RESULT/FASTA/OTHER
                "size_mb": round((f.get("fileSizeBytes") or 0) / 1e6, 2),
                "ftp_url": ftp,
                "aspera_url": asp,
                "downloads": f.get("totalDownloads"),
            })
        if len(batch) < page_size:
            break
        page += 1

    df = pd.DataFrame(rows)
    if file_type:
        df = df[df["category"] == file_type]
    return df

files_df = get_project_files("PXD004131")
print(f"Total files: {len(files_df)}")
print(files_df.groupby("category")["size_mb"].agg(["count", "sum"]).round(1).to_string())

raw_only = files_df[files_df["category"] == "RAW"]
print(f"\nRAW files: {len(raw_only)}; combined {raw_only['size_mb'].sum():.0f} MB")
print(raw_only[["file_name", "size_mb", "downloads"]].head(5).to_string(index=False))

# /files/all returns every file in one response — convenient for small projects
files = requests.get(f"{PRIDE}/projects/PXD000001/files/all", timeout=60).json()
print(f"PXD000001 files (all): {len(files)}")
for f in files[:4]:
    print(f"  [{f.get('fileCategory',{}).get('value','?'):<6}] {f['fileName']}  "
          f"{f.get('fileSizeBytes',0)/1e6:.2f} MB")

import requests, pandas as pd, io

PRIDE = "https://www.ebi.ac.uk/pride/ws/archive/v3"

def get_sdrf(accession):
    """Fetch the SDRF sample-to-run mapping for a project (404 if not provided)."""
    r = requests.get(f"{PRIDE}/files/sdrf/{accession}", timeout=30)
    if r.status_code == 404:
        return None
    r.raise_for_status()
    return pd.read_csv(io.StringIO(r.text), sep="\t")

# Many older projects have no SDRF — newer ones typically do
sdrf = get_sdrf("PXD000001")
if sdrf is None or sdrf.empty:
    print("No SDRF available for this project")
else:
    print(f"SDRF rows: {len(sdrf)}  cols: {len(sdrf.columns)}")
    print(f"First columns: {list(sdrf.columns)[:8]}")

import requests

PRIDE = "https://www.ebi.ac.uk/pride/ws/archive/v3"

def get_protein_projects(uniprot_acc):
    """Return the list of PRIDE project accessions that mention this UniProt accession.
    No PSM/peptide/coverage counts are available at this endpoint."""
    r = requests.get(f"{PRIDE}/proteins/{uniprot_acc}", timeout=30)
    if r.status_code == 404:
        return None
    r.raise_for_status()
    data = r.json()
    return data.get("projects", [])

tp53 = get_protein_projects("P04637")
print(f"TP53 (P04637) is reported in {len(tp53)} PRIDE projects")
print(f"First 8: {tp53[:8]}")

unknown = get_protein_projects("Q99999")
print(f"\nQ99999 (no real protein): "
      f"{'no PRIDE evidence' if not unknown else f'{len(unknown)} projects'}")

import requests, pandas as pd

PRIDE = "https://www.ebi.ac.uk/pride/ws/archive/v3"

# Find similar projects to one of interest
similar = requests.get(f"{PRIDE}/projects/PXD004131/similarProjects",
                       params={"pageSize": 5}, timeout=30).json()
print(f"Similar to PXD004131: {len(similar)} projects")
for p in similar[:5]:
    print(f"  {p['accession']}  {(p.get('title') or '')[:70]}")

# Autocomplete suggestions for a project-title prefix
suggestions = requests.get(f"{PRIDE}/search/autocomplete",
                           params={"keyword": "tp53"}, timeout=30).json()
print(f"\nAutocomplete for 'tp53': {len(suggestions)} suggestions")
for s in suggestions[:5]:
    print(f"  {s}")

import requests

PRIDE = "https://www.ebi.ac.uk/pride/ws/archive/v3"

n_projects = int(requests.get(f"{PRIDE}/projects/count", timeout=30).text)
n_files    = int(requests.get(f"{PRIDE}/files/count", timeout=30).text)
print(f"PRIDE Archive current scale:")
print(f"  Projects: {n_projects:,}")
print(f"  Files:    {n_files:,}")

# Valid filter forms
"organisms_facet==Homo sapiens (human)"
"instruments_facet==Q Exactive"
"diseases_facet==Prostate adenocarcinoma"
"softwares_facet==MaxQuant"

# Combine with commas
filter="organisms_facet==Homo sapiens (human),instruments_facet==Orbitrap Fusion Lumos"

import requests, pandas as pd

PRIDE = "https://www.ebi.ac.uk/pride/ws/archive/v3"
disease_kw = "colorectal cancer"

# 1) Inspect facet counts to learn which filter values dominate
facets = requests.get(f"{PRIDE}/facet/projects",
                      params={"keyword": disease_kw, "facetPageSize": 10},
                      timeout=30).json()

top_instr = sorted(facets.get("instruments", {}).items(), key=lambda kv: -kv[1])[:5]
top_org = sorted(facets.get("organisms", {}).items(), key=lambda kv: -kv[1])[:3]
print(f"Top instruments for '{disease_kw}':")
for k, v in top_instr: print(f"  {k:<35} {v}")
print(f"Top organisms:")
for k, v in top_org: print(f"  {k:<35} {v}")

# 2) Build a filtered search using one top instrument
target_instr = top_instr[0][0]
projects = requests.get(f"{PRIDE}/search/projects",
                        params={"keyword": disease_kw,
                                "filter": f"organisms_facet==Homo sapiens (human),instruments_facet=={target_instr}",
                                "pageSize": 50,
                                "sortFields": "submission_date",
                                "sortDirection": "DESC"},
                        timeout=30).json()

df = pd.DataFrame([{
    "accession": p["accession"],
    "title": (p.get("title") or "")[:70],
    "submission_date": p.get("submissionDate"),
    "tissues": ", ".join(p.get("organismsPart", []))[:40],
    "submitter": (p.get("submitters") or [""])[0] if p.get("submitters") else "",
} for p in projects])
print(f"\nFiltered projects: {len(df)}  (target instrument: {target_instr})")
print(df.head(10).to_string(index=False))
df.to_csv(f"{disease_kw.replace(' ', '_')}_{target_instr.replace(' ', '_')}_projects.csv",
          index=False)

import requests, pandas as pd
from pathlib import Path

PRIDE = "https://www.ebi.ac.uk/pride/ws/archive/v3"
accession = "PXD004131"
keep_categories = {"RAW", "RESULT"}
output_dir = Path(f"/data/pride/{accession}")

files = requests.get(f"{PRIDE}/projects/{accession}/files/all", timeout=120).json()

manifest = []
for f in files:
    cat = (f.get("fileCategory") or {}).get("value")
    if cat not in keep_categories:
        continue
    ftp = next((loc["value"] for loc in f.get("publicFileLocations", [])
                if loc.get("name") == "FTP Protocol"), None)
    if not ftp:
        continue
    manifest.append({
        "file_name": f["fileName"],
        "category": cat,
        "size_mb": round((f.get("fileSizeBytes") or 0) / 1e6, 2),
        "ftp": ftp,
    })

mdf = pd.DataFrame(manifest).sort_values(["category", "file_name"])
print(f"{accession}: keeping {len(mdf)}/{len(files)} files "
      f"({mdf['size_mb'].sum():.0f} MB total)")
print(mdf.groupby("category")[["size_mb"]].sum().round(0))

# aria2c -i pride_dl.list -d /data/pride/PXD004131 -x 8 -j 4
with open("pride_dl.list", "w") as fh:
    fh.write("\n".join(mdf["ftp"]))
print(f"\nWrote pride_dl.list with {len(mdf)} URLs (use aria2c -i)")

import requests, time, pandas as pd, matplotlib.pyplot as plt

PRIDE = "https://www.ebi.ac.uk/pride/ws/archive/v3"

candidates = {
    "P04637": "TP53", "P38398": "BRCA1", "P31749": "AKT1",
    "P40763": "STAT3", "O15530": "PDPK1", "P10275": "AR",
}

rows = []
for acc, sym in candidates.items():
    r = requests.get(f"{PRIDE}/proteins/{acc}", timeout=30)
    projs = r.json().get("projects", []) if r.status_code == 200 else []
    rows.append({"uniprot": acc, "symbol": sym, "n_projects": len(projs)})
    time.sleep(0.3)

df = pd.DataFrame(rows).sort_values("n_projects", ascending=False)
print(df.to_string(index=False))

fig, ax = plt.subplots(figsize=(8, 3.5))
bars = ax.bar(df["symbol"], df["n_projects"], color="#3182BD")
ax.bar_label(bars, fmt="%d", fontsize=9, padding=2)
ax.set_ylabel("# PRIDE projects mentioning the protein")
ax.set_title("PRIDE project-level occurrence — candidate panel")
plt.tight_layout()
plt.savefig("pride_protein_occurrence.png", dpi=150, bbox_inches="tight")
print("Saved pride_protein_occurrence.png")