Build a competitive landscape

import collections
import os

import requests

API = "https://api.pav.bio"
HEADERS = {"Authorization": f"Bearer {os.environ['PAV_API_KEY']}"}


def get(path, **params):
    resp = requests.get(f"{API}{path}", headers=HEADERS, params=params, timeout=60)
    resp.raise_for_status()
    return resp.json()


# 1. Search by meaning, then add exact target matches.
found = {}
for query in ["KRAS G12C inhibitor", "pan-KRAS inhibitor"]:
    for p in get("/v1/programs", q=query, limit=200)["data"]:
        found[p["id"]] = p
for target in ["KRAS G12C", "KRAS"]:
    for p in get("/v1/programs", target=target, limit=500)["data"]:
        found[p["id"]] = p


# 2. Keep programs that name KRAS in their target, mechanism or drug.
def mentions_kras(p):
    text = " ".join([p.get("target", ""), p.get("mechanism_of_action", ""), p["drug"]])
    return "KRAS" in text.upper()


landscape = [p for p in found.values() if mentions_kras(p)]

# 3. Count by phase and list the most advanced programs.
RANK = ["Approved", "Registration", "Filed", "Phase 3", "Phase 2/3", "Phase 2",
        "Phase 1/2", "Phase 1", "Preclinical", "Unknown"]
by_phase = collections.Counter(p.get("phase_norm", "Unknown") for p in landscape)
print(f"{len(landscape)} KRAS programs across {len({p['company_id'] for p in landscape})} companies")
for phase in RANK:
    if by_phase[phase]:
        print(f"  {phase:<12} {by_phase[phase]}")

landscape.sort(key=lambda p: RANK.index(p.get("phase_norm", "Unknown")))
print()
for p in landscape[:8]:
    trials = len(p.get("clinical_trials", []))
    print(f"{p.get('phase_norm', 'Unknown'):<10} | {p['company']} | {p['drug']} | {p.get('indication', '')[:40]} | trials={trials}")

50 KRAS programs across 27 companies
  Approved     2
  Registration 1
  Phase 3      16
  Phase 2      6
  Phase 1/2    9
  Phase 1      12
  Preclinical  4

Approved   | Shanghai Allist Pharmaceuticals | Glecirasib | 2nd Line Treatment for NSCLC | trials=10
Approved   | Innovent Biologics | DUPERT (Fulzerasib) |  | trials=15
Registration | Royalty Pharma | Rasonque | RAS mutant pancreatic cancer | trials=13
Phase 3    | Merck | calderasib | Colorectal cancer | trials=1
Phase 3    | Merck | calderasib | Non-small cell lung cancer | trials=5
Phase 3    | Bristol Myers Squibb | KRAZATI® (adagrasib) | 1L Non-Small Cell Lung Cancer PD-L1≥50% | trials=1
Phase 3    | Roche | divarasib (KRAS G12C) | 1L non small cell lung cancer (1L NSCLC) | trials=5
Phase 3    | Roche | divarasib (KRAS G12C) | 2L non small cell lung cancer (2L NSCLC) | trials=5