ScienceClaw
Autonomous Life Sciences Intelligence — HitchhikersAI
Oncology Market Intelligence
An autonomous knowledge graph spanning 8 US oncology market verticals, updated weekly from free public sources — no commercial data subscriptions. The primary output is disruption and shortage signal detection: FDA shortage flags, manufacturing recalls, and KG degree surges not visible in analyst consensus views. Approval ranking and revenue indices are directional tools, not forecasts.
Explore the Knowledge Graph View Market Signals Methods paper v1.0 (PDF)
1048
KG nodes
3656
KG edges
191
Drug × indication signals
66
High disruption signals (≥60%)
8/8
Verticals loaded this run
2026-07-19
Last updated
This week's top signals
View all signals →
AKEEGA 100%
Prostate Cancer
approval probability
Perfect approval score driven by regulatory_momentum=10 (abiraterone has many formulation/indication approvals). Pipeline density is only 2 trials — model cannot distinguish between drugs with many past approvals and genuine forward-looking expansion potential.
LENALIDOMIDE 100%
Multiple Myeloma
approval probability
Score of 1.0 with 10 prior approvals and 17 active trials. Plausible given lenalidomide's established MM dominance, but the model offers no incremental signal beyond 'drug has many approvals'.
BORTEZOMIB 100%
Multiple Myeloma
disruption risk score
Highest disruption score — driven by 9 approvals + shortage_risk=2 (Class I/II recalls). Aligns with EOI-002 which flagged biosimilar pressure. This is the model's strongest signal this week.
Data verticals
01
Academic research
PubMed · NIH Reporter
High coverage
02
Drug discovery
ChEMBL · Open Targets
High coverage
03
Clinical trials
Thread 2 cross-reference
Daily signal
04
Manufacturing
openFDA enforcement
Structural only
05
Sales
CMS Part D / Part B
2yr lag
06
Distribution
HRSA 340B · NPI
Structural only
07
FDA regulatory
openFDA · Drugs@FDA
High coverage
08
Government policy
Fed Register · Congress.gov
Text extraction
Output pages
⚲
Market Knowledge Graph
Interactive force-directed network across all 8 verticals. Nodes coloured by type: indications, drugs, approvals, sponsors, grants, policy acts, and more. Filter by node type, hover for confidence and source metadata. Tier 3 inferred edges shown as dashed links.
Open KG →
▲
Market Intelligence Signals
Disruption risk and shortage signals for 191 drug × indication pairs, grounded in observable KG data: FDA shortage flags, manufacturing recalls, and degree surges not visible in analyst consensus. Approval rank is a relative ordering tool only — labels are in-sample. Revenue index is directional; CMS data carries a 2yr lag. Expand any row for per-feature contribution bars and raw feature values.
Open Signals →
Weekly pipeline
Collect
06:00 Fetch 8 verticals
→
Analyse
08:15 GLM-5 Tier 2 extract
09:00 KG write
09:30 Centrality
09:45 Lead-lag
10:00 GLM-5 classify
10:30 Feature matrix
10:45 sklearn models
→
Deploy
11:00 Vercel deploy

Runs every Sunday 06:00–11:00 UK. Staggered before Thread 2 (11:45 UK) to avoid concurrent LLM calls. Single-writer KG with atomic file writes throughout.

Data coverage and signal limitations

This platform uses free public data sources only. Manufacturing, distribution, and sales verticals have structural gaps — no drug volume or revenue data is available from public sources at the resolution required for commercial market sizing. CMS Part D spending data has a ~2-year publication lag and covers Medicare-reimbursed spend only. All signal outputs are directional indicators, not forecasts. This platform is a research initiative and does not substitute for commercial market intelligence services.

ScienceClaw · HitchhikersAI · raminderpal@hitchhikersai.org · hitchhikersai.org