Features
Everything You Get With Motif
Full-text extraction from PubMed, PMC, and Europe PMC. Every answer is grounded in real, citable literature (no fabricated citations). A cumulative knowledge graph your whole team builds together.
entity types mapped
relationship types
databases for cross-referencing
Plain-language input
Ask in plain English,
get structured evidence
Type your research question the same way you'd ask a colleague. Motif handles the retrieval strategy: precision-focused and recall-focused searches run in parallel for broad evidence coverage.
- Associations across every relationship type, including clinical, molecular, and causal
- Every result extracted with PMIDs and source links
Hi Alex, what would you like to explore?
Parallel research agents
Multiple agents working
simultaneously
Complex questions get decomposed into parallel tracks. Each agent searches, extracts, and cross-references independently. Results are then merged into a unified knowledge graph.
- Automatic query decomposition for multi-faceted research questions
- Independent extraction paths eliminate single-agent blind spots
- Results synthesized with conflict resolution and evidence scoring
Interactive knowledge graph
See connections others miss
Every query builds an interactive graph connecting genes, proteins, diseases, drugs, and pathways. Click any node to explore its associations. Filter by evidence strength, disease context, or biomarker type.
Grant-ready outputs
Export in any format
your workflow needs
From raw data pipelines to publication-ready figures. Every export includes the full evidence trail so your team can verify every claim before it reaches a grant application or manuscript.
- JSON and CSV for downstream analysis in R or Python
- GraphML for Gephi, Cytoscape, and yEd network tools
- PDF reports formatted for sharing and archival
- SVG vector graphics for editing and publications
- Neo4j Cypher statements for graph database import
Export Knowledge Graph
Export your organization's knowledge graph data. Active filters are applied to the export.
Research report
CAR-T resistance biomarkers in solid tumors
Direct answer
Across 3 included papers, CTLA-4 upregulation and PD-1 co-expression drive CAR-T resistance in solid tumors; epigenetic silencing of effector genes appears in every non-responder cohort studied.
TIL exhaustion phenotype
Terminal exhaustion is established epigenetically before infusion. CAR-T failure is predictable from baseline TIL phenotype. The epigenetic barrier score (EBS, AUC 0.81) separates responders from non-responders in solid-tumor models.
Next actions
Develop pre-infusion EBS assay: Adapt the published epigenetic barrier score to a flow-cytometry panel on baseline TIL samples from solid-tumor biopsies before CAR-T infusion.
Papers cited
Structured insights
Direct answers, cited evidence,
and next lab steps
After extraction, Motif synthesizes findings into a structured action report. Key claims are highlighted inline, and every conclusion traces back to a source paper.
- Literature review covering every paper Motif read and why
- Direct answer to your research question up front
- Themed evidence sections with highlighted biomarker associations
- Next lab and clinical steps ordered by feasibility
Cross-referencing
50+ databases, one search
Every biomarker is automatically cross-referenced against trusted clinical, genomic, and regulatory databases.
Technical details and limitations
Need the full methodology details? Expand each section below.
Methodology detailsExpand
AI extraction approach
Motif uses language models to extract biomarker-disease-drug relationships from published literature. We do not generate novel claims; we organize and cross-reference existing research with citations for verification.
Search coverage strategy
- Precision-focused retrieval for targeted matching
- Recall-focused retrieval to broaden evidence discovery
- Terminology handling for alternate scientific naming
Biomarker and relationship coverage
Motif recognizes 60+ biomarker types and multiple relationship classes, including:
Additional outputs
- Patent intelligence: cross-reference biomarker and therapeutic claims against patent and regulatory sources where integrated.
- Meta-analysis and synthesis: aggregated evidence views where comparable study data supports comparison.
Processing-time context
End-to-end runtime varies by query scope, evidence volume, and system load. Internal testing indicates per-article extraction around three minutes under representative conditions. This is one stage of the pipeline, not total run time.
Limitations and responsible useExpand
Motif is a research acceleration tool and should be used with expert review.
- Coverage gaps may exist for preprints, very new papers, or under-indexed topics.
- AI extraction can miss context or misclassify relationships in edge cases.
- External database updates may lag behind newly published findings.
- Evidence indicators reflect literature support, not clinical validity predictions.
- Researchers should verify key findings by reviewing the original source papers.
From the blog
See how Motif fits your use case
Deep dives on cited literature reviews, biomarker candidate discovery, and trial stratification evidence.
Cited literature review
Search PubMed, extract associations, and export a thematic Word review with PMIDs for grants and scoping studies.
See literature review workflow →Biomarker candidate discovery
Let candidates emerge from papers, cross-reference 50+ databases, score GRADE tiers, and pool meta-analyses.
See discovery workflow →Trial stratification evidence
Surface predictive and prognostic subgroup evidence with population modifiers and conflicting-effect flags.
See stratification workflow →Ready to speed up biomarker discovery?
Join the waitlist to try Motif's AI biomarker discovery platform.