Sigmatic Scout

Ask a research question.
Get an evidence-backed answer.

Scout orchestrates hundreds of specialized AI agents to run multi-step scientific investigations autonomously. One prompt. Full provenance.

One prompt. A complete scientific investigation.

Real Scout investigations run on the platform — each traceable from research question to evidence, tool chain, and calibrated confidence.
Research Question
"Evaluate the on-target/off-tumor safety of a FOLR1-directed CAR-T for ovarian cancer by integrating expression, clinical precedent, and toxicity evidence — and produce a tissue-level safety roadmap."
Investigation Stats
Tumor-selective
Normal ovary 0.14 TPM
54
GTEx tissues
High/Mod
Confidence (see report)
Roadmap
Go/no-go criteria
Agents Orchestrated
GTEx Bulk RNA-seq CELLxGENE Single-Cell UniProt P15328 DepMap ClinicalTrials.gov PubMed Composite Risk Scoring Ensemble Synthesis
Scroll to explore full report ↓

FOLR1-Targeted CAR-T: A Tumor-Selective Target with a Defined Safety Roadmap

Ensemble synthesis of expression, clinical precedent, and toxicity evidence — ovarian-cancer program

Target: FOLR1 / Folate Receptor Alpha Modality: CAR-T cell therapy Indication: Ovarian cancer Run: Ensemble · 2026-07-18

1Original Research Question

Evaluate the on-target/off-tumor safety of a FOLR1-directed CAR-T for ovarian cancer by integrating GTEx bulk RNA-seq, CELLxGENE single-cell expression, clinical precedent, and structured toxicity evidence — then produce a tissue-level safety roadmap.

2Key Finding

In a single prompt, Scout integrated four independent evidence streams into a decision-ready development package with explicit confidence and next steps.

Key finding: FOLR1 shows a favorable tumor-vs-normal-ovary contrast (normal ovary 0.140 TPM) and a clean hematopoietic window (effectively zero across bone-marrow cell types), supporting a genuine — but narrow — therapeutic window. Lung and kidney carry the highest normal-tissue expression and are the priority safety questions to resolve before the clinic.
◈ Provenance & Confidence

Evidence sources: GTEx bulk RNA-seq (54 tissues); CELLxGENE single-cell atlas; UniProt P15328; DepMap; ClinicalTrials.gov; 6 PubMed studies.

Tool chain: Expression retrieval → single-cell profiling → composite risk scoring → ensemble synthesis (2 runs).

Confidence: High for tumor-selectivity and the hematopoietic window; Moderate for the complete organ profile (7 tissues remain coverage gaps; no FOLR1 CAR-T clinical safety data yet).

Still to confirm: Direct tumor-vs-normal protein-density (IHC) for lung and renal tubule; primary-cell functional CAR-T testing.

3Normal-Tissue Expression (GTEx, 54 Tissues)

TissueFOLR1 (median TPM)Role in the roadmap
Normal ovary0.140FAVORABLE defines the window
Lung109.863Priority diligence — direct tissue-density confirmation
Minor salivary gland79.135Confirm with IHC
Kidney cortex / medulla50.5 / 52.8Priority diligence — proximal-tubule assessment
Thyroid33.956Routine monitoring
Fallopian tube5.845Relevant to HGSOC biology

4Single-Cell Resolution

Single-cell profiling confirms FOLR1 is restricted to specific epithelial/secretory populations, with hematopoietic/immune compartments effectively negative.

Cell typeExpression meanCells expressing
Pancreatic ductal cells17.62269/389 (17.7%)
Respiratory club cells0.59363/209 (30.1%)
Liver cholangiocytes0.21349/474 (10.3%)
Class-switched memory B cells0.0754/638 (0.6%)

UniProt P15328 (GPI-anchored receptor) and DepMap non-essential classification (mean dependency −0.0372) are consistent with tolerance of modulation.

5Clinical Precedent

The FOLR1-directed ADC mirvetuximab soravtansine provides a mature playbook: its most common events are ocular, largely low-grade and mostly reversible, and the evidence suggests they are substantially payload-mediated — so they may not carry over to CAR-T.

EventRateDetail
Blurred vision43% (integrated)71% resolved; predictable onset (~6 wks)
Keratopathy29–48%66% resolved; grade ≥3 only 5%

6Tissue-Level Safety Roadmap

TissueSignalDiligence action
Normal ovary0.140 TPMFAVORABLE window confirmed
Lung / kidneyHigh bulk expressionFOCUS tissue-density + functional testing
Thyroid / salivary glandModerate–high bulkCONFIRM targeted IHC
Ocular surfaceADC precedent (payload-linked)MONITOR established surveillance
Bone marrow / bloodEffectively zeroCLEAR validated window

7Path Forward

  • Confirm the window: comparative tumor-vs-normal FOLR1 protein density (lung, renal tubule).
  • Engineer selectivity: affinity/avidity tuning and activation-threshold control.
  • Differentiate modality: compare the same binder in ADC vs CAR-T formats.

Go/no-go: tumor-selective activation with minimal activity against primary normal cells — a defined, achievable bar this evidence base supports pursuing.

Research Question
"Compare osimertinib versus lazertinib as first-line therapy in EGFR-mutant NSCLC, synthesizing pivotal phase 3 efficacy, safety, and overall-survival evidence."
Investigation Stats
0.46 / 0.45
PFS HR (osi / laz)
80% / 76%
ORR
38.6 mo
Osi OS (mature)
Indirect
No head-to-head
Agents Orchestrated
PubMed ClinicalTrials.gov ChEMBL openFDA Labels Cross-Trial Extraction Indirect Synthesis
Scroll to explore full report ↓

Osimertinib versus Lazertinib: Two Leading First-Line EGFR-TKIs

Cross-trial synthesis of pivotal phase 3 efficacy and safety in EGFR-mutant NSCLC

Class: 3rd-gen irreversible EGFR-TKI Trials: FLAURA · LASER301 Indication: 1L EGFR-mutant NSCLC Run: Ensemble · 2026-07-17

1Original Research Question

Compare osimertinib versus lazertinib as first-line therapy in EGFR-mutant (exon 19 deletion / L858R) advanced NSCLC, synthesizing pivotal phase 3 efficacy, safety, and overall-survival evidence.

2Key Finding

Scout extracted and aligned the pivotal phase 3 evidence for both agents across two independent runs.

Key finding: Both agents deliver strong, comparable first-line efficacy — PFS hazard ratios of 0.46 (osimertinib) and 0.45 (lazertinib) versus gefitinib, with similar ORR (80% vs 76%) and identical AE discontinuation (15%). Osimertinib currently carries a mature, statistically significant OS benefit (38.6 vs 31.8 months; P=0.046); lazertinib OS data remain immature. No head-to-head trial exists, so this is an indirect comparison.
◈ Provenance & Confidence

Evidence sources: PubMed (FLAURA, LASER301); ClinicalTrials.gov (250 vs 34 trials); ChEMBL; openFDA labels.

Tool chain: Literature retrieval → structured cross-trial extraction → indirect synthesis (2 runs).

Confidence: High for individual trial values and PFS-HR similarity; Moderate for cross-trial safety (differing populations/grading); Low for any claim of true superiority.

Still to confirm: Mature LASER301 OS data; a formal IPD network meta-analysis (shared gefitinib comparator).

3Head-to-Head Efficacy

EndpointOsimertinib · FLAURALazertinib · LASER301
Patients556393
Median PFS18.9 vs 10.2 mo20.6 vs 9.7 mo
PFS HR0.46 (0.37–0.57)0.45 (0.34–0.58)
ORR80%76%
Median DoR17.2 mo19.4 mo
Grade ≥3 AE34%40%
AE discontinuation15%15%

4Overall Survival

AgentOS resultStatus
Osimertinib38.6 vs 31.8 mo; HR 0.80 (0.64–1.00); P=0.046Mature, significant
Lazertinib18-mo OS 80% vs 72%; HR 0.74 (0.51–1.08)Immature at interim

5Decision Guidance

  • Today: osimertinib is the evidence-backed first-line choice (mature OS + 6+ years real-world experience).
  • Watch: lazertinib PFS is fully competitive; maturing LASER301 OS will complete the picture.
  • Next step: formal IPD network meta-analysis via the shared gefitinib comparator.
Research Question
"Assess the ADA risk and developability of a human IgG1 candidate via germline analysis, HLA class II epitope prediction, and a developability screen — and identify precise, testable follow-ups."
Investigation Stats
2/2
Human germline chains
−80
SAP (low aggregation)
0
Aggregation hotspots
1
Verification target flagged
Agents Orchestrated
Germline Assignment MHC-II (internal custom model) AFND Coverage Developability Panel Spatial Aggregation Propensity Synthesis
Scroll to explore full report ↓

Antibody Developability & Immunogenicity: Favorable Profile, One Verification Target

Germline confirmation, developability screen, and HLA class II epitope triage for a human IgG1 candidate

Modality: Human IgG1 mAb Assessment: Developability + MHC-II Outcome: Advance with one targeted check Run: 2026-07-13

1Original Research Question

Assess the anti-drug-antibody (ADA) risk and developability of a human IgG1 candidate via germline analysis, HLA class II epitope prediction, and a developability screen — and identify precise, testable follow-ups.

2Key Finding

Scout ran a full developability and immunogenicity triage and returned a candidate that is strong on fundamentals, with one precisely-located item to confirm.

Key finding: Both variable chains are fully human germline (heavy IGHV3-66*01; light IGKV1-39*01), and developability is favorable — very low aggregation propensity (SAP −80.0), no aggregation hotspots, no destabilizing residues. The immunogenicity screen surfaced conflicting outputs and incomplete HLA coverage, so ADA risk is not yet classifiable; Scout isolated one CDR2-adjacent light-chain peptide as the single verification target.
◈ Provenance & Confidence

Evidence sources: VH/VL sequence; germline databases; AFND HLA population frequencies; developability panel.

Tool chain: Germline assignment → MHC-II epitope prediction (internal custom model) → population coverage → developability + spatial aggregation propensity → deterministic reconciliation.

Confidence: High for germline & developability (aggregation/stability); Indeterminate for population-level ADA (allele coverage recovered 0/26 — flagged, not hidden).

Still to confirm: Experimental HLA-DRB1*01:01 binding + CD4⁺ T-cell activation for the KLLIYSASFLYSGVP region; rerun MHC-II with full allele coverage.

3Developability — Strong Fundamentals

PropertyResultRead
Germline (heavy / light)IGHV3-66*01 / IGKV1-39*01Fully human
Spatial aggregation propensity−80.0 (threshold 10)Favorable
Aggregation hotspots (≥1.0)0None
Destabilizing residues0None
Chemical-motif liabilities12 (2 high, 2 mod, 8 low)Routine forced-degradation checklist

4Immunogenicity — A Precise, Testable Next Step

The MHC-II triage flagged incomplete allele coverage rather than over-claiming, and surfaced a single CDR2-adjacent light-chain peptide worth confirming. For HLA-DRB1*01:01 the peptide KLLIYSASFLYSGVP (light-chain positions 45–59) was a dual-method call at 49 nM.

This is a strength of the workflow: it flags where model coverage is incomplete and hands you one concrete verification target — rather than a false all-clear or a false alarm.

5Recommended Path

  • Confirm: experimental DRB1*01:01 binding + CD4⁺ T-cell activation for the flagged region.
  • Standard QC: forced-degradation on the two high-severity motifs.
  • If confirmed benign, the fully-human, low-aggregation profile supports advancement.
Research Question
"Generate developable small-molecule Factor Xa inhibitors from a 2W26 structure-guided workflow, and evaluate candidate quality with docking, synthetic-accessibility, and drug-likeness filters."
Investigation Stats
55
Molecules generated
−8.338
Best dock (in silico)
0.90
Top QED (lig_017)
Assay
Confirmation required
Agents Orchestrated
Pocket2Mol Generation AutoDock Vina (2W26/2P16) PubChem BindingDB FXa RDKit SA + Descriptors Computational Triage
Scroll to explore full report ↓

Structure-Guided Factor Xa Inhibitor Design: A Prioritized, Drug-Like Candidate Panel

De novo generation on the 2W26 pocket with docking, drug-likeness, and synthetic-accessibility triage

Target: Factor Xa (PDB 2W26) Generator: Pocket2Mol Output: Assay-ready candidate panel Run: 2026-07-17

1Original Research Question

Generate developable small-molecule Factor Xa inhibitors from a 2W26 structure-guided workflow, and evaluate candidate quality with docking, synthetic-accessibility, and drug-likeness filters.

2Key Finding

From a single prompt, Scout ran a full structure-based generation and triage pipeline against the Factor Xa pocket and ranked a shortlist for assay.

Key finding: Scout generated 55 valid molecules (0 PAINS, all valid SMILES) and prioritized a drug-like shortlist. The lead in silico is lig_017 — top docking score (−8.338 kcal/mol) with strong drug-likeness (QED 0.895) and easy synthesis (SA 1.78). These are computational predictions and require wet-lab confirmation; most candidates matched known public structures, so novelty must be verified.
◈ Provenance & Confidence

Evidence sources: Factor Xa structures 2W26 & 2P16; PubChem; BindingDB Factor Xa reference set.

Tool chain: Pocket2Mol generation → AutoDock Vina docking (2 receptors) → RDKit SA + descriptors → PubChem identity/similarity → triage.

Confidence: Computational only. Docking scores and QED/SA are in-silico proxies, not measured affinity or synthesizability. 32/55 were exact public matches; lig_017 was a similar-only match (potentially differentiated).

Still to confirm: Purified Factor Xa concentration-response assays; identity/pose confirmation; novelty & selectivity vs related serine proteases.

3Docking Performance (AutoDock Vina)

Metric2W262P16 (cross-receptor)
Ligands docked5554 (paired)
Best predicted affinity−8.338 kcal/mol−8.313 kcal/mol
Median predicted affinity−5.887 kcal/mol
Poses / exhaustiveness / failed5 / 32 / 0

4Prioritized Candidate Panel

Candidate2W26 dockQEDSAMW (Da)Note
lig_017−8.3380.8951.78255.3LEAD best dock + drug-likeness; similar-only match
lig_041−7.2340.7381.40High QED, very synthesizable
lig_016−7.6780.6182.95172.2Solid assay candidate (exact match)
lig_030−7.7170.5613.14160.2Solid assay candidate (exact match)

5Recommended Path

  • Advance the panel to purified Factor Xa concentration-response assays.
  • Confirm identity/pose for lig_017; assess novelty vs the closest public match.
  • Follow through: retrosynthesis, solubility/stability, selectivity vs related proteases.
Research Question
"Systematically examine approved direct Factor Xa inhibitors as alternatives to rivaroxaban across VTE prophylaxis, AF stroke prevention, and DVT/PE treatment; rank candidates and assess comparative evidence."
Investigation Stats
874
Trials screened
Apixaban
Lead alternative
82.15
Apixaban score
2
Direct comparisons found
Agents Orchestrated
F10 Target ID Open Targets ChEMBL / Pharos ClinicalTrials.gov Comparative Ranking Synthesis
Scroll to explore full report ↓

Direct Factor Xa Inhibitors as Alternatives to Rivaroxaban — Apixaban Leads

Evidence-ranked comparison across VTE prophylaxis, AF stroke prevention, and DVT/PE treatment

Target: F10 / Factor Xa (P00742) Reference: Rivaroxaban Indications: VTE · AF · DVT/PE Run: 2026-07-18

1Original Research Question

Systematically examine approved direct Factor Xa inhibitors as alternatives to rivaroxaban across VTE prophylaxis, AF stroke prevention, and DVT/PE treatment; rank candidates and assess comparative evidence.

2Key Finding

Scout screened 874 deduplicated trials across four direct Factor Xa inhibitors and produced a transparent, weighted evidence ranking.

Key finding: Apixaban is the strongest evidence-backed alternative — composite score 82.15, 406 trials, coverage of all three core indications, and two direct head-to-head studies against rivaroxaban already available. Edoxaban is a solid second for AF/VTE. The ranking reflects development breadth and maturity, not head-to-head clinical superiority.
◈ Provenance & Confidence

Evidence sources: ClinicalTrials.gov (874 deduplicated trials); Open Targets; ChEMBL; Pharos; F10 target record (UniProt P00742).

Tool chain: F10 target ID → trial metadata retrieval → per-candidate summaries → weighted comparative ranking (maturity 50% · breadth 35% · adoption 15%).

Confidence: High for trial-evidence breadth and the apixaban ranking; Moderate for comparative safety/efficacy (few direct head-to-head outcomes; counts are metadata, not efficacy).

Still to confirm: Indication-specific comparative analysis using the identified COBRRA / COVET head-to-head studies.

3Evidence-Ranked Candidates

CandidateTrialsCompositeRecommendation
Apixaban40682.15LEAD all indications covered
Edoxaban16559.23STRONG #2 AF/VTE, pivotal warfarin data
Rivaroxaban55386.76Reference agent
Betrixaban1432.93Niche; smaller evidence base

4Why Apixaban Leads

TrialRegistryResult
ARISTOTLENCT00412984Superior to warfarin for stroke/SE, less bleeding, lower mortality
ADVANCE-3NCT00423319Ortho VTE prophylaxis vs enoxaparin (9.0% vs 8.8%; HR 1.02)
CARAVAGGIONCT03045406Cancer-associated VTE (1,170 patients)
COBRRA / COVETNCT03266783 / NCT03196349Direct apixaban-vs-rivaroxaban comparisons available

5Recommended Path

  • Lead with apixaban for a development or clinical-substitution program.
  • Edoxaban as the AF/VTE alternative (ENGAGE AF-TIMI 48, Hokusai-VTE).
  • Next step: indication-specific comparison using the identified head-to-head studies.

Not a chatbot. An agentic operating system.

Scout doesn't guess at science. It orchestrates real computational tools on your real data with full provenance.

Scientist-in-the-Loop

Scout augments expert judgment, never bypasses it. ASK_USER pauses when the planner encounters genuine ambiguity. The scientist directs; the AI executes.

Hundreds of Specialized Agents

Not one model trying to do everything. Hundreds of purpose-built computational agents — ADMET, docking, retrosynthesis, expression profiling, literature mining — orchestrated by an LLM planner, with more added every week.

Two Modes of Operation

Hand-craft validated pipelines that run autonomously across hundreds of compounds. Or let Scout plan from a research question. The pipeline handles volume; the planner handles novelty.

See Scout answer your research questions

Schedule a live demo with a real research question. No slides. Just science.

Request a Demo