Question: You are an expert researcher providing comprehensive, well-cited information.

Provide detailed information focusing on: 1. Key concepts and definitions with current understanding 2. Recent developments and latest research (prioritize 2023-2024 sources) 3. Current applications and real-world implementations 4. Expert opinions and analysis from authoritative sources 5. Relevant statistics and data from recent studies

Format as a comprehensive research report with proper citations. Include URLs and publication dates where available. Always prioritize recent, authoritative sources and provide specific citations for all major claims.

Disease Characteristics Research Template

Target Disease

• Disease Name: ROS1-Rearranged Non-Small Cell Lung Cancer
• MONDO ID: (if available)
• Category:

Research Objectives

Please provide a comprehensive research report on ROS1-Rearranged Non-Small Cell Lung Cancer covering all of the disease characteristics listed below. This report will be used to populate a disease knowledge base entry. Be thorough and cite primary literature (PMID preferred) for all claims.

For each section, suggested databases/resources are listed. These are the first places you should search for information on each topic.

1. Disease Information

Search first: OMIM, Orphanet, ICD-10/ICD-11, MeSH, PubMed

• What is the disease? Provide a concise overview.
• What are the key identifiers? (OMIM, Orphanet, ICD-10/ICD-11, MeSH, Mondo)
• What are the common synonyms and alternative names?
• Is the information derived from individual patients (e.g., EHR) or aggregated disease-level resources?

2. Etiology

• Disease Causal Factors: What are the primary causes? (genetic, environmental, infectious, mechanistic)
• Risk Factors:

  Search first: PubMed, Cochrane Library, UpToDate, clinical guidelines, ClinVar, ClinGen, GWAS Catalog, PheGenI, CTD, CDC, WHO, epidemiological databases

• Genetic risk factors (causal variants, susceptibility loci, modifier genes)
• Environmental risk factors (toxins, lifestyle, occupational exposures, age, sex, family history)
• Protective Factors:

  Search first: PubMed, Cochrane Library, clinical trial databases, GWAS Catalog, gnomAD, WHO, CDC, nutrition databases

• Genetic protective factors (protective variants, modifier alleles)
• Environmental protective factors (diet, lifestyle, exposures that reduce risk)
• Gene-Environment Interactions: How do genetic and environmental factors interact to influence disease?

  Search first: CTD, PubMed, PheGenI, GxE databases

3. Phenotypes

Search first: HPO (Human Phenotype Ontology), OMIM, Orphanet, PubMed, clinicaltrials.gov, MedDRA, SNOMED CT, DECIPHER, LOINC

For each phenotype, provide: - Phenotype type: symptoms, clinical signs, physical manifestations, behavioral changes, or laboratory abnormalities

For symptoms/signs: HPO, OMIM, Orphanet, PubMed For behavioral changes: HPO, DSM, RDoC (Research Domain Criteria), PubMed For laboratory abnormalities: LOINC, SNOMED CT, LabTests Online, PubMed - Phenotype characteristics: Search first: OMIM, Orphanet, HPO, PubMed - Age of symptom onset (neonatal, childhood, adult-onset, late-onset) - Symptom severity (mild, moderate, severe, variable) - Symptom progression (stable, progressive, episodic, fluctuating) - Frequency among affected individuals (percentage or qualitative) - Quality of life impact: Effects on daily functioning and well-being (per-phenotype when possible) Search first: EQ-5D database, SF-36, WHO QOL databases, PubMed - Suggest HPO (Human Phenotype Ontology) terms for each phenotype

4. Genetic/Molecular Information

• Causal Genes: Gene mutations or chromosomal abnormalities responsible for disease (gene symbols, OMIM IDs)

  Search first: OMIM, ClinVar, HGMD, Ensembl, NCBI Gene

• Pathogenic Variants:
• Affected genes (gene symbols, HGNC IDs) > Search first: OMIM, NCBI Gene, Ensembl, HGNC, UniProt, GeneCards
• Variant classification (pathogenic, likely pathogenic, VUS per ACMG/AMP guidelines) > Search first: ClinVar, ClinGen, ACMG/AMP guidelines, VarSome
• Variant type/class (missense, frameshift, nonsense, splice-site, structural)
• Allele frequency in population databases > Search first: gnomAD, 1000 Genomes, ExAC, TOPMed, dbSNP
• Somatic vs germline origin > Search first: COSMIC (somatic), ClinVar, ICGC, TCGA
• Functional consequences (loss of function, gain of function, dominant negative)
• Modifier Genes: Genes that modify disease severity or expression
• Epigenetic Information: DNA methylation, histone modifications, chromatin changes affecting disease

  Search first: ENCODE, Roadmap Epigenomics, MethBase, DiseaseMeth

• Chromosomal Abnormalities: Large-scale genetic changes (aneuploidy, translocations, inversions)

  Search first: DECIPHER, ClinVar, ECARUCA, UCSC Genome Browser

5. Environmental Information

• Environmental Factors: Non-genetic contributing factors (toxins, radiation, pollution, occupational exposure)

  Search first: CTD (Comparative Toxicogenomics Database), TOXNET, PubMed, EPA databases

• Lifestyle Factors: Behavioral factors (smoking, diet, exercise, alcohol consumption)

  Search first: CDC databases, WHO, PubMed, NHANES

• Infectious Agents: If applicable, pathogens causing or triggering disease (bacteria, viruses, fungi, parasites)

  Search first: NCBI Taxonomy, ViPR, BV-BRC, MicrobeDB, GIDEON

6. Mechanism / Pathophysiology

• Molecular Pathways: Specific signaling cascades or biochemical pathways involved (Wnt, MAPK, mTOR, PI3K-AKT, etc.)

  Search first: KEGG, Reactome, WikiPathways, PathBank, BioCyc

• Cellular Processes: Cell-level mechanisms (apoptosis, autophagy, cell cycle dysregulation, inflammation, etc.)

  Search first: Gene Ontology (GO), Reactome, KEGG, PubMed

• Protein Dysfunction: How protein structure or function is altered (misfolding, aggregation, loss of function, gain of function)

  Search first: UniProt, PDB (Protein Data Bank), InterPro, Pfam, AlphaFold

• Metabolic Changes: Alterations in metabolic processes (energy metabolism, lipid metabolism, amino acid metabolism)

  Search first: KEGG, BioCyc, HMDB (Human Metabolome Database), BRENDA

• Immune System Involvement: Role of immune response (autoimmunity, immunodeficiency, chronic inflammation)

  Search first: ImmPort, Immunome Database, IEDB, Gene Ontology

• Tissue Damage Mechanisms: How tissues/ are injured (oxidative stress, ischemia, fibrosis, necrosis)

  Search first: PubMed, Gene Ontology, Reactome

• Biochemical Abnormalities: Specific molecular defects (enzyme deficiencies, receptor dysfunction, ion channel defects)

  Search first: BRENDA, UniProt, KEGG, OMIM, PubMed

• Epigenetic Changes: DNA methylation, histone modifications affecting gene expression in disease

  Search first: ENCODE, Roadmap Epigenomics, MethBase, DiseaseMeth

• Molecular Profiling (if available):
• Transcriptomics/gene expression changes > Search first: GEO (Gene Expression Omnibus), ArrayExpress, GTEx, Human Cell Atlas, SRA
• Proteomics findings > Search first: PRIDE, ProteomeXchange, Human Protein Atlas, STRING, BioGRID
• Metabolomics signatures > Search first: MetaboLights, Metabolomics Workbench, HMDB, METLIN
• Lipidomics alterations > Search first: LIPID MAPS, SwissLipids, LipidHome, Metabolomics Workbench
• Genomic structural features > Search first: UCSC Genome Browser, Ensembl, NCBI, dbVar, DGV
• Advanced Technologies (if applicable):
• Single-cell analysis findings (cell-type specific mechanisms, cellular heterogeneity) > Search first: Human Cell Atlas, Single Cell Portal, GEO, CELLxGENE
• Spatial transcriptomics findings > Search first: GEO, Spatial Research, Vizgen, 10x Genomics data
• Multi-omics integration results > Search first: TCGA, ICGC, cBioPortal, LinkedOmics, PubMed
• Functional genomics screens (CRISPR, RNAi) > Search first: DepMap, GenomeRNAi, PubMed, BioGRID ORCS

For each mechanism, describe: - The causal chain from initial trigger to clinical manifestation - Which mechanisms are upstream vs downstream - What cell types and biological processes are involved - Suggest GO terms for biological processes and CL terms for cell types

7. Anatomical Structures Affected

• Organ Level:
• Primary organs directly affected
• Secondary organ involvement (complications, secondary effects)
• Body systems involved (cardiovascular, nervous, digestive, respiratory, endocrine, etc.)

  Search first: Uberon, FMA (Foundational Model of Anatomy), OMIM, HPO, ICD-11, MeSH, SNOMED CT

• Tissue and Cell Level:
• Specific tissue types affected (epithelial, connective, muscle, nervous)
• Specific cell populations targeted (with Cell Ontology terms)

  Search first: Uberon, Human Protein Atlas, Cell Ontology, Human Cell Atlas, CellMarker, PanglaoDB

• Subcellular Level:
• Cellular compartments involved (mitochondria, nucleus, ER, lysosomes) (with GO Cellular Component terms)

  Search first: Gene Ontology (Cellular Component), UniProt, Human Protein Atlas

• Localization:
• Specific anatomical sites (with UBERON terms) > Search first: FMA, Uberon, NeuroNames (for brain), SNOMED CT
• Lateralization (unilateral, bilateral, asymmetric) > Search first: HPO, clinical literature, imaging databases

8. Temporal Development

• Onset:
• Typical age of onset (congenital, pediatric, adult, geriatric)
• Onset pattern (acute, subacute, chronic, insidious)

  Search first: OMIM, Orphanet, HPO, PubMed

• Progression:
• Disease stages (early, intermediate, advanced, end-stage) > Search first: Cancer Staging Manual (AJCC), WHO classifications, PubMed
• Progression rate (rapid, slow, variable)
• Disease course pattern (episodic, relapsing-remitting, progressive, stable)
• Disease duration (self-limited, chronic lifelong)

  Search first: Disease registries, longitudinal cohort databases, natural history studies, PubMed, Orphanet, OMIM

• Patterns:
• Remission patterns (spontaneous, treatment-induced) > Search first: Clinical trial databases, disease registries, PubMed
• Critical periods (time windows of vulnerability or opportunity for intervention) > Search first: PubMed, developmental biology databases, clinical guidelines

9. Inheritance and Population

• Epidemiology:
• Prevalence (cases per 100,000 at given time)
• Incidence (new cases per 100,000 per year)

  Search first: Orphanet, CDC, WHO, GBD (Global Burden of Disease), national registries, SEER, disease registries

• For Genetic Etiology:
• Inheritance pattern (AD, AR, X-linked, mitochondrial, multifactorial, polygenic) > Search first: OMIM, Orphanet, ClinVar, GTR (Genetic Testing Registry)
• Penetrance (complete, incomplete, age-dependent) > Search first: ClinVar, OMIM, PubMed, ClinGen
• Expressivity (variable, consistent) > Search first: OMIM, ClinVar, PubMed
• Genetic anticipation (increasing severity in successive generations) > Search first: OMIM, PubMed (especially for repeat expansion disorders)
• Germline mosaicism > Search first: ClinVar, OMIM, genetic counseling literature, PubMed
• Founder effects (population-specific mutations) > Search first: gnomAD, population genetics databases, PubMed
• Consanguinity role > Search first: OMIM, population studies, genetic counseling resources
• Carrier frequency > Search first: gnomAD, carrier screening databases, GeneReviews, GTR
• Population Demographics:
• Affected populations (ethnic or demographic groups with higher prevalence) > Search first: gnomAD, 1000 Genomes, PAGE Study, PubMed, population registries
• Geographic distribution (endemic areas, regional variation) > Search first: WHO, CDC, GBD, Orphanet, geographic epidemiology databases
• Geographic distribution of specific variants
• Sex ratio (male:female) > Search first: Disease registries, OMIM, PubMed, epidemiological databases
• Age distribution of affected individuals > Search first: CDC, disease registries, SEER, Orphanet

10. Diagnostics

• Clinical Tests:
• Laboratory tests (blood, urine, tissue chemistry, specific enzyme assays) > Search first: LOINC, LabTests Online, PubMed
• Biomarkers (proteins, metabolites, genetic markers, circulating biomarkers) > Search first: FDA Biomarker List, BEST (Biomarkers, EndpointS, and other Tools), PubMed
• Imaging studies (X-ray, CT, MRI, PET, ultrasound) > Search first: RadLex, DICOM, Radiopaedia, imaging databases
• Functional tests (pulmonary function, cardiac stress tests) > Search first: LOINC, clinical guidelines, PubMed
• Electrophysiology (EEG, EMG, ECG, nerve conduction studies) > Search first: LOINC, clinical neurophysiology databases, PubMed
• Biopsy findings (histopathology, immunohistochemistry) > Search first: SNOMED CT, College of American Pathologists resources, PubMed
• Pathology findings (microscopic examination) > Search first: SNOMED CT, Digital Pathology databases, PubMed
• Genetic Testing:

  Search first: GTR (Genetic Testing Registry), GeneReviews, ClinGen

• Overview of recommended genetic testing approach
• Whole genome sequencing (WGS) utility > Search first: GTR, ClinVar, GEL (Genomics England), gnomAD
• Whole exome sequencing (WES) utility > Search first: GTR, ClinVar, OMIM, GeneMatcher
• Gene panels (which panels, which genes) > Search first: GTR, ClinVar, laboratory-specific databases
• Single gene testing > Search first: GTR, ClinVar, OMIM, GeneReviews
• Chromosomal microarray (CMA) > Search first: DECIPHER, ClinVar, dbVar, ECARUCA
• Karyotyping > Search first: Chromosome Abnormality Database, ClinVar, cytogenetics resources
• FISH > Search first: ClinVar, cytogenetics databases, PubMed
• Mitochondrial DNA testing > Search first: MITOMAP, MSeqDR, ClinVar, GTR
• Repeat expansion testing > Search first: GTR, ClinVar, repeat expansion databases, PubMed
• Omics-Based Diagnostics (if applicable):
• RNA sequencing / transcriptomics > Search first: GEO, ArrayExpress, GTEx, RNA-seq databases
• Proteomics > Search first: PRIDE, ProteomeXchange, FDA Biomarker database
• Metabolomics > Search first: MetaboLights, Metabolomics Workbench, HMDB
• Epigenomics > Search first: GEO, ENCODE, Roadmap Epigenomics, MethBase
• Liquid biopsy > Search first: COSMIC, ClinVar, liquid biopsy databases, PubMed
• Clinical Criteria:
• Standardized diagnostic criteria (DSM, ICD, society guidelines) > Search first: DSM-5, ICD-11, clinical society guidelines, UpToDate
• Differential diagnosis (other conditions to rule out, with distinguishing features) > Search first: DynaMed, UpToDate, clinical decision support systems
• Screening:
• Screening methods for asymptomatic individuals (newborn screening, carrier screening, cascade screening) > Search first: ACMG recommendations, CDC newborn screening, GTR

11. Outcome/Prognosis

• Survival and Mortality:
• Survival rate (5-year, 10-year, overall) > Search first: SEER, cancer registries, disease-specific registries, PubMed
• Life expectancy (with and without treatment if applicable) > Search first: Orphanet, disease registries, actuarial databases, PubMed
• Mortality rate > Search first: CDC, WHO, GBD, national mortality databases
• Disease-specific mortality (deaths directly attributable to disease) > Search first: Disease registries, CDC Wonder, GBD, PubMed
• Morbidity and Function:
• Morbidity (disease-related disability and health impacts) > Search first: GBD, WHO, disability databases, PubMed
• Disability outcomes (long-term functional impairments) > Search first: ICF (International Classification of Functioning), disability registries
• Quality of life measures (EQ-5D, SF-36, PROMIS, disease-specific tools) > Search first: EQ-5D database, SF-36, PROMIS, PubMed
• Disease Course:
• Complications (secondary problems: infections, organ failure, etc.) > Search first: ICD codes, disease registries, clinical databases, PubMed
• Recovery potential (likelihood and extent of recovery, with vs without treatment) > Search first: Natural history studies, rehabilitation databases, PubMed
• Prediction:
• Prognostic factors (age, disease severity, biomarkers, treatment response) > Search first: Prognostic models databases, clinical calculators, PubMed
• Prognostic biomarkers (molecular markers predicting disease course) > Search first: FDA Biomarker database, PubMed, cancer prognostic databases

12. Treatment

• Pharmacotherapy:
• Pharmacological treatments (drug names, drug classes, mechanisms of action) > Search first: DrugBank, RxNorm, ATC classification, DailyMed, FDA databases
• Pharmacogenomics (how genetic variants affect drug metabolism, efficacy, toxicity) > Search first: PharmGKB, CPIC (Clinical Pharmacogenetics), FDA Table of PGx Biomarkers
• Advanced Therapeutics:
• Gene therapy (viral vectors, CRISPR, gene replacement, gene editing) > Search first: ClinicalTrials.gov, FDA gene therapy database, ASGCT resources
• Cell therapy (stem cell transplant, CAR-T, cellular therapeutics) > Search first: ClinicalTrials.gov, FDA cell therapy database, FACT standards
• RNA-based therapies (ASOs, siRNA, mRNA therapies) > Search first: ClinicalTrials.gov, FDA approvals, PubMed
• Targeted therapies (treatments directed at specific molecular targets) > Search first: My Cancer Genome, OncoKB, ClinicalTrials.gov, FDA approvals
• Immunotherapies (checkpoint inhibitors, monoclonal antibodies) > Search first: Cancer Immunotherapy Database, FDA approvals, ClinicalTrials.gov
• Surgical and Interventional:
• Surgical interventions (types of surgery, timing, outcomes) > Search first: CPT codes, surgical registries, clinical guidelines, PubMed
• Supportive and Rehabilitative:
• Supportive care (symptom management, pain control, nutrition) > Search first: Clinical guidelines, Cochrane Library, PubMed
• Rehabilitation (physical therapy, occupational therapy, speech therapy) > Search first: Rehabilitation medicine databases, clinical guidelines, PubMed
• Experimental:
• Experimental treatments in clinical trials (with NCT identifiers if available) > Search first: ClinicalTrials.gov, EU Clinical Trials Register, WHO ICTRP
• Treatment Outcomes:
• Treatment response rates > Search first: Clinical trial databases, FDA reviews, systematic reviews, PubMed
• Side effects and adverse events > Search first: FDA Adverse Event Reporting System (FAERS), MedWatch, PubMed
• Treatment Strategy:
• Treatment algorithms (clinical pathways, decision trees) > Search first: Clinical practice guidelines, NCCN Guidelines, UpToDate
• Combination therapies > Search first: ClinicalTrials.gov, treatment guidelines, PubMed
• Personalized medicine approaches (genotype-guided treatment) > Search first: My Cancer Genome, CIViC, PharmGKB, precision medicine databases

For each treatment, suggest MAXO (Medical Action Ontology) terms where applicable.

13. Prevention

• Prevention Levels:
• Primary prevention (preventing disease occurrence: vaccination, risk factor modification) > Search first: CDC, WHO, USPSTF recommendations, Cochrane Library
• Secondary prevention (early detection and treatment: screening programs, early intervention) > Search first: USPSTF, CDC screening guidelines, WHO
• Tertiary prevention (preventing complications in those with disease) > Search first: Clinical guidelines, disease management protocols, PubMed
• Immunization: Vaccine strategies (if applicable)

  Search first: CDC vaccine schedules, WHO immunization, FDA vaccine database

• Screening and Early Detection:
• Screening programs (population-based: newborn screening, cancer screening) > Search first: CDC screening programs, USPSTF, cancer screening databases
• Genetic screening (carrier screening, preimplantation genetic diagnosis, prenatal testing) > Search first: ACMG recommendations, ACOG guidelines, GTR
• Risk stratification (identifying high-risk individuals for targeted prevention) > Search first: Risk prediction models, clinical calculators, PubMed
• Behavioral Interventions: Lifestyle modifications to reduce risk

  Search first: CDC, WHO, behavioral intervention databases, Cochrane Library

• Counseling: Genetic counseling (risk assessment, family planning guidance)

  Search first: NSGC resources, ACMG guidelines, GeneReviews

• Public Health:
• Public health interventions (sanitation, vector control, health education) > Search first: CDC, WHO, public health databases, PubMed
• Environmental interventions (reducing environmental risk factors) > Search first: EPA databases, WHO environmental health, PubMed
• Prophylaxis: Preventive medications or procedures

  Search first: Clinical guidelines, FDA approvals, PubMed

14. Other Species / Natural Disease

• Taxonomy: Species affected (with NCBI Taxon identifiers)

  Search first: NCBI Taxonomy

• Breed: Specific breeds affected (with VBO identifiers if applicable)

  Search first: VBO (Vertebrate Breed Ontology)

• Gene: Orthologous genes in other species (with NCBI Gene IDs)

  Search first: NCBI Gene

• Natural Disease:
• Naturally occurring disease in other species (companion animals, wildlife) > Search first: OMIA (Online Mendelian Inheritance in Animals), VetCompass, PubMed
• Veterinary relevance and importance in animal health > Search first: OMIA, veterinary databases, PubMed
• Comparative Biology:
• Comparative pathology (similarities and differences across species) > Search first: OMIA, comparative pathology databases, PubMed
• Evolutionary conservation of disease mechanisms > Search first: HomoloGene, OrthoMCL, Alliance of Genome Resources
• Transmission (if applicable):
• Zoonotic potential > Search first: CDC zoonotic diseases, WHO zoonoses, GIDEON
• Cross-species susceptibility > Search first: NCBI Taxonomy, veterinary databases, PubMed

15. Model Organisms

• Model Types:
• Model organism type (mammalian, invertebrate, cellular, in vitro) > Search first: Alliance of Genome Resources, model organism databases
• Specific model systems (mouse, rat, zebrafish, Drosophila, C. elegans, yeast, cell lines, organoids, iPSCs) > Search first: MGI, RGD, ZFIN, FlyBase, WormBase, SGD, ATCC, Cellosaurus
• Induced models (drug treatment, surgical intervention, environmental manipulation) > Search first: MGI, model organism databases, PubMed
• Genetic Models:
• Types available (knockout, knock-in, transgenic, conditional, humanized) > Search first: MGI, IMPC, KOMP, EuMMCR, IMSR
• Model Characteristics:
• Phenotype recapitulation (how well model reproduces human disease features) > Search first: Model organism databases, comparative studies, PubMed
• Model limitations (aspects of human disease not captured) > Search first: Model organism databases, PubMed, review articles
• Applications:
• Research applications (what aspects of disease can be studied) > Search first: Model organism databases, PubMed
• Resources:
• Model databases > Search first: MGI, RGD, ZFIN, FlyBase, WormBase, IMSR, EMMA, MMRRC

Citation Requirements

• Cite primary literature (PMID preferred) for all mechanistic and clinical claims
• Prioritize recent reviews and landmark papers
• Include direct quotes from abstracts where possible to support key statements
• Distinguish evidence source types: human clinical, model organism, in vitro, computational

Output Format

Structure your response as a comprehensive narrative organized by the sections above. For each section, provide: - Factual content with specific details (numbers, percentages, gene names, variant nomenclature) - Ontology term suggestions (HPO, GO, CL, UBERON, CHEBI, MAXO, MONDO) where applicable - Evidence citations with PMIDs - Direct quotes from abstracts to support key claims - Clear indication when information is not available or not applicable for this disease

This report will be used to populate a disease knowledge base entry with: - Pathophysiology descriptions with causal chains - Gene/protein annotations (HGNC, GO terms) - Phenotype associations (HP terms) with frequencies - Cell type involvement (CL terms) - Anatomical locations (UBERON terms) - Chemical entities (CHEBI terms) - Treatment annotations (MAXO terms) - Evidence items with PMIDs and exact abstract quotes - Epidemiology, prognosis, diagnostic, and prevention information - Animal model descriptions with phenotype recapitulation details

ROS1-Rearranged Non-Small Cell Lung Cancer (ROS1+ NSCLC): Disease Characteristics Report (2023–2024 emphasis)

Target disease

• Disease name: ROS1-rearranged non-small cell lung cancer (ROS1 fusion–positive NSCLC)
• Category: Molecularly-defined subtype of lung adenocarcinoma / NSCLC (oncogene-driven thoracic malignancy) (testa2023ros1rearrangedlungadenocarcinoma pages 1-2)
• MONDO ID: Not identified in the retrieved sources in this run (information gap).

1. Disease information

Overview (current understanding)

ROS1-rearranged NSCLC is a molecular subset of NSCLC characterized by chromosomal rearrangements that create ROS1 gene fusions with constitutive kinase activation, conferring sensitivity to ROS1 tyrosine kinase inhibitors (TKIs). Reviews consistently describe ROS1 fusions in ~1–2.5% of NSCLC and occurring predominantly in lung adenocarcinoma and often in never-smokers/younger patients (testa2023ros1rearrangedlungadenocarcinoma pages 1-2).

Representative abstract quote (definition/epidemiology): - “A molecular subset of NSCLC (1–2.5%) harboring molecular rearrangements of the tyrosine kinase gene ROS1 is defined as ROS1-positive and is almost exclusively diagnosed in patients with lung adenocarcinoma histology, predominantly nonsmokers.” (Testa et al., 2023) (testa2023ros1rearrangedlungadenocarcinoma pages 1-2)

Common synonyms / alternative names

• ROS1+ NSCLC; ROS1 fusion-positive NSCLC; ROS1-positive lung adenocarcinoma; ROS1-rearranged lung adenocarcinoma (janzic2024nonsmallcelllungcancer pages 11-13, testa2023ros1rearrangedlungadenocarcinoma pages 1-2).

Key identifiers (ontology/code gaps)

The retrieved sources did not provide explicit mappings to ICD-10/ICD-11, MeSH, MONDO, Orphanet, or OMIM entries for this molecular subtype (information gap for this run). The disease is typically operationalized in oncology practice/guidelines as NSCLC with a ROS1 fusion rather than a standalone nosologic code (boulanger2024advancesandfuture pages 2-3).

Data provenance

The evidence cited here is derived from: - Aggregated disease-level resources (recent reviews and FDA approval summary) (barbato2024fdaapprovalsummary pages 3-4, boulanger2024advancesandfuture pages 1-2) - Prospective interventional clinical trial data (TRIDENT-1; TRUST-I) (drilon2024repotrectinibinros1 pages 1-3, li2024efficacyandsafety pages 1-2) - Prospective biomarker-driven platform trial (liquid biopsy selection) (BFAST Cohort D) (peters2024entrectinibinros1positive pages 5-6, peters2024entrectinibinros1positive pages 3-4) - Real-world retrospective cohort (ROS1REAL) (janzic2024nonsmallcelllungcancer pages 1-2, janzic2024nonsmallcelllungcancer pages 5-7)

2. Etiology

Disease causal factors

Primary causal factor: acquisition of oncogenic ROS1 rearrangements/fusions (somatic driver alteration). The ROS1 kinase domain is fused to an N-terminal partner gene, yielding constitutive signaling and oncogenic dependency on ROS1 kinase activity (testa2023ros1rearrangedlungadenocarcinoma pages 1-2, testa2023ros1rearrangedlungadenocarcinoma pages 4-5).

Risk factors and demographics (proxy for etiology)

Across multiple sources, ROS1+ NSCLC is enriched in: - Never-smokers and younger patients compared with unselected NSCLC (janzic2024nonsmallcelllungcancer pages 1-2, testa2023ros1rearrangedlungadenocarcinoma pages 1-2).

TRUST-I (China) demographic data (2024): median age 55; 58% female; 73% never smoked (li2024efficacyandsafety pages 1-2, li2024efficacyandsafety pages 3-5).

Protective factors / gene–environment interactions

No specific protective factors or gene–environment interaction evidence was present in the retrieved texts (information gap).

3. Phenotypes (clinical presentation) and natural history

Core clinical phenotype

Clinical features are those of lung cancer/advanced NSCLC; importantly, patients frequently present with advanced stage and CNS involvement.

Advanced-stage presentation / CNS disease: A 2024 review reports that ~85% present with stage IV disease and 20–40% have brain metastases at diagnosis (boulanger2024advancesandfuture pages 1-2).

Abstract quote (CNS and resistance framing): - “The early-generation ROS1 tyrosine kinase inhibitors (TKIs)… have antitumor activity, but resistance develops in tumors, and intracranial activity is suboptimal.” (Drilon et al., 2024) (drilon2024repotrectinibinros1 pages 1-3)

Quality of life impact

QoL endpoints were not directly reported in the retrieved excerpts (information gap). However, treatment-emergent neurologic AEs (e.g., dizziness, dysgeusia, neuropathy) are common with some ROS1 TKIs and may affect daily functioning (barbato2024fdaapprovalsummary pages 13-15, drilon2024repotrectinibinros1 pages 7-8).

Suggested HPO terms (examples; to be validated against specific patient-level descriptions)

Given the lung cancer context and CNS involvement emphasis in this subtype: - HP:0002094 Dyspnea (relevant in advanced NSCLC; also appears as an AE context in repotrectinib safety listing) (barbato2024fdaapprovalsummary pages 1-3) - HP:0001945 Fever (general cancer symptom; not specifically documented in retrieved excerpts—use cautiously) - HP:0001250 Seizure / HP:0002511 Brain metastasis (brain metastasis is a clinical state; HPO mapping often uses neurologic manifestations—evidence supports frequent brain metastases but not specific neurologic symptom frequencies) (boulanger2024advancesandfuture pages 1-2) - HP:0001290 Dizziness (also a common repotrectinib AE, can be recorded as a phenotype/adverse event) (drilon2024repotrectinibinros1 pages 7-8)

Note: This run did not retrieve dedicated phenotype frequency tables; additional phenotype-specific sources would be needed for robust HPO frequency annotation.

4. Genetic / molecular information

Causal gene and alteration class

• Causal gene: ROS1 (proto-oncogene receptor tyrosine kinase) (testa2023ros1rearrangedlungadenocarcinoma pages 1-2)
• Alteration type: Somatic gene fusion/rearrangement involving ROS1 kinase domain (structural variant/translocation) (testa2023ros1rearrangedlungadenocarcinoma pages 1-2).

Common fusion partners (with reported frequencies)

A 2023 review compiled partner frequencies including: - CD74–ROS1 ~49.8% - EZR–ROS1 ~23.6% - SDC4–ROS1 ~9.1% - SLC34A2–ROS1 ~5.1% (testa2023ros1rearrangedlungadenocarcinoma pages 4-5)

Oncogenic mechanisms and pathways

ROS1 fusions signal through canonical RTK pathways including MAPK. - Example mechanistic detail: EZR–ROS1 and SLC34A2–ROS1 can engage GRB2–SOS1 complexes, activating MAPK signaling (testa2023ros1rearrangedlungadenocarcinoma pages 4-5).

Suggested GO biological process terms (examples): - GO:0007169 transmembrane receptor protein tyrosine kinase signaling pathway - GO:0000165 MAPK cascade

Resistance mechanisms (current understanding)

Resistance emerges under TKI selective pressure and includes: - On-target ROS1 kinase domain mutations, especially solvent-front ROS1 G2032R; also gatekeeper and other mutations (e.g., L2026M; S1986F/Y) (barbato2024fdaapprovalsummary pages 4-6, stanzione2023therapeuticaloptionsin pages 7-8). - Off-target/bypass mechanisms (reported in review context) including MAPK pathway activation and MET alterations, among others (testa2023ros1rearrangedlungadenocarcinoma pages 15-16, stanzione2023therapeuticaloptionsin pages 7-8).

Repotrectinib resistance subgroup results (TRIDENT-1): 10/17 (59%) responses in baseline ROS1 G2032R mutant disease (drilon2024repotrectinibinros1 pages 7-8).

Epigenetics / multi-omics

No epigenetic or multi-omics profiling results specific to ROS1+ NSCLC were captured in the retrieved excerpts (information gap).

5. Environmental information

Environmental and lifestyle causal factors specific to developing ROS1 fusions were not described in the retrieved sources. Patient populations are frequently never-smokers (suggesting ROS1 fusions arise in a distinct etiologic context compared with smoking-driven NSCLC), but no specific environmental triggers were identified here (li2024efficacyandsafety pages 1-2).

6. Mechanism / pathophysiology

Causal chain (high-level)

1. Somatic chromosomal rearrangement generates a ROS1 fusion oncoprotein (structural variant). (testa2023ros1rearrangedlungadenocarcinoma pages 1-2)
2. Fusion leads to constitutive ROS1 kinase signaling and downstream pathway activation (e.g., MAPK), driving proliferation/survival. (testa2023ros1rearrangedlungadenocarcinoma pages 4-5)
3. Tumor becomes oncogene addicted to ROS1 signaling, yielding marked responses to ROS1 TKIs. (boulanger2024advancesandfuture pages 1-2)
4. Under therapy, acquired resistance develops (on-target mutations such as G2032R, bypass signaling), causing progression; CNS sanctuary sites are clinically important due to variable BBB penetration. (boulanger2024advancesandfuture pages 2-3, stanzione2023therapeuticaloptionsin pages 7-8)

Cell types (suggested)

• Primary malignant population is typically lung epithelial tumor cells (adenocarcinoma lineage) (testa2023ros1rearrangedlungadenocarcinoma pages 1-2).

Suggested CL terms (examples): - CL:0000084 T cell (relevance for immunotherapy context; not mechanistically emphasized here) - CL:0000066 epithelial cell (tumor cell-of-origin context)

Note: The retrieved sources did not provide single-cell or spatial transcriptomics evidence.

7. Anatomical structures affected

Primary organ/system

• Lung (UBERON:0002048) as the primary site of malignancy (lung adenocarcinoma predominance) (testa2023ros1rearrangedlungadenocarcinoma pages 1-2).

Secondary involvement / metastasis

• Brain/CNS involvement is common: 20–40% have brain metastases at diagnosis per 2024 review, and intracranial endpoints are central to modern ROS1 TKI development (boulanger2024advancesandfuture pages 1-2, drilon2024repotrectinibinros1 pages 7-8).

8. Temporal development

Onset and progression

• Typically adult-onset; many patients present with advanced (stage IV) disease (~85% in a 2024 review) (boulanger2024advancesandfuture pages 1-2).
• Disease course in the targeted-therapy era is characterized by initial response to ROS1 TKIs and eventual acquired resistance with progression, including CNS progression patterns (boulanger2024advancesandfuture pages 1-2, boulanger2024advancesandfuture pages 2-3).

9. Inheritance and population

Inheritance

Not inherited in a Mendelian pattern in standard clinical framing; ROS1 fusions are somatic tumor alterations (testa2023ros1rearrangedlungadenocarcinoma pages 1-2).

Epidemiology

• Frequency in NSCLC: typically ~1–2% (boulanger2024advancesandfuture pages 1-2) and ~1–2.5% in another review (testa2023ros1rearrangedlungadenocarcinoma pages 1-2).
• Estimated global annual case count: ~18,500–37,000 new cases worldwide annually (boulanger2024advancesandfuture pages 1-2).

Population demographics

• Enrichment in never-smokers and younger patients (janzic2024nonsmallcelllungcancer pages 1-2, testa2023ros1rearrangedlungadenocarcinoma pages 1-2).
• TRUST-I: 73% never smoked; 58% female (li2024efficacyandsafety pages 1-2).

10. Diagnostics

Testing modalities (current practice)

Methods used for ROS1 fusion detection include: - FISH, IHC, RT-PCR, NGS (tissue-based and, increasingly, liquid biopsy-based) (boulanger2024advancesandfuture pages 2-3).

A 2024 expert review notes “NGS is a preferred method” (broad profiling and fusion detection), while liquid biopsy is useful when tissue is limited but can be less sensitive than tissue NGS (boulanger2024advancesandfuture pages 2-3).

Liquid biopsy (real-world implementation and performance implication)

BFAST Cohort D operationalized an all-blood (ctDNA) selection approach and demonstrated strong entrectinib activity in a liquid-biopsy identified cohort.

Abstract quote (liquid biopsy value): - “Genomic testing in liquid biopsies can be utilized to overcome the inherent limitations of tissue sampling and identify the most appropriate biomarker-informed treatment option for patients.” (Peters et al., 2024) (peters2024entrectinibinros1positive pages 1-2)

Diagnostic yield statistic from BFAST screening

• Among 5,220 patients screened, 92 (1.8%) were ROS1-positive by blood NGS (peters2024entrectinibinros1positive pages 2-3).

11. Outcome / prognosis

Targeted-therapy era outcomes (selected)

Modern next-generation ROS1 TKIs yield prolonged systemic disease control in TKI-naïve patients: - Repotrectinib (TKI-naïve): median PFS 35.7 months (drilon2024repotrectinibinros1 pages 1-3) - Taletrectinib TRUST-I (TKI-naïve): 24-month PFS 70.5% and DoR 78.6% (li2024efficacyandsafety pages 3-5)

CNS control is a key outcome dimension; repotrectinib shows high intracranial response rates in measurable CNS disease (drilon2024repotrectinibinros1 pages 7-8).

Prognostic factors (evidence captured here)

• Co-alterations such as TP53 are discussed as negatively impacting outcomes in review context (and were associated with numerically shorter outcomes in BFAST post hoc analyses) (testa2023ros1rearrangedlungadenocarcinoma pages 15-16, peters2024entrectinibinros1positive pages 5-6).

Note: This run did not retrieve population registry (SEER/GBD) 5-year survival statistics specific to ROS1+ NSCLC.

12. Treatment

Current applications (approved and guideline-preferred systemic therapies)

A 2024 expert review describes the preferred FDA-approved first-line therapies as: - Crizotinib - Entrectinib - Repotrectinib (boulanger2024advancesandfuture pages 1-2)

Abstract quote (practice framing): - “The preferred Food and Drug Administration-approved first-line therapies include crizotinib, entrectinib, and repotrectinib, and currently, selection amongst these options requires consideration of the systemic and CNS efficacy, tolerability, and access to therapy.” (Boulanger et al., 2024) (boulanger2024advancesandfuture pages 1-2)

Repotrectinib (next-generation ROS1 TKI; FDA approval; TRIDENT-1)

• FDA approval date: Nov 15, 2023 for adult locally advanced/metastatic ROS1+ NSCLC, based on TRIDENT-1 (NCT03093116) (barbato2024fdaapprovalsummary pages 1-3).
• TRIDENT-1 (NEJM 2024) systemic efficacy:
• TKI-naïve (n=71): ORR 79%, median DoR 34.1 months, median PFS 35.7 months (drilon2024repotrectinibinros1 pages 1-3).
• Prior 1 ROS1 TKI, no chemotherapy (n=56): ORR 38%, median DoR 14.8 months, median PFS 9.0 months (drilon2024repotrectinibinros1 pages 1-3).
• Intracranial activity:
• FDA summary: measurable CNS disease had intracranial responses in 7/8 TKI-naïve and 5/12 pretreated patients (barbato2024fdaapprovalsummary pages 3-4, barbato2024fdaapprovalsummary pages 4-6).
• NEJM report: measurable brain metastases intracranial responses 8/9 (89%) in TKI-naïve and 5/13 (38%) in one-TKI pretreated; estimated 12-month intracranial PFS 91% and 82%, respectively (drilon2024repotrectinibinros1 pages 7-8).
• Resistance mutation activity:
• Baseline ROS1 G2032R: ORR 59% (10/17) (drilon2024repotrectinibinros1 pages 1-3, drilon2024repotrectinibinros1 pages 7-8).
• Key safety signals: dizziness/dysgeusia/paresthesia are common; discontinuation due to treatment-related AEs 3% in NEJM summary (drilon2024repotrectinibinros1 pages 1-3, drilon2024repotrectinibinros1 pages 7-8).

Abstract quote (repotrectinib efficacy): - “Response occurred in 56 of the 71 patients (79%… ) with ROS1 fusion-positive NSCLC who had not previously received a ROS1 TKI…” (Drilon et al., 2024) (drilon2024repotrectinibinros1 pages 1-3)

Entrectinib (CNS-active ROS1/ALK/TRK inhibitor; BFAST 2024)

• BFAST Cohort D (Nature Medicine 2024; ctDNA-selected): confirmed ORR 81.5% (95% CI 68.6–90.8); median PFS 12.9 months (95% CI 8.7–18.5); median DoR 13.0 months (95% CI 6.3–18.4) (peters2024entrectinibinros1positive pages 5-6, peters2024entrectinibinros1positive pages 3-4).
• CNS control: 12-month CNS progression-free rate 86.4% (IRF) with median time to CNS progression not reached (peters2024entrectinibinros1positive pages 2-3, peters2024entrectinibinros1positive pages 6-7).

Taletrectinib (next-generation ROS1 TKI; TRUST-I 2024)

• TRUST-I (JCO 2024; NCT04395677; China):
• TKI-naïve: confirmed ORR 91%, intracranial confirmed ORR 88%; median PFS and DoR not reached at ~22–23 month follow-up (li2024efficacyandsafety pages 1-2).
• Crizotinib-pretreated: ORR 52%, intracranial ORR 73%; median PFS 7.6 months; median DoR 10.6 months (li2024efficacyandsafety pages 1-2).
• G2032R: 8/12 (67%) responded (li2024efficacyandsafety pages 1-2).

Crizotinib (first-generation ROS1 TKI)

Crizotinib established the targeted-therapy paradigm for ROS1+ NSCLC; PROFILE 1001 outcomes summarized in reviews include ORR 72% and median PFS ~19.2–19.3 months and median OS ~51.4 months, but with limited BBB penetration and CNS relapses (boulanger2024advancesandfuture pages 2-3, testa2023ros1rearrangedlungadenocarcinoma pages 4-5).

Sequencing and resistance management (expert analysis)

• Resistance “invariably develops” and subsequent therapy decisions should account for progression pattern and (when known) resistance mechanism (boulanger2024advancesandfuture pages 1-2).
• Next-generation TKIs aim to broaden resistance mutation coverage and improve CNS penetration (boulanger2024advancesandfuture pages 1-2, stanzione2023therapeuticaloptionsin pages 7-8).

Real-world implementation: ROS1REAL (2024)

In a multicenter retrospective cohort (n=49 advanced cases), first-line utilization and outcomes were: - First-line distribution: crizotinib 57%, entrectinib/repotrectinib 29%, platinum doublet 14% (janzic2024nonsmallcelllungcancer pages 5-7). - ORR/DCR: crizotinib 68%/82% vs newer agents 86%/93% (janzic2024nonsmallcelllungcancer pages 1-2). - Median PFS: 1.6 years (crizotinib) vs 2.35 years (entrectinib/repotrectinib) (janzic2024nonsmallcelllungcancer pages 1-2).

Treatment mapping to MAXO (suggestions)

• ROS1 tyrosine kinase inhibitor therapy (e.g., crizotinib, entrectinib, repotrectinib, taletrectinib)
• Antineoplastic chemotherapy (e.g., platinum doublet)
• Molecularly targeted therapy

Note: Exact MAXO IDs were not retrieved in this run.

13. Prevention

No ROS1-specific primary prevention strategies were described in retrieved sources. Secondary prevention in practice relies on lung cancer detection paradigms and, for patients with advanced NSCLC, comprehensive biomarker testing before initiating systemic therapy (as emphasized in BFAST background) (peters2024entrectinibinros1positive pages 1-2).

14. Other species / natural disease

No naturally occurring ROS1-rearranged NSCLC analogs in non-human species were described in retrieved sources (information gap).

15. Model organisms

The retrieved excerpts reference that ROS1 fusions can be tumorigenic in transgenic mouse models (preclinical evidence for oncogenicity), but no specific strain/model identifiers were captured in the provided excerpts (testa2023ros1rearrangedlungadenocarcinoma pages 4-5).

Key 2023–2024 developments (highlights)

1. Repotrectinib demonstrated long PFS in TKI-naïve ROS1+ NSCLC (median PFS 35.7 months) and intracranial activity, supporting its FDA approval (Nov 2023) and subsequent FDA approval summary publication (2024) (drilon2024repotrectinibinros1 pages 1-3, barbato2024fdaapprovalsummary pages 1-3).
2. Liquid biopsy-selected treatment strategy validated in BFAST Cohort D for entrectinib, providing prospective evidence that ctDNA-based ROS1 detection can support effective targeted therapy selection (peters2024entrectinibinros1positive pages 1-2, peters2024entrectinibinros1positive pages 5-6).
3. Taletrectinib TRUST-I (2024) reported high systemic and intracranial response rates in both TKI-naïve and crizotinib-pretreated populations, including activity in G2032R (li2024efficacyandsafety pages 1-2).

Summary table of key trial and real-world statistics

Table: This table compares pivotal and real-world efficacy, durability, CNS activity, and adverse-event patterns across major ROS1-targeted therapies in ROS1-positive NSCLC. It is useful for quickly contrasting first-generation and next-generation inhibitors, especially for CNS disease and resistance settings.

Image-based evidence (key efficacy visualizations)

The TRIDENT-1 NEJM publication includes figures and a results table summarizing systemic and intracranial efficacy for repotrectinib (waterfall plots, Kaplan–Meier PFS, intracranial response/PFS). (drilon2024repotrectinibinros1 media ec1cfcb8, drilon2024repotrectinibinros1 media 29c59cf5, drilon2024repotrectinibinros1 media 7dc28074)

Evidence limitations and gaps for knowledge-base completion

• This run did not retrieve explicit ontology identifiers (MONDO/MeSH/ICD) for the molecular subtype.
• Several excerpts lacked PMIDs; where absent, DOIs/URLs and publication months/years are provided.
• Phenotype frequency (HPO) and QoL outcomes were not systematically captured in available excerpts.
• Prevention, environmental triggers, other species natural disease, and detailed model organism resources require additional targeted searches.

References

1. (testa2023ros1rearrangedlungadenocarcinoma pages 1-2): Ugo Testa, Germana Castelli, and Elvira Pelosi. Ros1-rearranged lung adenocarcinoma: from molecular genetics to target therapy. Onco, 3:189-204, Aug 2023. URL: https://doi.org/10.3390/onco3030014, doi:10.3390/onco3030014. This article has 4 citations.

2. (janzic2024nonsmallcelllungcancer pages 11-13): Urska Janzic, Natalie Maimon Rabinovich, Walid Shalata, Waleed Kian, Katarzyna Szymczak, Rafal Dziadziuszko, Marko Jakopovic, Giannis Mountzios, Adam Pluzanski, Antonio Araujo, Andriani Charpidou, Sameh Daher, and Abed Agbarya. Non-small-cell lung cancer patients harboring ros1 rearrangement: real world testing practices, characteristics and treatment patterns (ros1real study). Current Oncology, 31:4369-4381, Jul 2024. URL: https://doi.org/10.3390/curroncol31080326, doi:10.3390/curroncol31080326. This article has 7 citations.

3. (boulanger2024advancesandfuture pages 2-3): Mary C Boulanger, Jaime L Schneider, and Jessica J Lin. Advances and future directions in ros1 fusion-positive lung cancer. The Oncologist, 29:943-956, Aug 2024. URL: https://doi.org/10.1093/oncolo/oyae205, doi:10.1093/oncolo/oyae205. This article has 28 citations.

4. (barbato2024fdaapprovalsummary pages 3-4): Michael I. Barbato, Diana Bradford, Yi Ren, Stephanie L. Aungst, Claudia P. Miller, Lili Pan, Jeanne F. Zirkelbach, Yangbing Li, Youwei Bi, Jianghong Fan, Manuela Grimstein, Sarah E. Dorff, Anup K. Amatya, Pallavi S. Mishra-Kalyani, Barbara Scepura, Peter Schotland, Opeyemi Udoka, Idara Ojofeitimi, John K. Leighton, Nam A. Rahman, Richard Pazdur, Harpreet Singh, Paul G. Kluetz, and Nicole Drezner. Fda approval summary: repotrectinib for locally advanced or metastatic ros1-positive non-small cell lung cancer. Clinical cancer research : an official journal of the American Association for Cancer Research, 30:3364-3370, Jun 2024. URL: https://doi.org/10.1158/1078-0432.ccr-24-0949, doi:10.1158/1078-0432.ccr-24-0949. This article has 19 citations.

5. (boulanger2024advancesandfuture pages 1-2): Mary C Boulanger, Jaime L Schneider, and Jessica J Lin. Advances and future directions in ros1 fusion-positive lung cancer. The Oncologist, 29:943-956, Aug 2024. URL: https://doi.org/10.1093/oncolo/oyae205, doi:10.1093/oncolo/oyae205. This article has 28 citations.

6. (drilon2024repotrectinibinros1 pages 1-3): Alexander Drilon, D. Ross Camidge, Jessica J. Lin, Sang-We Kim, Benjamin J. Solomon, Rafal Dziadziuszko, Benjamin Besse, Koichi Goto, Adrianus Johannes de Langen, Jürgen Wolf, Ki Hyeong Lee, Sanjay Popat, Christoph Springfeld, Misako Nagasaka, Enriqueta Felip, Nong Yang, Vamsidhar Velcheti, Shun Lu, Steven Kao, Christophe Dooms, Matthew G. Krebs, Wenxiu Yao, Muhammad Shaalan Beg, Xiufeng Hu, Denis Moro-Sibilot, Parneet Cheema, Shanna Stopatschinskaja, Minal Mehta, Denise Trone, Armin Graber, Gregory Sims, Yong Yuan, and Byoung Chul Cho. Repotrectinib in ros1 fusion-positive non-small-cell lung cancer. The New England journal of medicine, 390 2:118-131, Jan 2024. URL: https://doi.org/10.1056/nejmoa2302299, doi:10.1056/nejmoa2302299. This article has 248 citations and is from a highest quality peer-reviewed journal.

7. (li2024efficacyandsafety pages 1-2): Wei Li, Anwen Xiong, Nong Yang, Huijie Fan, Qitao Yu, Yanqiu Zhao, Yongsheng Wang, Xue Meng, Jingxun Wu, Ziping Wang, Yunpeng Liu, Xicheng Wang, Xintian Qin, Kaihua Lu, Wu Zhuang, Yizhong Ren, Xianyu Zhang, Bing Yan, Christine M. Lovly, and Caicun Zhou. Efficacy and safety of taletrectinib in chinese patients with ros1+ non–small cell lung cancer: the phase ii trust-i study. Journal of Clinical Oncology, 42:2660-2670, Aug 2024. URL: https://doi.org/10.1200/jco.24.00731, doi:10.1200/jco.24.00731. This article has 50 citations and is from a highest quality peer-reviewed journal.

8. (peters2024entrectinibinros1positive pages 5-6): Solange Peters, Shirish M. Gadgeel, Tony Mok, Ernest Nadal, Saadettin Kilickap, Aurélie Swalduz, Jacques Cadranel, Shunichi Sugawara, Chao-Hua Chiu, Chong-Jen Yu, Mor Moskovitz, Tomohiro Tanaka, Rhea Nersesian, Sarah M. Shagan, Margaret Maclennan, Michael Mathisen, Vijay Bhagawati-Prasad, Cheick Diarra, Zoe June Assaf, Venice Archer, and Rafal Dziadziuszko. Entrectinib in ros1-positive advanced non-small cell lung cancer: the phase 2/3 bfast trial. Nature Medicine, 30:1923-1932, Jun 2024. URL: https://doi.org/10.1038/s41591-024-03008-4, doi:10.1038/s41591-024-03008-4. This article has 32 citations and is from a highest quality peer-reviewed journal.

9. (peters2024entrectinibinros1positive pages 3-4): Solange Peters, Shirish M. Gadgeel, Tony Mok, Ernest Nadal, Saadettin Kilickap, Aurélie Swalduz, Jacques Cadranel, Shunichi Sugawara, Chao-Hua Chiu, Chong-Jen Yu, Mor Moskovitz, Tomohiro Tanaka, Rhea Nersesian, Sarah M. Shagan, Margaret Maclennan, Michael Mathisen, Vijay Bhagawati-Prasad, Cheick Diarra, Zoe June Assaf, Venice Archer, and Rafal Dziadziuszko. Entrectinib in ros1-positive advanced non-small cell lung cancer: the phase 2/3 bfast trial. Nature Medicine, 30:1923-1932, Jun 2024. URL: https://doi.org/10.1038/s41591-024-03008-4, doi:10.1038/s41591-024-03008-4. This article has 32 citations and is from a highest quality peer-reviewed journal.

10. (janzic2024nonsmallcelllungcancer pages 1-2): Urska Janzic, Natalie Maimon Rabinovich, Walid Shalata, Waleed Kian, Katarzyna Szymczak, Rafal Dziadziuszko, Marko Jakopovic, Giannis Mountzios, Adam Pluzanski, Antonio Araujo, Andriani Charpidou, Sameh Daher, and Abed Agbarya. Non-small-cell lung cancer patients harboring ros1 rearrangement: real world testing practices, characteristics and treatment patterns (ros1real study). Current Oncology, 31:4369-4381, Jul 2024. URL: https://doi.org/10.3390/curroncol31080326, doi:10.3390/curroncol31080326. This article has 7 citations.

11. (janzic2024nonsmallcelllungcancer pages 5-7): Urska Janzic, Natalie Maimon Rabinovich, Walid Shalata, Waleed Kian, Katarzyna Szymczak, Rafal Dziadziuszko, Marko Jakopovic, Giannis Mountzios, Adam Pluzanski, Antonio Araujo, Andriani Charpidou, Sameh Daher, and Abed Agbarya. Non-small-cell lung cancer patients harboring ros1 rearrangement: real world testing practices, characteristics and treatment patterns (ros1real study). Current Oncology, 31:4369-4381, Jul 2024. URL: https://doi.org/10.3390/curroncol31080326, doi:10.3390/curroncol31080326. This article has 7 citations.

12. (testa2023ros1rearrangedlungadenocarcinoma pages 4-5): Ugo Testa, Germana Castelli, and Elvira Pelosi. Ros1-rearranged lung adenocarcinoma: from molecular genetics to target therapy. Onco, 3:189-204, Aug 2023. URL: https://doi.org/10.3390/onco3030014, doi:10.3390/onco3030014. This article has 4 citations.

13. (li2024efficacyandsafety pages 3-5): Wei Li, Anwen Xiong, Nong Yang, Huijie Fan, Qitao Yu, Yanqiu Zhao, Yongsheng Wang, Xue Meng, Jingxun Wu, Ziping Wang, Yunpeng Liu, Xicheng Wang, Xintian Qin, Kaihua Lu, Wu Zhuang, Yizhong Ren, Xianyu Zhang, Bing Yan, Christine M. Lovly, and Caicun Zhou. Efficacy and safety of taletrectinib in chinese patients with ros1+ non–small cell lung cancer: the phase ii trust-i study. Journal of Clinical Oncology, 42:2660-2670, Aug 2024. URL: https://doi.org/10.1200/jco.24.00731, doi:10.1200/jco.24.00731. This article has 50 citations and is from a highest quality peer-reviewed journal.

14. (barbato2024fdaapprovalsummary pages 13-15): Michael I. Barbato, Diana Bradford, Yi Ren, Stephanie L. Aungst, Claudia P. Miller, Lili Pan, Jeanne F. Zirkelbach, Yangbing Li, Youwei Bi, Jianghong Fan, Manuela Grimstein, Sarah E. Dorff, Anup K. Amatya, Pallavi S. Mishra-Kalyani, Barbara Scepura, Peter Schotland, Opeyemi Udoka, Idara Ojofeitimi, John K. Leighton, Nam A. Rahman, Richard Pazdur, Harpreet Singh, Paul G. Kluetz, and Nicole Drezner. Fda approval summary: repotrectinib for locally advanced or metastatic ros1-positive non-small cell lung cancer. Clinical cancer research : an official journal of the American Association for Cancer Research, 30:3364-3370, Jun 2024. URL: https://doi.org/10.1158/1078-0432.ccr-24-0949, doi:10.1158/1078-0432.ccr-24-0949. This article has 19 citations.

15. (drilon2024repotrectinibinros1 pages 7-8): Alexander Drilon, D. Ross Camidge, Jessica J. Lin, Sang-We Kim, Benjamin J. Solomon, Rafal Dziadziuszko, Benjamin Besse, Koichi Goto, Adrianus Johannes de Langen, Jürgen Wolf, Ki Hyeong Lee, Sanjay Popat, Christoph Springfeld, Misako Nagasaka, Enriqueta Felip, Nong Yang, Vamsidhar Velcheti, Shun Lu, Steven Kao, Christophe Dooms, Matthew G. Krebs, Wenxiu Yao, Muhammad Shaalan Beg, Xiufeng Hu, Denis Moro-Sibilot, Parneet Cheema, Shanna Stopatschinskaja, Minal Mehta, Denise Trone, Armin Graber, Gregory Sims, Yong Yuan, and Byoung Chul Cho. Repotrectinib in ros1 fusion-positive non-small-cell lung cancer. The New England journal of medicine, 390 2:118-131, Jan 2024. URL: https://doi.org/10.1056/nejmoa2302299, doi:10.1056/nejmoa2302299. This article has 248 citations and is from a highest quality peer-reviewed journal.

16. (barbato2024fdaapprovalsummary pages 1-3): Michael I. Barbato, Diana Bradford, Yi Ren, Stephanie L. Aungst, Claudia P. Miller, Lili Pan, Jeanne F. Zirkelbach, Yangbing Li, Youwei Bi, Jianghong Fan, Manuela Grimstein, Sarah E. Dorff, Anup K. Amatya, Pallavi S. Mishra-Kalyani, Barbara Scepura, Peter Schotland, Opeyemi Udoka, Idara Ojofeitimi, John K. Leighton, Nam A. Rahman, Richard Pazdur, Harpreet Singh, Paul G. Kluetz, and Nicole Drezner. Fda approval summary: repotrectinib for locally advanced or metastatic ros1-positive non-small cell lung cancer. Clinical cancer research : an official journal of the American Association for Cancer Research, 30:3364-3370, Jun 2024. URL: https://doi.org/10.1158/1078-0432.ccr-24-0949, doi:10.1158/1078-0432.ccr-24-0949. This article has 19 citations.

17. (barbato2024fdaapprovalsummary pages 4-6): Michael I. Barbato, Diana Bradford, Yi Ren, Stephanie L. Aungst, Claudia P. Miller, Lili Pan, Jeanne F. Zirkelbach, Yangbing Li, Youwei Bi, Jianghong Fan, Manuela Grimstein, Sarah E. Dorff, Anup K. Amatya, Pallavi S. Mishra-Kalyani, Barbara Scepura, Peter Schotland, Opeyemi Udoka, Idara Ojofeitimi, John K. Leighton, Nam A. Rahman, Richard Pazdur, Harpreet Singh, Paul G. Kluetz, and Nicole Drezner. Fda approval summary: repotrectinib for locally advanced or metastatic ros1-positive non-small cell lung cancer. Clinical cancer research : an official journal of the American Association for Cancer Research, 30:3364-3370, Jun 2024. URL: https://doi.org/10.1158/1078-0432.ccr-24-0949, doi:10.1158/1078-0432.ccr-24-0949. This article has 19 citations.

18. (stanzione2023therapeuticaloptionsin pages 7-8): Brigida Stanzione, Alessandro Del Conte, Elisa Bertoli, Elisa De Carlo, Alberto Revelant, Michele Spina, and Alessandra Bearz. Therapeutical options in ros1—rearranged advanced non small cell lung cancer. International Journal of Molecular Sciences, 24:11495, Jul 2023. URL: https://doi.org/10.3390/ijms241411495, doi:10.3390/ijms241411495. This article has 23 citations.

19. (testa2023ros1rearrangedlungadenocarcinoma pages 15-16): Ugo Testa, Germana Castelli, and Elvira Pelosi. Ros1-rearranged lung adenocarcinoma: from molecular genetics to target therapy. Onco, 3:189-204, Aug 2023. URL: https://doi.org/10.3390/onco3030014, doi:10.3390/onco3030014. This article has 4 citations.

20. (peters2024entrectinibinros1positive pages 1-2): Solange Peters, Shirish M. Gadgeel, Tony Mok, Ernest Nadal, Saadettin Kilickap, Aurélie Swalduz, Jacques Cadranel, Shunichi Sugawara, Chao-Hua Chiu, Chong-Jen Yu, Mor Moskovitz, Tomohiro Tanaka, Rhea Nersesian, Sarah M. Shagan, Margaret Maclennan, Michael Mathisen, Vijay Bhagawati-Prasad, Cheick Diarra, Zoe June Assaf, Venice Archer, and Rafal Dziadziuszko. Entrectinib in ros1-positive advanced non-small cell lung cancer: the phase 2/3 bfast trial. Nature Medicine, 30:1923-1932, Jun 2024. URL: https://doi.org/10.1038/s41591-024-03008-4, doi:10.1038/s41591-024-03008-4. This article has 32 citations and is from a highest quality peer-reviewed journal.

21. (peters2024entrectinibinros1positive pages 2-3): Solange Peters, Shirish M. Gadgeel, Tony Mok, Ernest Nadal, Saadettin Kilickap, Aurélie Swalduz, Jacques Cadranel, Shunichi Sugawara, Chao-Hua Chiu, Chong-Jen Yu, Mor Moskovitz, Tomohiro Tanaka, Rhea Nersesian, Sarah M. Shagan, Margaret Maclennan, Michael Mathisen, Vijay Bhagawati-Prasad, Cheick Diarra, Zoe June Assaf, Venice Archer, and Rafal Dziadziuszko. Entrectinib in ros1-positive advanced non-small cell lung cancer: the phase 2/3 bfast trial. Nature Medicine, 30:1923-1932, Jun 2024. URL: https://doi.org/10.1038/s41591-024-03008-4, doi:10.1038/s41591-024-03008-4. This article has 32 citations and is from a highest quality peer-reviewed journal.

22. (peters2024entrectinibinros1positive pages 6-7): Solange Peters, Shirish M. Gadgeel, Tony Mok, Ernest Nadal, Saadettin Kilickap, Aurélie Swalduz, Jacques Cadranel, Shunichi Sugawara, Chao-Hua Chiu, Chong-Jen Yu, Mor Moskovitz, Tomohiro Tanaka, Rhea Nersesian, Sarah M. Shagan, Margaret Maclennan, Michael Mathisen, Vijay Bhagawati-Prasad, Cheick Diarra, Zoe June Assaf, Venice Archer, and Rafal Dziadziuszko. Entrectinib in ros1-positive advanced non-small cell lung cancer: the phase 2/3 bfast trial. Nature Medicine, 30:1923-1932, Jun 2024. URL: https://doi.org/10.1038/s41591-024-03008-4, doi:10.1038/s41591-024-03008-4. This article has 32 citations and is from a highest quality peer-reviewed journal.

23. (li2024efficacyandsafety pages 6-7): Wei Li, Anwen Xiong, Nong Yang, Huijie Fan, Qitao Yu, Yanqiu Zhao, Yongsheng Wang, Xue Meng, Jingxun Wu, Ziping Wang, Yunpeng Liu, Xicheng Wang, Xintian Qin, Kaihua Lu, Wu Zhuang, Yizhong Ren, Xianyu Zhang, Bing Yan, Christine M. Lovly, and Caicun Zhou. Efficacy and safety of taletrectinib in chinese patients with ros1+ non–small cell lung cancer: the phase ii trust-i study. Journal of Clinical Oncology, 42:2660-2670, Aug 2024. URL: https://doi.org/10.1200/jco.24.00731, doi:10.1200/jco.24.00731. This article has 50 citations and is from a highest quality peer-reviewed journal.

24. (drilon2024repotrectinibinros1 media ec1cfcb8): Alexander Drilon, D. Ross Camidge, Jessica J. Lin, Sang-We Kim, Benjamin J. Solomon, Rafal Dziadziuszko, Benjamin Besse, Koichi Goto, Adrianus Johannes de Langen, Jürgen Wolf, Ki Hyeong Lee, Sanjay Popat, Christoph Springfeld, Misako Nagasaka, Enriqueta Felip, Nong Yang, Vamsidhar Velcheti, Shun Lu, Steven Kao, Christophe Dooms, Matthew G. Krebs, Wenxiu Yao, Muhammad Shaalan Beg, Xiufeng Hu, Denis Moro-Sibilot, Parneet Cheema, Shanna Stopatschinskaja, Minal Mehta, Denise Trone, Armin Graber, Gregory Sims, Yong Yuan, and Byoung Chul Cho. Repotrectinib in ros1 fusion-positive non-small-cell lung cancer. The New England journal of medicine, 390 2:118-131, Jan 2024. URL: https://doi.org/10.1056/nejmoa2302299, doi:10.1056/nejmoa2302299. This article has 248 citations and is from a highest quality peer-reviewed journal.

25. (drilon2024repotrectinibinros1 media 29c59cf5): Alexander Drilon, D. Ross Camidge, Jessica J. Lin, Sang-We Kim, Benjamin J. Solomon, Rafal Dziadziuszko, Benjamin Besse, Koichi Goto, Adrianus Johannes de Langen, Jürgen Wolf, Ki Hyeong Lee, Sanjay Popat, Christoph Springfeld, Misako Nagasaka, Enriqueta Felip, Nong Yang, Vamsidhar Velcheti, Shun Lu, Steven Kao, Christophe Dooms, Matthew G. Krebs, Wenxiu Yao, Muhammad Shaalan Beg, Xiufeng Hu, Denis Moro-Sibilot, Parneet Cheema, Shanna Stopatschinskaja, Minal Mehta, Denise Trone, Armin Graber, Gregory Sims, Yong Yuan, and Byoung Chul Cho. Repotrectinib in ros1 fusion-positive non-small-cell lung cancer. The New England journal of medicine, 390 2:118-131, Jan 2024. URL: https://doi.org/10.1056/nejmoa2302299, doi:10.1056/nejmoa2302299. This article has 248 citations and is from a highest quality peer-reviewed journal.

26. (drilon2024repotrectinibinros1 media 7dc28074): Alexander Drilon, D. Ross Camidge, Jessica J. Lin, Sang-We Kim, Benjamin J. Solomon, Rafal Dziadziuszko, Benjamin Besse, Koichi Goto, Adrianus Johannes de Langen, Jürgen Wolf, Ki Hyeong Lee, Sanjay Popat, Christoph Springfeld, Misako Nagasaka, Enriqueta Felip, Nong Yang, Vamsidhar Velcheti, Shun Lu, Steven Kao, Christophe Dooms, Matthew G. Krebs, Wenxiu Yao, Muhammad Shaalan Beg, Xiufeng Hu, Denis Moro-Sibilot, Parneet Cheema, Shanna Stopatschinskaja, Minal Mehta, Denise Trone, Armin Graber, Gregory Sims, Yong Yuan, and Byoung Chul Cho. Repotrectinib in ros1 fusion-positive non-small-cell lung cancer. The New England journal of medicine, 390 2:118-131, Jan 2024. URL: https://doi.org/10.1056/nejmoa2302299, doi:10.1056/nejmoa2302299. This article has 248 citations and is from a highest quality peer-reviewed journal.

1. Disease Information

Overview

ROS1-rearranged NSCLC is a molecular subtype of non-small cell lung cancer driven by chromosomal rearrangements involving the ROS1 proto-oncogene (chromosome 6q22). These rearrangements produce chimeric fusion proteins with constitutive tyrosine kinase activity, functioning as oncogenic drivers. The disease was first recognized as a distinct targetable entity following the identification of ROS1 fusions in lung cancer in 2007, and the subsequent demonstration that ROS1 TKIs could produce durable clinical responses.

"ROS1 rearrangements define a molecular subset of non-small cell lung cancer (NSCLC) by accounting for 1%-2% of cases" (PMID: 40171848). "ROS1 fusion-positive non-small cell lung cancer (NSCLC) represents a rare but clinically important subset, occurring in 1-2% of patients and often associated with younger, never-smoker populations" (PMID: 41548253).

Key Identifiers

Synonyms and Alternative Names

• ROS1-positive NSCLC / ROS1+ NSCLC
• ROS1 fusion-positive non-small cell lung cancer
• ROS1-rearranged lung adenocarcinoma
• c-ros oncogene 1 rearranged NSCLC

Information Source

This report is derived from aggregated disease-level resources including published clinical trials, molecular biology studies, population-based registries (SEER), and curated databases (COSMIC, ClinVar, UniProt, PDB), supplemented by individual patient case reports documenting resistance mechanisms and treatment sequences.

2. Etiology

Disease Causal Factors

ROS1+ NSCLC is caused by somatic chromosomal rearrangements that fuse the 3' kinase domain of the ROS1 gene to the 5' portion of various partner genes, producing constitutively active fusion kinases. These are acquired somatic events, not germline inherited mutations. The rearrangements are typically interchromosomal or intrachromosomal inversions/translocations.

The most common fusion partners include: - CD74-ROS1 (~35–44% of cases): the most frequent partner - EZR-ROS1: ezrin gene on 6q25 - SLC34A2-ROS1: solute carrier on 4p15 - SDC4-ROS1: syndecan-4 on 20q12 - TPM3-ROS1: tropomyosin-3 on 1q21 - GOPC-ROS1 (also known as FIG-ROS1): on 6q22 (intrachromosomal) - CLIP1-ROS1, KIF21A-ROS1, and other rare partners

{{figure:ros1_protein_and_partners.png|caption=ROS1 protein domain architecture, fusion breakpoints, resistance mutation sites, and landscape of fusion partners with approximate frequencies}}

Risk Factors

Genetic risk factors: - ROS1 rearrangements are somatic, not inherited; no germline susceptibility loci have been identified - Co-occurring TP53 mutations are frequent and associated with worse prognosis (PMID: 37261522) - CDKN2A/B copy number loss co-occurs in ~15% of fusion-positive patients

Environmental risk factors: - Unlike most NSCLC, ROS1+ disease is not associated with tobacco smoking—75.7% of patients are never-smokers (PMID: 29883837) - The etiology of the chromosomal rearrangement is unknown in most cases - No occupational, dietary, or environmental exposures have been definitively linked

Demographic associations: - Age: Younger patients (median 50–56 years vs. ~65 years for general NSCLC) - Sex: Female predominance (58.9% female in one cohort; fusion frequency 3.71% in women vs. 1.81% in men, p < 0.01) (PMID: 30468296) - Ethnicity: Reported across all ethnicities; Indian populations show frequencies of 3.5–4.1% (PMID: 35634796); Hispanic/Latino ~2% (PMID: 37729688)

Protective Factors

No specific genetic or environmental protective factors have been identified for ROS1+ NSCLC. General lung cancer protective factors (avoidance of tobacco, radon mitigation) apply but are less relevant given the never-smoker predominance of this subtype.

Gene-Environment Interactions

There is no established gene-environment interaction for ROS1 rearrangements. The disease appears to arise from stochastic somatic rearrangement events rather than environmental mutagen exposure.

3. Phenotypes

Clinical Presentation

Phenotype Characteristics

• Age of onset: Adult-onset, typically 5th–6th decade (median 50–56 years), significantly younger than general NSCLC population. "ROS1 fusion-positive patients were significantly younger (55.68 +/- 11.34 vs. negative 61.02 +/- 10.44 years; P < 0.01)" (PMID: 30468296)
• Progression: Progressive without treatment; variable with TKI therapy (initial response followed by eventual progression)
• CNS tropism: High rate of brain metastases (~22–36% at diagnosis), a hallmark of the disease and a key clinical challenge

Histopathological Phenotype

ROS1+ NSCLC shows characteristic histological features: "Histologically, the carcinoma was an adenocarcinoma with a predominant acinar pattern; notably, a mucinous cribriform pattern and a solid signet-ring cell pattern were also observed" (PMID: 23877438). Adenocarcinoma accounts for 98.1% of ROS1+ cases; rare pleomorphic carcinoma has been reported (PMID: 29883837).

Quality of Life

Entrectinib treatment maintains stable global health status and quality of life as measured by EORTC QLQ-C30, QLQ-LC13, and EQ-5D-3L instruments in the STARTRK-2 trial (PMID: 33930659). Post-TKI chemo-immunotherapy carries substantially higher toxicity burden with grade 3–4 adverse events in 63.9–83.8% of patients (PMID: 38830303).

4. Genetic/Molecular Information

Causal Gene

ROS1 (ROS proto-oncogene 1, receptor tyrosine kinase) - Chromosome: 6q22.1 - HGNC ID: HGNC:10261 - OMIM: 165020 - UniProt: P08922 - Protein: 2,347 amino acids; type I transmembrane receptor tyrosine kinase - Normal function: Epithelial cell differentiation, regionalization of proximal epididymal epithelium via NELL2-mediated lumicrine signaling; activates PI3K-mTOR, STAT3, VAV3 pathways (PMID: 38169386)

Pathogenic Variants

Fusion rearrangements (somatic):

All fusions retain the ROS1 kinase domain (exons 34–43) and are classified as gain-of-function (constitutive kinase activation). The fusion partner contributes the promoter (driving expression) and often a dimerization domain (facilitating ligand-independent activation).

Resistance mutations (acquired, somatic):

"ROS1 L2086F mutant kinase is resistant to type I TKI including crizotinib, entrectinib, lorlatinib, repotrectinib, taletrectinib, while the type II TKI cabozantinib and merestinib retain activity" (PMID: 38293020).

Chromosomal Abnormalities

The defining event is a chromosomal rearrangement (translocation, inversion, or deletion) producing the ROS1 fusion gene. These are detected by FISH (break-apart probes), RT-PCR, or next-generation sequencing (RNA-based panels preferred).

Modifier Genes

• TP53 co-mutations: Most frequent co-alteration (31% in fusion-positive patients); associated with worse prognosis and shorter duration of TKI response (PMID: 37261522)
• CDKN2A/B copy number loss: Co-occurs in ~15%; combined with TP53 creates immunosuppressive microenvironment
• SPP1 overexpression: Associated with poor outcomes in ALK/ROS1 fusion-positive cancers not receiving targeted therapy (PMID: 34234236)

Epigenetic Information

Limited data specific to ROS1+ NSCLC. General NSCLC epigenetic alterations (promoter methylation of tumor suppressors) likely apply. No ROS1-specific methylation biomarkers established.

5. Environmental Information

Environmental Factors

No specific environmental toxins, radiation exposures, or occupational hazards have been causally linked to ROS1 rearrangements. This contrasts sharply with general NSCLC, where tobacco smoke and radon are dominant risk factors.

Lifestyle Factors

• Smoking: ROS1+ NSCLC is enriched in never-smokers (75.7%); smoking does not appear to be a causative factor (PMID: 29883837)
• Diet, exercise, alcohol: No established associations

Infectious Agents

No infectious agents have been implicated in ROS1+ NSCLC.

6. Mechanism / Pathophysiology

Molecular Pathways

ROS1 fusion proteins activate multiple oncogenic signaling cascades:

{{figure:ros1_signaling_resistance.png|caption=ROS1 fusion signaling pathways showing convergence on STAT3 and SHP2, downstream MAPK and PI3K-AKT-mTOR effectors, and acquired resistance mechanisms}}

Primary signaling axes:

1. STAT3 pathway: "All studied fusions converge on STAT3 activation" (PMID: 41790556)
2. SHP2 (PTPN11) pathway: ROS1 fusions directly interact with and phosphorylate SHP2 "to a greater extent than ALK fusions, and analyses of downstream pathways suggest MAPK-independent, non-canonical SHP2-driven functions" (PMID: 41790556)
3. RAS-MAPK cascade: ERK1/2 activation via SOS1/GRB2 and SHP2
4. PI3K-AKT-mTOR pathway: Cell survival, growth, and metabolism
5. PLCgamma pathway: Calcium signaling and PKC activation

GO terms for biological processes: - GO:0007169 (transmembrane receptor protein tyrosine kinase signaling pathway) - GO:0070372 (regulation of ERK1 and ERK2 cascade) - GO:0032006 (regulation of TOR signaling) - GO:0030154 (cell differentiation) - GO:0046777 (protein autophosphorylation) - GO:0006468 (protein phosphorylation)

Causal Chain

Chromosomal rearrangement (somatic)
    |
    v
ROS1 fusion gene (e.g., CD74-ROS1)
    |
    v
Constitutively active ROS1 kinase (ligand-independent dimerization)
    |
    v
Phosphorylation of SHP2/STAT3/PLCgamma/IRS1
    |
    v
Activation of MAPK, PI3K-AKT-mTOR, STAT3 cascades
    |
    v
Uncontrolled proliferation, survival, migration
    |
    v
Lung adenocarcinoma (mucinous cribriform/signet ring features)
    |
    v
Metastasis (high CNS tropism)

Cellular Processes

• Proliferation: Constitutive MAPK/ERK activation drives cell cycle progression
• Anti-apoptosis: PI3K-AKT-mTOR and STAT3 signaling promote cell survival
• Migration/invasion: Fusion partner-specific effects (e.g., CLIP1-ROS1 increases cell motility via microtubule interactions) (PMID: 41790556)
• Angiogenesis: Downstream VEGF pathway activation

Cell types involved: - CL:0000066 (epithelial cell) — specifically pulmonary type II pneumocytes/Clara cells - CL:0002063 (type II pneumocyte)

Protein Dysfunction

The ROS1 fusion protein represents a gain-of-function alteration. The fusion partner provides: 1. A constitutively active promoter (driving expression) 2. A coiled-coil or dimerization domain (enabling ligand-independent activation) 3. Subcellular localization signals (e.g., GOPC-ROS1 localizes to Golgi)

Five crystal structures of the human ROS1 kinase domain are available in the PDB:

Additional structures include the full-length extracellular domain (9PVP, 4.57 A) and the ROS1-NELL2 complex (10FT, 3.21 A).

Immune System Involvement

"Patients with co-occurring TP53/CDKN2A/B variations and ALK/RET/ROS1 rearrangements are associated with high TMB, more neoantigens, an immunosuppressive microenvironment and a worse prognosis" (PMID: 37261522). Despite higher TMB and neoantigen burden, these tumors show lower CD8+ T-cell infiltration, creating a paradoxical immune phenotype. PD-L1 positivity is not significantly associated with ROS1 fusion status (PMID: 34600407).

Metabolic Changes

Pemetrexed (an antifolate) shows superior efficacy in ROS1+ NSCLC compared to non-pemetrexed chemotherapy (PFS 179 vs. 110 days, p = 0.0107), with low thymidylate synthase (TS) expression associated with better outcomes (PFS 184 vs. 110 days, p = 0.0105) (PMID: 27738334). This suggests altered folate metabolism in ROS1+ tumors.

SHP2 as a Therapeutic Vulnerability

SHP2 inhibition enhances the effects of TKIs in preclinical models of treatment-naive ALK/ROS1-fusion NSCLC (PMID: 34158345). Given that all ROS1 fusions converge on strong SHP2 activation via direct interaction (PMID: 41790556), combination of ROS1 TKIs with SHP2 inhibitors represents a mechanistically rational therapeutic strategy.

Resistance Mechanisms

On-target (kinase domain mutations): - G2032R (solvent front) — most common - L2026M (gatekeeper) - L2086F (xDFG motif) — pan-type I TKI resistant - D2033N (solvent front)

Off-target/bypass mechanisms: - MET amplification: "acquired MET amplification as a resistance driver in a ROS1-rearranged lung adenocarcinoma after sequential treatment with ROS1 inhibitors" (PMID: 37923925) - HGF-mediated MET activation: "HGF most potently induced entrectinib resistance in KM12SM and HCC78 cells by activating its receptor MET" (PMID: 36416133) - KRAS mutations - RET rearrangements (RUFY1-RET reported) (PMID: 39907599) - FGFR3 amplification

7. Anatomical Structures Affected

Organ Level

Primary organ: Lung (UBERON:0002048) - Predominantly affects the peripheral lung parenchyma - Adenocarcinoma histology typically arising in distal airways

Secondary organ involvement (metastatic sites): - Brain/CNS (UBERON:0000955) — high tropism, 22–36% at diagnosis - Bone (UBERON:0002481) - Liver (UBERON:0002107) - Adrenal glands (UBERON:0002369) - Pleura (UBERON:0000977) — pleural effusion common - Lymph nodes (UBERON:0000029)

Body systems: Respiratory system (primary), nervous system (CNS metastases), skeletal system, lymphatic system

Tissue and Cell Level

• Tissue: Pulmonary epithelium (UBERON:0000115)
• Cell types: Type II pneumocytes (CL:0002063), Clara/Club cells (CL:0000158)
• Histological pattern: Adenocarcinoma with mucinous cribriform pattern, solid signet ring cell pattern, acinar pattern

Subcellular Level

• Cell membrane (GO:0005886): ROS1 receptor localization
• Cytoplasm (GO:0005737): Signaling cascade components
• Nucleus (GO:0005634): STAT3 transcription factor translocation
• Golgi apparatus (GO:0005794): GOPC-ROS1 fusion specifically localizes here

Localization

• Typically peripheral lung nodules/masses
• No lateralization preference (bilateral involvement possible in advanced disease)
• Leptomeningeal carcinomatosis can occur as a specific pattern of CNS spread

8. Temporal Development

Onset

• Typical age: 5th–6th decade (median 50–56 years)
• Onset pattern: Insidious; often diagnosed at advanced stage (stage IIIB/IV) due to nonspecific symptoms
• 42.9% of patients present with stage IV disease in surgical series (PMID: 34234236)

Progression

Staging: Standard AJCC/TNM staging for NSCLC applies (stages I–IV)

Natural history without targeted therapy: - Rapid progression; platinum-based chemotherapy yields median PFS of ~6–7 months - Pemetrexed-based chemotherapy: ORR 40.8%, median PFS 179 days (PMID: 27738334)

With targeted therapy: - First-line crizotinib: median PFS ~12–19 months - First-line repotrectinib: median PFS 35.7 months (PMID: 39402859) - Eventual resistance is near-universal; sequential TKI strategies can extend disease control

Disease course: Progressive; no spontaneous remission. Treatment-induced responses are common but resistance develops.

Critical Periods

• Diagnosis: Molecular testing at diagnosis is essential for treatment selection
• CNS monitoring: Regular brain imaging due to high CNS metastasis risk
• Resistance emergence: Molecular profiling at progression guides sequential therapy

{{figure:ros1_timeline.png|caption=Timeline of key milestones in ROS1-rearranged NSCLC research and treatment, from initial discovery through next-generation TKI approvals}}

9. Inheritance and Population

Epidemiology

Inheritance Pattern

• Not inherited: ROS1 rearrangements are somatic events with no Mendelian inheritance pattern
• No germline ROS1 mutations predisposing to cancer have been established
• Not applicable: penetrance, expressivity, anticipation, carrier frequency

Population Demographics

• Sex ratio: Female predominance (~59% female; fusion frequency 3.71% in women vs. 1.81% in men)
• Age distribution: Younger than general NSCLC (median ~50–56 years); enriched in patients <40 years (ROS1 fusions found in 7% of young-onset NSCLC in India) (PMID: 40122770)
• Ethnic distribution: Present across all populations; potentially higher frequency in East Asian and South Asian populations
• Smoking status: 75% or more are never-smokers

10. Diagnostics

Molecular Diagnostic Testing

ROS1 rearrangement detection is mandatory before initiating TKI therapy. Multiple methods are available:

Recommended approach: IHC screening followed by FISH/NGS confirmation, or upfront comprehensive NGS (RNA-based preferred). "Targeted RNA NGS was confirmed to be the most efficient technique for gene fusion identification in clinical practice" (PMID: 37190044). "FISH should not be dismissed, as they can crucially contribute to the completion of the molecular characterization" (PMID: 37190044).

Imaging Studies

• CT chest/abdomen: Standard staging
• Brain MRI: Mandatory at diagnosis and surveillance (high CNS tropism)
• PET-CT: For comprehensive staging
• Bone scan: If bone metastases suspected

Biopsy and Pathology

• Tissue biopsy preferred; adequate material for molecular testing essential
• IHC: ROS1 protein expression (D4D6 clone, SP384 clone)
• Characteristic: adenocarcinoma with mucinous cribriform pattern, signet ring cells
• ROSE (Rapid On-Site Evaluation) improves specimen adequacy for biomarker testing (PMID: 37805343)

Liquid Biopsy

• ctDNA-based NGS panels can detect ROS1 fusions in plasma
• CSF ctDNA superior to plasma for CNS disease monitoring (PMID: 32838487)
• Useful for resistance mutation detection at progression

Differential Diagnosis

• Other oncogene-driven NSCLC (ALK, RET, NTRK fusions — mutually exclusive with ROS1)
• EGFR-mutant NSCLC (also younger, never-smokers, adenocarcinoma)
• KRAS-mutant NSCLC
• Driver-negative NSCLC

11. Outcome/Prognosis

Survival and Mortality

{{figure:ros1_treatment_landscape.png|caption=Comparison of ROS1 TKI efficacy across generations showing objective response rates (ORR) and median progression-free survival (PFS)}}

"In the TKI-naive cohort (n = 71), 79% of patients achieved an objective response, with a median progression-free survival (PFS) of 35.7 months, surpassing all previously approved ROS1 TKIs" (PMID: 39402859).

"Taletrectinib demonstrated high objective response rates in both TKI-naive (88.8%) and TKI-pretreated (55.8%) patients, including robust intracranial activity and efficacy against the G2032R mutation" (PMID: 41548253).

Prognostic Factors

Favorable: - ROS1 fusion-positive status (vs. driver-negative NSCLC) - Absence of TP53 co-mutation - Absence of CNS metastases at diagnosis - Access to appropriate TKI therapy

Unfavorable: - TP53/CDKN2A/B co-mutations (immunosuppressive microenvironment, worse prognosis) - CNS metastases at diagnosis - G2032R resistance mutation emergence - Lack of access to molecular testing or targeted therapy

Complications

• CNS metastases / leptomeningeal carcinomatosis
• Pleural effusion / respiratory failure
• Bone metastases with pathological fractures
• Hepatic metastases
• Treatment-related toxicity (see Treatment section)

12. Treatment

First-Line Targeted Therapy

MAXO:0000058 (pharmacotherapy)

Second-Line and Beyond

• Lorlatinib: Third-gen ALK/ROS1 TKI; good CNS penetration; used post-crizotinib; limited by neurocognitive side effects (PMID: 38201357)
• Zidesamtinib (NVL-520): ROS1-selective, TRK-sparing; ORR 73% post-crizotinib, 38% post-repotrectinib (PMID: 40118657); crystal structure of G2032R-zidesamtinib complex available (PDB: 9QEK)
• Cabozantinib: Type II multi-kinase inhibitor; retains activity against L2086F mutation (PMID: 38293020, PMID: 40826797)
• Brigatinib: ORR 71.4% in TKI-naive, 31.6% post-crizotinib (PMID: 39018589)

Chemotherapy

MAXO:0000647 (chemotherapy)

Pemetrexed-based platinum doublet is the preferred chemotherapy regimen: "crizotinib-treated group had a higher overall response rate (ORR, 80.0%), disease control rate (DCR, 90.0%) and longer progression-free survival (PFS, 294 days) compared with the rates in pemetrexed-treated group (ORR, 40.8%; DCR, 71.4%; PFS, 179 days) and non-pemetrexed-treated group (ORR, 25.0%; DCR, 47.7%; PFS, 110 days)" (PMID: 27738334).

Immunotherapy

MAXO:0001298 (immunotherapy)

Immune checkpoint inhibitors have limited single-agent activity in ROS1+ NSCLC: - PD-L1 expression is not significantly associated with ROS1 fusion status (PMID: 34600407) - TP53/CDKN2A/B co-mutation creates an immunosuppressive microenvironment despite high TMB (PMID: 37261522) - NCCN guidelines recommend against first-line immunotherapy in ROS1+ NSCLC - May have a role in combination with chemotherapy after TKI exhaustion

Surgical Interventions

MAXO:0000004 (surgical procedure)

• Surgical resection is standard for early-stage disease (stage I–IIIA)
• Limited data on adjuvant targeted therapy post-resection in ROS1+ patients
• ROS1 appears less frequent in early-stage resected disease (0.6% vs 1–2% in advanced) (PMID: 37237384)

Emerging Combination Strategies

• ROS1 TKI + SHP2 inhibitor: Preclinical data supports enhanced efficacy (PMID: 34158345); mechanistic rationale from convergent SHP2 activation across all fusions (PMID: 41790556)
• ROS1 TKI + MET inhibitor: For MET amplification-driven resistance; lorlatinib + capmatinib combination reported (PMID: 37923925)
• APG-2449: FAK + ALK/ROS1 TKI; CNS-penetrant (CSF:plasma ratio 0.65–1.66); phase I data available (PMID: 41146927)

Treatment Algorithm

Diagnosis of advanced ROS1+ NSCLC
    |
    v
1st Line: Next-gen ROS1 TKI (repotrectinib or taletrectinib preferred)
         Consider CNS status when selecting agent
    | (progression)
    v
Rebiopsy / liquid biopsy for resistance mechanism
    |
    v
On-target resistance (e.g., G2032R):
  -> Switch to TKI with activity against specific mutation
  -> G2032R: taletrectinib, zidesamtinib
  -> L2086F: cabozantinib/merestinib (type II TKI)
    |
    v
Off-target/bypass resistance (e.g., MET amp):
  -> Combination therapy (ROS1 TKI + pathway-specific inhibitor)
  -> Consider clinical trials
    |
    v
Post-TKI exhaustion:
  -> Pemetrexed-based chemotherapy +/- immunotherapy
  -> Clinical trials (SHP2 inhibitor combos, novel agents)

13. Prevention

Primary Prevention

• Smoking cessation: While ROS1+ NSCLC is not smoking-related, general lung cancer prevention includes tobacco avoidance
• No specific primary prevention strategies exist for ROS1 rearrangements (stochastic somatic events)

Secondary Prevention (Screening and Early Detection)

• Low-dose CT screening: USPSTF-recommended for high-risk individuals (age 50–80 with 20+ pack-year history); less applicable to the ROS1+ demographic (younger never-smokers)
• Molecular testing at diagnosis: Universal molecular profiling of all advanced non-squamous NSCLC ensures detection of ROS1 fusions
• Guidelines mandate testing for EGFR, ALK, ROS1, BRAF, RET, MET, NTRK, KRAS in advanced NSCLC (PMID: 37455124)

Tertiary Prevention

• Regular surveillance imaging (CT, brain MRI) during and after TKI therapy
• Molecular profiling at disease progression to identify resistance mechanisms and guide sequential therapy
• Supportive care and symptom management

Genetic Counseling

Not typically indicated as ROS1 rearrangements are somatic. No hereditary cancer syndromes are associated with ROS1 fusions (unlike the rare pediatric Li-Fraumeni-associated angiosarcoma with ROS1 rearrangement) (PMID: 36307212).

14. Other Species / Natural Disease

Comparative Biology

ROS1 orthologs:

Animal Models — Normal ROS1 Function

c-ros knockout mice demonstrate the normal physiological role of ROS1: "Transgenic mice with male infertility, the c-ros knockout (KO) and GPX5-Tag2 transgenic mouse models... exhibit severely angulated sperm flagella explaining the infertility" (PMID: 15109745). This results from defective differentiation of the initial segment epithelium of the epididymis.

The NELL2-ROS1 lumicrine signaling axis is conserved in humans: "There was a significant correlation between the epididymal expressions of mouse genes upregulated by the trans-luminal signaling and those of their human orthologs, as evaluated by the correlation coefficient of 0.604" (PMID: 38169386).

Naturally Occurring ROS1 Fusions in Animals

No naturally occurring ROS1 fusion-driven lung cancers have been reported in companion animals or wildlife. Canine and feline lung tumors are rare and not characterized for ROS1 status.

15. Model Organisms

In Vivo Models

Cell Line Models

HCC78 cells are the most widely used model for studying ROS1 TKI efficacy and resistance. HGF-mediated resistance was characterized using both HCC78 and KM12SM cells (PMID: 36416133).

Model Characteristics

• Ba/F3 system: Excellent for rapid assessment of fusion oncogenicity and drug sensitivity; used to characterize L2086F pan-type I TKI resistance (PMID: 38293020)
• PDX models: Best recapitulation of human tumor biology; used for preclinical TKI evaluation
• Limitations: No single model fully captures the human tumor microenvironment, immune interactions, or CNS tropism

Key Findings Summary

Finding 1: ROS1 Rearrangements Define a Rare Molecular Subset

ROS1 fusions occur in 1–2% of NSCLC cases globally, with variation by population (2.59% in China, 3.5–4.1% in India, ~2% in Hispanic/Latino populations). The disease is enriched in younger, female, never-smoking patients with adenocarcinoma.

Finding 2: Distinctive Clinical-Demographic Profile

Median age 50–56 years, 58.9% female, 75.7% never-smokers, 98.1% adenocarcinoma. Statistically significant differences versus ROS1-negative NSCLC in age (p < 0.01), sex (p < 0.01), and smoking status (p < 0.01).

Finding 3: Rapidly Evolving TKI Landscape

First-generation TKIs (crizotinib, entrectinib) achieve ORR 60–80% with PFS 12–19 months. Next-generation agents have dramatically improved outcomes: repotrectinib (ORR 79%, PFS 35.7 months), taletrectinib (ORR 89%), unecritinib (ORR 80.2%).

Finding 4: Complex Resistance Mechanisms

On-target mutations (G2032R, L2086F, L2026M) and off-target bypass pathways (MET amplification, HGF-mediated resistance, KRAS mutations, RET rearrangements) necessitate serial molecular profiling and rational TKI sequencing.

Finding 5: Convergent STAT3/SHP2 Signaling

All ROS1 fusions converge on STAT3 activation and directly interact with SHP2, with significantly greater SHP2 phosphorylation than ALK fusions. This distinguishes ROS1 from ALK biology and identifies SHP2 as a therapeutic vulnerability.

Finding 6: Normal ROS1 Biology — NELL2-Mediated Lumicrine Signaling

ROS1 normally functions in NELL2-mediated epithelial differentiation; c-ros KO mice are infertile. This pathway is conserved in humans (correlation r = 0.604 between mouse and human ortholog expression).

Finding 7: Immunosuppressive Co-Mutation Microenvironment

TP53/CDKN2A/B co-mutations (present in ~31% and ~15% respectively) create a paradoxical phenotype: high TMB and neoantigens but low CD8+ T-cell infiltration, resulting in worse prognosis.

Finding 8: Pemetrexed Biomarker Association

Pemetrexed-based chemotherapy shows superior efficacy in ROS1+ NSCLC (PFS 179 vs. 110 days for non-pemetrexed, p = 0.0107), with low thymidylate synthase expression predicting benefit.

Finding 9: Structural Biology Resources

Five crystal structures of the ROS1 kinase domain are available, including the G2032R mutant-zidesamtinib complex (PDB: 9QEK), enabling structure-based drug design for next-generation inhibitors.

Finding 10: Characteristic Histopathology

ROS1+ adenocarcinoma shows distinctive mucinous cribriform and signet ring cell patterns on histology, which can serve as morphological clues for molecular testing.

Finding 11: Conserved Normal Biology

The NELL2-ROS1 lumicrine signaling axis essential for male fertility is conserved from rodents to humans, providing insights into normal receptor function and potential off-target effects of ROS1 inhibitors.

Finding 12: Quality of Life with Targeted Therapy

Entrectinib maintains stable quality of life (STARTRK-2 PROs), while post-TKI chemo-immunotherapy carries substantially higher toxicity, underscoring the importance of maintaining patients on targeted therapy as long as possible.

Finding 13: SHP2 Inhibition as Combination Strategy

Preclinical data demonstrates that SHP2 inhibition enhances ROS1 TKI efficacy, supported by the finding that all ROS1 fusions uniquely converge on SHP2 activation, providing a mechanistic rationale for clinical combination trials.

Mechanistic Model / Interpretation

The pathophysiology of ROS1+ NSCLC can be understood as a multi-level cascade:

Level 1 — Genomic initiation: A stochastic somatic chromosomal rearrangement fuses the ROS1 kinase domain to a partner gene. The partner provides constitutive expression and a dimerization interface, converting ROS1 from a ligand-dependent receptor (normally activated by NELL2 in epididymal epithelium) to a ligand-independent oncogene.

Level 2 — Signaling amplification: The constitutively active ROS1 fusion kinase phosphorylates SHP2 (more strongly than ALK fusions do) and activates STAT3. These two nodes then fan out to the canonical MAPK and PI3K-AKT-mTOR cascades, plus non-canonical SHP2-dependent pathways that are MAPK-independent.

Level 3 — Phenotypic consequences: Sustained signaling drives proliferation (MAPK/ERK), survival (AKT/mTOR), and migration (fusion partner-specific, e.g., CLIP1 microtubule effects). The result is adenocarcinoma with mucinous/signet ring features and a notable tropism for the CNS.

Level 4 — Therapeutic response and resistance: ROS1 TKIs block the fusion kinase, collapsing the signaling cascade and producing dramatic tumor regression (ORR 70–90%). However, tumor evolution under selective pressure leads to resistance through on-target mutations (G2032R, L2086F) or bypass pathways (MET, RET, KRAS). The type of resistance mutation dictates the next therapeutic strategy: type II TKIs for L2086F, taletrectinib/zidesamtinib for G2032R, MET inhibitor combinations for MET amplification.

Level 5 — Microenvironment modulation: Co-occurring TP53/CDKN2A/B mutations reshape the immune microenvironment, creating an immunosuppressive milieu despite increased neoantigen load. This partially explains the limited efficacy of checkpoint inhibitors and suggests that combination strategies (TKI + SHP2 inhibitor or TKI + immunotherapy) may be needed for durable disease control.

Evidence Base

Landmark Studies

Limitations and Knowledge Gaps

1. Rarity limits clinical trial power: With only 1–2% prevalence, most clinical trials are single-arm; head-to-head comparisons between ROS1 TKIs are lacking and rely on indirect comparisons (MAICs)
2. Optimal TKI sequencing undefined: No randomized data guide the choice between first-line repotrectinib vs. taletrectinib, or optimal sequencing at resistance
3. Immunotherapy role unclear: While immune checkpoint inhibitors are largely ineffective as monotherapy, their role in combination with TKIs or chemotherapy post-TKI exhaustion requires further study
4. Early-stage targeted therapy: No data exist for adjuvant/neoadjuvant ROS1 TKIs in resectable disease
5. Long-term survival data: 5-year and 10-year overall survival with modern TKIs are not yet mature
6. Fusion partner-specific biology: While fusion partners confer different subcellular localizations and additional functions (e.g., CLIP1 motility effects), clinical significance remains uncertain
7. Biomarker-guided immunotherapy: Whether specific co-mutation profiles (high TMB, PD-L1+) predict immunotherapy benefit in the subset of ROS1+ patients remains unknown
8. Liquid biopsy standardization: ctDNA-based monitoring for ROS1 fusions and resistance mutations needs prospective validation
9. Epigenetic landscape: ROS1-specific epigenetic alterations are poorly characterized
10. Pediatric/young adult: Limited data on ROS1+ NSCLC in patients under 30 years

Proposed Follow-up Experiments/Actions

Clinical Priorities

1. Randomized trials comparing next-gen ROS1 TKIs: Head-to-head comparison of repotrectinib vs. taletrectinib in treatment-naive patients to establish optimal first-line therapy
2. Adjuvant ROS1 TKI trials: Phase III studies of post-surgical TKI therapy in resected ROS1+ NSCLC (analogous to ADAURA for EGFR)
3. SHP2 inhibitor combination trials: Based on preclinical evidence of enhanced TKI efficacy with SHP2 inhibition, phase I/II trials combining ROS1 TKIs with SHP2 inhibitors (e.g., TNO155, RMC-4630) are warranted
4. Biomarker-stratified immunotherapy: Trials evaluating checkpoint inhibitors in the TP53-co-mutated, high-TMB subset of ROS1+ patients

Research Priorities

1. Single-cell and spatial transcriptomics: Characterize the tumor microenvironment of ROS1+ NSCLC to understand immune evasion mechanisms and identify combination therapy targets
2. Resistance monitoring with ctDNA: Prospective validation of liquid biopsy-guided adaptive therapy (switching TKIs at molecular progression before radiographic progression)
3. Fusion partner functional studies: Systematic comparison of signaling, metastatic potential, and drug sensitivity across different fusion partners using isogenic models
4. CNS tropism mechanisms: Investigate why ROS1+ NSCLC has high brain metastasis rates; identify targetable pathways driving CNS invasion
5. Type II TKI development: Expand the arsenal of type II ROS1 TKIs to address L2086F and compound mutations
6. Real-world outcomes registry: Multi-national ROS1+ NSCLC registry to capture treatment patterns, sequential therapy outcomes, and long-term survival with modern TKIs

Ontology Term Summary

Report generated from autonomous scientific discovery analysis of 93 published studies with 13 confirmed findings across 5 investigation iterations. Last updated: 2026-05-06.