Structural Alterations Driving Castration-Resistant Prostate Cancer Revealed by Linked-Read Genome Sequencing.

Nearly all prostate cancer deaths are from metastatic castration-resistant prostate cancer (mCRPC), but there have been few whole-genome sequencing (WGS) studies of this disease state. We performed linked-read WGS on 23 mCRPC biopsy specimens and analyzed cell-free DNA sequencing data from 86 patients with mCRPC. In addition to frequent rearrangements affecting known prostate cancer genes, we observed complex rearrangements of the AR locus in most cases. Unexpectedly, these rearrangements include highly recurrent tandem duplications involving an upstream enhancer of AR in 70%-87% of cases compared with <2% of primary prostate cancers. A subset of cases displayed AR or MYC enhancer duplication in the context of a genome-wide tandem duplicator phenotype associated with CDK12 inactivation. Our findings highlight the complex genomic structure of mCRPC, nominate alterations that may inform prostate cancer treatment, and suggest that additional recurrent events in the non-coding mCRPC genome remain to be discovered.

Cancer aneuploidies are shaped primarily by effects on tumour fitness.

Aneuploidies-whole-chromosome or whole-arm imbalances-are the most prevalent alteration in cancer genomes1,2. However, it is still debated whether their prevalence is due to selection or ease of generation as passenger events1,2. Here we developed a method, BISCUT, that identifies loci subject to fitness advantages or disadvantages by interrogating length distributions of telomere- or centromere-bounded copy-number events. These loci were significantly enriched for known cancer driver genes, including genes not detected through analysis of focal copy-number events, and were often lineage specific. BISCUT identified the helicase-encoding gene WRN as a haploinsufficient tumour-suppressor gene on chromosome 8p, which is supported by several lines of evidence. We also formally quantified the role of selection and mechanical biases in driving aneuploidy, finding that rates of arm-level copy-number alterations are most highly correlated with their effects on cellular fitness1,2. These results provide insight into the driving forces behind aneuploidy and its contribution to tumorigenesis.

Genomic Characterization of Prostatic Basal Cell Carcinoma.

Basal cell carcinoma (BCC) of the prostate is a rare tumor. Compared with the more common acinar adenocarcinoma (AAC) of the prostate, BCCs show features of basal cell differentiation and are thought to be biologically distinct from AAC. The spectrum of molecular alterations of BCC has not been comprehensively described, and genomic studies are lacking. Herein, whole genome sequencing was performed on archival formalin-fixed, paraffin-embedded specimens of two cases with BCC. Prostatic BCCs were characterized by an overall low copy number and mutational burden. Recurrent copy number loss of chromosome 16 was observed. In addition, putative driver gene alterations in KIT, DENND3, PTPRU, MGA, and CYLD were identified. Mechanistically, depletion of the CYLD protein resulted in increased proliferation of prostatic basal cells in vitro. Collectively, these studies show that prostatic BCC displays distinct genomic alterations from AAC and highlight a potential role for loss of chromosome 16 in the pathogenesis of this rare tumor type.

Genetic and transcriptional evolution alters cancer cell line drug response.

Human cancer cell lines are the workhorse of cancer research. Although cell lines are known to evolve in culture, the extent of the resultant genetic and transcriptional heterogeneity and its functional consequences remain understudied. Here we use genomic analyses of 106 human cell lines grown in two laboratories to show extensive clonal diversity. Further comprehensive genomic characterization of 27 strains of the common breast cancer cell line MCF7 uncovered rapid genetic diversification. Similar results were obtained with multiple strains of 13 additional cell lines. Notably, genetic changes were associated with differential activation of gene expression programs and marked differences in cell morphology and proliferation. Barcoding experiments showed that cell line evolution occurs as a result of positive clonal selection that is highly sensitive to culture conditions. Analyses of single-cell-derived clones demonstrated that continuous instability quickly translates into heterogeneity of the cell line. When the 27 MCF7 strains were tested against 321 anti-cancer compounds, we uncovered considerably different drug responses: at least 75% of compounds that strongly inhibited some strains were completely inactive in others. This study documents the extent, origins and consequences of genetic variation within cell lines, and provides a framework for researchers to measure such variation in efforts to support maximally reproducible cancer research.

Implementation of a prostate cancer-specific targeted sequencing panel for credentialing of patient-derived cell lines and genomic characterization of patient samples.

BACKGROUND: Primary and metastatic prostate cancers have low mutation rates and recurrent alterations in a small set of genes, enabling targeted sequencing of prostate cancer-associated genes as an efficient approach to characterizing patient samples (compared to whole-exome and whole-genome sequencing). For example, targeted sequencing provides a flexible, rapid, and cost-effective method for genomic assessment of patient-derived cell lines to evaluate fidelity to initial patient tumor samples. METHODS: We developed a prostate cancer-specific targeted next-generation sequencing (NGS) panel to detect alterations in 62 prostate cancer-associated genes as well as recurring gene fusions with ETS family members, representing the majority of common alterations in prostate cancer. We tested this panel on primary prostate cancer tissues and blood biopsies from patients with metastatic prostate cancer. We generated patient-derived cell lines from primary prostate cancers using conditional reprogramming methods and applied targeted sequencing to evaluate the fidelity of these cell lines to the original patient tumors. RESULTS: The prostate cancer-specific panel identified biologically and clinically relevant alterations, including point mutations in driver oncogenes and ETS family fusion genes, in tumor tissues from 29 radical prostatectomy samples. The targeted panel also identified genomic alterations in cell-free DNA and circulating tumor cells (CTCs) from patients with metastatic prostate cancer, and in standard prostate cancer cell lines. We used the targeted panel to sequence our set of patient-derived cell lines; however, no prostate cancer-specific mutations were identified in the tumor-derived cell lines, suggesting preferential outgrowth of normal prostate epithelial cells. CONCLUSIONS: We evaluated a prostate cancer-specific targeted NGS panel to detect common and clinically relevant alterations (including ETS family gene fusions) in prostate cancer. The panel detected driver mutations in a diverse set of clinical samples of prostate cancer, including fresh-frozen tumors, cell-free DNA, CTCs, and cell lines. Targeted sequencing of patient-derived cell lines highlights the challenge of deriving cell lines from primary prostate cancers and the importance of genomic characterization to credential candidate cell lines. Our study supports that a prostate cancer-specific targeted sequencing panel provides an efficient, clinically feasible approach to identify genetic alterations across a spectrum of prostate cancer samples and cell lines.

Dynamics of genomic clones in breast cancer patient xenografts at single-cell resolution.

Human cancers, including breast cancers, comprise clones differing in mutation content. Clones evolve dynamically in space and time following principles of Darwinian evolution, underpinning important emergent features such as drug resistance and metastasis. Human breast cancer xenoengraftment is used as a means of capturing and studying tumour biology, and breast tumour xenografts are generally assumed to be reasonable models of the originating tumours. However, the consequences and reproducibility of engraftment and propagation on the genomic clonal architecture of tumours have not been systematically examined at single-cell resolution. Here we show, using deep-genome and single-cell sequencing methods, the clonal dynamics of initial engraftment and subsequent serial propagation of primary and metastatic human breast cancers in immunodeficient mice. In all 15 cases examined, clonal selection on engraftment was observed in both primary and metastatic breast tumours, varying in degree from extreme selective engraftment of minor (<5% of starting population) clones to moderate, polyclonal engraftment. Furthermore, ongoing clonal dynamics during serial passaging is a feature of tumours experiencing modest initial selection. Through single-cell sequencing, we show that major mutation clusters estimated from tumour population sequencing relate predictably to the most abundant clonal genotypes, even in clonally complex and rapidly evolving cases. Finally, we show that similar clonal expansion patterns can emerge in independent grafts of the same starting tumour population, indicating that genomic aberrations can be reproducible determinants of evolutionary trajectories. Our results show that measurement of genomically defined clonal population dynamics will be highly informative for functional studies using patient-derived breast cancer xenoengraftment.

Correction: Detection of circulating tumour DNA is associated with inferior outcomes in Ewing sarcoma and osteosarcoma: a report from the Children's Oncology Group.

The authors have noticed that the final paragraph of the Results section contains errors in the number of patients involved. The correct number of patients is included in the text below. These errors do not affect the Figure referenced.In osteosarcoma, we focused on 8q gain as a specific biological feature of interest. Among the 41 patients with detectable ctDNA in the osteosarcoma cohort, 8q gain was detected in 73.2% (30/41). The 3-year EFS for patients with 8q gain (n = 30) in ctDNA was 60.0% (95% CI 40.5-75.0) compared to 80.8 (95% CI 42.4-94.9) in patients without 8q gain (n = 11) in ctDNA (p = 0.18; Fig. 3).

Detection of circulating tumour DNA is associated with inferior outcomes in Ewing sarcoma and osteosarcoma: a report from the Children's Oncology Group.

BACKGROUND: New prognostic markers are needed to identify patients with Ewing sarcoma (EWS) and osteosarcoma unlikely to benefit from standard therapy. We describe the incidence and association with outcome of circulating tumour DNA (ctDNA) using next-generation sequencing (NGS) assays. METHODS: A NGS hybrid capture assay and an ultra-low-pass whole-genome sequencing assay were used to detect ctDNA in banked plasma from patients with EWS and osteosarcoma, respectively. Patients were coded as positive or negative for ctDNA and tested for association with clinical features and outcome. RESULTS: The analytic cohort included 94 patients with EWS (82% from initial diagnosis) and 72 patients with primary localised osteosarcoma (100% from initial diagnosis). ctDNA was detectable in 53% and 57% of newly diagnosed patients with EWS and osteosarcoma, respectively. Among patients with newly diagnosed localised EWS, detectable ctDNA was associated with inferior 3-year event-free survival (48.6% vs. 82.1%; p = 0.006) and overall survival (79.8% vs. 92.6%; p = 0.01). In both EWS and osteosarcoma, risk of event and death increased with ctDNA levels. CONCLUSIONS: NGS assays agnostic of primary tumour sequencing results detect ctDNA in half of the plasma samples from patients with newly diagnosed EWS and osteosarcoma. Detectable ctDNA is associated with inferior outcomes.

The genomic and transcriptomic architecture of 2,000 breast tumours reveals novel subgroups.

The elucidation of breast cancer subgroups and their molecular drivers requires integrated views of the genome and transcriptome from representative numbers of patients. We present an integrated analysis of copy number and gene expression in a discovery and validation set of 997 and 995 primary breast tumours, respectively, with long-term clinical follow-up. Inherited variants (copy number variants and single nucleotide polymorphisms) and acquired somatic copy number aberrations (CNAs) were associated with expression in ~40% of genes, with the landscape dominated by cis- and trans-acting CNAs. By delineating expression outlier genes driven in cis by CNAs, we identified putative cancer genes, including deletions in PPP2R2A, MTAP and MAP2K4. Unsupervised analysis of paired DNA­RNA profiles revealed novel subgroups with distinct clinical outcomes, which reproduced in the validation cohort. These include a high-risk, oestrogen-receptor-positive 11q13/14 cis-acting subgroup and a favourable prognosis subgroup devoid of CNAs. Trans-acting aberration hotspots were found to modulate subgroup-specific gene networks, including a TCR deletion-mediated adaptive immune response in the 'CNA-devoid' subgroup and a basal-specific chromosome 5 deletion-associated mitotic network. Our results provide a novel molecular stratification of the breast cancer population, derived from the impact of somatic CNAs on the transcriptome.

The clonal and mutational evolution spectrum of primary triple-negative breast cancers.

Primary triple-negative breast cancers (TNBCs), a tumour type defined by lack of oestrogen receptor, progesterone receptor and ERBB2 gene amplification, represent approximately 16% of all breast cancers. Here we show in 104 TNBC cases that at the time of diagnosis these cancers exhibit a wide and continuous spectrum of genomic evolution, with some having only a handful of coding somatic aberrations in a few pathways, whereas others contain hundreds of coding somatic mutations. High-throughput RNA sequencing (RNA-seq) revealed that only approximately 36% of mutations are expressed. Using deep re-sequencing measurements of allelic abundance for 2,414 somatic mutations, we determine for the first time-to our knowledge-in an epithelial tumour subtype, the relative abundance of clonal frequencies among cases representative of the population. We show that TNBCs vary widely in their clonal frequencies at the time of diagnosis, with the basal subtype of TNBC showing more variation than non-basal TNBC. Although p53 (also known as TP53), PIK3CA and PTEN somatic mutations seem to be clonally dominant compared to other genes, in some tumours their clonal frequencies are incompatible with founder status. Mutations in cytoskeletal, cell shape and motility proteins occurred at lower clonal frequencies, suggesting that they occurred later during tumour progression. Taken together, our results show that understanding the biology and therapeutic responses of patients with TNBC will require the determination of individual tumour clonal genotypes.

TITAN: inference of copy number architectures in clonal cell populations from tumor whole-genome sequence data.

The evolution of cancer genomes within a single tumor creates mixed cell populations with divergent somatic mutational landscapes. Inference of tumor subpopulations has been disproportionately focused on the assessment of somatic point mutations, whereas computational methods targeting evolutionary dynamics of copy number alterations (CNA) and loss of heterozygosity (LOH) in whole-genome sequencing data remain underdeveloped. We present a novel probabilistic model, TITAN, to infer CNA and LOH events while accounting for mixtures of cell populations, thereby estimating the proportion of cells harboring each event. We evaluate TITAN on idealized mixtures, simulating clonal populations from whole-genome sequences taken from genomically heterogeneous ovarian tumor sites collected from the same patient. In addition, we show in 23 whole genomes of breast tumors that the inference of CNA and LOH using TITAN critically informs population structure and the nature of the evolving cancer genome. Finally, we experimentally validated subclonal predictions using fluorescence in situ hybridization (FISH) and single-cell sequencing from an ovarian cancer patient sample, thereby recapitulating the key modeling assumptions of TITAN.

PyClone: statistical inference of clonal population structure in cancer.

We introduce PyClone, a statistical model for inference of clonal population structures in cancers. PyClone is a Bayesian clustering method for grouping sets of deeply sequenced somatic mutations into putative clonal clusters while estimating their cellular prevalences and accounting for allelic imbalances introduced by segmental copy-number changes and normal-cell contamination. Single-cell sequencing validation demonstrates PyClone's accuracy.

An RCOR1 loss-associated gene expression signature identifies a prognostically significant DLBCL subgroup.

Effective treatment of diffuse large B-cell lymphoma (DLBCL) is plagued by heterogeneous responses to standard therapy, and molecular mechanisms underlying unfavorable outcomes in lymphoma patients remain elusive. Here, we profiled 148 genomes with 91 matching transcriptomes in a DLBCL cohort treated with rituximab plus cyclophosphamide, doxorubicin, vincristine, and prednisolone (R-CHOP) to uncover molecular subgroups linked to treatment failure. Systematic integration of high-resolution genotyping arrays and RNA sequencing data revealed novel deletions in RCOR1 to be associated with unfavorable progression-free survival (P = .001). Integration of expression data from the clinical samples with data from RCOR1 knockdowns in the lymphoma cell lines KM-H2 and Raji yielded an RCOR1 loss-associated gene signature comprising 233 genes. This signature identified a subgroup of patients with unfavorable overall survival (P = .023). The prognostic significance of the 233-gene signature for overall survival was reproduced in an independent cohort comprising 195 R-CHOP-treated patients (P = .039). Additionally, we discovered that within the International Prognostic Index low-risk group, the gene signature provides additional prognostic value that was independent of the cell-of-origin phenotype. We present a novel and reproducible molecular subgroup of DLBCL that impacts risk-stratification of R-CHOP-treated DLBCL patients and reveals a possible new avenue for therapeutic intervention strategies.

Multifocal endometriotic lesions associated with cancer are clonal and carry a high mutation burden.

Endometriosis is a significant risk factor for clear cell and endometrioid ovarian cancers and is often found contiguous with these cancers. Using whole-genome shotgun sequencing of seven clear cell ovarian carcinomas (CCC) and targeted sequencing in synchronous endometriosis, we have investigated how this carcinoma may evolve from endometriosis. In every case we observed multiple tumour-associated somatic mutations in at least one concurrent endometriotic lesion. ARID1A and PIK3CA mutations appeared consistently in concurrent endometriosis when present in the primary CCC. In several cases, one or more endometriotic lesions carried the near-complete complement of somatic mutations present in the index CCC tumour. Ancestral mutations were detected in both tumour-adjacent and -distant endometriotic lesions, regardless of any cytological atypia. These findings provide objective evidence that multifocal benign endometriotic lesions are clonally related and that CCCs arising in these patients progress from endometriotic lesions that may already carry sufficient cancer-associated mutations to be considered neoplasms themselves, albeit with low malignant potential. We speculate that genomically distinct classes of endometriosis exist and that ovarian endometriosis with high mutational burden represents one class at high risk for malignant transformation.

Recurrent somatic DICER1 mutations in nonepithelial ovarian cancers.

BACKGROUND: Germline truncating mutations in DICER1, an endoribonuclease in the RNase III family that is essential for processing microRNAs, have been observed in families with the pleuropulmonary blastoma-family tumor and dysplasia syndrome. Mutation carriers are at risk for nonepithelial ovarian tumors, notably sex cord-stromal tumors. METHODS: We sequenced the whole transcriptomes or exomes of 14 nonepithelial ovarian tumors and noted closely clustered mutations in the region of DICER1 encoding the RNase IIIb domain of DICER1 in four samples. We then sequenced this region of DICER1 in additional ovarian tumors and in certain other tumors and queried the effect of the mutations on the enzymatic activity of DICER1 using in vitro RNA cleavage assays. RESULTS: DICER1 mutations in the RNase IIIb domain were found in 30 of 102 nonepithelial ovarian tumors (29%), predominantly in Sertoli-Leydig cell tumors (26 of 43, or 60%), including 4 tumors with additional germline DICER1 mutations. These mutations were restricted to codons encoding metal-binding sites within the RNase IIIb catalytic centers, which are critical for microRNA interaction and cleavage, and were somatic in all 16 samples in which germline DNA was available for testing. We also detected mutations in 1 of 14 nonseminomatous testicular germ-cell tumors, in 2 of 5 embryonal rhabdomyosarcomas, and in 1 of 266 epithelial ovarian and endometrial carcinomas. The mutant DICER1 proteins had reduced RNase IIIb activity but retained RNase IIIa activity. CONCLUSIONS: Somatic missense mutations affecting the RNase IIIb domain of DICER1 are common in nonepithelial ovarian tumors. These mutations do not obliterate DICER1 function but alter it in specific cell types, a novel mechanism through which perturbation of microRNA processing may be oncogenic. (Funded by the Terry Fox Research Institute and others.).

Integrative analysis of genome-wide loss of heterozygosity and monoallelic expression at nucleotide resolution reveals disrupted pathways in triple-negative breast cancer.

Loss of heterozygosity (LOH) and copy number alteration (CNA) feature prominently in the somatic genomic landscape of tumors. As such, karyotypic aberrations in cancer genomes have been studied extensively to discover novel oncogenes and tumor-suppressor genes. Advances in sequencing technology have enabled the cost-effective detection of tumor genome and transcriptome mutation events at single-base-pair resolution; however, computational methods for predicting segmental regions of LOH in this context are not yet fully explored. Consequently, whole transcriptome, nucleotide-level resolution analysis of monoallelic expression patterns associated with LOH has not yet been undertaken in cancer. We developed a novel approach for inference of LOH from paired tumor/normal sequence data and applied it to a cohort of 23 triple-negative breast cancer (TNBC) genomes. Following extensive benchmarking experiments, we describe the nucleotide-resolution landscape of LOH in TNBC and assess the consequent effect of LOH on the transcriptomes of these tumors using RNA-seq-derived measurements of allele-specific expression. We show that the majority of monoallelic expression in the transcriptomes of triple-negative breast cancer can be explained by genomic regions of LOH and establish an upper bound for monoallelic expression that may be explained by other tumor-specific modifications such as epigenetics or mutations. Monoallelically expressed genes associated with LOH reveal that cell cycle, homologous recombination and actin-cytoskeletal functions are putatively disrupted by LOH in TNBC. Finally, we show how inference of LOH can be used to interpret allele frequencies of somatic mutations and postulate on temporal ordering of mutations in the evolutionary history of these tumors.

Distinct evolutionary trajectories of primary high-grade serous ovarian cancers revealed through spatial mutational profiling.

High-grade serous ovarian cancer (HGSC) is characterized by poor outcome, often attributed to the emergence of treatment-resistant subclones. We sought to measure the degree of genomic diversity within primary, untreated HGSCs to examine the natural state of tumour evolution prior to therapy. We performed exome sequencing, copy number analysis, targeted amplicon deep sequencing and gene expression profiling on 31 spatially and temporally separated HGSC tumour specimens (six patients), including ovarian masses, distant metastases and fallopian tube lesions. We found widespread intratumoural variation in mutation, copy number and gene expression profiles, with key driver alterations in genes present in only a subset of samples (eg PIK3CA, CTNNB1, NF1). On average, only 51.5% of mutations were present in every sample of a given case (range 10.2-91.4%), with TP53 as the only somatic mutation consistently present in all samples. Complex segmental aneuploidies, such as whole-genome doubling, were present in a subset of samples from the same individual, with divergent copy number changes segregating independently of point mutation acquisition. Reconstruction of evolutionary histories showed one patient with mixed HGSC and endometrioid histology, with common aetiologic origin in the fallopian tube and subsequent selection of different driver mutations in the histologically distinct samples. In this patient, we observed mixed cell populations in the early fallopian tube lesion, indicating that diversity arises at early stages of tumourigenesis. Our results revealed that HGSCs exhibit highly individual evolutionary trajectories and diverse genomic tapestries prior to therapy, exposing an essential biological characteristic to inform future design of personalized therapeutic solutions and investigation of drug-resistance mechanisms.

Assay Validation of Cell-Free DNA Shallow Whole-Genome Sequencing to Determine Tumor Fraction in Advanced Cancers.

Blood-based liquid biopsy is increasingly used in clinical care of patients with cancer, and fraction of tumor-derived DNA in circulation (tumor fraction; TFx) has demonstrated clinical validity across multiple cancer types. To determine TFx, shallow whole-genome sequencing of cell-free DNA (cfDNA) can be performed from a single blood sample, using an established computational pipeline (ichorCNA), without prior knowledge of tumor mutations, in a highly cost-effective manner. We describe assay validation of this approach to facilitate broad clinical application, including evaluation of assay sensitivity, precision, repeatability, reproducibility, pre-analytic factors, and DNA quality/quantity. Sensitivity to detect TFx of 3% (lower limit of detection) was 97.2% to 100% at 1× and 0.1× mean sequencing depth, respectively. Precision was demonstrated on distinct sequencing instruments (HiSeqX and NovaSeq) with no observable differences. The assay achieved prespecified 95% agreement of TFx across replicates of the same specimen (repeatability) and duplicate samples in different batches (reproducibility). Comparison of samples collected in EDTA and Streck tubes from single venipuncture in 23 patients demonstrated that EDTA or Streck tubes were comparable if processed within 8 hours. On the basis of a range of DNA inputs (1 to 50 ng), 20 ng cfDNA is the preferred input, with 5 ng minimum acceptable. Overall, this shallow whole-genome sequencing of cfDNA and ichorCNA approach offers sensitive, precise, and reproducible quantitation of TFx, facilitating assay application in clinical cancer care.

FinaleMe: Predicting DNA methylation by the fragmentation patterns of plasma cell-free DNA.

Analysis of DNA methylation in cell-free DNA (cfDNA) reveals clinically relevant biomarkers but requires specialized protocols and sufficient input material that limits its applicability. Millions of cfDNA samples have been profiled by genomic sequencing. To maximize the gene regulation information from the existing dataset, we developed FinaleMe, a non-homogeneous Hidden Markov Model (HMM), to predict DNA methylation of cfDNA and, therefore, tissues-of-origin directly from plasma whole-genome sequencing (WGS). We validated the performance with 80 pairs of deep and shallow-coverage WGS and whole-genome bisulfite sequencing (WGBS) data.

Molecular phenotyping of small cell lung cancer using targeted cfDNA profiling of transcriptional regulatory regions.

We report an approach for cancer phenotyping based on targeted sequencing of cell-free DNA (cfDNA) for small cell lung cancer (SCLC). In SCLC, differential activation of transcription factors (TFs), such as ASCL1, NEUROD1, POU2F3, and REST defines molecular subtypes. We designed a targeted capture panel that identifies chromatin organization signatures at 1535 TF binding sites and 13,240 gene transcription start sites and detects exonic mutations in 842 genes. Sequencing of cfDNA from SCLC patient-derived xenograft models captured TF activity and gene expression and revealed individual highly informative loci. Prediction models of ASCL1 and NEUROD1 activity using informative loci achieved areas under the receiver operating characteristic curve (AUCs) from 0.84 to 0.88 in patients with SCLC. As non-SCLC (NSCLC) often transforms to SCLC following targeted therapy, we applied our framework to distinguish NSCLC from SCLC and achieved an AUC of 0.99. Our approach shows promising utility for SCLC subtyping and transformation monitoring, with potential applicability to diverse tumor types.