Established human GBM stem-like cell lines (GBM4 and GBM8) [18, 19] were implanted in the nude rat brain. Control animals underwent an identical surgical procedure and were inoculated with medium only. Quantitative magnetic resonance imaging techniques were implemented on a 3T whole-body clinical scanner (Philips Achieva) to phenotype the tumors. Fast bound-pool fraction imaging (FBFI), a method validated with histology to measure myelin density and identify tumor associated disruption of normal brain tissues [20], was used to produce bound-pool fraction maps (f maps) to detect and differentiate between bulky and infiltrative lesions. The variable flip angle method [21] was used to measure T₁ relaxivity (R₁ maps, where R₁ = 1/T₁) before and after administration of gadolinium (gadopentetate dimeglumine, Bayer HealthCare), an intravenous contrast agent that shortens T₁ and identifies disruption of the blood-brain barrier (i.e., hyperintense signal on post-contrast R₁ maps relative to pre-contrast R₁ maps). Our initial experiments found that GBM4 yielded small, focal, non-enhancing lesions (Fig 1A and 1B, S1A and S1B Fig). In contrast, GBM8 produced heterogenous lesions that ranged from large, well-circumscribed tumors with strong contrast enhancement (i.e. disruption of the blood-brain barrier) to infiltrative lesions with absent or minimal contrast enhancement (Fig 1A and 1B, S1A and S1B Fig).

Detection of human ctDNA associated with GBM4 was not greater than the control animals (Fig 1C), which was attributable to the small tumor size and absence of blood-brain barrier disruption. Human ctDNA was detected in all animals implanted with GBM8 including infiltrative lesions with absent (e.g., GBM8₃, Fig 1A and 1B) to minimal (e.g., GBM8₂, S1A and S1B Fig) disruption of the blood-brain barrier (Fig 1C, S1C Fig). The percent human ctDNA in the buffy coat, where some residual plasma remains present, appeared correlated with the fraction in plasma, but much lower, indicating that neither intact tumor cells nor a high molecular weight fraction of ctDNA were present in the circulation (Fig 1C). Unexpectedly, there was a precise difference in fragment length between human ctDNA and rat cell-free DNA. The most common fragment lengths in human ctDNA were 134 bp and 144 bp (Fig 1D, S1D Fig), which was in contrast to the most common fragment length of 167 bp in rat cell-free DNA (Fig 1F). Human ctDNA fragment lengths also exhibited a strong ~10 bp periodicity that was not as evident in the rat cell-free DNA. This pattern was consistent across all animals where human ctDNA was detected (Fig 1E).

To determine if the fragment length and periodicity extended beyond the GBM8 cell line, nude rats were again implanted with either GBM4 or GBM8. Animals implanted with GBM4 were serially imaged until the presence of blood-brain barrier disruption was evident (i.e., contrast-enhancement on MRI) or animals lost more than 10% bodyweight. As before, GBM8 animals developed tumors that were large and exhibited a range of phenotypes (Fig 2A and S2 Fig). Fragment length and periodicity was consistent with that present in the initial experiment (Fig 2C). After a post-surgical interval nearly twice as long as GBM8, GBM4 tumors developed (Fig 2 and S2 Fig). GBM4 tumors tended to grow more anteriorly towards the olfactory bulbs, which led to weight loss in animals before tumor size was similar to GBM8. In a single animal implanted with GBM4, ctDNA was adequately detected and a similar fragment length and periodicity as seen with GBM8 was identified (Fig 2C).

To evaluate the role of both GBM and the blood-brain barrier in determining fragment length and periodicity, human hepatocellular carcinoma cells (Hep G2) were implanted subcutaneously in the flank of three nude rats. A palpable tumor (approximately 10 mm at maximal diameter), confirmed with histology, formed in a single animal (Fig 2D). The fragment length of ctDNA was consistent with that described in GBM4 and GBM8 (Fig 2E). There was evidence for a similar periodicity, but the relatively low amount of detected ctDNA may have contributed to a noisier distribution of fragment size. Regardless, the replication of results in a xenograft model of hepatocellular carcinoma suggested that the periodicity and reduced fragment length of ctDNA may be general properties of ctDNAs in cancers beyond GBM.

We next considered the effects of the xenograft model on ctDNA fragment length and periodicity and sought to determine if evidence of the observed differences in fragment length were present in other types of solid tumors such as melanoma. In contrast to the xenograft models, the cell-free DNA from tumor patients represented an indistinguishable mix of both ctDNA and cell-free DNA derived from normal healthy cells. By densitometry (TapeStation 2200), the cell-free DNA from melanoma patients had globally shorter fragment lengths compared to healthy controls (Fig 3A).

Potential differences in fragment length size between tumor patients and healthy controls were explored by sequencing the cell-free DNA from a melanoma patient with an elevated concentration of cell-free DNA (36.4 ng/mL plasma; Fig 3A, black arrow) to obtain a large sample for comparison to sequencing results from a pooled sample of control cell-free DNA. The most common fragment length in the melanoma patient was shorter than the most common fragment length in the control sample (145 bp vs. 165 bp, respectively; Fig 3B). There was also evidence for more pronounced fragment length periodicity in the cell-free DNA from the melanoma patient (Fig 3B). In the melanoma patient cell-free DNA, the BRAF V600E allele frequency was increased at shorter fragment lengths compared to the WT allele (Fig 3C). Of note, the broad distribution of the WT allele (Fig 3C, blue line) included a substantial proportion of overlapping fragment sizes with the mutant allele since the BRAF V600E mutation is heterozygous and tumor cells also introduced shorter fragment lengths into the circulation with the WT allele. Subsequently, fragment length for the melanoma patient and the healthy volunteer were binned (e.g. 50 = 50–59 bp; 60 = 60–69 bp, etc.) and the frequency of mutant allele and WT allele was determined, respectively. For a given fragment length, the proportion of the V600E BRAF allele to the WT allele was highest in the 110–140 bp fragment length, which was in contrast to the WT allele in the pooled healthy control sample that occurred at the highest frequency between 160–180 bp (Fig 3D). Importantly, there were limited observations of ctDNA fragments <100 bp in the melanoma patient (Fig 3D, black line), which were likely present but not well recovered by current approaches to library preparation [22]. These collective findings indicated an overall shortening of ctDNA fragment size relative to cell-free DNA that was not an effect of the xenograft model, but rather inherent to ctDNAs across different tumor types.

We then sought to characterize tumor-related differences in cell-free DNA and ctDNA associated with human lung cancer. A comparison of cell-free DNA from 15 lung cancer patients and 9 healthy controls found a statistically significant difference in plasma concentration of cell-free DNA (31.0±23.3 vs. 11.3±4.6 ng mL/plasma, p = 0.006; respectively); however, the range of concentration in tumor patients was broad and overlapped with the concentrations present in healthy controls (S3 Fig). Libraries made with duplex truncated molecular barcoded adapters, which added ~99 bp to each strand of cell-free DNA, were created to enable loading of a consistent concentration (2 ng/μL) of each sample and clear identification of upper/lower markers for direct comparison of densitometry data (TapeStation 2200; S4 Fig). Consistent with our observation in melanoma patients, peak fragment length by densitometry was significantly shorter compared to healthy controls (277.0±4.7 vs. 283.7±4.1 bp, p = 0.002; respectively; S3B Fig) indicating a global shift towards smaller fragments in lung cancer patients. However, there was also considerable overlap of peak fragment length between tumor patients and controls (S3B Fig). There was not an association between peak fragment length by densitometry and plasma concentration of cell-free DNA in the lung cancer patients (Pearson’s r = –0.20, p = 0.47; Fig 4C) or the healthy controls (Pearson’s r = 0.19, p = 0.63; S3C Fig).

For a subset of samples (tumor, N = 7; control N = 5), cell-free DNA was converted to Illumina sequencing libraries and enriched for cancer-relevant genes using a 16-gene capture panel. Utilizing fragment lengths from the complete 16 gene capture panel, we observed that the cell-free DNA from tumor patients ranged from a shorter fragment length with (Fig 4A) and without (Fig 4B and S5A–S5D Fig) a strong periodicity to indistinguishable (Fig 4C and S5E–S5G Fig) in fragment length distribution from healthy controls. Cell-free DNA from the tumor patients did not exhibit a fragment length larger than the controls (S5 Fig), which was consistent with densitometry (S3B Fig).

Cell-free DNA from two lung cancer patients (LC5 and LC10) contained the classic EGFR L858R mutation [23]. Fragments containing the mutant allele, which originate from the tumor rather than from breakdown of normal cells, were shorter than those bearing the WT allele in healthy controls (Fig 4D). This difference was especially pronounced in one sample (LC5; Fig 4E) with a relatively high mutant allele frequency (74.6%; likely due to EGFR amplification, S6 Fig).

Cell-free DNA from six of the lung cancer patients contained the EGFR T790M mutation. In 5 out of 6 patients, the mutant allele frequency was relatively low (0.2–6.6%). However, the general trend in these samples was for mutant alleles to occur at shorter fragment lengths (Fig 4F). In one sample (LC9) with a relatively high mutant allele frequency (25.1%; most likely due to an EGFR amplification, S5 Fig) the mutant allele more commonly occurred at shorter fragment lengths compared to the fragment lengths from healthy controls (Fig 4G). The distribution of fragment lengths of the EGFR WT allele between tumor patients and healthy controls largely reflected differences seen in S5 Fig, although noisier due to fewer total reads (S7 Fig). Within each lung cancer patient with the mutant T790M allele, comparison of the distribution of the EGFR WT allele and the mutant T790M allele fragment lengths identified a general trend for the mutant allele to occur more commonly at shorter fragment lengths (Fig 4H). As with the melanoma patient (Fig 4C), fragment length analysis of the WT allele from tumor patients included an indistinguishable mixture of ctDNA and normal cell-free DNA since the mutant T790M allele is heterozygous. As such, the representative WT allele fragment length distribution from tumor patients included WT alleles derived from tumor cells. This observation may explain, at least in part, why the differences in fragment length between the WT allele and the mutant T790M allele presented in Fig 4H were less pronounced than differences observed between the WT allele from healthy controls and the mutant T790M allele shown in Fig 4F.

We next set out to determine whether selection for shorter fragment lengths could be used to enrich for ctDNA fragments against the large background of cell-free DNA derived from normal cells. Cell-free DNA sequencing libraries from four lung cancer patients (LC1, LC3, LC4, and LC10) with EGFR T790M mutations and one healthy control (C5) were selected for serial fraction collection. By sequencing, LC1 and LC3 had EGFR T790M mutant allele frequencies of 1.2% and 6.6%, respectively, and evidence of overall shorter cell-free DNA fragments compared to healthy controls (Fig 4B and S5B Fig, respectively). LC4 and LC10 had EGFR T790M mutant allele frequencies of 2.3% and 1.7%, respectively, and a similar size distribution of cell-free DNA fragments compared to healthy controls (S5G Fig and Fig 4C, respectively). None of the samples had an EGFR amplification present (S6 Fig). For each sample, 1 μg of sequencing library was loaded onto an 8% native polyacrylamide gel and six adjacent gel fragments were collected (S8 Fig). Extracted DNA (5–10 ng) from each gel fragment was then amplified using the full-length adapter primer and the EGFR T790M mutant allele frequency was determined via digital droplet PCR (Fig 5).

Compared to the mutant allele frequency in the library, three samples (LC1, LC4, and LC10) demonstrated a 2.5-fold to 9.1-fold increase in the mutant allele frequency in a subset of fractions that contained a shorter distribution of cell-free DNA fragments relative to the peak fragment length in the library (Fig 6 and S9–S11 Figs). The fraction associated with the greatest increase in mutant allele frequency for each tumor patient is identified in Fig 6A–6C. In one sample (LC1), the mutant allele frequency did not increase in any fraction relative to the mutant allele frequency in the library (S12 Fig). However, a decrease in the mutant allele frequency was observed in fractions containing longer fragments, while fractions with shorter fragments contained a relatively consistent mutant allele frequency (Fig 6D and S12 Fig). Enrichment for the mutant allele was greatest in fractions that were centered approximately 20–50 bp shorter than the peak fragment length associated with each corresponding library (Fig 6E). The increase in mutant allele frequency was greatest in LC10 (Fig 5 and S11 Fig) and LC4 (S10 Fig), which were the two tumor patients with a similar fragment size distribution profile as that seen in the healthy controls (Fig 4C and S5G Fig, respectively). This finding suggests that the fractional selection of shorter cell-free DNA fragment lengths may improve mutant allele sensitivity when ctDNA is not the predominant component of cell-free DNA. Also notable is that the percentage of mutant allele detected in a sample low in ctDNA prior to enrichment may not represent the true allele frequency present in the tumor due to dilution by normal cell-free DNA. In LC1 (S12 Fig) and LC3 (S9 Fig), the tumor patients with evidence of overall shorter cell-free DNA fragments compared to healthy controls, the increase in mutant allele frequency in fractions 20–50 bp shorter than the peak fragment length associated with each library was not as substantial; however, selecting these fractions also did not diminish the mutant allele frequency (Fig 6E). In contrast, the selection of fractions longer than the library’s peak fragment length substantially reduced the mutant allele frequency in three of the tumor samples (LC1, LC4, and LC10; Fig 6E and S10–S12 Figs). Similarly, the selection of fractions containing cell-free DNA fragments >50 bp shorter than the library’s peak fragment length reduced the mutant allele frequency in all of the samples (Fig 6E). This latter observation may be a consequence of recovery during library preparation as discussed earlier (Fig 3D) [22]. Regardless, these observations provide compelling evidence that the fragment length of ctDNA is shorter than cell-free DNA from healthy cells and selection of shorter cell-free DNA fragments may improve mutant allele frequency. Of note, the EGFR T790M mutant allele was not present above the noise level associated with digital droplet PCR in the fractions obtained from the control sample (S13 Fig).

All human subject research was approved by the University of Utah Institutional Review Board prior to study initiation. Written informed consent was obtained for samples from melanoma patients and healthy controls according to IRB approved studies 10924 and 7740. Informed consent was not obtained for the lung cancer samples as specimens were obtained from residual clinical samples scheduled for disposal and after de-identification according to IRB approved study 7275. Adult male RNU rats were used in this study. All procedures were approved by the University of Washington Internal Animal Care and Use Committee prior to study initiation. For surgery, rats were anesthetized with ketamine and xylazine administered IP. For imaging, rats were anesthetized with isoflurane mixed with oxygen. Rats were euthanized with Beuthanasia-D administered IP.

Established human GBM stem-like cell lines (GBM4, GBM8) [18, 19] were maintained in serum-free Neurobasal medium (ThermoFisher Scientific) with 2 mM glutamine, 5 μg/mL heparin, 100 U/ml penicillin-streptomycin, N2 at 0.5X, B27 supplement minus vitamin A at 0.5X, and bi-weekly pulsing of FGF and EGF (20 ng/mL each). Human hepatocellular carcinoma cells (Hep G2; ATCC) were maintained in Williams’ medium E with glutamine and 10% fetal bovine serum. All cells were maintained in a humidified incubator at 37°C in 5% CO₂.

For implantation, single cell suspensions of GBM4 and GBM8 were achieved using heparin-EDTA and trituration followed by spin and wash ×2 with Neurobasal medium, then spin and resuspend in Neurobasal medium with DNase (4k U/ml), trituration, and incubation ×5 minutes at room temperature. Cells were then washed ×2 with Neurobasal medium to remove DNase and resuspended in Neurobasal medium for cell counting. Cells were counted with a hemacytometer after suspension in Trypan blue. For implantation, 1×10⁶ cells were resuspended in 10 μL of Neurobasal medium. Hep G2 cells were harvested by heparin-EDTA, counted using a hemocytometer after suspension in Trypan blue. For implantation, 5×10⁶ cells were resuspended in 100 μL of Williams’ medium E.

Adult male RNU rats (Charles River Laboratories, Wilmington, MA) were used in this study. All procedures were approved by the University of Washington Internal Animal Care and Use Committee prior to study initiation.

Rats were anesthetized with 60 mg/kg ketamine and 5 mg/kg xylazine administered IP. For intracranial inoculation (GBM4 and GBM8), the head was immobilized in a stereotactic head set with ear bars and a teeth bar. The skull was exposed by a 2 cm midline incision, and a burr hole was created on the right side 1 mm anterior and 2 mm lateral to the bregma. A microsyringe (Hamilton, Reno, NV) was used to inject the 10 μL aliquot of 10⁶ cells into the frontal lobe at a depth of 5 mm from the skull surface over a period of 5 minutes. The needle was kept in place 2 minutes after injection to prevent backflow prior to removal. The burr hole was filled with bone wax (Ethicon, Somerville, NJ). The skin was closed with surgical staples that were removed prior to MR imaging. For flank injections (Hep G2), a 22-gauge needle attached to a TB syringe was used to inject the cells subcutaneously into the right flank.

After the final imaging time point, the rats were anesthetized with Beuthanasia-D (2 mL/kg). A midline abdominal incision followed by thoracotomy was made to access the left ventricle of the heart. A 22-gauge needle attached to a syringe containing heparin was used to remove as much blood as possible (6–10 mL). Subsequently, 4% paraformaldehyde (PFA) was injected into the left ventricle (total volume 150 mL) as the right atrium was opened. Brains were subsequently removed intact, held in 4% PFA×24 hours under gentle agitation, and then maintained in PBS.

After fixation, brains were sectioned to correspond with the anatomic coronal plane. Brains were subsequently embedded in paraffin and sections (5 μm thick) were stained with hematoxylin-eosin. Stained slides were scanned using an Olympus VS110 virtual microscopy system (Olympus, Center Valley, PA) for display on NDP.view (v2.3.1).

Rats were imaged on a 3.0 T Philips Achieva whole-body MRI scanner (Philips Medical Systems, Best, Netherlands) using a dual coil approach. A quadrature transmit/receive head coil (Philips Medical Systems) was utilized for RF transmission, and an in-house-built combined solenoid-surface coil [30] dedicated to high spatial resolution whole-brain rat imaging was used for RF reception. After induction in an anesthesia chamber with 5% isoflurane mixed with oxygen, the rats were positioned within the dual coils and maintained on 2% isoflurane mixed with oxygen via nose cone inhalation. Total scan time for all images was < 1 hour.

Images necessary for construction of bound-pool fraction maps in the rat brain were acquired as previously described [20]. Briefly, Z-spectra data points were acquired for each rat using a 3D MT-prepared spoiled gradient echo (GRE) sequence with TR/TE = 42/4.6 ms, excitation flip angle α = 10°, NEX = 1, and three offset frequencies (Δ = 4, 8, and 96 kHz) of the off-resonance saturation pulse (effective flip angle = 950°). Complementary R₁ maps necessary for parameter fitting were obtained using the variable flip angle method [21] with a 3D spoiled GRE sequence (TR/TE = 20/2.3 ms, α = 4 (NEX = 3), 10 (NEX = 1), 20 (NEX = 2), and 30° (NEX = 3)). All Z-spectral and VFA images were acquired with a FOV = 29×29×19.8 mm³, matrix = 97×97×66, acquisition resolution = 0.3×0.3×0.3 mm³ (zero-interpolated to 0.15×0.15×0.15 mm³), and full-Fourier acquisition. Whole-brain 3D B₀ and B₁ maps were acquired to correct for field heterogeneities. For B₀ mapping, the GRE-based dual-TE phase-difference method [31] was used with TR/TE₁/TE₂ = 20/4.7/5.7 ms and α = 10°. B₁ maps were obtained using the actual flip angle imaging method [32] and the following sequence parameters: TR₁/TR₂/TE = 25/125/6.6 ms and α = 60°. 3D B₀ and B₁ maps were acquired with a FOV = 29×29×19.8, matrix = 64×64×33, acquisition resolution = 0.45×0.45×0.6 mm³ (zero-interpolated to 0.15×0.15×0.15 mm³), and NEX = 1. All images were acquired in the coronal plane.

For administration of gadolinium (gadopentetate dimeglumine, Bayer HealthCare; 0.5 M/L) a 22 Gauge angiocatheter (Becton-Dickinson, Sandy, Utah) was inserted into the rat tail vein. The catheter was attached to a small bore bifurcated extension (Smiths Medical, Dublin, OH) containing a dilution of gadolinium in one arm and a normal saline flush in the other. The catheter setup was maintained with a saline lock until immediately prior to imaging. At time of injection, 0.2 mmol/kg (0.167 M/L) of gadolinium was manually injected at 50 μL/s followed by a 250 μL flush of normal saline at 50 μL/s. Complementary pre-contrast R₁ maps necessary for parameter fitting and post-contrast R₁ maps obtained 5 minutes after contrast injection were acquired using the variable flip angle method [21] with a 3D SPGR sequence (TR/TE = 4.6/20 ms, α = 4 (NEX = 3), 10 (NEX = 1), 20 (NEX = 2), and 30° (NEX = 3)) and FOV = 24×24×8.25 mm³, matrix = 64×64×5.5 for an acquisition resolution of 0.38×0.38×1.5 mm³ (zero-interpolated to 0.19×0.19×0.75 mm³). Pre-contrast B₁ maps using the actual flip angle imaging method [32] were acquired with the following parameters: TR₁/TR₂/TE = 25/125/6.7 ms and α = 60°. 3D B₁ maps were acquired with a NEX = 1 and an identical resolution as the variable flip angle data points. All images were acquired in the axial plane.

Fast bound-pool fraction parametric maps (f maps) were constructed consistent with a previously described methodology [20] for single parameter determination of f. Briefly, R₁ maps were used to define R₁^F and reconstructed from VFA data using a linear fit to the signal intensities (S) transformed into the coordinates [S(α) / sin α, S(α) / tan α][21] after voxel-based B₁ corrections were applied to α. In the MT data, the Δ = 96 kHz Z-spectra images were used to normalize the Δ = 4 and 8 kHz data points and voxel-based B₀ and B₁ corrections were applied to Δ and α, respectively, during voxel-based fitting for f. The parameters k, T₂^FR₁^F, and T₂^B were constrained to 29 x f/(1-f) s^-1, 0.030, 10.7 μs, respectively, as previously determined [20]. R₁^B, the longitudinal relaxation of the bound-pool, was set to a fixed value of 1 s^-1 by convention [33–35].

Pre- and post-contrast R₁ maps were similarly constructed from the respective VFA data that was acquired in the axial plane. Corresponding pre-contrast B₁ maps were similarly applied for correction of α during fitting of both pre- and post-contrast R₁ maps. Image processing dedicated to whole-brain voxel-based determination of f maps and R₁ maps was performed using in-house written Matlab (The Mathworks, Natick, MA) and C/C++ language software.

Whole blood acquired from each animal was centrifuged at 1,600 g ×10 minutes at 4°C. The plasma layer was removed and centrifuged at 16,000 g ×10 minutes at 4°C. The buffy coat was then collected and stored at -80°C. After centrifugation, plasma was removed excepting a residual amount near the bottom that may have been in contact with any debris and stored at -80°C. Both plasma samples and the buffy coat were stored at -80°C <1 hour from time of collection from the animal.

DNA was isolated from buffy coat cell pellets using the Qiagen DNeasy Blood and Tissue kit. Shotgun sequencing libraries were constructed with 50 nanograms of gDNA from each animal using the Nextera DNA library prep kit (Illumina). Following the manufacturer’s direction, sample index sequences were added during the PCR step to allow libraries to be pooled for multiplexed sequencing on a single lane.

Cell-free DNA was extracted from rat plasma using the QIAamp Circulating Nucleic Acid kit. DNA yield was measured with a Qubit dsDNA HS assay (Invitrogen) and 1–10 ng of cell-free DNA was used as input for library construction with the Thruplex-LC kit (Rubicon Genomics). For samples with low input concentration (<100 pg/ul), cell-free DNA was first concentrated across Zymo Clean-Concentrate-5 column (Zymo Research).

During library construction, enrichment PCR was performed using a BioRad MiniOpticon real-time thermocycler, with SYBR Green I dye (Invitrogen) added to each reaction at a final concentration of 0.25X. Reactions were individually removed upon entering log-phase amplification as indicated by SYBR signal (7–17 cycles).

Libraries were normalized to 2 nM each and pooled for paired-end 101-bp sequencing across four lanes on an Illumina Hiseq 2000 instrument. A 9-bp index read was also collected and used to demultiplex reads according to input sample, requiring fewer than 2 mismatches to the known indices.

For each buffy coat and cell-free DNA library, adapter sequences were trimmed and paired end reads were mapped to human and rat reference assemblies (hg19 and rn5, respectively) using bwa [36]. For each read pair, the species origin (rat or human) was then determined using the mapping status against both references. Only reads that could be unambiguously mapped to one or the other species were included: reads with low mapping quality score (<30) in both species’ references were discarded, as were reads of comparable mapping quality to both references (absolute difference in map quality scores <20). Tumor DNA abundance in each cell-free DNA and buffy coat fraction was then computed as (# human read pairs) / (# human read pairs + #rat read pairs). Fragment length were then takes as the absolute distances between the outermost bases of each pair of forward and reverse ends.

As a quality control check, an aliquot of each xenografted cell line at the time of implantation was genotyped across a panel of 96 human polymorphisms using a custom BeadArray assay performed by the Northwest Genomics Center. Cell lines with identical genotype calls in ≥ 95 of 96 markers were considered to be identical in origin, whereas all other pairs of cell lines shared genotypes at many fewer markers (34–45; S15 Fig).

All procedures were approved by the University of Utah Internal Review Board prior to study initiation. Blood samples were collected in Streck BCT tubes, stored at 4°C, and processed within 24 hours of collection. Plasma was separated by centrifugation for 10 minutes at 1900g and aspiration to a new tube. Plasma was further centrifuged for 16,000g x 10 minutes to remove any cellular debris, and resulting supernatant was stored at –20°C until cell-free DNA isolation. Custom kits that combined Qiagen lysis and binding buffer with Zymo silica-based columns were assembled to reduce expense during isolation of cell-free DNA. Cell-free DNA was prepared from 8 mL of plasma by adding 800 μL of Proteinase K (20 mg/mL) and 6.4 mL Buffer ACL (Qiagen) followed by incubation at 60°C x 30 minutes. Next, 14.4 mL of buffer ACB (Qiagen) was added to the lysate and incubated on ice for 5 minutes. DNA was isolated from the lysate with Zymo DNA Clean and Concentrator 100 kit according to the manufacturer’s instructions and eluted in 150 μL. A final purification step was performed using two volumes of Ampure XP magnetic beads followed by elution in 25–30 μL 10mM Tris (pH 8.0).

For continuous variables, the means and standard deviations (SDs) were calculated for each group. The student’s independent t-test assuming equal or unequal variance based on Levene’s test was used to compare mean values between tumor patients and healthy controls. Pearson’s r was used to identify correlations between continuous variables. Statistical analyses were performed with SPSS for Windows (Version 12.0, SPSS, Chicago, IL). Statistical significance was defined as P < 0.05.