Putcha, G. | Search bioRxiv

bioRxiv2019

Spatial co-fragmentation pattern of cell-free DNA recapitulates in vivo chromatin organization and identifies tissues-of-origin

Three-dimensional chromatin organization varies across cell types and is essential for gene regulation. However, current technologies are unable to assess in vivo genome-wide chromatin organization non-invasively. Here we show that distant correlations in the fragment length of cell-free DNA (cfDNA) recapitulate three-dimensional chromatin organization. The inferred organization is highly concordant with that measured by Hi-C in white blood cells from healthy donors, and is not explained by technical bias or sequence composition. Furthermore, the inferred organization reflects different genomic organization in the various cell types contributing to cfDNA, allowing identification and quantification of tissues of origin. This approach is concordant with previous methods, but with more complete representations of cfDNA. Our results, demonstrated in cfDNA from healthy individuals and cancer patients, may enable noninvasive monitoring of in vivo genome organization and accurate quantification of cell death in different clinical conditions.

genomics↗

bioRxiv2018

Machine learning enables detection of early-stage colorectal cancer by whole-genome sequencing of plasma cell-free DNA

BackgroundBlood-based methods using cell-free DNA (cfDNA) are under development as an alternative to existing screening tests. However, early-stage detection of cancer using tumor-derived cfDNA has proven challenging because of the small proportion of cfDNA derived from tumor tissue in early-stage disease. A machine learning approach to discover signatures in cfDNA, potentially reflective of both tumor and non-tumor contributions, may represent a promising direction for the early detection of cancer.\n\nMethodsWhole-genome sequencing was performed on cfDNA extracted from plasma samples (N=546 colorectal cancer and 271 non-cancer controls). Reads aligning to protein-coding gene bodies were extracted, and read counts were normalized. cfDNA tumor fraction was estimated using IchorCNA. Machine learning models were trained using k-fold cross-validation and confounder-based cross-validation to assess generalization performance.\n\nResultsIn a colorectal cancer cohort heavily weighted towards early-stage cancer (80% stage I/II), we achieved a mean AUC of 0.92 (95% CI 0.91-0.93) with a mean sensitivity of 85% (95% CI 83-86%) at 85% specificity. Sensitivity generally increased with tumor stage and increasing tumor fraction. Stratification by age, sequencing batch, and institution demonstrated the impact of these confounders and provided a more accurate assessment of generalization performance.\n\nConclusionsA machine learning approach using cfDNA achieved high sensitivity and specificity in a large, predominantly early-stage, colorectal cancer cohort. The possibility of systematic technical and institution-specific biases warrants similar confounder analyses in other studies. Prospective validation of this machine learning method and evaluation of a multi-analyte approach are underway.

cancer biology↗