Tumors are complex tissues of cancerous cells surrounded by a heterogeneous cellular microenvironment with which they interact. Single-cell sequencing enables molecular characterization of single cells within the tumor. However, cell annotation—the assignment of cell type or cell state to each sequenced cell—is a challenge, especially identifying tumor cells within single-cell or spatial sequencing experiments. Here, we propose ikarus, a machine learning pipeline aimed at distinguishing tumor cells from normal cells at the single-cell level. We test ikarus on multiple single-cell datasets, showing that it achieves high sensitivity and specificity in multiple experimental contexts.

Cells adopt highly polarized shapes and form distinct subcellular compartments in many cases due to the localization of many mRNAs to specific areas, where they are translated into proteins with local functions. This mRNA localization is mediated by specific cis-regulatory elements in mRNAs, commonly called ‘zipcodes’. Although there are hundreds of localized mRNAs, only a few zipcodes have been characterized. Here we describe a novel neuronal zipcode identification protocol (N-zip) that can identify zipcodes across hundreds of 3′ untranslated regions. This approach combines a method of separating the principal subcellular compartments of neurons—cell bodies and neurites—with a massively parallel reporter assay. N-zip identifies the let-7 binding site and (AU)n motif as de novo zipcodes in mouse primary cortical neurons. Our analysis also provides, to our knowledge, the first demonstration of an miRNA affecting mRNA localization and suggests a strategy for detecting many more zipcodes.

No abstract

Comprehensive genomic profiling using cancer gene panels has been shown to improve treatment options for a variety of cancer types. However, genomic aberrations detected via such gene panels don't necessarily serve as strong predictors of drug sensitivity. In this study, using pharmacogenomics datasets of cell lines, patient-derived xenografts, and ex-vivo treated fresh tumor specimens, we demonstrate that utilizing the transcriptome on top of gene panel features substantially improves drug response prediction performance in cancer.

Comprehensive genomic profiling using cancer gene panels has been shown to improve treatment options for a variety of cancer types. However, genomic aberrations detected via such gene panels do not necessarily serve as strong predictors of drug sensitivity. In this study, using pharmacogenomics datasets of cell lines, patient-derived xenografts, and ex vivo treated fresh tumor specimens, we demonstrate that utilizing the transcriptome on top of gene panel features substantially improves drug response prediction performance in cancer.