Each patient's cancer consists of multiple cell subpopulations that are inherently heterogeneous and may develop differing phenotypes such as drug sensitivity or resistance. A personalized treatment regimen should therefore target multiple oncoproteins in the cancer cell populations that are driving the treatment resistance or disease progression in a given patient to provide maximal therapeutic effect, while avoiding severe co-inhibition of non-malignant cells that would lead to toxic side effects. To address the intra- and inter-tumoral heterogeneity when designing combinatorial treatment regimens for cancer patients, we have implemented a machine learning-based platform to guide identification of safe and effective combinatorial treatments that selectively inhibit cancer-related dysfunctions or resistance mechanisms in individual patients. In this case study, we show how the platform enables prediction of cancer-selective drug combinations for patients with high-grade serous ovarian cancer using single-cell imaging cytometry drug response assay, combined with genome-wide transcriptomic and genetic profiles. The platform makes use of drug-target interaction networks to prioritize those combinations that warrant further preclinical testing in scarce patient-derived primary cells. During the case study in ovarian cancer patients, we investigated (i) the relative performance of various ensemble learning algorithms for drug response prediction, (ii) the use of matched single-cell RNA-sequencing data to deconvolute cell population-specific transcriptome profiles from bulk RNA-seq data, (iii) and whether multi-patient or patient-specific predictive models lead to better predictive accuracy. The general platform and the comparison results are expected to become useful for future studies that use similar predictive approaches also in other cancer types.

MOTIVATION: Single-cell proteomics technologies, such as mass cytometry, have enabled characterization of cell-to-cell variation and cell populations at a single-cell resolution. These large amounts of data, require dedicated, interactive tools for translating the data into knowledge. RESULTS: We present a comprehensive, interactive method called Cyto to streamline analysis of large-scale cytometry data. Cyto is a workflow-based open-source solution that automates the use of state-of-the-art single-cell analysis methods with interactive visualization. We show the utility of Cyto by applying it to mass cytometry data from peripheral blood and high-grade serous ovarian cancer (HGSOC) samples. Our results show that Cyto is able to reliably capture the immune cell sub-populations from peripheral blood and cellular compositions of unique immune- and cancer cell subpopulations in HGSOC tumor and ascites samples. AVAILABILITYAND IMPLEMENTATION: The method is available as a Docker container at https://hub.docker.com/r/anduril/cyto and the user guide and source code are available at https://bitbucket.org/anduril-dev/cyto. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Fusion genes are both useful cancer biomarkers and important drug targets. Finding relevant fusion genes is challenging due to genomic instability resulting in a high number of passenger events. To reveal and prioritize relevant gene fusion events we have developed FUsionN Gene Identification toolset (FUNGI) that uses an ensemble of fusion detection algorithms with prioritization and visualization modules. RESULTS: We applied FUNGI to an ovarian cancer dataset of 107 tumor samples from 36 patients. Ten out of 11 detected and prioritized fusion genes were validated. Many of detected fusion genes affect the PI3K-AKT pathway with potential role in treatment resistance. AVAILABILITYAND IMPLEMENTATION: FUNGI and its documentation are available at https://bitbucket.org/alejandra_cervera/fungi as standalone or from Anduril at https://www.anduril.org. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: A major challenge in analyzing cancer patient transcriptomes is that the tumors are inherently heterogeneous and evolving. We analyzed 214 bulk RNA samples of a longitudinal, prospective ovarian cancer cohort and found that the sample composition changes systematically due to chemotherapy and between the anatomical sites, preventing direct comparison of treatment-naive and treated samples. RESULTS: To overcome this, we developed PRISM, a latent statistical framework to simultaneously extract the sample composition and cell-type-specific whole-transcriptome profiles adapted to each individual sample. Our results indicate that the PRISM-derived composition-free transcriptomic profiles and signatures derived from them predict the patient response better than the composite raw bulk data. We validated our findings in independent ovarian cancer and melanoma cohorts, and verified that PRISM accurately estimates the composition and cell-type-specific expression through whole-genome sequencing and RNA in situ hybridization experiments. AVAILABILITYAND IMPLEMENTATION: https://bitbucket.org/anthakki/prism. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOTIVATION: Non-parametric dimensionality reduction techniques, such as t-distributed stochastic neighbor embedding (t-SNE), are the most frequently used methods in the exploratory analysis of single-cell datasets. Current implementations scale poorly to massive datasets and often require downsampling or interpolative approximations, which can leave less-frequent populations undiscovered and much information unexploited. RESULTS: We implemented a fast t-SNE package, qSNE, which uses a quasi-Newton optimizer, allowing quadratic convergence rate and automatic perplexity (level of detail) optimizer. Our results show that these improvements make qSNE significantly faster than regular t-SNE packages and enables full analysis of large datasets, such as mass cytometry data, without downsampling. AVAILABILITY AND IMPLEMENTATION: Source code and documentation are openly available at https://bitbucket.org/anthakki/qsne/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Motivation: DNA methylation aberrations are common in many cancer types. A major challenge hindering comparison of patient-derived samples is that they comprise of heterogeneous collection of cancer and microenvironment cells. We present a computational method that allows comparing cancer methylomes in two or more heterogeneous tumor samples featuring differing, unknown fraction of cancer cells. The method is unique in that it allows comparison also in the absence of normal cell control samples and without prior tumor purity estimates, as these are often unavailable or unreliable in clinical samples. Results: We use simulations and next-generation methylome, RNA and whole-genome sequencing data from two cancer types to demonstrate that the method is accurate and outperforms alternatives. The results show that our method adapts well to various cancer types and to a wide range of tumor content, and works robustly without a control or with controls derived from various sources. Availability and implementation: The method is freely available at https://bitbucket.org/anthakki/dmml. Supplementary information: Supplementary data are available at Bioinformatics online.