Bonilla, X. | Search bioRxiv

bioRxiv2022

A deep learning approach for improved detection of homologous recombination deficiency from shallow genomic profiles

Homologous Recombination Deficiency (HRD) is a predictive biomarker of poly-ADP ribose polymerase 1 inhibitors (PARPi) response. Most HRD detection methods are based on genome wide enumeration of scarring events and require deep genome sequence profiles (> 30x). The cost and workflow-specific biases introduced by these genome profiling methods currently limits clinical adoption of HRD testing. We introduce the Genomic Integrity Index (GII), a Convolutional Neuronal Network, that leverages features from low pass (1x) Whole Genome Sequencing data to distinguish HRD positive and negative samples. In a cohort of 230 ovarian and breast cancer, we found GII supports accurate stratification of samples yielding results that are highly concordant with state-of-the-art HRD detection methods (0.865<AUC<0.996) which require 50x deeper coverage. We conclude that the deep learning framework supporting GII allows accurate detection of HRD from shallow genome profiles, reducing biases and data generation costs making it uniquely suited for clinical applications.

cancer biology↗

bioRxiv2020

SCIM: Universal Single-Cell Matching with Unpaired Feature Sets

AO_SCPLOWBSTRACTC_SCPLOWO_ST_ABSMotivationC_ST_ABSRecent technological advances have led to an increase in the production and availability of single-cell data. The ability to integrate a set of multi-technology measurements would allow the identification of biologically or clinically meaningful observations through the unification of the perspectives afforded by each technology. In most cases, however, profiling technologies consume the used cells and thus pairwise correspondences between datasets are lost. Due to the sheer size single-cell datasets can acquire, scalable algorithms that are able to universally match single-cell measurements carried out in one cell to its corresponding sibling in another technology are needed. ResultsWe propose Single-Cell data Integration via Matching (SCIM), a scalable approach to recover such correspondences in two or more technologies. SCIM assumes that cells share a common (low-dimensional) underlying structure and that the underlying cell distribution is approximately constant across technologies. It constructs a technology-invariant latent space using an auto-encoder framework with an adversarial objective. Multi-modal datasets are integrated by pairing cells across technologies using a bipartite matching scheme that operates on the low-dimensional latent representations. We evaluate SCIM on a simulated cellular branching process and show that the cell-to-cell matches derived by SCIM reflect the same pseudotime on the simulated dataset. Moreover, we apply our method to two real-world scenarios, a melanoma tumor sample and a human bone marrow sample, where we pair cells from a scRNA dataset to their sibling cells in a CyTOF dataset achieving 93% and 84% cell-matching accuracy for each one of the samples respectively. Availabilityhttps://github.com/ratschlab/scim

bioinformatics↗