Search

Deep learning (DL) has shown potential to provide powerful representations of bulk RNA-seq data in cancer research. However, there is no consensus regarding the impact of design choices of DL approaches on the performance of the learned representation, including the model architecture, the training methodology and the various hyperparameters. To address this problem, we evaluate the performance of various design choices of DL representation learning methods using TCGA and DepMap pan-cancer datasets and assess their predictive power for survival and gene essentiality predictions. We demonstrate that baseline methods achieve comparable or superior performance compared to more complex models on survival predictions tasks. DL representation methods, however, are the most efficient to predict the gene essentiality of cell lines. We show that auto-encoders (AE) are consistently improved by techniques such as masking and multi-head training. Our results suggest that the impact of DL representations and of pretraining are highly task- and architecture-dependent, highlighting the need for adopting rigorous evaluation guidelines. These guidelines for robust evaluation are implemented in a pipeline made available to the research community. [ABSTRACT FROM AUTHOR]

Motivation The identification and discovery of phenotypes from high content screening images is a challenging task. Earlier works use image analysis pipelines to extract biological features, supervised training methods or generate features with neural networks pretrained on non-cellular images. We introduce a novel unsupervised deep learning algorithm to cluster cellular images with similar Mode-of-Action (MOA) together using only the images' pixel intensity values as input. It corrects for batch effect during training. Importantly, our method does not require the extraction of cell candidates and works from the entire images directly. Results The method achieves competitive results on the labeled subset of the BBBC021 dataset with an accuracy of 97.09% for correctly classifying the MOA by nearest neighbors matching. Importantly, we can train our approach on unannotated datasets. Therefore, our method can discover novel MOAs and annotate unlabeled compounds. The ability to train end-to-end on the full resolution images makes our method easy to apply and allows it to further distinguish treatments by their effect on proliferation. Availability and implementation Our code is available at https://github.com/Novartis/UMM-Discovery. Supplementary information Supplementary data are available at Bioinformatics online. [ABSTRACT FROM AUTHOR]

Inhibitors of double minute 2 protein (MDM2)-tumor protein 53 (TP53) interaction are predicted to be effective in tumors in which the TP53 gene is wild type, by preventing TP53 protein degradation. One such setting is represented by the frequent CDKN2A deletion in human cancer that, through inactivation of p14ARF, activates MDM2 protein, which in turn degrades TP53 tumor suppressor. Here we used piggyBac (PB) transposon insertional mutagenesis to anticipate resistance mechanisms occurring during treatment with the MDM2-TP53 inhibitor HDM201. Constitutive PB mutagenesis in Arf-/- mice provided a collection of spontaneous tumors with characterized insertional genetic landscapes. Tumors were allografted in large cohorts of mice to assess the pharmacologic effects of HDM201. Sixteen out of 21 allograft models were sensitive to HDM201 but ultimately relapsed under treatment. A comparison of tumors with acquired resistance to HDM201 and untreated tumors identified 87 genes that were differentially and significantly targeted by the PB transposon. Resistant tumors displayed a complex clonality pattern suggesting the emergence of several resistant subclones. Among the most frequent alterations conferring resistance, we observed somatic and insertional loss-of-function mutations in transformation-related protein 53 (Trp53) in 54% of tumors and transposonmediated gain-of-function alterations in B-cell lymphoma-extra large (Bcl-xL), Mdm4, and two TP53 family members, resulting in expression of the TP53 dominant negative truncations △NTrp63 and △NTrp73. Enhanced BCL-xL and MDM4 protein expression was confirmed in resistant tumors, as well as in HDM201-resistant patient-derived tumor xenografts. Interestingly, concomitant inhibition of MDM2 and BCL-xL demonstrated significant synergy in p53 wild-type cell lines in vitro. Collectively, our findings identify several potential mechanisms by which TP53 wild-type tumors may escape MDM2-targeted therapy. [ABSTRACT FROM AUTHOR]

Analysis of genomic segments shared identical-by-descent (IBD) between individuals is fundamental to many genetic applications, from demographic inference to estimating the heritability of diseases, but IBD detection accuracy in nonsimulated data is largely unknown. In principle, it can be evaluated using known pedigrees, as IBD segments are by definition inherited without recombination down a family tree. We extracted 25,432 genotyped European individuals containing 2,952 father–mother–child trios from the 23andMe, Inc. data set. We then used GERMLINE, a widely used IBD detection method, to detect IBD segments within this cohort. Exploiting known familial relationships, we identified a false-positive rate over 67% for 2–4 centiMorgan (cM) segments, in sharp contrast with accuracies reported in simulated data at these sizes. Nearly all false positives arose from the allowance of haplotype switch errors when detecting IBD, a necessity for retrieving long (>6 cM) segments in the presence of imperfect phasing. We introduce HaploScore, a novel, computationally efficient metric that scores IBD segments proportional to the number of switch errors they contain. Applying HaploScore filtering to the IBD data at a precision of 0.8 produced a 13-fold increase in recall when compared with length-based filtering. We replicate the false IBD findings and demonstrate the generalizability of HaploScore to alternative data sources using an independent cohort of 555 European individuals from the 1000 Genomes project. HaploScore can improve the accuracy of segments reported by any IBD detection method, provided that estimates of the genotyping error rate and switch error rate are available. [ABSTRACT FROM PUBLISHER]

Neanderthals have been shown to share more genetic variants with present-day non-Africans than Africans. Recent admixture between Neanderthals and modern humans outside of Africa was proposed as the most parsimonious explanation for this observation. However, the hypothesis of ancient population structure within Africa could not be ruled out as an alternative explanation. We use simulations to test whether the site frequency spectrum, conditioned on a derived Neanderthal and an ancestral Yoruba (African) nucleotide (the doubly conditioned site frequency spectrum [dcfs]), can distinguish between models that assume recent admixture or ancient population structure. We compare the simulations to the dcfs calculated from data taken from populations of European, Chinese, and Japanese descent in the Complete Genomics Diversity Panel. Simulations under a variety of plausible demographic parameters were used to examine the shape of the dcfs for both models. The observed shape of the dcfs cannot be explained by any set of parameter values used in the simulations of the ancient structure model. The dcfs simulations for the recent admixture model provide a good fit to the observed dcfs for non-Africans, thereby supporting the hypothesis that recent admixture with Neanderthals accounts for the greater similarity of Neanderthals to non-Africans than Africans. [ABSTRACT FROM PUBLISHER]

Species range shifts in response to climate and land use change are commonly forecasted with species distribution models based on species occurrence or abundance data. Although appealing, these models ignore the genetic structure of species, and the fact that different populations might respond in different ways because of adaptation to their environment. Here, we introduced ancestry distribution models, that is, statistical models of the spatial distribution of ancestry proportions, for forecasting intra-specific changes based on genetic admixture instead of species occurrence data. Using multi-locus genotypes and extensive geographic coverage of distribution data across the European Alps, we applied this approach to 20 alpine plant species considering a global increase in temperature from 0.25 to 4 °C. We forecasted the magnitudes of displacement of contact zones between plant populations potentially adapted to warmer environments and other populations. While a global trend of movement in a north-east direction was predicted, the magnitude of displacement was species-specific. For a temperature increase of 2 °C, contact zones were predicted to move by 92 km on average (minimum of 5 km, maximum of 212 km) and by 188 km for an increase of 4 °C (minimum of 11 km, maximum of 393 km). Intra-specific turnover-measuring the extent of change in global population genetic structure-was generally found to be moderate for 2 °C of temperature warming. For 4 °C of warming, however, the models indicated substantial intra-specific turnover for ten species. These results illustrate that, in spite of unavoidable simplifications, ancestry distribution models open new perspectives to forecast population genetic changes within species and complement more traditional distribution-based approaches. [ABSTRACT FROM AUTHOR]

One enduring question in evolutionary biology is the extent of archaic admixture in the genomes of present-day populations. In this paper, we present a test for ancient admixture that exploits the asymmetry in the frequencies of the two nonconcordant gene trees in a three-population tree. This test was first applied to detect interbreeding between Neandertals and modern humans. We derive the analytic expectation of a test statistic, called the D statistic, which is sensitive to asymmetry under alternative demographic scenarios. We show that the D statistic is insensitive to some demographic assumptions such as ancestral population sizes and requires only the assumption that the ancestral populations were randomly mating. An important aspect of D statistics is that they can be used to detect archaic admixture even when no archaic sample is available. We explore the effect of sequencing error on the false-positive rate of the test for admixture, and we show how to estimate the proportion of archaic ancestry in the genomes of present-day populations. We also investigate a model of subdivision in ancestral populations that can result in D statistics that indicate recent admixture. [ABSTRACT FROM PUBLISHER]

Habitat fragmentation can restrict geneflow, reduce neighbourhood effective population size, and increase genetic drift and inbreeding in small, isolated habitat remnants. The extent to which habitat fragmentation leads to population fragmentation, however, differs among landscapes and taxa. Commonly, researchers use information on the current status of a species to predict population effects of habitat fragmentation. Such methods, however, do not convey information on species-specific responses to fragmentation. Here, we compare levels of past population differentiation, estimated from microsatellite genotypes, with contemporary dispersal rates, estimated from multi-strata capture-recapture models, to infer changes in mobility over time in seven sympatric, forest-dependent bird species of a Kenyan cloud forest archipelago. Overall, populations of sedentary species were more strongly differentiated and clustered compared to those of vagile ones, while geographical patterning suggested an important role of landscape structure in shaping genetic variation. However, five of seven species with broadly similar levels of genetic differentiation nevertheless differed substantially in their current dispersal rates. We conclude that post-fragmentation levels of vagility, without reference to past population connectivity, may not be the best predictor of how forest fragmentation affects the life history of forest-dependent species. As effective conservation strategies often hinge on accurate prediction of shifts in ecological and genetic relationships among populations, conservation practices based solely upon current population abundances or movements may, in the long term, prove to be inadequate. [ABSTRACT FROM AUTHOR]