Biology subjects

Lippert, C.

Publications and source records attributed to Lippert, C..

6 recordsLinked to original sources

bioRxiv2026

TorchLIMIX: GPU-accelerated multivariate genome-wideassociation studies

SummaryWe introduce TO_SCPLOWORCHC_SCPLOWLIMIX, a GPU-accelerated PyTorch implementation of the LIMIX multivariate genome-wide association study pipeline. By leveraging batched GPU linear algebra, TO_SCPLOWORCHC_SCPLOWLIMIX achieves speedups of up to two orders of magnitude over the original CPU-based implementation while maintaining numerically equivalent results and full concordance of significantly associated loci. In simulation studies, replacing the default initialization of the genetic covariance factor with a QR-based strategy reduces genomic inflation factors to near-unity values under the common and interaction effect null hypotheses, ensuring well-calibrated type I error control. Applying TO_SCPLOWORCHC_SCPLOWLIMIX to metabolic traits of Arabidopsis thaliana measured in two experiments uncovered 37 additional associated SNPs at the same significance threshold used in the original univariate GWAS. AvailabilityThe TO_SCPLOWORCHC_SCPLOWLIMIX pipeline is openly available on GitHub at https://github.com/bi-horn/torchLIMIX. An adapted version of the multivariate association testing part of the original LIMIX pipeline is available at https://github.com/bi-horn/LIMIX_modified. Contactbibiana.horn@hpi.de Supplementary informationSupplementary materials are included with this submission.

bioinformatics↗

bioRxiv2022

HAPNEST: efficient, large-scale generation and evaluation of synthetic datasets for genotypes and phenotypes

Existing methods for simulating synthetic genotype and phenotype datasets have limited scalability, constraining their usability for large-scale analyses. Moreover, a systematic approach for evaluating synthetic data quality and a benchmark synthetic dataset for developing and evaluating methods for polygenic risk scores are lacking. We present HAPNEST, a novel approach for efficiently generating diverse individual-level genotypic and phenotypic data. In comparison to alternative methods, HAPNEST shows faster computational speed and a lower degree of relatedness with reference panels, while generating datasets that preserve key statistical properties of real data. These desirable synthetic data properties enabled us to generate 6.8 million common variants and nine phenotypes with varying degrees of heritability and polygenicity across 1 million individuals. We demonstrate how HAPNEST can facilitate biobank-scale analyses through the comparison of seven methods to generate polygenic risk scoring across multiple ancestry groups and different genetic architectures.

bioinformatics↗

bioRxiv2021

transferGWAS: GWAS of images using deep transfer learning

AO_SCPLOWBSTRACTC_SCPLOWO_ST_ABSMotivationC_ST_ABSMedical images can provide rich information about diseases and their biology. However, investigating their association with genetic variation requires non-standard methods. We propose transferGWAS, a novel approach to perform genome-wide association studies directly on full medical images. First, we learn semantically meaningful representations of the images based on a transfer learning task, during which a deep neural network is trained on independent but similar data. Then, we perform genetic association tests with these representations. ResultsWe validate the type I error rates and power of transferGWAS in simulation studies of synthetic images. Then we apply transferGWAS in a genome-wide association study of retinal fundus images from the UK Biobank. This first-of-a-kind GWAS of full imaging data yielded 60 genomic regions associated with retinal fundus images, of which 7 are novel candidate loci for eye-related traits and diseases. Contactmatthias.kirchler@hpi.de, christoph.lippert@hpi.de Supplementary informationOur method is implemented in Python and available at https://github.com/mkirchler/transferGWAS/

genetics↗

bioRxiv2021

Identifying interpretable gene-biomarker associations with functionally informed kernel-based tests in 190,000 exomes

Here we present an exome-wide rare genetic variant association study for 30 blood biomarkers in 191,971 individuals in the UK Biobank. We compare gene-based association tests for separate functional variant categories to increase interpretability and identify 193 significant gene-biomarker associations. Genes associated with biomarkers were ~ 4.5-fold enriched for conferring Mendelian disorders. In addition to performing weighted gene-based variant collapsing tests, we design and apply variant-category-specific kernel-based tests that integrate quantitative functional variant effect predictions for missense variants, splicing and the binding of RNA-binding proteins. For these tests, we present a statistically powerful and computationally efficient combination of the likelihood-ratio and score tests that found 36% more associations than the score test alone. Kernel-based tests identified 13% more associations than their gene-based collapsing counterparts and had advantages in the presence of gain of function missense variants. We introduce local collapsing by amino acid position for missense variants and use it to interpret associations and identify potential novel gain of function variants in PIEZO1. Our results show the benefits of investigating different functional mechanisms when performing rare-variant association tests, and demonstrate pervasive rare-variant contribution to biomarker variability.

genetics↗

bioRxiv2020

HistoFlow: Label-Efficient and Interactive Deep Learning Cell Analysis

Instance segmentation is a common task in quantitative cell analysis. While there are many approaches doing this using machine learning, typically, the training process requires a large amount of manually annotated data. We present HistoFlow, a software for annotation-efficient training of deep learning models for cell segmentation and analysis with an interactive user interface. It provides an assisted annotation tool to quickly draw and correct cell boundaries and use biomarkers as weak annotations. It also enables the user to create artificial training data to lower the labeling effort. We employ a universal U-Net neural network architecture that allows accurate instance segmentation and the classification of phenotypes in only a single pass of the network. Transfer learning is available through the user interface to adapt trained models to new tissue types. We demonstrate HistoFlow for fluorescence breast cancer images. The models trained using only artificial data perform comparably to those trained with time-consuming manual annotations. They outperform traditional cell segmentation algorithms and match state-of-the-art machine learning approaches. A user test shows that cells can be annotated six times faster than without the assistance of our annotation tool. Extending a segmentation model for classification of epithelial cells can be done using only 50 to 1500 annotations. Our results show that, unlike previous assumptions, it is possible to interactively train a deep learning model in a matter of minutes without many manual annotations.

bioinformatics↗

bioRxiv2017

No major flaws in "Identification of individuals by trait prediction using whole-genome sequencing data"

In a recently published PNAS article, we studied the identifiability of genomic samples using machine learning methods [Lippert et al., 2017]. In a response, Erlich [2017] argued that our work contained major flaws. The main technical critique of Erlich [2017] builds on a simulation experiment that shows that our proposed algorithm, which uses only a genomic sample for identification, performed no better than a strategy that uses demographic variables. Below, we show why this comparison is misleading and provide a detailed discussion of the key critical points in our analyses that have been brought up in Erlich [2017] and in the media. Further, not only faces may be derived from DNA, but a wide range of phenotypes and demographic variables. In this light, the main contribution of Lippert et al. [2017] is an algorithm that identifies genomes of individuals by combining multiple DNA-based predictive models for a myriad of traits.

genomics↗