Biology subjects

Bernett, J.

Publications and source records attributed to Bernett, J..

6 recordsLinked to original sources

bioRxiv2026

Towards reconstruction of the human interactome from positive and negative experimental evidence

Protein-protein interactions (PPIs) have been detected and reported in the millions, but while they are used in many different contexts for better understanding cellular processes in health and disease, the knowledge of the human PPI network is far from complete, containing many false positive measurements and being highly biased. Both to chart the extent of those problems and to solve them requires not just a knowledge of high-confidence positive interactions, but also likely non-interacting protein pairs. However, this information is typically not reported in PPI studies. We developed a methodology to reconstruct this knowledge from existing PPI data. We reconstruct the experimental search space in which PPI screens have been performed and then create a model that informs how likely a PPI is real given its testing and observation frequency. We argue that negative protein pairs allow us to estimate the error rates of experimental and computational screens. We show how this knowledge could be incorporated for calibration. Finally, we evaluate a simple machine learning approach to PPI prediction and propose how such negative data can be used for training instead of random protein pairs. Together, our results show that reconstructing the experimental search space recovers a largely overlooked layer of information from existing PPI data that can help guide a more accurate and complete mapping of the human interactome.

bioinformatics↗

bioRxiv2025

From Hype to Health Check: Critical Evaluation of Drug Response Prediction Models with DrEval

MotivationLarge-scale drug sensitivity screens have enabled training drug response prediction models based on cancer cell line omics profiles to facilitate personalized medicine. While model performances reported in the literature appear promising, no successful translation to the clinic has been reported. ResultsWe identify six primary obstacles to this: non-reproducible models, data leakage leading to poor generalization, pseudoreplication, biased evaluation metrics, missing ablation studies, and inconsistent viability data reducing comparability across models. Together, these issues lead to overly optimistic performance estimates of state-of-the-art models and make it challenging to track progress in the field. To address this, we present DrEval, a pipeline for unbiased and biologically meaningful evaluation of cancer drug response models. It includes baseline and literature models with consistent hyperparameter tuning, statistically sound evaluations, and cross-study benchmarks. DrEval enables ablation studies and publication-ready visualizations. It allows researchers to focus on model development without implementing their own evaluation protocol. We find that deep learning models barely outperform a naive model predicting the mean drug and cell line effects, while no complex model significantly outperforms properly tuned tree-based ensemble baselines in relevant settings. We advocate making our pipeline a standard benchmark for cancer drug response prediction, ensuring a clinically relevant and robust assessment. Availability and implementationDrEval consists of a Python package, available on PyPI (drevalpy) and GitHub (github.com/daisybio/drevalpy), and an accompanying nf-core pipeline (github.com/nf-core/drugresponseeval). All data is available on Zenodo (DOI: 10.5281/zenodo.12633909), preprocessing scripts on github.com/daisybio/preprocess_drp_data.

bioinformatics↗

bioRxiv2025

Refinement Strategies for Tangram for Reliable Single-Cell to Spatial Mapping

MotivationSingle-cell RNA sequencing (scRNA-seq) provides comprehensive gene expression data at a single-cell level but lacks spatial context. In contrast, spatial transcriptomics captures both spatial and transcriptional information but is limited by resolution, sensitivity, or feasibility. No single technology combines both the high spatial resolution and deep transcriptomic profiling at the single-cell level without trade-offs. Spatial mapping tools that integrate scRNA-seq and spatial transcriptomics data are crucial to bridge this gap. However, we found that Tangram, one of the most prominent spatial mapping tools, provides inconsistent results over repeated runs. ResultsWe refine Tangram to achieve more consistent cell mappings and investigate the challenges that arise from data characteristics. We find that the mapping quality depends on the gene expression sparsity. To address this, we (1) train the model on an informative gene subset, (2) apply cell filtering, (3) introduce several forms of regularization, and (4) incorporate neighborhood information. Evaluations on real and simulated mouse datasets demonstrate that this approach improves both gene expression prediction and cell mapping. Consistent cell mapping strengthens the reliability of the projection of cell annotations and features into space, gene imputation, and correction of low-quality measurements. Our pipeline, which includes gene set and hyperparameter selection, can serve as guidance for applying Tangram on other datasets, while our benchmarking framework with data simulation and inconsistency metrics is useful for evaluating other tools or Tangram modifications. AvailabilityThe refinements for Tangram and our benchmarking pipeline are available in https://github.com/daisybio/Tangram_Refinement_Strategies. O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=97 SRC="FIGDIR/small/634996v1_ufig1.gif" ALT="Figure 1"> View larger version (41K): org.highwire.dtl.DTLVardef@5ef8a8org.highwire.dtl.DTLVardef@11707d7org.highwire.dtl.DTLVardef@103e1f2org.highwire.dtl.DTLVardef@1e713e9_HPS_FORMAT_FIGEXP M_FIG C_FIG

bioinformatics↗

bioRxiv2025

Deep learning models for unbiased sequence-based PPI prediction plateau at an accuracy of 0.65

As most proteins interact with other proteins to perform their respective functions, methods to computationally predict these interactions have been developed. However, flawed evaluation schemes and data leakage in test sets have obscured the fact that sequence-based protein-protein interaction (PPI) prediction is still an open problem. Recently, methods achieving better-than-random performance on leakage-free PPI data have been proposed. Here, we show that the use of ESM-2 protein embeddings explains this performance gain irrespective of model architecture. We compared the performance of models with varying complexity, per-protein, and per-token embeddings, as well as the influence of self- or cross-attention, where all models plateaued at an accuracy of 0.65. Moreover, we show that the tested sequence-based models cannot implicitly learn a contact map as an intermediate layer. These results imply that other input types, such as structure, might be necessary for producing reliable PPI predictions.

bioinformatics↗

bioRxiv2023

Cracking the black box of deep sequence-based protein-protein interaction prediction

Identifying protein-protein interactions (PPIs) is crucial for deciphering biological pathways. Numerous prediction methods have been developed as cheap alternatives to biological experiments, reporting surprisingly high accuracy estimates. We systematically investigated how much reproducible deep learning models depend on data leakage, sequence similarities, and node degree information, and compared them to basic machine learning models. We found that overlaps between training and test sets resulting from random splitting lead to strongly overestimated performances. In this setting, models learn solely from sequence similarities and node degrees. When data leakage is avoided by minimizing sequence similarities between training and test set, performances become random. Moreover, baseline models directly leveraging sequence similarity and network topology show good performances at a fraction of the computational cost. Thus, we advocate that any improvements should be reported relative to baseline methods in the future. Our findings suggest that predicting protein-protein interactions remains an unsolved task for proteins showing little sequence similarity to previously studied proteins, highlighting that further experimental research into the "dark" protein interactome and better computational methods are needed.

bioinformatics↗

bioRxiv2021

A Systematic Comparison of Differential Analysis Methods for CyTOF Data

Cytometry techniques are widely used to discover cellular characteristics at single-cell resolution. Many data analysis methods for cytometry data focus solely on identifying subpopulations via clustering and testing for differential cell abundance. For differential expression analysis of markers between conditions, only few tools exist. These tools either reduce the data distribution to medians, discarding valuable information, or have underlying assumptions that may not hold for all expression patterns. Here, we systematically evaluated existing and novel approaches for differential expression analysis on real and simulated CyTOF data. We found that methods using median marker expressions compute fast and reliable results when the data is not strongly zero-inflated. Methods using all data detect changes in strongly zero-inflated markers, but partially suffer from overprediction or cannot handle big datasets. We present a new method, CyEMD, based on calculating the Earth Movers Distance between expression distributions that can handle strong zero-inflation without being too sensitive. Additionally, we developed CYANUS, a user-friendly R Shiny App allowing the user to analyze cytometry data with state-of-the-art tools, including well-performing methods from our comparison. A public web interface is available at https://exbio.wzw.tum.de/cyanus/.

bioinformatics↗