JKJack Kuipers

Jack Kuipers

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jack Kuipers has a total of 348 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Survival-informed mutational network clustering reveals prognostic glioma architectures

    by Beatriz N. Leitão, Jack Kuipers, Niko Beerenwinkel, Susana Vinga

    Cancer heterogeneity remains a major challenge for predicting patient outcomes. To address this challenge, we introduce SNOWS (Survival-iNfOrmed netWork cluStering), a probabilistic framework that integrates somatic mutations, clinical covariates and survival information to discover patient groups with distinct mutation patterns and survival profiles, using Bayesian networks to capture dependencies involving mutations and clinical variables. Applied to 950 adult-type diffuse gliomas from TCGA, SNOWS identified three clusters that transferred successfully to classify an independent CGGA cohort of 181 patients using mutation and clinical data, without requiring their survival outcomes. The transferred clusters showed distinct survival, mutation profiles and dependency structures, and provided prognostic information beyond WHO 2021 tumour subtype, age and sex, significantly increasing the C-index from 0.691 to 0.712. Cluster assignments were driven by specific mutation frequencies, with network dependencies improving the assignments of patients with less typical molecular profiles. Beyond glioma, SNOWS also improved prognostic discrimination in pan-kidney and pan-myeloid cohorts. These results support survival-informed network clustering as a general framework for resolving clinically relevant cancer heterogeneity.

  • Open Access

    Reliable single-cell perturbations explain and improve model performance

    by Xi Wang, Jack Kuipers, Florian Hugi, Randall Jeffrey Platt, Niko Beerenwinkel

    Predicting single-cell transcriptional responses to perturbations is central to building the virtual cell, yet recent benchmarks show that simple baseline methods often outperform complex models, and model comparisons depend on the evaluation metric. Most studies assume that preprocessed RNA sequencing data are reliable ground truth for both training and evaluation. Here, we test this assumption by measuring the reliability of perturbations and their alignment with shared perturbation responses, classifying each perturbation as specific, shared, or unreliable. Among 7,170 perturbations from 29 datasets, 65% are unreliable, 11% shared, and 24% specific. Applying these quality labels to published benchmarks shows that model comparisons depend on perturbation quality. Training with reliable perturbations alone matches or outperforms full-data performance while using 55% of all training perturbations. Our framework also enables prospective experimental design: for most perturbations, a 28-cell pilot experiment accurately predicts how many cells a full screen needs to be reliable.

  • Open Access

    A tumor profiling resource for ovarian cancer: insights into chemotherapy-driven heterogeneity and personalized treatment strategy

    by Francis Jacob, Rebekka Wegmann, Joanna Ficek-Pascual, Ulrike Lischetti, Jack Kuipers, Stéphane Chevrier, Michael Prummer, Nora C Toussaint, Ilaria Alborelli, Ricardo Coelho, et al.

    In women with high-grade serous ovarian cancer, chemotherapy remains the primary standard treatment, despite growing recognition of the disease as highly heterogeneous. Here, we examine the feasibility and clinical utility of comprehensive multimodal molecular profiling to inform treatment decisions. We analyze blood, single-cell and bulk tumor tissue, and malignant ascites using up to eleven technologies (DNA, RNA, protein, and functional assays) within a four-week turnaround time. Hypothetical treatment recommendations are altered for 76% of patients, and multi-omics-guided maintenance therapy is associated with prolonged overall survival in a subset of patients. Subsequent cohort analysis reveals distinct cellular and molecular profiles in ascites-derived single-cells compared to solid tumor tissue, unique per-patient ex vivo drug responses, and a marked increase in cancer cell heterogeneity following chemotherapy exposure. This coincides with genomic signature alterations in whole-genome-amplified patients. Our data suggest that molecularly guided treatments should be tested as adjuvant therapies prior to chemotherapy in the future.


  • Open Access

    Phylogenetic tree inference from single-cell RNA sequencing data with SCITE-RNA

    by Norio Zimmermann, Xiaoyu Sun, Joanna Hård, Jack Kuipers, Niko Beerenwinkel

    We present SCITE-RNA, a novel phylogenetic tree inference method designed for single-cell RNA sequencing data which takes reference and alternative read co


  • Open Access

    Clone-level multi-modal prediction of tumour drug response

    by Quentin Duchemin, Daniel Trejo Banos, Anne Bertolini, Pedro F. Ferreira, Rudolf Schill, Matthias Lienhard, Rebekka Wegmann, Tumor Profiler Consortium, Berend Snijder, Daniel Stekhoven, et al.

    Tumour heterogeneity presents a major challenge for precision oncology, as genetically and phenotypically distinct tumour clones may respond differently to therapy. To address this, we introduce scClone2DR, a probabilistic multi-modal framework that predicts drug responses at the level of individual tumour clones by integrating single-cell DNA and RNA sequencing with ex-vivo drug-screening data. In simulations, scClone2DR substantially outperforms alternatives in recovering true drug-effects and clonal sensitivities. Applied to 60 melanoma and 21 acute myeloid leukaemia patient samples, the method identifies heterogeneous clonal responses, yields biologically meaningful feature rankings, highlights clones that may be resistant to treatment, and improves the prediction of clinical outcomes compared to models ignoring clonal structure. These results demonstrate that modelling tumour evolution and clonal diversity is crucial for accurate drug-response prediction and provides a foundation for more effective, clone-aware precision oncology.

  • Open Access

    Melanoma cell states define therapeutic vulnerabilities in a multimodal single-cell atlas

    by Mitchell Levesque, Rebekka Wegmann, Stéphane Chevrier, Kjong-Van Lehmann, Michael Prummer, Marina Tusup, Gabriele Gut, Ruben Casanova, Jack Kuipers, Ulrike Lischetti, et al.

    PURPOSE: High-dimensional tumor profiling has the potential to refine therapeutic decisions in metastatic melanoma, especially in the beyond-standard-of-care setting, but its clinical utility remains uncertain. The Tumor Profiler Study prospectively integrated multi-platform molecular, single-cell, spatial, and functional analyses into a 4-week clinical workflow. We report the biological and clinically actionable findings from the melanoma cohort. METHODS: Tumor and blood samples from 116 patients (126 tumors) underwent comprehensive profiling including CyTOF, single-cell RNA and DNA sequencing, imaging mass cytometry, proteotyping, bulk RNA/DNA sequencing, and two ex vivo drug-response platforms. Cross-modal integration defined melanoma phenotypes and identified treatment-relevant features. RESULTS: Single-cell protein profiling of 1.7 million melanoma cells identified six recurrent melanoma phenotypes present across melanoma subtypes and oncogenic drivers. Resulting tumor phenotypes stratified patients into six CyTOF-derived groups with distinct molecular characteristics and significantly different ex vivo responses to FDA-approved therapies. TYRP1-high classical melanocytic tumors showed broad drug resistance but reproducible sensitivity to cisplatin plus vindesine, consistent with elevated p53-associated DNA damage response pathways. Conversely, melanomas with heightened unfolded-protein-response activity exhibited marked sensitivity to proteasome inhibitors, supported by transcriptomic, proteomic, and functional readouts. CONCLUSION: This study establishes a clinically annotated, single-cell–resolved multi-omic atlas of advanced melanoma that links tumor phenotypes to actionable drug vulnerabilities. These findings provide a biological rationale for biomarker-driven, phenotype-guided interventional trials aimed at improving therapeutic outcomes in metastatic melanoma.


  • Open Access

    Scaling Up Bayesian DAG Sampling

    by Daniele Nikzad, Alexander Zhilkin, Juha Harviainen, Jack Kuipers, Giusi Moffa, Mikko Koivisto

    Bayesian inference of Bayesian network structures is often performed by sampling directed acyclic graphs along an appropriately constructed Markov chain. We present two techniques to improve sampling. First, we give an efficient implementation of basic moves, which add, delete, or reverse a single arc. Second, we expedite summing over parent sets, an expensive task required for more sophisticated moves: we devise a preprocessing method to prune possible parent sets so as to approximately preserve the sums. Our empirical study shows that our techniques can yield substantial efficiency gains compared to previous methods.

  • Open Access

    Phylogenetic tree inference from single-cell RNA sequencing data

    by Norio Zimmermann, Xiaoyu Sun, Joanna Hård, Jack Kuipers, Niko Beerenwinkel

    Single-cell RNA sequencing technologies enable the large-scale measurement of gene expression profiles at the individual cell level to assess cellular diversity and function. In oncology, leveraging these single-cell transcriptomic data to reconstruct the phylogenetic relationships among cancer cells can provide insights into tumor evolution, metastasis formation, and the development of treatment resistance. However, phylogenetic inference from single-cell RNA sequencing is challenging due to sparse and noisy data and large dataset sizes. We present a novel tree inference method designed for such data that takes reference and alternative read counts of single-nucleotide variants and reconstructs a phylogenetic tree of the sequenced cells via maximum likelihood using a random-scan greedy search. To overcome local optima in the search, our algorithm alternates between two different tree representations: cell lineage trees, where cells are represented by nodes and mutations are attached to edges, and mutation trees, where mutation nodes encode the mutational events and cells are attached to them. Because a local optimum in one tree space generally does not correspond to a local optimum in the other space, we maximize the likelihood by switching between the two tree spaces until convergence is achieved in both. We demonstrate superior performance of our approach on simulated data with complex clonal architectures compared to existing methods. Furthermore, we show its applicability to cancer single-cell RNA sequencing data, which allows us to link evolutionary trajectories of cells to their gene expression profiles.

  • Open Access

    Phylogenetic inference reveals clonal heterogeneity in circulating tumor cell clusters

    by David Gremmelspacher, Johannes Gawron, Barbara M. Szczerba, Katharina Jahn, Francesc Castro-Giner, Jack Kuipers, Jochen Singer, Francesco Marass, Ana Gvozdenovic, Selina Budinjas, et al.

    Circulating tumor cell (CTC) clusters are highly efficient metastatic seeds in various cancers. Yet, their genetic heterogeneity and clonal architecture is poorly characterized. Using whole-exome sequencing coupled with phylogenetic inference from CTC clusters of patients with breast and prostate cancer, as well as mouse cancer models alongside barcode-mediated clonal tracking in vivo, we demonstrate oligoclonal composition of individual CTC clusters. These results improve our understanding of metastasis-relevant clonal dynamics.


  • Open Access

    Network-based clustering unveils interconnected landscapes of genomic and clinical features across myeloid malignancies

    by Fritz Bayer, Marco Roncador, Giusi Moffa, Kiyomi Morita, Koichi Takahashi, Niko Beerenwinkel, Jack Kuipers

    Myeloid malignancies exhibit considerable heterogeneity with overlapping clinical and genetic features among subtypes. We present a data-driven approach that integrates mutational features and clinical covariates at diagnosis within networks of their probabilistic relationships, enabling the discovery of patient subgroups. A key strength is its ability to include presumed causal directions in the edges linking clinical and mutational features, and account for them aptly in the clustering. In a cohort of 1323 patients, we identify subgroups that outperform established risk classifications in prognostic accuracy. Our approach generalises well to unseen cohorts with classification based on our subgroups similarly offering advantages in predicting prognosis. Our findings suggest that mutational patterns are often shared across myeloid malignancies, with distinct subtypes potentially representing evolutionary stages en route to leukemia. With pancancer TCGA data, we observe that our modelling framework extends naturally to other cancer types while still offering improvements in subgroup discovery.