Nico Pfeifer

Marius de Arruda Botelho Herr, Michael Graf, Peter Placzek et al.

The need for data privacy and security -- enforced through increasingly strict data protection regulations -- renders the use of healthcare data for machine learning difficult. In particular, the transfer of data between different hospitals is often not permissible and thus cross-site pooling of data not an option. The Personal Health Train (PHT) paradigm proposed within the GO-FAIR initiative implements an 'algorithm to the data' paradigm that ensures that distributed data can be accessed for analysis without transferring any sensitive data. We present PHT-meDIC, a productively deployed open-source implementation of the PHT concept. Containerization allows us to easily deploy even complex data analysis pipelines (e.g, genomics, image analysis) across multiple sites in a secure and scalable manner. We discuss the underlying technological concepts, security models, and governance processes. The implementation has been successfully applied to distributed analyses of large-scale data, including applications of deep neural networks to medical image data.

Jonas Christian Ditz, Jacqueline Wistuba-Hamprecht, Timo Maier et al.

Motivation: Machine learning methods can be used to support scientific discovery in healthcare-related research fields. However, these methods can only be reliably used if they can be trained on high-quality and curated datasets. Currently, no such dataset for the exploration of Plasmodium falciparum protein antigen candidates exists. The parasite Plasmodium falciparum causes the infectious disease malaria. Thus, identifying potential antigens is of utmost importance for the development of antimalarial drugs and vaccines. Since exploring antigen candidates experimentally is an expensive and time-consuming process, applying machine learning methods to support this process has the potential to accelerate the development of drugs and vaccines, which are needed for fighting and controlling malaria. Results: We developed PlasmoFAB, a curated benchmark that can be used to train machine learning methods for the exploration of Plasmodium falciparum protein antigen candidates. We combined an extensive literature search with domain expertise to create high-quality labels for Plasmodium falciparum specific proteins that distinguish between antigen candidates and intracellular proteins. Additionally, we used our benchmark to compare different well-known prediction models and available protein localization prediction services on the task of identifying protein antigen candidates. We show that available general-purpose services are unable to provide sufficient performance on identifying protein antigen candidates and are outperformed by our models that were trained on this tailored data. Availability: PlasmoFAB is publicly available on Zenodo with DOI 10.5281/zenodo.7433087. Furthermore, all scripts that were used in the creation of PlasmoFAB and the training and evaluation of machine learning models are open source and publicly available on GitHub here: https://github.com/msmdev/PlasmoFAB.

Valerie Bürger, Marlie Besouw, Jana Fehr et al.

Meta-research and Trustworthy AI (TAI) share common goals, namely improving evidence, robustness, and transparency, yet there is very little interplay between the two fields. To investigate the potential benefits of closer collaboration between the domains of TAI in healthcare and meta-research, we convened an interdisciplinary workshop funded by the Volkswagen Foundation in February 2025. The workshop aimed to collaboratively examine key tensions in translating AI ethics principles into practice and to identify potential solutions informed by meta-research approaches. A Design Thinking-informed co-creation approach was followed by an inductive descriptive analysis of the outputs. Our results demonstrate how meta-research can offer concrete contributions to address pressing challenges of TAI in healthcare. These challenges include achieving robustness, reproducibility, and replicability; late-stage development and the integration of AI into clinical practice; the selection of appropriate evaluation metrics; specific AI-related challenges in preclinical and biomedical research; gaps of transparency in medical AI, as well as the need for improved conceptual clarity and AI literacy among stakeholders. Finally, we offer a catalog of ideas and roadmap for future research to inform scholars in both fields on existing interconnections and serve as a foundation for guiding future interdisciplinary efforts.

Sofiane Ouaari, Ali Burak Ünal, Mete Akgün et al.

Several domains increasingly rely on machine learning in their applications. The resulting heavy dependence on data has led to the emergence of various laws and regulations around data ethics and privacy and growing awareness of the need for privacy-preserving machine learning (ppML). Current ppML techniques utilize methods that are either purely based on cryptography, such as homomorphic encryption, or that introduce noise into the input, such as differential privacy. The main criticism given to those techniques is the fact that they either are too slow or they trade off a model s performance for improved confidentiality. To address this performance reduction, we aim to leverage robust representation learning as a way of encoding our data while optimizing the privacy-utility trade-off. Our method centers on training autoencoders in a multi-objective manner and then concatenating the latent and learned features from the encoding part as the encoded form of our data. Such a deep learning-powered encoding can then safely be sent to a third party for intensive training and hyperparameter tuning. With our proposed framework, we can share our data and use third party tools without being under the threat of revealing its original form. We empirically validate our results on unimodal and multimodal settings, the latter following a vertical splitting system and show improved performance over state-of-the-art.

Jonas C. Ditz, Bernhard Reuter, Nico Pfeifer

Motivation: The size of available omics datasets is steadily increasing with technological advancement in recent years. While this increase in sample size can be used to improve the performance of relevant prediction tasks in healthcare, models that are optimized for large datasets usually operate as black boxes. In high stakes scenarios, like healthcare, using a black-box model poses safety and security issues. Without an explanation about molecular factors and phenotypes that affected the prediction, healthcare providers are left with no choice but to blindly trust the models. We propose a new type of artificial neural network, named Convolutional Omics Kernel Network (COmic). By combining convolutional kernel networks with pathway-induced kernels, our method enables robust and interpretable end-to-end learning on omics datasets ranging in size from a few hundred to several hundreds of thousands of samples. Furthermore, COmic can be easily adapted to utilize multi-omics data. Results: We evaluated the performance capabilities of COmic on six different breast cancer cohorts. Additionally, we trained COmic models on multi-omics data using the METABRIC cohort. Our models performed either better or similar to competitors on both tasks. We show how the use of pathway-induced Laplacian kernels opens the black-box nature of neural networks and results in intrinsically interpretable models that eliminate the need for post-hoc explanation models.

Christopher Kolberg, Katharina Eggensperger, Nico Pfeifer

Revealing novel insights from the relationship between molecular measurements and pathology remains a very impactful application of machine learning in biomedicine. Data in this domain typically contain only a few observations but thousands of potentially noisy features, posing challenges for conventional machine learning approaches. While prior-data fitted networks emerge as foundation models for tabular data, they are currently not suited to handle large feature counts (>500). Although feature reduction enables their application, it hinders feature importance analysis. We propose a strategy that extends existing models through continued pre-training on synthetic data sampled from a customized prior. The resulting model, TabPFN-Wide, matches or exceeds its base model's performance while exhibiting improved robustness to noise. It seamlessly scales beyond 50,000 features, regardless of noise levels, while maintaining inherent interpretability, which is critical for biomedical applications. Our results show that prior-informed adaptation is suitable to enhance the capability of foundation models for high-dimensional data. On real-world biomedical datasets many of the most relevant features identified by the model overlap with previous biological findings, while others propose potential starting points for future studies.

Cem Ata Baykara, Ali Burak Ünal, Nico Pfeifer et al.

Machine learning models often struggle with generalization in small, heterogeneous datasets due to domain shifts caused by variations in data collection and population differences. This challenge is particularly pronounced in biological data, where data is high-dimensional, small-scale, and decentralized across institutions. While federated domain adaptation methods (FDA) aim to address these challenges, most existing approaches rely on deep learning and focus on classification tasks, making them unsuitable for small-scale, high-dimensional applications. In this work, we propose freda, a privacy-preserving federated method for unsupervised domain adaptation in regression tasks. Unlike deep learning-based FDA approaches, freda is the first method to enable the federated training of Gaussian Processes to model complex feature relationships while ensuring complete data privacy through randomized encoding and secure aggregation. This allows for effective domain adaptation without direct access to raw data, making it well-suited for applications involving high-dimensional, heterogeneous datasets. We evaluate freda on the challenging task of age prediction from DNA methylation data, demonstrating that it achieves performance comparable to the centralized state-of-the-art method while preserving complete data privacy.

Ali Burak Ünal, Nico Pfeifer, Mete Akgün

Since ML algorithms have proven their success in many different applications, there is also a big interest in privacy preserving (PP) ML methods for building models on sensitive data. Moreover, the increase in the number of data sources and the high computational power required by those algorithms force individuals to outsource the training and/or the inference of a ML model to the clouds providing such services. To address this, we propose a secure 3-party computation framework, CECILIA, offering PP building blocks to enable complex operations privately. In addition to the adapted and common operations like addition and multiplication, it offers multiplexer, most significant bit and modulus conversion. The first two are novel in terms of methodology and the last one is novel in terms of both functionality and methodology. CECILIA also has two complex novel methods, which are the exact exponential of a public base raised to the power of a secret value and the inverse square root of a secret Gram matrix. We use CECILIA to realize the private inference on pre-trained RKNs, which require more complex operations than most other DNNs, on the structural classification of proteins as the first study ever accomplishing the PP inference on RKNs. In addition to the successful private computation of basic building blocks, the results demonstrate that we perform the exact and fully private exponential computation, which is done by approximation in the literature so far. Moreover, they also show that we compute the exact inverse square root of a secret Gram matrix up to a certain privacy level, which has not been addressed in the literature at all. We also analyze the scalability of CECILIA to various settings on a synthetic dataset. The framework shows a great promise to make other ML algorithms as well as further computations privately computable by the building blocks of the framework.

Jonas C. Ditz, Bernhard Reuter, Nico Pfeifer

Artificial neural networks show promising performance in detecting correlations within data that are associated with specific outcomes. However, the black-box nature of such models can hinder the knowledge advancement in research fields by obscuring the decision process and preventing scientist to fully conceptualize predicted outcomes. Furthermore, domain experts like healthcare providers need explainable predictions to assess whether a predicted outcome can be trusted in high stakes scenarios and to help them integrating a model into their own routine. Therefore, interpretable models play a crucial role for the incorporation of machine learning into high stakes scenarios like healthcare. In this paper we introduce Convolutional Motif Kernel Networks, a neural network architecture that involves learning a feature representation within a subspace of the reproducing kernel Hilbert space of the position-aware motif kernel function. The resulting model enables to directly interpret and evaluate prediction outcomes by providing a biologically and medically meaningful explanation without the need for additional post-hoc analysis. We show that our model is able to robustly learn on small datasets and reaches state-of-the-art performance on relevant healthcare prediction tasks. Our proposed method can be utilized on DNA and protein sequences. Furthermore, we show that the proposed method learns biologically meaningful concepts directly from data using an end-to-end learning scheme.

Ali Burak Ünal, Nico Pfeifer, Mete Akgün

Computing an AUC as a performance measure to compare the quality of different machine learning models is one of the final steps of many research projects. Many of these methods are trained on privacy-sensitive data and there are several different approaches like $ε$-differential privacy, federated machine learning and cryptography if the datasets cannot be shared or used jointly at one place for training and/or testing. In this setting, it can also be a problem to compute the global AUC, since the labels might also contain privacy-sensitive information. There have been approaches based on $ε$-differential privacy to address this problem, but to the best of our knowledge, no exact privacy preserving solution has been introduced. In this paper, we propose an MPC-based solution, called ppAURORA, with private merging of individually sorted lists from multiple sources to compute the exact AUC as one could obtain on the pooled original test samples. With ppAURORA, the computation of the exact area under precision-recall and receiver operating characteristic curves is possible even when ties between prediction confidence values exist. We use ppAURORA to evaluate two different models predicting acute myeloid leukemia therapy response and heart disease, respectively. We also assess its scalability via synthetic data experiments. All these experiments show that we efficiently and privately compute the exact same AUC with both evaluation metrics as one can obtain on the pooled test samples in plaintext according to the semi-honest adversary setting.

Ali Burak Ünal, Mete Akgün, Nico Pfeifer

To train sophisticated machine learning models one usually needs many training samples. Especially in healthcare settings these samples can be very expensive, meaning that one institution alone usually does not have enough on its own. Merging privacy-sensitive data from different sources is usually restricted by data security and data protection measures. This can lead to approaches that reduce data quality by putting noise onto the variables (e.g., in $ε$-differential privacy) or omitting certain values (e.g., for $k$-anonymity). Other measures based on cryptographic methods can lead to very time-consuming computations, which is especially problematic for larger multi-omics data. We address this problem by introducing ESCAPED, which stands for Efficient SeCure And PrivatE Dot product framework, enabling the computation of the dot product of vectors from multiple sources on a third-party, which later trains kernel-based machine learning algorithms, while neither sacrificing privacy nor adding noise. We evaluated our framework on drug resistance prediction for HIV-infected people and multi-omics dimensionality reduction and clustering problems in precision medicine. In terms of execution time, our framework significantly outperforms the best-fitting existing approaches without sacrificing the performance of the algorithm. Even though we only show the benefit for kernel-based algorithms, our framework can open up new research opportunities for further machine learning models that require the dot product of vectors from multiple sources.

Efe Bozkir, Ali Burak Ünal, Mete Akgün et al.

Eye tracking is handled as one of the key technologies for applications that assess and evaluate human attention, behavior, and biometrics, especially using gaze, pupillary, and blink behaviors. One of the challenges with regard to the social acceptance of eye tracking technology is however the preserving of sensitive and personal information. To tackle this challenge, we employ a privacy-preserving framework based on randomized encoding to train a Support Vector Regression model using synthetic eye images privately to estimate the human gaze. During the computation, none of the parties learn about the data or the result that any other party has. Furthermore, the party that trains the model cannot reconstruct pupil, blinks or visual scanpath. The experimental results show that our privacy-preserving framework is capable of working in real-time, with the same accuracy as compared to non-private version and could be extended to other eye tracking related problems.

Nora K. Speicher, Nico Pfeifer

Due to the complexity of cancer, clustering algorithms have been used to disentangle the observed heterogeneity and identify cancer subtypes that can be treated specifically. While kernel based clustering approaches allow the use of more than one input matrix, which is an important factor when considering a multidimensional disease like cancer, the clustering results remain hard to evaluate and, in many cases, it is unclear which piece of information had which impact on the final result. In this paper, we propose an extension of multiple kernel learning clustering that enables the characterization of each identified patient cluster based on the features that had the highest impact on the result. To this end, we combine feature clustering with multiple kernel dimensionality reduction and introduce FIPPA, a score which measures the feature cluster impact on a patient cluster. Results: We applied the approach to different cancer types described by four different data types with the aim of identifying integrative patient subtypes and understanding which features were most important for their identification. Our results show that our method does not only have state-of-the-art performance according to standard measures (e.g., survival analysis), but, based on the high impact features, it also produces meaningful explanations for the molecular bases of the subtypes. This could provide an important step in the validation of potential cancer subtypes and enable the formulation of new hypotheses concerning individual patient groups. Similar analysis are possible for other disease phenotypes.

Nora K. Speicher, Nico Pfeifer

Personalized treatment of patients based on tissue-specific cancer subtypes has strongly increased the efficacy of the chosen therapies. Even though the amount of data measured for cancer patients has increased over the last years, most cancer subtypes are still diagnosed based on individual data sources (e.g. gene expression data). We propose an unsupervised data integration method based on kernel principal component analysis. Principal component analysis is one of the most widely used techniques in data analysis. Unfortunately, the straight-forward multiple-kernel extension of this method leads to the use of only one of the input matrices, which does not fit the goal of gaining information from all data sources. Therefore, we present a scoring function to determine the impact of each input matrix. The approach enables visualizing the integrated data and subsequent clustering for cancer subtype identification. Due to the nature of the method, no free parameters have to be set. We apply the methodology to five different cancer data sets and demonstrate its advantages in terms of results and usability.

Lisa Handl, Adrin Jalali, Michael Scherer et al.

Over the last years, huge resources of biological and medical data have become available for research. This data offers great chances for machine learning applications in health care, e.g. for precision medicine, but is also challenging to analyze. Typical challenges include a large number of possibly correlated features and heterogeneity in the data. One flourishing field of biological research in which this is relevant is epigenetics. Here, especially large amounts of DNA methylation data have emerged. This epigenetic mark has been used to predict a donor's 'epigenetic age' and increased epigenetic aging has been linked to lifestyle and disease history. In this paper we propose an adaptive model which performs feature selection for each test sample individually based on the distribution of the input data. The method can be seen as partially blind domain adaptation. We apply the model to the problem of age prediction based on DNA methylation data from a variety of tissues, and compare it to a standard model, which does not take heterogeneity into account. The standard approach has particularly bad performance on one tissue type on which we show substantial improvement with our new adaptive approach even though no samples of that tissue were part of the training data.