arXiv subjects

Christoph Klein

Publications and source records attributed to Christoph Klein.

4 recordsLinked to original sources

arXiv2025

A Privacy-Preserving Ecosystem for Developing Machine Learning Algorithms Using Patient Data: Insights from the TUM.ai Makeathon

The integration of clinical data offers significant potential for the development of personalized medicine. However, its use is severely restricted by the General Data Protection Regulation (GDPR), especially for small cohorts with rare diseases. High-quality, structured data is essential for the development of predictive medical AI. In this case study, we propose a novel, multi-stage approach to secure AI training: (1) The model is designed on a simulated clinical knowledge graph (cKG). This graph is used exclusively to represent the structural characteristics of the real cKG without revealing any sensitive content. (2) The model is then integrated into the FeatureCloud (FC) federated learning framework, where it is prepared in a single-client configuration within a protected execution environment. (3) Training then takes place within the hospital environment on the real cKG, either under the direct supervision of hospital staff or via a fully automated pipeline controlled by the hospital. (4) Finally, verified evaluation scripts are executed, which only return aggregated performance metrics. This enables immediate performance feedback without sensitive patient data or individual predictions, leaving the clinic. A fundamental element of this approach involves the incorporation of a cKG, which serves to organize multi-omics and patient data within the context of real-world hospital environments. This approach was successfully validated during the TUM.ai Makeathon 2024 (TUMaiM24) challenge set by the Dr. von Hauner Children's Hospital (HCH-LMU): 50 students developed models for patient classification and diagnosis without access to real data. Deploying secure algorithms via federated frameworks, such as the FC framework, could be a practical way of achieving privacy-preserving AI in healthcare.

cs.DC↗

arXiv2024

KinDEL: DNA-Encoded Library Dataset for Kinase Inhibitors

DNA-Encoded Libraries (DELs) represent a transformative technology in drug discovery, facilitating the high-throughput exploration of vast chemical spaces. Despite their potential, the scarcity of publicly available DEL datasets presents a bottleneck for the advancement of machine learning methodologies in this domain. To address this gap, we introduce KinDEL, one of the largest publicly accessible DEL datasets and the first one that includes binding poses from molecular docking experiments. Focused on two kinases, Mitogen-Activated Protein Kinase 14 (MAPK14) and Discoidin Domain Receptor Tyrosine Kinase 1 (DDR1), KinDEL includes 81 million compounds, offering a rich resource for computational exploration. Additionally, we provide comprehensive biophysical assay validation data, encompassing both on-DNA and off-DNA measurements, which we use to evaluate a suite of machine learning techniques, including novel structure-based probabilistic models. We hope that our benchmark, encompassing both 2D and 3D structures, will help advance the development of machine learning models for data-driven hit identification using DELs.

q-bio.QM↗

arXiv2023

Democratising Knowledge Representation with BioCypher

Standardising the representation of biomedical knowledge among all researchers is an insurmountable task, hindering the effectiveness of many computational methods. To facilitate harmonisation and interoperability despite this fundamental challenge, we propose to standardise the framework of knowledge graph creation instead. We implement this standardisation in BioCypher, a FAIR (findable, accessible, interoperable, reusable) framework to transparently build biomedical knowledge graphs while preserving provenances of the source data. Mapping the knowledge onto biomedical ontologies helps to balance the needs for harmonisation, human and machine readability, and ease of use and accessibility to non-specialist researchers. We demonstrate the usefulness of this framework on a variety of use cases, from maintenance of task-specific knowledge stores, to interoperability between biomedical domains, to on-demand building of task-specific knowledge graphs for federated learning. BioCypher (https://biocypher.org) frees up valuable developer time; we encourage further development and usage by the community.

q-bio.MN↗

arXiv2018

Formalizing Atom-typing and the Dissemination of Force Fields with Foyer

A key component to enhancing reproducibility in the molecular simulation community is reducing ambiguity in the parameterization of molecular models. Ambiguity in molecular models often stems from the dissemination of molecular force fields in a format that is not directly usable or is ambiguously documented via a non-machine readable mechanism. Specifically, the lack of a general tool for performing automated atom-typing under the rules of a particular force field facilitates errors in model parameterization that may go unnoticed if other researchers are unable reproduce this process. Here, we present Foyer, a Python tool that enables users to define force field atom-typing rules in a format that is both machine- and human-readable thus eliminating ambiguity in atom-typing and additionally providing a framework for force field dissemination. Foyer defines force fields in an XML format, where SMARTS strings are used to define the chemical context of a particular atom type. Herein we describe the underlying methodology of the Foyer package, highlighting its advantages over typical atom-typing approaches and demonstrate is application in several use-cases.

physics.comp-ph↗