005 Computerprogrammierung, Programme, Daten
Refine
Document Type
- Article (2)
- Workingpaper / Report (2)
- Lecture (1)
- Preprint (1)
- Researchdata (1)
Language
- English (5)
- Multiple languages (2)
Is part of the Bibliography
- yes (7)
Keywords
- Computational chemistry (3)
- Naturstoffchemie (3)
- Digitales Archiv (2)
- Intermedialität (2)
- Maschinelles Lernen (2)
- Massenspektrometrie (2)
- Medienkunst (2)
- Metabolomik (2)
- FPGA acceleration (1)
- Kria KV260 (1)
Department/institution
Rapid Deployment of Hardware-Accelerated Vision AI Applications on the Xilinx Kria KV260 Platform
(2026)
This teaching-oriented paper presents a structured introduction to the deployment of hardware-accelerated vision AI applications on the Xilinx Kria KV260 platform. Rather than focusing on low-level hardware design, the material emphasises system integration, runtime configuration, and the interaction between software and reconfigurable logic within a modern heterogeneous embedded system. Using a pre-integrated smart camera application as a guiding example, the paper demonstrates how FPGA-based acceleration can be accessed through standard Linux tools, containerised execution environments, and network-based video streaming. The approach is specifically designed for higher education, enabling students to gain practical insight into adaptive computing platforms while maintaining a clear conceptual understanding of hardware–software co-design principles.
With over 3000 representatives, the monoterpene indole alkaloids (MIAs) class is among the most diverse families of plant natural products. The MS/MS spectral space exploration of these complex compounds using chemoinformatic and computational mass spectrometry tools offers a valuable opportunity to extract and share chemical insights from this emblematic family of natural products (NPs). In this work, we first present a substantially updated version of the MIADB, a database now containing 422 MS/MS spectra of MIAs that has been uploaded to the GNPS library versus 172 initial entries. We then introduce an innovative workflow that leverages hundreds of fragmentation spectra to support the FAIRification, extraction and dissemination of chemical knowledge. This workflow aims at the extraction of spectral patterns matching finely defined MIA skeletons. These extracted signatures can then be queried against complex biological extract datasets using MassQL. By applying this strategy to an LC-MS/MS dataset of 75 plant extracts, our results demonstrated the efficiency of this approach in identifying the diversity of MIA skeletons present in the analyzed samples. Additionally, our work enabled the digitization of structural data for diverse MIA skeletons by converting them into machine-readable formats and thereby enhancing their dissemination for the scientific community.
Scientific contribution
A comprehensive investigation of the monoterpene indole alkaloid chemical space, aiming to highlight skeleton-dependent fragmentation similarity trends and to generate valuable spectrometric signatures that could be used as queries.
Quantifying molecular similarity is a cornerstone of cheminformatics, underpinning applications from virtual screening to chemical space visualization. A wide range of molecular fingerprints and similarity metrics, most notably Tanimoto scores, are employed, but their effectiveness is highly context-dependent. In this study, we systematically evaluate several 2D fingerprint types, including circular, path-based, and distance-encoded variants, using both binary and count representations. We highlight the consequences of fingerprint choice, vector folding, and similarity metric selection, revealing critical issues such as fingerprint duplication, mass dependent score biases, and high bit collision rates. Sparse and count-based fingerprints consistently outperform fixed-size binary vectors in preserving structural distinctions. Furthermore, we introduce percentile-based normalization, propose inverse-document-frequency (IDF) weighting, and benchmark all methods against graph-based MCES similarities. Our results offer practical guidance for selecting molecular similarity measures, emphasizing the need for conscious, task-aware fingerprinting choices in large-scale chemical analyses.
In natural products research, chemodiverse extracts coming from multiple organisms are explored for novel bioactive molecules, sometimes over extended periods. Samples are usually analyzed by liquid chromatography coupled with fragmentation mass spectrometry to acquire informative mass spectral ensembles. Such data is then exploited to establish relationships among analytes or samples (e.g., via molecular networking) and annotate metabolites. However, the comparison of samples profiled in different batches is challenging with current metabolomics methods since the experimental variation—changes in chromatographical or mass spectrometric conditions - hinders the direct comparison of the profiled samples. Here we introduce MEMO—MS2 BasEd SaMple VectOrization—a method allowing to cluster large amounts of chemodiverse samples based on their LC-MS/MS profiles in a retention time agnostic manner. This method is particularly suited for heterogeneous and chemodiverse sample sets. MEMO demonstrated similar clustering performance as state-of-the-art metrics considering fragmentation spectra. More importantly, such performance was achieved without the requirement of a prior feature alignment step and in a significantly shorter computational time. MEMO thus allows the comparison of vast ensembles of samples, even when analyzed over long periods of time, and on different chromatographic or mass spectrometry platforms. This new addition to the computational metabolomics toolbox should drastically expand the scope of large-scale comparative analysis.
Modelle der sogenannten Künstlichen Intelligenz (KI) ermöglichen eine systematische Strukturierung von riesigen Datenmengen zum Zweck der Erkenntnisgewinnung aus bestehenden Informationen. Ein Verfahren wie das Maschinelle Lernen kann dabei unterstützen, einen neuen Blick auf vorhandenes Wissen in digitalen Archiven zu werfen. Diese lernfähigen Maschinen sollen im Projekt „IMAI – Intermediale Sammlungsforschung mit Artificial Intelligence“ untersucht werden, um Archivar*innen sowie Kunst- und Medienhistoriker*innen bei der Sichtung des audiovisuellen Materials zu unterstützen und den Umgang mit Sammlungen zeitbasierter Medien effizienter sowie komfortabler zu machen. In einer ersten Projektphase (2024) sollten durch die Erprobung verfügbarer Prototypen und durch die Sichtung des Videoarchivs des Inter Media Art Institute Anwendungsoptionen abgewogen werden. Die bislang genutzten Werkzeuge zur Erschließung von Archiven wurden dabei genauso betrachtet wie die Arbeitsweisen weiterer betroffener Anwender*innen. Der Bericht fasst die Erkenntnisse aus der Vorstudie zusammen
Modelle der sogenannten Künstlichen Intelligenz (KI) ermöglichen eine systematische Strukturierung von riesigen Datenmengen zum Zweck der Erkenntnisgewinnung aus bestehenden Informationen. Ein Verfahren wie das Maschinelle Lernen kann dabei unterstützen, einen neuen Blick auf vorhandenes Wissen in digitalen Archiven zu werfen. Diese lernfähigen Maschinen sollen im Projekt „IMAI – Intermediale Sammlungsforschung mit Artificial Intelligence“ untersucht werden, um Archivar*innen sowie Kunst- und Medienhistoriker*innen bei der Sichtung des audiovisuellen Materials zu unterstützen und den Umgang mit Sammlungen zeitbasierter Medien effizienter sowie komfortabler zu machen. In einer ersten Projektphase (2024) sollten durch die Erprobung verfügbarer Prototypen und durch die Sichtung des Videoarchivs des Inter Media Art Institute Anwendungsoptionen abgewogen werden. Die bislang genutzten Werkzeuge zur Erschließung von Archiven wurden dabei genauso betrachtet wie die Arbeitsweisen weiterer betroffener Anwender*innen. Der Bericht fasst die Erkenntnisse aus der Vorstudie zusammen.