Forschungsseminar der Arbeitsgruppe Data Integration in the Life Sciences (DILiS). Auch offen für Seminarteilnahmen im Masterstudium, Online-Teilnahme möglich. Bitte entnehmen Sie Termine dem aktuellen Plan im Whiteboard!
We start at 14:00 s.t.. We meet in T9/SR137. This is the link for online participation https://fu-berlin.webex.com/fu-berlin/j.php?MTID=m5ba1c59d104b0b852cdbdd2834d485e8
Das Seminar bietet Raum für die Diskussion weiterführender und integrativer Datenanalysetechniken, insbesondere Vorträge und Diskussion von laufenden oder geplanten Forschungsprojekten, Neuigkeiten von Konferenzen, Besprechung aktueller Literatur und Diskussion möglicher zukünftiger Lehrformate und -inhalte, und Vorstellungen, sowie Abschlussvorträge zu Abschlussarbeiten oder Projektseminaren. Die Seminarsprache ist weitestgehend Englisch. Gern können interessierte Studierende teilnehmen und unverbindlich vorbeischauen oder ein selbst gewähltes Thema von Interesse für die Arbeitsgruppe vorstellen. Achtung: Einzelne Termine können ausfallen oder verschoben werden. Kontaktieren Sie mich gern für Fragen (katharina.baum@fu-berlin.de)!
Agenda
| Date | Speaker | Topic |
|---|---|---|
| 7.10. | DILiS internal | Teaching at DILiS, Organization |
| 14.10. | Katharina Baum + DILiS | Introduction to DILiS + this course as a seminar |
| 21.10. |
Camila Baselly (15 + 15) Oussama Bouanani (15 + 10) |
BSc thesis defense: Simulation-based transfer learning in systems biology: Modeling insulin dynamics with ODE-generated data Intro to MSc thesis topic: Contrastive Explanations for Neuron Semantic Labeling |
| 28.10. | Pascal Iversen* (45 + 15) | Challenges in drug response prediction in cancer |
| 4.11. |
Max Alcer (30 + 15) Sören Seidack (15 + 15) |
MSc thesis colloquium BSc thesis colloquium: Ensemble models for drug response prediction in DrEval |
| 11.11. | Martin Mašek* (45 + 15) |
Gene expression prediction with informed ML |
|
18.11. |
Katharina Baum & DILiS (40 + 15) | AI: perspectives and pitfalls, Guidelines for the report |
| 25.11. | Leonard Vonk (45 + 15) | From Trial and Error to Prediction: Comparing Approaches Toward Personalizing Cancer Drug Combinations |
| 2.12. | Leon Barbut (45 + 15) | Scalable Fine-Tuning of Large Models Using Low-Rank Decomposition |
| 9.12. | Renk Asik (40 + 15) Zhaguo Wei (15 + 15) Michael Flanderka (15 + 15) |
Turning cells into sentences: Scaling single-cell foundation models with LLMs BSc thesis defense: Quantifying the impact of aleatoric and epistemic uncertainty on drug response prediction in an active learning setting BSc thesis defense: Active learning in drug response prediction: A divergence-based approach |
| 16.12. |
Xhemal Kodragjini (30 + 15) Lilly Wiesmann (40 + 15) |
MSc colloquium: Deciphering signaling pathway cross-talk by universal differential equations Foundation Models for Single-Cell Biology: A Comparative Analysis of scGPT and scFoundation |
| X-mas break | ||
| 6.1.26 | Jonah Reiner (45 + 15) | tbd |
| 13.1. | Jingwen Luo (40 + 12) Lorenzo Spiridioni (40 + 12) |
tbd tbd |
| 20.1. | Tania Valencia J (45 + 15) | tbd |
| 27.1. | [tentative] Yagmur Simsek (30 + 15) | MSc thesis colloquium: Steady-state simulations and transfer learning with SimbaML |
| 3.2. | Yan Sheng (45 + 15) | tbd |
| 10.2. | Edda Gieseler (45 + 15) | Overestimated Model Quality: How Label Leakage Skews the Evaluation of AI Systems in Healthcare |
| 17.2. | Zirui Zang (45 + 15) | tbd |
| 24.2. |
Some possible presentation topics - list of literature
- Heinken, A., Hertel, J., Acharya, G. et al. Genome-scale metabolic reconstruction of 7,302 human microorganisms for personalized medicine. Nat Biotechnol 41, 1320–1331 (2023). https://doi.org/10.1038/s41587-022-01628-0
- [taken by Tania Valencia] Azeloglu EU, Iyengar R. Signaling networks: information flow, computation, and decision making. Cold Spring Harb Perspect Biol. 2015 Apr 1;7(4):a005934. doi: 10.1101/cshperspect.a005934.
- [taken by Jonah R] Trang Nguyen, Anthony Campbell, Ankit Kumar, Edwin Amponsah, Madalina Fiterau, Leili Shahriyari, Optimal fusion of genotype and drug embeddings in predicting cancer drug response, Briefings in Bioinformatics, Volume 25, Issue 3, May 2024, bbae227, https://doi.org/10.1093/bib/bbae227
- [taken by Leonard Vonk] Halil Ibrahim Kuru, A Ercument Cicek, Oznur Tastan, From cell lines to cancer patients: personalized drug synergy prediction, Bioinformatics, Volume 40, Issue 5, May 2024, btae134, https://doi.org/10.1093/bioinformatics/btae134
- Sharon E Davis, Michael E Matheny, Suresh Balu, Mark P Sendak, A framework for understanding label leakage in machine learning for health care, Journal of the American Medical Informatics Association, Volume 31, Issue 1, January 2024, Pages 274–280, https://doi.org/10.1093/jamia/ocad178
- Li et al., Artificial intelligence-powered pharmacovigilance: A review of machine and deep learning in clinical text-based adverse drug event detection for benchmark datasets; Journal of Biomedical Informatics, Volume 152, 2024, https://doi.org/10.1016/j.jbi.2024.104621
- DysRegNet: Patient-specific and confounder-aware dysregulated network inference;
- [taken by Lilly Wiesmann] Hao, M., Gong, J., Zeng, X. et al. Large-scale foundation model on single-cell transcriptomics. Nat Methods 21, 1481–1491 (2024). https://doi.org/10.1038/s41592-024-02305-7