Florian Haselbeck

A Perspective from @itisalist @judith_bernett @RomanJoeres @ok55991 @FloHasee @dg_grimm @bit_tumcs & @dbblumenthal discusses the issue of data leakage in machine learning models and presents 7 questions to identify and avoid problems as a result. nature.com/articles/s4159…

First publication out with @bit_tumcs!! Read this contribution about a #prediction model (#ProLaTherm) for #thermophilicsproteins. Protein thermostability is instrumental for protein #hybrid #optoelectronics! 👉academic.oup.com/nargab/article…

A new home for one of our flagship projects: Thanks to great work by @dg_grimm, and great support from #ArminLambacher, @easyGWAS has moved to @MPI_Biochem! easygwas.biochem.mpg.de easyGWAS.org is a cloud-based service for #GWAS on public datasets.

@BMBF_Bund Gute Punkte dabei. Leider aber nicht die eigtl. Probleme: (i) kaum Perspektive außer Prof aus Mangel unbefristeter oder verbeamteter, finanziell interessanter Stellen, (ii) oft keine 100% Bezahlung, (iii) Ausnutzen extremes Machtgefälle Prof/PhDs. 2/3 könnte der Staat lösen.

Mit einer Reform des #WissZeitVG wollen wir die Arbeitsbedingungen für #Wissenschaftlerinnen und #Wissenschaftler verbessern. Dazu haben wir heute unseren Referentenentwurf vorgestellt. Die wesentlichen Inhalte zusammengefasst 👇 Mehr: bmbf.de/bmbf/shareddoc…

Our #ICLR2023 contribution „Policy-Based Self-Competition for Planning Problems“ #ReinforcementLearning #HSWT #TUMCS @TU_Muenchen openreview.net/forum?id=SmufN…

Happy to share our newest work easyPheno, developed with Maura John and @dg_grimm at @bit_tumcs. We make state-of-the-art phenotype prediction easy to use while providing a powerful tool for developing new models. Thanks @BioinfoAdv and @Nicky_Mulder. doi.org/10.1093/bioadv…

easyPheno: An easy-to-use and easy-to-extend Python framework for phenotype prediction using Bayesian optimization by @FloHasee, Maura John, @dg_grimm in @BioinfoAdv doi.org/10.1093/bioadv… edited by @Nicky_Mulder

Tomorrow Maura John will present our new work on „Efficient permutation-based genome-wide association studies for normal and skewed phenotypic distributions“ @ECCBinfo awesome collaboration with @arthurkorte @IIMOG @bit_tumcs @TU_Muenchen #TUMCS #HSWT academic.oup.com/bioinformatics…

Das @BMBF_Bund stoppt zurzeit viele in Aussicht gestellte Forschungsvorhaben. Begründung: "neue Schwerpunktsetzungen hin zu Forschungsaktivitäten, die einen schnellen Impact erzeugen" Welche Folgen das hat, berichten Marianne Braig & Regine Schönenberg: fu-berlin.de/campusleben/fo…

@probabilisticai Thanks! Looking forward to participating in this year's ProbAI :)

💌 All applicants have been notified via email. ⚠️ Please check your spam folders.

Happy to share our brand-new publication on #MachineLearning for Horticultural Sales Predictions: doi.org/10.1016/j.mlwa… Thanks to all co-authors: Jennifer Killinger, Klaus Menrad, Thomas Hannus, @dg_grimm Feel free to contact us.