Herbert B Schiller

Happy to share that our work together with @SchillerLab, Scott Budinger, Ben Singer and Sasha Misharin from @NorthwesternMed is now online on @JCI_insight. A full tweetorial that summarizes the study follows! @LMU_Muenchen @HelmholtzMunich @LungHealthMUC

As I have pointed out many times publicly, single cell foundation model performance will scale with the number of perturbations, not the number of cells. We barely have ~100k perturbations in the public domain and it is reasonable to expect we need millions to truly go OOD. Factor in also: modalities, time points, combinations etc. Short term, there is little to do using public data. Best medium term option, consider semi-mechanistic modelling: arxiv.org/abs/2501.19178 Long term, …, wait for the press release ;)

Mapping How Human Lungs Respond to Treatments 🫁 👉t1p.de/kj98f #HelmholtzMunich has entered into a collaboration with @ParseBio to generate one of the largest lung disease perturbation atlases to date. Using Parse’s GigaLab platform, researchers will study an extensive set of lung cells at once to reveal how different drugs affect them. 🔬 What the project will do ▪️Test 900 potential treatments on lung tissue from healthy donors and patients with chronic lung disease. ▪️Uncover how cells communicate and identify new targets for future therapies. 💬 “Measuring the effects of drug treatments at single cell level directly in human lung tissue at scale will help us to find strategies that improve lung tissue regeneration, which may lead to the targeted combination therapies of the future.” – Prof. Herbert Schiller, Director of Helmholtz Munich’s Precision Regenerative Medicine Research Unit 💬 “To build foundational AI models of cell and tissue biology, we are in urgent need for more high-quality perturbation data – such a complex drug perturbation dataset will enable meaningful progress towards understanding gene regulation in lung health and disease.” – Prof. Fabian Theis, Head of the Computational Health Center at Helmholtz Munich 💡 This collaboration is a major step toward data-driven precision medicine and the development of better therapies for chronic lung conditions. @SchillerLab @fabian_theis @CompHealthMuc #LungResearch #PrecisionMedicine #AI #Genomics

New Collaboration – Advancing Drug Discovery for Pulmonary Fibrosis 🫁 👉t1p.de/qhm8a #HelmholtzMunich and Boehringer Ingelheim have joined forces to improve treatment options for idiopathic pulmonary fibrosis (IPF), a severe and progressive lung disease. 💡 Supported by €1.1 million in funding from Boehringer Ingelheim, the project will combine single-cell genomics and #AImodels to analyze drug effects on cultured human lung tissue. While current treatments can slow disease progression, there is a high remaining patient need with no treatments capable of stopping or reversing the disease available to date. This collaboration aims to help close this gap by developing a more physiologically relevant platform for drug discovery. Key aspects: 🌟 Cutting-edge methods: Analysis of drug effects at single-cell resolution in precision-cut human lung slices to enable testing of new anti-fibrotic candidates. 🌟 Synergy of disciplines: Integrating experimental biology and data science to more accurately predict how potential drugs – and their combinations – might act in complex human tissues. 🌟 Strong industry contribution: Beyond funding, Boehringer Ingelheim is providing a selection of compounds from its development pipeline for testing. 🌟 Ultimate goal: Accelerating the development of improved treatment options and better outcomes for people living with IPF. At Helmholtz Munich, the collaboration is led by lung expert Prof. Herbert Schiller and biomedical AI specialist Prof. Fabian Theis. The Boehringer Ingelheim team is led by Prof. Matthew Thomas. @fabian_theis @SchillerLab @BoehringerDE @CompHealthMuc #PulmonaryFibrosis #DrugDiscovery #SingleCell #AIinMedicine

Are you ready to make a difference in the field of respiratory medicine? Join the RESPIRE-EXCEL consortium and get your PhD training in my lab at Helmholtz Munich. In the project we will dissect specific disease mechanisms affecting respiratory airway stem cells (RASC) located in terminal and respiratory bronchioles of the human lung, in particular in the context of COPD. Our program offers advanced interdisciplinary courses led by top experts in Precision Medicine for Respiratory Diseases. You will gain cross-sectoral competencies and multidisciplinary knowledge, enabling you to collaborate effectively with industry, healthcare, and academia. The RESPIRE-EXCEL consortium includes numerous academic, industrial, and societal partners from across Europe and the UK, such as the European Lung Foundation and the European Respiratory Society. You can apply until 2nd of March 2025. Apply through this link: respire-excel.eu/vacancies Lab webpage: helmholtz-munich.de/en/envir… @HelmholtzMunich @EuroRespSoc @dzlacademy @3Assembly @atscommunity @ATS_Assemblies @ATS_RCMB @EMBO @EMBO_YIP @BTSrespiratory @EuropeanLung @NM_Lung @lungmapnet @LungHealthMUC @FIRS_LungsFirst

Excited to have Naftali Kaminski (@KaminskiMed) at LHI/@HelmholtzMunich with an insightful overview of 30 years of experience in the lung fibrosis field and new insights into how the lung ages. Unforgettable citation by Naftali: “You only see things you shine the light upon!”

This morning all our participants enjoyed the beautiful views of sunny Malta whilst networking over a cup of coffee. 🌞☕️🇲🇹 #Fusionlung24 @Delanghelab @ana_saganta @Tatalab_Duke

During our annual meeting at the @radboudumc in February 2024, my colleagues and I recorded our pitches with @SciMingo where we talk about our individual research projects in @SkinTERM_EU ✨👩🏻‍🔬 YouTube: youtube.com/playlist?list=PL…

Great motivator to head into the weekend: Our donor deconvolution pipeline 'hadge' is out in Genome Biology! genomebiology.biomedcentral.… This Nextflow pipeline combines 12 hashing and genotype based deconvolution methods to also enable a novel joint deconvolution strategy