Renard Lab retweeted
Check out “Electronic Health Records-based identification of newly diagnosed Crohn’s Disease cases”, a new paper from HPI·MS PhD student @SusanneIbing, Masters graduate @JulianHug0, and collaborators, now available in Artificial Intelligence in Medicine.
sciencedirect.com/science/ar…
Renard Lab retweeted
New working paper: Sparse Explanations of Neural Networks Using Pruned Layer-Wise Relevance Propagation✂️
by Paulo Yanez Sarmiento, Simon Witzke, Nadja Klein & Bernhard Y. Renard now available on arxiv
arxiv.org/pdf/2404.14271.pdf
🧵1/5 Thread below:
Renard Lab retweeted
🎉Our paper 'Beware of data leakage from protein LLM pretraining' was accepted at #MLCB2024! Meet Leon and Tobias at the spotlight talk and poster session on Thursday in Seattle to chat about how to address this important problem!! @jmbartoszewicz xitter.cf/jmbartoszewicz/status/…
🚨Beware of data leakage from protein LLM pretraining!
@MelaniaNowicka & I kept discussing how data leakage from pretrained embeddings can inflate performance metrics. So, our @HPI_DE students Leon, Tobias and An actually measured it! Check it out: biorxiv.org/content/10.1101/… 1/3
Renard Lab retweeted
🚨Beware of data leakage from protein LLM pretraining!
@MelaniaNowicka & I kept discussing how data leakage from pretrained embeddings can inflate performance metrics. So, our @HPI_DE students Leon, Tobias and An actually measured it! Check it out: biorxiv.org/content/10.1101/… 1/3
Renard Lab retweeted
New preprint! 🥳👉 biorxiv.org/content/10.1101/…
Embeddings from Protein Language Models (PLMs) are increasingly used to develop predictors of protein features and mutation effects. It is critical however to compare PLM embeddings before using them for downstream tasks
#LLMs #protein
Renard Lab retweeted
#eshg2024 - very excited to support the great work of my team members. Check out posters by @andrea_eoli at 13:00 (P11.090.A) and @JulianWanner (P07.002.B) and Nicolas Walk (P23.032.B) at 15:45 on Sunday - we’re looking forward to your feedback.
Renard Lab retweeted
Happy to see that our use case on automating Crohn's disease phenotyping sparked interest at #DDW2024! Thank you @charlie_lees for mentioning our work, and @DDWMeeting for a great conference and the invitation to present. #CrohnsDisease #NLP
New tech to monitor and treat IBD
• wearables
• sweat patches
• AI using GTPs to phenotype
• robot pills to inject biologic drugs
Further insights from #DDW2024 in Atomic IBD Uncut - Episode Seventeen
Renard Lab retweeted
Clever usage of @nanopore Adaptive Sampling to enrich bacterial plasmids - tell the sequencer to start kicking out the bacterial chromosome reads, thereby generating more plasmid reads!
We're delighted that our study "Nanopore adaptive sampling effectively enriches bacterial plasmids" 🧬🦠has been published @mSystemsJ journals.asm.org/doi/full/10…
Renard Lab retweeted
Late, happy news! @MelaniaNowicka and I started our postdoc adventure @MIT_CSAIL, with @BarzilayRegina & @RenardLab. Thx to the Designing for Sustainability Program of @MITDesignAcad & @HPI_DE, we explore the use of AI to design therapeutic agents to combat antibiotic resistance!
Renard Lab retweeted
Can prompt-tuning become a low-cost alternative to fine-tuning of protein LMs for sequence generation? NLP metrics are not enough - biological eval is a must! Check out our paper at #MLCB2023, by Andrea&Kevin, advised by @MelaniaNowicka & me at @RenardLab biorxiv.org/content/10.1101/…
Renard Lab retweeted
Final day of #ISMBECCB2023 came with the wonderful invited keynote from Bernhard @RenardLab on his journey with spectra and their current and outlook!
#CompMS
Renard Lab retweeted
And now for some monkey pox at #BOSC2023, @ferbsx presenting on genomic surveillance of Mpox and the need for a platform including the latest data with crucial (otherwise missing) metadata. Aligns to reference genomes, allows data exploration tools #ISMBECCB2023 – at Lyon, France
Renard Lab retweeted
MpoxRadar is an interactive dashboard that enables global tracking of mutation profiles and variants of the #mpox virus. [co-authored by EVBC members A. Nitsche @RenardLab] doi.org/10.1093/nar/gkad325
Renard Lab retweeted
Good morning at day 3 in Valencia for #ViBioM2023! Keynote speaker Bernhard Renard @RenardLab is getting us into the #machinelearning mood to talk about viral #surveillance in the first session. Glad to see so many people up after the great conference dinner!
Renard Lab retweeted
Proof-of-principle for predicting earlier time for #decision-making based on Illumina #sequencing cycles for #pathogen #diagnosis using #machinelearning, which can save several hours of turnaround time. [preprint co-authored by EVBC member @RenardLab] doi.org/10.1101/2023.03.07.5…
Renard Lab retweeted
We are happy to announce the final speaker in our list of keynote speakers! Rob Edwards @linsalrob will join us in Valencia at #ViBioM2023 to speak about the promise and pitfalls of #prophages. Registration is still open: evbc.uni-jena.de/events/vibi…
Renard Lab retweeted
Review about available sources and approaches for the processing of secondary data for #globalhealth #digitalisation. [co-authored by EVBC members @Heiderlab, M. von Kleist, @RenardLab] doi.org/10.1016/s2589-7500(2…
Renard Lab retweeted
#KI -Experte und HPI-Prof. Christoph Lippert (@LippertChr ) und HPI-Wissenschaftlerin Dr. Henrike Heyne (@HHeyne ) haben mit Gunnar Göpel (@Lyrikkauz) vom @TspBackgroundGE @Tagesspiegel über ihre Forschung im Rahmen des Projekts #Intervene gesprochen: xitter.cf/TspBackgroundGE/status…
Im europäischen Forschungsprojekt #Intervene werden Daten von mehr als 1,7 Millionen sequenzierten #Genomen verknüpft. Das Ziel: Risiko-Scores, die Vorhersagen zu Erkrankungsrisiken ermöglichen. #KI-Modelle dafür werden u. a. in Potsdam entwickelt. @HPI_DE background.tagesspiegel.de/g…
Renard Lab retweeted
Thank you to @HPI_de Professor and Vice-Dean Bernhard Renard, PhD, (@renardlab) for his insightful talk on computational approaches to pathogen discovery and #MetaOmics, part of the AI & Human Health Seminar Series!
