Shashi, M.S.
@shashi_lab
Ph.D. Student @RutgersU | Alumni @UOGTriton | Metabolomics of Bacteria, Plant, Human | All views & posts are my own.
🚀 Ever tried training multiple ML models in one line of code? With fastml, you can: fastml(data = df, label = "target") 🎯 Auto preprocessing 📊 Compare models instantly 🧠 SHAP, ROC, accuracy & more Perfect for fast prototyping in R! 💻⚡️ #rstats #MachineLearning
First @MetabolomicsSoc 2025 conference and not the last. Great experience seeing the applications, translational research, and developments in the field. Crazy to meet and see many of the pioneers. Great vibes all around!! Dr. Wu and I presenting a small piece of my…
✨✨Meet Us at the 21st Annual International #Conference of the Metabolomics Society (#Metabolomics2025)! 🎉 📅 Date: 22–26 June 2025 📍 Location: Prague, Czech Republic 🏷️ #MetabolitesMDPI #MetabolomicsResearch 🔗 For More Info: mdpi.com/about/announce…
🚀 Headed to #Metabolomics2025? Visit us June 22 - 26 in Prague!📍 Booth #G1 | Discover the new MxP® Quant 1000 kit | 🧩 Join the online jigsaw puzzle #challenge | 🎤 Join our vendor talk & #posterpresentations | More info on our Metabolomics 2025 page 👉 biocrates.com/metabolomics-2…
🧪 Is the dark metabolome just noise? In Part 1 of our 5-part series, El Abiead & Dorrestein push back on claims that most LC-MS/MS features are fragments — and explain why this matters for science & careers. 🔗 Read: ow.ly/f0Yp50W4CZM #Metabolomics #MassSpec
🌟 Editor's Choice Paper 📖 #Bridging #Ethnobotanical Knowledge and Multi-Omics Approaches for #Plant-Derived #Natural #Product Discovery 🧑🏻🔬By Prof. Justin J.J. van der Hooft, Dr. Fidele Tugizimana, et al. 🔗mdpi.com/2218-1989/15/6…
Delighted to announce the release of Boltz-2, which demonstrates unprecedented accuracy in predicting structure and binding affinity! Congrats to @GabriCorso and @jeremyWohlwend on this breakthrough achievement! 📄Paper: bit.ly/boltz2-pdf 💻Code: github.com/jwohlwend/boltz
Major update for untargeted workflows using Agilent’s MassHunter Explorer.. annotation by MS/MS, custom libraries, and integrating SIRIUS for unknowns #ASMS2025
An AI BioSync rendition of METLIN 960K as a dot matrix. Celebrating the creation of METLIN with 960,000 molecular standards, and going live in its original classic form - reengineered. 🔗 Sign in for access: metlin.scripps.edu/auth-login.html 📖 Read more: DOI: 10.1002/ansa.70012
DIA-NN 2.2.0 is released! In this update we have focused on analysis speed, which is becoming increasingly critical given the rapid transition to high-throughput proteomics. The new DIA-NN 2.2.0 Enterprise achieves up to ~1.6x median speedup on 64-cores under Windows (please see…
I think this will change many things. adds a new dimension for a metabolomist. Surprised (but not surprised cause of age of the field) this has only just been done.. Mass spec data is ultimately continuous data. Accelerate
Self-supervised learning of molecular representations from millions of tandem mass spectra using DreaMS go.nature.com/4k1n5iC
🚨🚨
Me in a cage 🤣🤣You know me better than that @houmanhemmati. The advantage I have is I am a clinician seeing the microbiome in action and he is not. To understand the microbiome, one needs to reach a cure. To reach a cure one needs to practice the art of medicine. Case of…
Self-supervised learning of molecular representations from millions of tandem mass spectra using DreaMS go.nature.com/4k1n5iC
ChatGPT now can analyze, manipulate, and visualize molecules and chemical information via the RDKit library. Useful for scientific work across health, biology, and chemistry.