Fair, but bro please listen you don’t think after we achieve AGI or even before there’s no use in your job? What are you doing as a biologist to where there’s no need for RoseTTAFold ESMFold CellPose DeepCell Ilastik DeepVariant Google DeepMind Enformer scVI Scanpy based clustering models Gene expression autoencoder models AI assisted primer and construct design Any of this?! Like none at all not even image processing?

We’re pleased to announce Mahyar “Yar” Salek @mahyarsalek, Co-founder, CTO & President of @deepcellbio, as one of the featured speakers at the Global AI Show 2025. A leading innovator at the intersection of AI and biology, Yar has built the REM-I platform and one of the world’s largest single-cell morphology foundation models, trained on more than 3 billion cell images. Under his leadership, Deepcell has raised $100M , partnered with top hospitals and biopharma, and earned global recognition — including BioTech Breakthrough Company of the Year and The Scientist’s Top 10 Innovations. With a PhD in Computer Science, a research background from Microsoft Research Cambridge, and prior work at Google leading AI-powered ad products, Yar brings unmatched expertise in applied AI, computer vision, and biotech innovation. Hear his insights this December at the Global AI Show 2025. 📍 8–9 December 2025 | Space42 Arena, Abu Dhabi 🎟 Get your free pass: globalaishow.com/abu-dhabi/t… Want the full VIP experience? ⚡️ Use promo code AI15 to get 15% off VIP & Delegate passes! #GlobalAIShow #GAIS2025

subCellSAM: Zero-Shot (Sub-)Cellular Segmentation for Hit Validation in Drug Discovery 1. Introducing subCellSAM, a novel method for zero-shot segmentation of cellular and subcellular structures in high-content screening (HCS) for drug discovery. This novel approach leverages a pre-trained segmentation foundation model without any fine-tuning, guided by an in-context learning strategy that incorporates morphological and topological priors of cell images. 2. The core innovation of subCellSAM lies in its three-step process for nuclei, cell, and subcellular segmentation. It employs a self-prompting mechanism that uses growing masks and strategically placed foreground/background points to guide the segmentation process, ensuring biologically plausible and accurate results without dataset-specific tuning. 3. subCellSAM demonstrates superior performance in cell segmentation across diverse datasets, outperforming specialized methods such as CellPose 3, DeepCell, and CellSAM. It achieves a mean Dice Score (DSC) of 0.901 and Intersection over Union (IoU) of 0.832 on the BBBC008 dataset, showcasing its robustness and generalizability. 4. In the context of hit validation for drug discovery, subCellSAM effectively segments subcellular structures without any parameter tuning, resulting in high-quality downstream results. It achieves Z'-factor values comparable to baseline methods and accurately calculates EC50 values for compound potency, highlighting its potential for automated HCS analysis pipelines. 5. The method's modular design allows for flexible integration of different models, and its reliance on pre-defined morphological and topological priors makes it a viable strategy for reducing manual configuration in HCS analysis. This approach paves the way for more efficient and accurate drug discovery processes. 📜Paper: arxiv.org/abs/2508.13701 #ComputationalBiology #DrugDiscovery #CellSegmentation #ZeroShotLearning #InContextLearning

“The worst part about a Brown Indian Ugandan Muslim Deepcell Terrorist pretending to be American is the woke socialist policies he’s suggesting”

Deepcell Announces Collaboration with @MayoClinic to Advance AI-Driven IVF Technology. Link in the comments.

Awesome to see @fiftyyears companies on the @norrsken_org Impact/100 list: norrsken.org/impact100 Congrats Deepcell, Molten, Planet A, and Unspun!

Is this why DeepCell didn’t make it far?

DeepCell in deep trouble? And a good reminder for us all that the “customer” who put the most money into your company in the early days are not the ones buying your products in the lab

Happy International Women's Day 💜 We want to celebrate the incredible power of courage, compassion, and resilience of all the women at Deepcell and in the field of STEM. With deep gratitude and respect, we wish you a day filled with abundance of joy and recognition! #IWD2024

The SF Bay Area has an incredibly deep roster of deep tech startups. Did I miss any? Astra Astranis Ansa Bio Antora Energy Astro Mechanica Atom Computing Atom Semiconductor Atomic Industries Atomic Semi AtomLimbs BillionToOne Boundary Layer Technologies Buoyant Cruise Deepcell Bio Embark Trucks Extropic Faction Form Energy Geltor Inc Genfabco GenMat Gordian Bio Gridware Itemfarm Joby Lightcell Lucid Motors Lygos Matterport Mission Barns Molten Industries Momentus Multiply Labs Navier Nobell Foods Octant Bio Oklo OpenAI Orangewood Labs Outsail Planet Poseidon Rigetti Saildrone Skydio Spire Ukama Unspun Upside Foods Utvate Vitro Labs Wildtype Worldcoin Zipline

Did you know we offer free personalized demos? If you want to learn more about the REM-I Platform, we can connect you up with a Deepcell expert who will walk you through tailored applications and capabilities for your research needs. Request your demo 👇 deepcell.com/request-demo/

Deepcell is honored to be named a finalist for the #SLAS2024 New Product Award! A big thank you to @SLAS_Org for this incredible recognition! To learn more about REM-I visit deepcell.com/product More details regarding our participation at SLAS coming soon!

Not content to only compete with illumina, element biosciences decides to also take on the full spectrum of protein firms and deepcell

Deepcell Partners With Nvidia to Incorporate Generative AI Into Single-Cell Analysis. Deepcell, which was founded as a spinout of Stanford University in 2017, recently launched its flagship REM-I platform for single-cell imaging and sorting. ow.ly/culH1058hlV

Deepcell announces their REM-I instrument for single cell morphology analysis #JPM24

We’re thrilled to announce that our REM-I instrument has been installed for testing at an academic institution where the platform will be used in Alzheimer’s disease research. But that’s not all that’s been happening at Deepcell recently:

Subcellular #SpatialTranscriptomics Cell Segmentation #TransformerNeuralNetwork based on Image AND Transcriptome For Single-Cell/Subcellular ST Stereo-seq; Seq-scope vs other #DeepLearning methods #StarDist #CellPose #DeepCell @naturemethods 2023 nature.com/articles/s41592-0…

What a great year for @Deepcell!

Check out the latest Deepcell Summit presentation featuring @Andy_P_Tsai from Stanford, who highlights the capabilities of using cell morphology as a readout for distinguishing between healthy brains and those with MCI or AD from peripheral immune cells: deepcell.com/science/?play=3…

Looking back at a fantastic Deepcell Summit in Chicago, Il earlier this fall! 🌐 Countless engaging discussions with our valued collaborators who shed light on the versatile applications of the REM-I platform across diverse life science domains.