pinboard November 16, 2022

  • Documentation — scvi-tools
    scvi-tools (single-cell variational inference tools) is a package for end-to-end analysis of single-cell omics data primarily developed and maintained by the Yosef Lab at UC Berkeley. scvi-tools has two components

    Interface for easy use of a range of probabilistic models for single-cell omics (e.g., scVI, scANVI, totalVI).

    Tools to build new probabilistic models, which are powered by PyTorch, PyTorch Lightning, and Pyro.

    If you find a model useful for your research, please consider citing the corresponding publication, which can be found in the corresponding model documentation.

  • Artemisia Gentileschi's 1616 nude to be digitally unveiled | AP News
  • 12 Weird Short Forms Of Popular Names That Make You Go "Huh?"
  • The Rise and Fall of AlphaBay, Part 1: The Shadow King — WIRED
    It was the largest online drug and crime bazaar in history, run by an elusive technological mastermind who seemed untouchable—until his tech was turned against him.
  • CLIM?TE DR?FT | Climate Career Resources for Tech Workers
    We recognize that many of you didn’t choose to be looking for work right now, let alone exploring a career in climate tech. We’re here to help you navigate the climate ecosystem, where the the skills and experiences you’ve developed while working at some of the world’s most important tech companies are in high demand. Climate Draft is a coalition of climate tech startups and VCs. Our mission is to expose more people to the inspiring, impactful, and lucrative opportunities at venture-backed startups focused on decarbonizing the global economy.
  • CLIM?TE DR?FT
    Mobilizing top talent to work on climate
    Learn about climate tech and connect with leading climate startups looking for advisors, investors, and team members.
  • How to Find Your Twitter Friends on Mastodon — WIRED
    If you’re pondering a move to the decentralized social network, here’s how to find the people you know and want to talk to.
  • Fifteen Ways to Share Your Joke After Twitter Implodes
  • What happened at Alameda Research
  • Everything Is Silicon Valley Now
    Because Elon Musk is so rich, his defects are everyone’s business. And because he owns Twitter, his bone-deep personal wackness is now everyone else’s problem.
  • U.S. Department of Health & Human Services – Office for Civil Rights
    As required by section 13402(e)(4) of the HITECH Act, the Secretary must post a list of breaches of unsecured protected health information affecting 500 or more individuals. The following breaches have been reported to the Secretary:

    Cases Currently Under Investigation
    This page lists all breaches reported within the last 24 months that are currently under investigation by the Office for Civil Rights.

  • You Might Go Through Hell for Your Post-Ozempic Body
    Patients describe constant nausea and vomiting. But doctors say everyone is asking for it.
  • Research | Research Laboratory for Machine Learning and Biomedical Data Analytics | Perelman School of Medicine at the University of Pennsylvania
    Our research focuses on the field of imaging analytics, machine learning, pattern recognition, and more generally in computational imaging. We have been focusing on both methodology development and applications of machine learning techniques that quantify morphology and function from medical images, integrate multimodal information to aid diagnosis and prediction of clinical outcomes, and guide personalized treatments.

    The methodological focus has been on the general field of artificial intelligence, with emphasis on machine learning methods applied to complex and large imaging and clinical data. The image analytic methods being and to be developed include functional connectomics, radiomics, image registration and segmentation, and personalized neuromodulatory therapies.

    On the clinical side, our primary focus is on applications in clinical neuroscience, in cancer, and in chronic kidney disease, aiming to develop precision diagnostic tools using machine learning and pattern recognition techniques. The clinical research studies include brain development, brain diseases such as Alzheimer’s, schizophrenia, depression, and addiction, pediatric kidney diseases, and predictive modeling of treatment outcomes of cancer patients such as rectal and lung cancers.

  • Allen Institute and Google team up to build platform exploring the immune system – GeekWire
    The Allen Institute for Immunology unveiled a new interactive platform on Wednesday to showcase the human immune system, the Human Immune System Explorer.

    Built in partnership with Google, the explorer is a central place for researchers and the public to find analysis tools, resources and data. The platform adds to the growing toolkit of similar resources across the Allen Institute, such as the Allen Cell Explorer and the Allen Brain Map.

    It’s also the first time the Allen Institute has leveraged Google’s cloud offerings like Vertex AI to build such a platform. Google’s team meets weekly with institute researchers. “They’ve just been deeply committed to working with people in the Allen Institute,” said Paul Meijer, director of software development, database and pipelines at the immunology institute.

  • PALMO (Platform for Analyzing Longitudinal Multi-omics data) R package
    A comprehensive platform to analyze multimodal longitudinal omics data is lacking. We present PALMO (https://github.com/aifimmunology/PALMO), a platform that analyzes longitudinal bulk and single-cell multi-omics data from multiple directions to extract biological insights. We demonstrate that PALMO can be used to decompose important data variations, identify variable, stable, or abnormal temporal behavior, discover genes that distinguish blood cell types, and reveal the heterogeneous nature of COVID-19 patient recovery.

Digest powered by RSS Digest