CZII’s particle picking machine learning challenge is up and running. There are already 1000 signups on Kaggle. Follow this page for an introduction and links to all sorts of material and resources, including two preprints: cryoetdataportal.czscience.c…
Annotating CryoET Volumes: A Machine Learning Challenge
1. This study tackles a major bottleneck in cryo-electron tomography (cryoET)—the challenging and time-consuming process of annotating 3D cellular volumes. To address this, the authors introduced a machine learning challenge to drive innovation in automated particle labeling for cryoET datasets.
2. A key innovation is the creation of a “phantom” sample that mimics the cellular environment, allowing for the generation of high-quality ground truth annotations. This approach provides a diverse dataset that includes various protein complexes, each with distinct shapes and sizes, to train and benchmark machine learning algorithms.
3. The challenge aims to foster collaboration between cryoET and ML experts. By creating a standardized, annotated dataset, the authors hope to push the limits of current particle-picking algorithms, making the annotation of cellular tomograms more efficient and accurate.
4. The dataset, available on the CryoET Data Portal, consists of 492 tomograms featuring six distinct particle types. The dataset serves as a resource for participants to develop ML models capable of recognizing multiple protein classes across various cellular environments.
5. The evaluation metric for the challenge prioritizes models that can accurately label smaller particles, with weighted scoring emphasizing hard-to-detect particles. This is crucial for advancing the accuracy and reliability of cryoET analyses in biological research.
6. The study highlights several newly developed tools, including DenoisET, Copick, and DeepFindET, which enhance cryoET data processing and annotation. These tools were instrumental in curating the phantom dataset and are open to the community for further cryoET advancements.
7. The authors anticipate that this challenge will serve as the foundation for future contests, aiming to solve more complex annotation problems, such as distinguishing particles in crowded cellular environments and labeling membrane-bound proteins.
@kisharrington@bcarra2@DanielSerwas@emontabana@kimanius
📜Paper: biorxiv.org/content/10.1101/…#CryoET#MachineLearning#StructuralBiology#Bioinformatics#MLChallenge#ProteinAnnotation#CellBiology
I am at Photonics West till Monday. Please let me know if I should come to your talk or poster, especially if you may be interested in openings at @czbiohub.
I just gave an invited talk (spie.org/PW24B/conferencedet…) on our recently preprinted work (x.com/czbiohub/status/173757…).
Introducing Mantis, a two-in-one microscope designed at #CZBiohubSF that enables rapid high-dimensional imaging of molecular dynamics in the context of cell morphology. 🧵1/7
Preprint: ⬇️
biorxiv.org/content/10.1101/…
I am excited to share that I will start my lab at the Chan Zuckerberg Imaging Institute in Jan 2024! Happy to talk to anyone who's interested in applying cryo-ET, FLIM, and other imaging modalities to study the structure and function of primary cilia in neurons and beyond!
The @DammermannLab is looking for a highly motivated Master’s student with a solid background in molecular and cell biology. Previous experience with C. elegans would be an asset but is not essential.
➡️Read more and apply: tinyurl.com/57c6vum5#sciencejobs@univienna
Thrilled to announce that I started a new position at the Chan Zuckerberg Imaging Institute (Chan Zuckerberg Biohub Network)! I look forward to the incredible research endeavors ahead.
I am attending my first in-person symposium since Jan 2020: #BAMPS2022@UCSF. Looking forward to give my presentation on a novel method: multicolor organelle flow #MCOF. Stay tuned!
If you are a Ukrainian citizen and would like to look for a position in the field of proteomics, mass spectrometry or (bio)informatics in Vienna funded by us, you can contact me at any time. I would be happy if this content can be shared.
🚨 New pre-print on (perhaps) the largest proteinaceous organelle: the phage nucleus!. A cumulative effort of labs across @UCSD 1/n
biorxiv.org/content/10.1101/…
On the way back to SF my husband and I were debating if we should pull our kid out of daycare due to the recent surge. The decision was made for us with one case in our daycare. Comes at a great time as we both have papers to finish and faculty positions to apply for…@Momademia
I started this poll after two conversations with different academic parents who told me that kids don’t get sick and there is nothing to worry about. Thank you twitter for showing me that others share my fears. Helped to keep me sane. @Momademia
As we hear that there will be no vaccines for <5 year olds soon I am curious how worried you are if you would be/are a parent of a kid 0-5 years with omicron around the corner. Ranging from: not worried - kids do not get severe disease, to: minimizing contacts and isolating.
Last #cellbio2021 poster discussion session will be today. We combined in situ cryo-electron tomography and mathematical modeling to study actin function in endocytosis. If you want to hear more, come to my poster! @MatthewAkamatsu @DavidGDrubin @RangamaniUCSD.