1
|
Van Veen D, Galaz-Montoya JG, Shen L, Baldwin P, Chaudhari AS, Lyumkis D, Schmid MF, Chiu W, Pauly J. Missing Wedge Completion via Unsupervised Learning with Coordinate Networks. Int J Mol Sci 2024; 25:5473. [PMID: 38791508 PMCID: PMC11121946 DOI: 10.3390/ijms25105473] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/10/2024] [Revised: 04/29/2024] [Accepted: 04/30/2024] [Indexed: 05/26/2024] Open
Abstract
Cryogenic electron tomography (cryoET) is a powerful tool in structural biology, enabling detailed 3D imaging of biological specimens at a resolution of nanometers. Despite its potential, cryoET faces challenges such as the missing wedge problem, which limits reconstruction quality due to incomplete data collection angles. Recently, supervised deep learning methods leveraging convolutional neural networks (CNNs) have considerably addressed this issue; however, their pretraining requirements render them susceptible to inaccuracies and artifacts, particularly when representative training data is scarce. To overcome these limitations, we introduce a proof-of-concept unsupervised learning approach using coordinate networks (CNs) that optimizes network weights directly against input projections. This eliminates the need for pretraining, reducing reconstruction runtime by 3-20× compared to supervised methods. Our in silico results show improved shape completion and reduction of missing wedge artifacts, assessed through several voxel-based image quality metrics in real space and a novel directional Fourier Shell Correlation (FSC) metric. Our study illuminates benefits and considerations of both supervised and unsupervised approaches, guiding the development of improved reconstruction strategies.
Collapse
Affiliation(s)
- Dave Van Veen
- Department of Electrical Engineering, Stanford University, Stanford, CA 94305, USA;
| | - Jesús G. Galaz-Montoya
- Department of Bioengineering, Stanford University, Stanford, CA 94305, USA; (J.G.G.-M.); (W.C.)
| | - Liyue Shen
- Department of Electrical and Computer Engineering, University of Michigan, Ann Arbor, MI 48109, USA;
| | - Philip Baldwin
- Department of Biochemistry and Molecular Pharmacology, Baylor College of Medicine, Houston, TX 77030, USA;
- Department of Genetics, The Salk Institute of Biological Sciences, La Jolla, CA 92037, USA;
| | | | - Dmitry Lyumkis
- Department of Genetics, The Salk Institute of Biological Sciences, La Jolla, CA 92037, USA;
- Graduate School of Biological Sciences, University of California San Diego, La Jolla, CA 92037, USA
| | - Michael F. Schmid
- Division of CryoEM and Bioimaging, SSRL, SLAC National Accelerator Laboratory, Menlo Park, CA 94025, USA;
| | - Wah Chiu
- Department of Bioengineering, Stanford University, Stanford, CA 94305, USA; (J.G.G.-M.); (W.C.)
- Division of CryoEM and Bioimaging, SSRL, SLAC National Accelerator Laboratory, Menlo Park, CA 94025, USA;
- Department of Microbiology and Immunology, Stanford University School of Medicine, Stanford, CA 94305, USA
| | - John Pauly
- Department of Electrical Engineering, Stanford University, Stanford, CA 94305, USA;
| |
Collapse
|
2
|
Van Veen D, Galaz-Montoya JG, Shen L, Baldwin P, Chaudhari AS, Lyumkis D, Schmid MF, Chiu W, Pauly J. Missing Wedge Completion via Unsupervised Learning with Coordinate Networks. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2024:2024.04.12.589090. [PMID: 38712113 PMCID: PMC11071277 DOI: 10.1101/2024.04.12.589090] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/08/2024]
Abstract
Cryogenic electron tomography (cryoET) is a powerful tool in structural biology, enabling detailed 3D imaging of biological specimens at a resolution of nanometers. Despite its potential, cryoET faces challenges such as the missing wedge problem, which limits reconstruction quality due to incomplete data collection angles. Recently, supervised deep learning methods leveraging convolutional neural networks (CNNs) have considerably addressed this issue; however, their pretraining requirements render them susceptible to inaccuracies and artifacts, particularly when representative training data is scarce. To overcome these limitations, we introduce a proof-of-concept unsupervised learning approach using coordinate networks (CNs) that optimizes network weights directly against input projections. This eliminates the need for pretraining, reducing reconstruction runtime by 3 - 20× compared to supervised methods. Our in silico results show improved shape completion and reduction of missing wedge artifacts, assessed through several voxel-based image quality metrics in real space and a novel directional Fourier Shell Correlation (FSC) metric. Our study illuminates benefits and considerations of both supervised and unsupervised approaches, guiding the development of improved reconstruction strategies.
Collapse
Affiliation(s)
- Dave Van Veen
- Dept. of Electrical Engineering, Stanford University
| | | | - Liyue Shen
- Dept. of Electrical and Computer Engineering, University of Michigan
| | - Philip Baldwin
- Dept. of Biochemistry and Molecular Pharmacology, Baylor College of Medicine
- Dept. of Genetics, The Salk Institute for Biological Sciences
| | | | - Dmitry Lyumkis
- Dept. of Genetics, The Salk Institute for Biological Sciences
- Graduate School of Biological Sciences, University of California San Diego
| | - Michael F. Schmid
- Division of CryoEM and Bioimaging, SSRL, SLAC National Accelerator Laboratory
| | - Wah Chiu
- Dept. of Bioengineering, Stanford University
- Division of CryoEM and Bioimaging, SSRL, SLAC National Accelerator Laboratory
- Dept. of Microbiology and Immunology, Stanford University
| | - John Pauly
- Dept. of Electrical Engineering, Stanford University
| |
Collapse
|
3
|
Trivanović D, Mojsilović S, Bogosavljević N, Jurišić V, Jauković A. Revealing profile of cancer-educated platelets and their factors to foster immunotherapy development. Transl Oncol 2024; 40:101871. [PMID: 38134841 PMCID: PMC10776659 DOI: 10.1016/j.tranon.2023.101871] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2023] [Revised: 12/03/2023] [Accepted: 12/15/2023] [Indexed: 12/24/2023] Open
Abstract
Among multiple hemostasis components, platelets hyperactivity plays major roles in cancer progression by providing surface and internal components for intercellular crosstalk as well as by behaving like immune cells. Since platelets participate and regulate immunity in homeostatic and disease states, we assumed that revealing platelets profile might help in conceiving novel anti-cancer immune-based strategies. The goal of this review is to compile and discuss the most recent reports on the nature of cancer-associated platelets and their interference with immunotherapy. An increasing number of studies have emphasized active communication between cancer cells and platelets, with platelets promoting cancer cell survival, growth, and metastasis. The anti-cancer potential of platelet-directed therapy has been intensively investigated, and anti-platelet agents may prevent cancer progression and improve the survival of cancer patients. Platelets can (i) reduce antitumor activity; (ii) support immunoregulatory cells and factors generation; (iii) underpin metastasis and, (iv) interfere with immunotherapy by expressing ligands of immune checkpoint receptors. Mediators produced by tumor cell-induced platelet activation support vein thrombosis, constrain anti-tumor T- and natural killer cell response, while contributing to extravasation of tumor cells, metastatic potential, and neovascularization within the tumor. Recent studies showed that attenuation of immunothrombosis, modulation of platelets and their factors have a good perspective in immunotherapy optimization. Particularly, blockade of intra-tumoral platelet-associated programmed death-ligand 1 might promote anti-tumor T cell-induced cytotoxicity. Collectively, these findings suggest that platelets might represent the source of relevant cancer staging biomarkers, as well as promising targets and carriers in immunotherapeutic approaches for combating cancer.
Collapse
Affiliation(s)
- Drenka Trivanović
- Group for Hematology and Stem Cells, Institute for Medical Research, National Institute of Republic of Serbia, University of Belgrade, Dr. Subotica 4, PBOX 102, 11129, Belgrade 11000, Serbia.
| | - Slavko Mojsilović
- Group for Hematology and Stem Cells, Institute for Medical Research, National Institute of Republic of Serbia, University of Belgrade, Dr. Subotica 4, PBOX 102, 11129, Belgrade 11000, Serbia
| | | | - Vladimir Jurišić
- Faculty of Medical Sciences, University of Kragujevac, Kragujevac 34000, Serbia
| | - Aleksandra Jauković
- Group for Hematology and Stem Cells, Institute for Medical Research, National Institute of Republic of Serbia, University of Belgrade, Dr. Subotica 4, PBOX 102, 11129, Belgrade 11000, Serbia
| |
Collapse
|
4
|
Chang ML, Erwin AL, Mosalaganti S. Image Processing Pipeline for In Situ Structural Characterization of Filaments. MICROSCOPY AND MICROANALYSIS : THE OFFICIAL JOURNAL OF MICROSCOPY SOCIETY OF AMERICA, MICROBEAM ANALYSIS SOCIETY, MICROSCOPICAL SOCIETY OF CANADA 2023; 29:952-953. [PMID: 37613656 DOI: 10.1093/micmic/ozad067.475] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 08/25/2023]
Affiliation(s)
- Matthew L Chang
- Life Sciences Institute, University of Michigan, Ann Arbor, Michigan, United States
- Department of Biomedical Engineering, University of Michigan, Ann Arbor, Michigan, United States
| | - Amanda L Erwin
- Life Sciences Institute, University of Michigan, Ann Arbor, Michigan, United States
- Departments of Cell and Developmental Biology and Biological Chemistry, University of Michigan Medical School, Ann Arbor, Michigan, United States
| | - Shyamal Mosalaganti
- Life Sciences Institute, University of Michigan, Ann Arbor, Michigan, United States
- Departments of Cell and Developmental Biology and Biological Chemistry, University of Michigan Medical School, Ann Arbor, Michigan, United States
- Department of Biophysics, University of Michigan, Ann Arbor, Michigan, United States
| |
Collapse
|