Trang Le

All Publications

• Segmenting functional tissue units across human organs using community-driven development of generalizable machine learning algorithms. Nature communications Jain, Y., Godwin, L. L., Joshi, S., Mandarapu, S., Le, T., Lindskog, C., Lundberg, E., Börner, K. 2023; 14 (1): 4656

  Abstract

  The development of a reference atlas of the healthy human body requires automated image segmentation of major anatomical structures across multiple organs based on spatial bioimages generated from various sources with differences in sample preparation. We present the setup and results of the Hacking the Human Body machine learning algorithm development competition hosted by the Human Biomolecular Atlas (HuBMAP) and the Human Protein Atlas (HPA) teams on the Kaggle platform. We create a dataset containing 880 histology images with 12,901 segmented structures, engaging 1175 teams from 78 countries in community-driven, open-science development of machine learning models. Tissue variations in the dataset pose a major challenge to the teams which they overcome by using color normalization techniques and combining vision transformers with convolutional models. The best model will be productized in the HuBMAP portal to process tissue image datasets at scale in support of Human Reference Atlas construction.

  View details for DOI 10.1038/s41467-023-40291-0

  View details for PubMedID 37537179

  View details for PubMedCentralID 10079270

• Segmenting functional tissue units across human organs using community-driven development of generalizable machine learning algorithms. bioRxiv : the preprint server for biology Jain, Y., Godwin, L. L., Joshi, S., Mandarapu, S., Le, T., Lindskog, C., Lundberg, E., Borner, K. 2023

  Abstract

  The development of a reference atlas of the healthy human body requires automated image segmentation of major anatomical structures across multiple organs based on spatial bioimages generated from various sources with differences in sample preparation. We present the setup and results of the "Hacking the Human Body" machine learning algorithm development competition hosted by the Human Biomolecular Atlas (HuBMAP) and the Human Protein Atlas (HPA) teams on the Kaggle platform. We showcase how 1,175 teams from 78 countries engaged in community- driven, open-science code development that resulted in machine learning models which successfully segment anatomical structures across five organs using histology images from two consortia and that will be productized in the HuBMAP data portal to process large datasets at scale in support of Human Reference Atlas construction. We discuss the benchmark data created for the competition, major challenges faced by the participants, and the winning models and strategies.

  View details for DOI 10.1101/2023.01.05.522764

  View details for PubMedID 36711953

• Analysis of the Human Protein Atlas Weakly Supervised Single-Cell Classification competition. Nature methods Le, T., Winsnes, C. F., Axelsson, U., Xu, H., Mohanakrishnan Kaimal, J., Mahdessian, D., Dai, S., Makarov, I. S., Ostankovich, V., Xu, Y., Benhamou, E., Henkel, C., Solovyev, R. A., Banić, N., Bošnjak, V., Bošnjak, A., Miličević, A., Ouyang, W., Lundberg, E. 2022

  Abstract

  While spatial proteomics by fluorescence imaging has quickly become an essential discovery tool for researchers, fast and scalable methods to classify and embed single-cell protein distributions in such images are lacking. Here, we present the design and analysis of the results from the competition Human Protein Atlas - Single-Cell Classification hosted on the Kaggle platform. This represents a crowd-sourced competition to develop machine learning models trained on limited annotations to label single-cell protein patterns in fluorescent images. The particular challenges of this competition include class imbalance, weak labels and multi-label classification, prompting competitors to apply a wide range of approaches in their solutions. The winning models serve as the first subcellular omics tools that can annotate single-cell locations, extract single-cell features and capture cellular dynamics.

  View details for DOI 10.1038/s41592-022-01606-z

  View details for PubMedID 36175767

• Spatiotemporal dissection of the cell cycle with single-cell proteogenomics. Nature Mahdessian, D., Cesnik, A. J., Gnann, C., Danielsson, F., Stenstrom, L., Arif, M., Zhang, C., Le, T., Johansson, F., Shutten, R., Backstrom, A., Axelsson, U., Thul, P., Cho, N. H., Carja, O., Uhlen, M., Mardinoglu, A., Stadler, C., Lindskog, C., Ayoglu, B., Leonetti, M. D., Ponten, F., Sullivan, D. P., Lundberg, E. 2021; 590 (7847): 649–54

  Abstract

  The cell cycle, over which cells grow and divide, is a fundamental process of life. Its dysregulation has devastating consequences, including cancer1-3. The cell cycle is driven by precise regulation of proteins in time and space, which creates variability between individual proliferating cells. To our knowledge, no systematic investigations of such cell-to-cell proteomic variability exist. Here we present a comprehensive, spatiotemporal map of human proteomic heterogeneity by integrating proteomics at subcellular resolution with single-cell transcriptomics and precise temporal measurements of individual cells in the cell cycle. We show that around one-fifth of the human proteome displays cell-to-cell variability, identify hundreds of proteins with previously unknown associations with mitosis and the cell cycle, and provide evidence that several of these proteins have oncogenic functions. Our results show that cell cycle progression explains less than half of all cell-to-cell variability, and that most cycling proteins are regulated post-translationally, rather than by transcriptomic cycling. These proteins are disproportionately phosphorylated by kinases that regulate cell fate, whereas non-cycling proteins that vary between cells are more likely to be modified by kinases that regulate metabolism. This spatially resolved proteomic map of the cell cycle is integrated into the Human Protein Atlas and will serve as a resource for accelerating molecular studies of the human cell cycle and cell proliferation.

  View details for DOI 10.1038/s41586-021-03232-9

  View details for PubMedID 33627808

• Individual variations in cardiovascular-disease-related protein levels are driven by genetics and gut microbiome NATURE GENETICS Zhernakova, D., Le, T. H., Kurilshikov, A., Atanasovska, B., Bonder, M., Sanna, S., Claringbould, A., Vosa, U., Deelen, P., Studys, L., Bios, C., Franke, L., de Boer, R. A., Kuipers, F., Netea, M. G., Hofker, M. H., Wijmenga, C., Zhernakova, A., Fu, J. 2018; 50 (11): 1524-+

  Abstract

  Despite a growing body of evidence, the role of the gut microbiome in cardiovascular diseases is still unclear. Here, we present a systems-genome-wide and metagenome-wide association study on plasma concentrations of 92 cardiovascular-disease-related proteins in the population cohort LifeLines-DEEP. We identified genetic components for 73 proteins and microbial associations for 41 proteins, of which 31 were associated to both. The genetic and microbial factors identified mostly exert additive effects and collectively explain up to 76.6% of inter-individual variation (17.5% on average). Genetics contribute most to concentrations of immune-related proteins, while the gut microbiome contributes most to proteins involved in metabolism and intestinal health. We found several host-microbe interactions that impact proteins involved in epithelial function, lipid metabolism, and central nervous system function. This study provides important evidence for a joint genetic and microbial effect in cardiovascular disease and provides directions for future applications in personalized medicine.

  View details for DOI 10.1038/s41588-018-0224-7

  View details for Web of Science ID 000448398000008

  View details for PubMedID 30250126

  View details for PubMedCentralID PMC6241851