Machine Learning: Finding the right type of cell

A new method allows researchers to automatically assign cells into different cell types and tissues, a step which is critical for understanding complex organisms.
  1. Louis K Scheffer  Is a corresponding author
  1. Janelia Research Campus, HHMI, United States

Since the advent of microscopy in the 17th century, it has become well established that organisms are divided into tissues made up of different types of cells, with cells of the same type typically performing the same role. This simplifies the task of understanding a biological system immensely, as there are many fewer cell types than individual cells (Masland, 2001).

Categorizing tissues and cell types has always been done manually, usually by grouping cells that look the same based on their shape, internal structures and various other features. This is also true for images collected using modern day techniques, such as electron microscopy, which can provide three-dimensional reconstructions of tissue samples, or even entire small organisms less than a millimeter cube in size.

While electron microscopy images can be automatically subdivided or ‘segmented’ into individual cells, assigning each one to a cell type by hand is both difficult and time consuming; for example, in a recent project, it took several experts many months to categorize one half of the fruit fly brain (Scheffer et al., 2020). The whole task becomes even more challenging if the object being studied is not a well-known model organism. Now, in eLife, Valentyna Zinchenko, Johannes Hugger, Virginie Uhlmann Detlev Arendt and Anna Kreshuk of the European Molecular Biology Laboratory report a new method that could simplify this process (Zinchenko et al., 2023).

Zinchenko et al. based their program on a machine learning method called unsupervised, contrastive learning (van den Oord et al., 2018). The program works by grouping cell types without having received prior examples of ‘human-classified’ cell types or features (i.e., it is unsupervised) and by finding features that maximize the difference (or contrast) between examples that should be grouped together and those that should not. The method requires many examples, both of cells that should be grouped together, and those that should not. For the positive examples (those that should be grouped together), Zinchenko et al. created synthetic copies of each existing cell with minor modifications, such as different rotations, reflections, and texture or shape variations. In this case, the original cell and the modified cell should be grouped together. For negative examples (those that are of different types), they picked pairs of cells at random from their sample. This will be wrong occasionally but it is sufficiently accurate to train their model while allowing unsupervised operation.

Machine learning was then applied to find features shared by the positive examples only. The system combined the learned features of each original cell into a vector that summarizes the cell’s shape and texture. The team found that cells belonging to the same type were close together within the space of the vector, which can be visualized and interpreted by existing dimension reduction techniques (McInnes et al., 2018).

Zinchenko et al. then tested their model on a three-dimensional reconstruction of the annelid worm (Platynereis dumerilii) obtained through electron microscopy. Their computer model was able to match the different cell types and could identify subgroups of cells that could not be distinguished using human-specified features. Moreover, when compared to a gene expression map of the whole animal, the cells that had been classified as similar based on their features also shared similar genetic signatures, more so than cells that had previously been clustered using ‘human-designed’ features.

Next, they extended their classification method to consider both the shape and texture of each cell, and a combination of these features of all physically adjacent cells. Grouping these enhanced features revealed different tissues and organs within the animal. The classification system of the model strongly agreed with human results, but also found subtle tissue distinctions and rare features that had been overlooked by humans examining the same data set. For example, the analyses revealed a specific type of neuron in the midgut region of the worm, which had previously not been confirmed to be located in this area of the body.

The ‘unsupervised’ aspect of the method created by Zinchenko et al. is critical because it means the program does not require a full library of the relevant cell types (or a full list of the features that can distinguish between the cell types). Instead, the program learns these characteristics from the data itself (Figure 1). This is particularly useful for systems where the cell types are not known. Moreover, it is not restricted to using cell features that humans deem important, such as the roundness of a cell or the presence of dark vesicles. This means that the model can often outperform humans and work without bias, as it is not told what to expect and is thus less likely to overlook rare or unexpected cell types.

Making cell and tissue classification an automatic process.

Three-dimensional reconstructions of organisms using electron microscopy harbor a multitude of scientific data about cell composition and structure. Zinchenko et al. created a machine learning system that can identify different features to distinguish one cell type from another. Since these features are learned, they do not necessarily correspond to human terms commonly used to describe the shape or texture of cells (such as rounded or speckled). The above images show cells with the best and worst match to two learned features, which can then be used to determine which aspect of the cell the feature corresponds to, such as texture (top) or shape (bottom).

Image credit: Adapted from Figure 3, Zinchenko et al., 2023 (CC BY 4.0).

Electron microscopy and related techniques provide an incredible level of detail, including the shape, location and structure of every cell. But analyzing this flood of data by hand is nearly impossible and automated techniques are desperately needed to unlock the potential of these findings (Eberle and Zeidler, 2018). Significant progress has already been made in turning some tasks, such as cell segmentation and identifying synapses, into automatic processes, leaving cell and tissue identification as some of the most time-consuming manual steps (Januszewski et al., 2018; Huang et al., 2018). By helping to automate this step, Zinchenko et al. make a critical step in the journey of understanding these invaluable but intimidating data sets.

References

Article and author information

Author details

  1. Louis K Scheffer

    Louis K Scheffer is in the Janelia Research Campus, HHMI, Ashburn, United States

    For correspondence
    schefferl@janelia.hhmi.org
    Competing interests
    No competing interests declared
    ORCID icon "This ORCID iD identifies the author of this article:" 0000-0002-3289-6564

Publication history

  1. Version of Record published: February 16, 2023 (version 1)

Copyright

© 2023, Scheffer

This article is distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use and redistribution provided that the original author and source are credited.

Metrics

  • 1,355
    views
  • 77
    downloads
  • 0
    citations

Views, downloads and citations are aggregated across all versions of this paper published by eLife.

Download links

A two-part list of links to download the article, or parts of the article, in various formats.

Downloads (link to download the article as PDF)

Open citations (links to open the citations from this article in various online reference manager services)

Cite this article (links to download the citations from this article in formats compatible with various reference manager tools)

  1. Louis K Scheffer
(2023)
Machine Learning: Finding the right type of cell
eLife 12:e86172.
https://doi.org/10.7554/eLife.86172

Further reading

    1. Computational and Systems Biology
    Hedi Chen, Xiaoyu Fan ... Boxue Tian
    Research Article

    Accurate prediction of the structurally diverse complementarity determining region heavy chain 3 (CDR-H3) loop structure remains a primary and long-standing challenge for antibody modeling. Here, we present the H3-OPT toolkit for predicting the 3D structures of monoclonal antibodies and nanobodies. H3-OPT combines the strengths of AlphaFold2 with a pre-trained protein language model and provides a 2.24 Å average RMSD between predicted and experimentally determined CDR-H3 loops, thus outperforming other current computational methods in our non-redundant high-quality dataset. The model was validated by experimentally solving three structures of anti-VEGF nanobodies predicted by H3-OPT. We examined the potential applications of H3-OPT through analyzing antibody surface properties and antibody–antigen interactions. This structural prediction tool can be used to optimize antibody–antigen binding and engineer therapeutic antibodies with biophysical properties for specialized drug administration route.

    1. Computational and Systems Biology
    2. Medicine
    Zachary Shaffer, Roberto Romero ... Nardhy Gomez-Lopez
    Research Article

    Background:

    Preterm birth is the leading cause of neonatal morbidity and mortality worldwide. Most cases of preterm birth occur spontaneously and result from preterm labor with intact (spontaneous preterm labor [sPTL]) or ruptured (preterm prelabor rupture of membranes [PPROM]) membranes. The prediction of spontaneous preterm birth (sPTB) remains underpowered due to its syndromic nature and the dearth of independent analyses of the vaginal host immune response. Thus, we conducted the largest longitudinal investigation targeting vaginal immune mediators, referred to herein as the immunoproteome, in a population at high risk for sPTB.

    Methods:

    Vaginal swabs were collected across gestation from pregnant women who ultimately underwent term birth, sPTL, or PPROM. Cytokines, chemokines, growth factors, and antimicrobial peptides in the samples were quantified via specific and sensitive immunoassays. Predictive models were constructed from immune mediator concentrations.

    Results:

    Throughout uncomplicated gestation, the vaginal immunoproteome harbors a cytokine network with a homeostatic profile. Yet, the vaginal immunoproteome is skewed toward a pro-inflammatory state in pregnant women who ultimately experience sPTL and PPROM. Such an inflammatory profile includes increased monocyte chemoattractants, cytokines indicative of macrophage and T-cell activation, and reduced antimicrobial proteins/peptides. The vaginal immunoproteome has improved predictive value over maternal characteristics alone for identifying women at risk for early (<34 weeks) sPTB.

    Conclusions:

    The vaginal immunoproteome undergoes homeostatic changes throughout gestation and deviations from this shift are associated with sPTB. Furthermore, the vaginal immunoproteome can be leveraged as a potential biomarker for early sPTB, a subset of sPTB associated with extremely adverse neonatal outcomes.

    Funding:

    This research was conducted by the Perinatology Research Branch, Division of Obstetrics and Maternal-Fetal Medicine, Division of Intramural Research, Eunice Kennedy Shriver National Institute of Child Health and Human Development, National Institutes of Health, U.S. Department of Health and Human Services (NICHD/NIH/DHHS) under contract HHSN275201300006C. ALT, KRT, and NGL were supported by the Wayne State University Perinatal Initiative in Maternal, Perinatal and Child Health.