This paper presents FlowCyt, the first comprehensive benchmark for multi-class single-cell classification in flow cytometry data. The dataset comprises bone marrow samples from 30 patients, with each cell characterized by twelve markers. Ground truth labels identify five hematological cell types: T lymphocytes, B lymphocytes, Monocytes, Mast cells, and Hematopoietic Stem/Progenitor Cells (HSPCs). Experiments utilize supervised inductive learning and semi-supervised transductive learning on up to 1 million cells per patient. Baseline methods include Gaussian Mixture Models, XGBoost, Random Forests, Deep Neural Networks, and Graph Neural Networks (GNNs). GNNs demonstrate superior performance by exploiting spatial relationships in graph-encoded data. The benchmark allows standardized evaluation of clinically relevant classification tasks, along with exploratory analyses to gain insights into hematological cell phenotypes. This represents the first public flow cytometry benchmark with a richly annotated, heterogeneous dataset. It will empower the development and rigorous assessment of novel methodologies for single-cell analysis.

Flow cytometry mainly used for detecting the characteristics of a number of biochemical substances based on the expression of specific markers in cells. It is particularly useful for detecting membrane surface receptors, antigens, ions, or during DNA/RNA expression. Not only can it be employed as a biomedical research tool for recognising distinctive types of cells in mixed populations, but it can also be used as a diagnostic tool for classifying abnormal cell populations connected with disease. Modern flow cytometers can rapidly analyse tens of thousands of cells at the same time while also measuring multiple parameters from a single cell. However, the rapid development of flow cytometers makes it challenging for conventional analysis methods to interpret flow cytometry data. Researchers need to be able to distinguish interesting-looking cell populations manually in multi-dimensional data collected from millions of cells. Thus, it is essential to find a robust approach for analysing flow cytometry data automatically, specifically in identifying cell populations automatically. This thesis mainly concerns discover the potential shortcoming of current automated-gating algorithms in both real datasets and synthetic datasets. Three representative automated clustering algorithms are selected to be applied, compared and evaluated by completely and partially automated gating. A subspace clustering ProClus also implemented in this thesis. The performance of ProClus in flow cytometry is not well, but it is still a useful algorithm to detect noise.

High dimensional (HD) cytometry, a technique that takes measurements of many features of a single blood cell simultaneously, generates so much data that it is difficult for people to parse through. "We think that HD cytometry can be particularly useful in understanding COVID-19," says Irish. The quickly developing trial will begin treating 19 patients the week of May 31, 2020, and begin collecting samples. Irish's role will be to analyze and interpret the findings. In rhinovirus, Irish's tool analyzes pairs of blood cells, one infected and the other not, to compare specific changes to the blood and identify immune cells that are reacting to the virus.

Data used in Flow Cytometry present pronounced variability due to biological and technical reasons. Biological variability is a well known phenomenon produced by measurements on different individuals, with different characteristics such as age, sex, etc... The use of different settings for measurement, the variation of the conditions during experiments or the different types of flow cytometers are some of the technical sources of variability. This high variability makes difficult the use of supervised machine learning for identification of cell populations. We propose optimalFlowTemplates, based on a similarity distance and Wasserstein barycenters, which clusterizes cytometries and produces prototype cytometries for the different groups. We show that supervised learning restricted to the new groups performs better than the same techniques applied to the whole collection. We also present optimalFlowClassification, which uses a database of gated cytometries and optimalFlowTemplates to assign cell types to a new cytometry. We show that this procedure can outperform state of the art techniques in the proposed datasets. Our code and data are freely available as R packages at https://github.com/HristoInouzhe/optimalFlow and https://github.com/HristoInouzhe/optimalFlowData.

Di Carlo et al. comment that our original results were insufficient to prove that the ghost cytometry technique is performing a morphologic analysis of cells in flow. We emphasize that the technique is primarily intended to acquire and classify morphological information of cells in a computationally efficient manner without reconstructing images. We provide additional supporting information, including images reconstructed from the compressive waveforms and a discussion of current and future throughput potentials. Ghost cytometry (GC) performs a direct analysis of compressive imaging waveforms and thereby substantially relieves the computational bottleneck hindering the realization of high-throughput cytometry based on morphological information (1). The comments by Di Carlo et al. argue against a number of our conclusions (2), but given the restricted length allowed for this response, we will address what we consider the most important points.

Ghost imaging was first observed with entangled photon pairs and viewed as a quantum phenomenon [1]. It acquires object information through the correlation calculations of the lightintensity fluctuations of two beams: object and reference [2, 3]. The object beam passes through the object and is detected using a single-pixel detector, and the reference beam does not interact with the object and is recorded using a multi-pixel detector with spatial resolution. It was experimentally demonstrated that ghost imaging can be achieved using only a single detector [4]. Computational ghost imaging is an imaging technique with which an object is imaged from light collected using a single-pixel detector with no spatial resolution [5, 6]. By replacing reference-beam measurements, it only requires a single-pixel detector, which simplifies the experiments in comparison to traditional two-detector ghost imaging. Using the signals and illumination pattern enables us to computationally reconstruct cell images. Let T (x, y) be a transmission function of an object. An object is illuminated by a speckle field generated by passing a laser beam through an optical diffuser, which is a material that diffuses light to transmit light.

Ghost imaging is a technique used to produce an object's image without using a spatially resolving detector. Here we develop a technique we term "ghost cytometry," an image-free ultrafast fluorescence "imaging" cytometry based on a single-pixel detector. Spatial information obtained from the motion of cells relative to a static randomly patterned optical structure is compressively converted into signals that arrive sequentially at a single-pixel detector. Combinatorial use of the temporal waveform with the intensity distribution of the random pattern allows us to computationally reconstruct cell morphology. More importantly, we show that applying machine-learning methods directly on the compressed waveforms without image reconstruction enables efficient image-free morphology-based cytometry.

Analysis of flow cytometry data is an essential tool for clinical diagnosis of hematological and immunological conditions. Current clinical workflows rely on a manual process called gating to classify cells into their canonical types. This dependence on human annotation limits the rate, reproducibility, and complexity of flow cytometry analysis. In this paper, we propose using Mondrian processes to perform automated gating by incorporating prior information of the kind used by gating technicians. The method segments cells into types via Bayesian nonparametric trees. Examining the posterior over trees allows for interpretable visualizations and uncertainty quantification - two vital qualities for implementation in clinical practice.