In view of the outstanding progress of machine learning (ML) and growing cost of health systems, it is a current challenge to incorporate artificial intelligence tools into actual medical practice. Here we explored the feasibility and reliability of using machine learning to perform an important immunological investigation that currently requires experienced biologists : Anti-nuclear cytoplasmic antibodies (ANCAs) are important markers for vasculitis and they may be evidenced by microscopic examination of cells labeled with patients' sera. The use of a reliable ML classifier to discriminate between positive and negative samples would increase the rapidity and decrease the cost of immunofluorescence-based ANCA detection. Here, we tested seven well-documented ML algorithms, ranging from simple models such as decision trees to more complex convolutional neural networks involving millions of adjustable parameter. We studied the feasibility and reliability of classifying 1114 serum samples that had been collected for about 3 years and assayed with conventional procedure. We compared four strategies consisting of assaying either whole microscope fields or individual cell images, and natural images or histograms. The following conclusions were obtained : (i) Several different strategies allowed us to build models stable enough to discriminate between positive and negative samples collected during about 27 months, with a comparison to human classification yielding a kappa index of about 0.7, that may be considered as fairly good and intermediate between the performance of junior and senior biologists. (ii) Task-specific ML models combined with theoretical thinking might provide the most rapid and efficient way of developing a reliable test within the framework of a single institution. (iii) In addition, the interpretability of the simplest model provided some theoretical insight into important classification parameters. (iv) An important point and caveat is that the multiplicity and versatility of currently available tools make it an essential requirement to test repeatedly a given model, that must be chosen as simple as possible, to achieve a reliability compatible with medical use. It is concluded that our study provides a strong incentive to incorporate task-specific ML tools in well defined medical tests, which might reduce the risk of human errors and pave the way to fully automatic procedures.

Elucidation of the mechanisms by which T-cells discriminate between self and foreign antigens has been a major challenge in immunology. In this issue of The EMBO Journal, Huhn and colleagues (Huhn et al, 2025) show that the affinity between soluble antigens and the widely-studied OT-I T-cell receptor is a good predictor of T-cell activation potency, which was previously thought to be determined by complex properties of the interactions between surface-bound antigens and receptors. A new study in The EMBO Journal provides new insights into T-cell activation potency upon receptor-antigen interaction.

During the last decade, artificial intelligence (AI) was applied to nearly all domains of human activity, including scientific research. It is thus warranted to ask whether AI thinking should be durably involved in biomedical research. This problem was addressed by examining three complementary questions (i) What are the major barriers currently met by biomedical investigators? It is suggested that during the last 2 decades there was a shift towards a growing need to elucidate complex systems, and that this was not sufficiently fulfilled by previously successful methods such as theoretical modeling or computer simulation (ii) What is the potential of AI to meet the aforementioned need? it is suggested that recent AI methods are well-suited to perform classification and prediction tasks on multivariate systems, and possibly help in data interpretation, provided their efficiency is properly validated. (iii) Recent representative results obtained with machine learning suggest that AI efficiency may be comparable to that displayed by human operators. It is concluded that AI should durably play an important role in biomedical practice. Also, as already suggested in other scientific domains such as physics, combining AI with conventional methods might generate further progress and new applications, involving heuristic and data interpretation.

The success of artificial intelligence and machine learning is an incentive to develop new algorithms to increase the rapidity and reliability of medical diagnosis. Here we compared different strategies aimed at processing microscope images used to detect anti-neutrophil cytoplasmic antibodies, an important vasculitis marker: (i) basic classifier methods (logistic regression, k-nearest neighbors and decision tree) were used to process custom-made indices derived from immunofluorescence images yielded by 137 sera. (ii) These methods were combined with dimensional reduction to analyze 1733 individual cell images. (iii) More complex models based on neural networks were used to analyze the same dataset. The efficiency of discriminating between positive and negative samples and different fluorescence patterns was quantified with Rand-type accuracy index, kappa index and ROC curve. It is concluded that basic models trained on a limited dataset allowed for positive/negative discrimination with an efficiency comparable to that obtained by conventional analysis performed by humans (0.84 kappa score). More extensive datasets and more sophisticated models may be required for efficient discrimination between fluorescence patterns generated by different auto-antibody species.

Cell biologists have long aimed at quantitatively modeling cell function. Recently, the outstanding progress of high-throughput measurement methods and data processing tools has made this a realistic goal. The aim of this paper is twofold: First, to suggest that, while much progress has been done in modeling cell states and transitions, current accounts of environmental cues driving these transitions remain insufficient. There is a need to provide an integrated view of the biochemical, topographical and mechanical information processed by cells to take decisions. It might be rewarding in the near future to try to connect cell environmental cues to physiologically relevant outcomes rather than modeling relationships between these cues and internal signaling networks. The second aim of this paper is to review exogenous signals that are sensed by living cells and significantly influence fate decisions. Indeed, in addition to the composition of the surrounding medium, cells are highly sensitive to the properties of neighboring surfaces, including the spatial organization of anchored molecules and substrate mechanical and topographical properties. These properties should thus be included in models of cell behavior. It is also suggested that attempts at cell modeling could strongly benefit from two research lines: (i) trying to decipher the way cells encode the information they retrieve from environment analysis, and (ii) developing more standardized means of assessing the quality of proposed models, as was done in other research domains such as protein structure prediction.

Supplementary Fig. S1 from Monoclonal antibody 16D10 to the COOH-terminal domain of the feto-acinar pancreatic protein targets pancreatic neoplastic tissues

Diagnosis is a key step of patient management. During decades, refined decision algorithms and numerical scores based on conventional statistic tools were elaborated to ensure optimal reliability. Recently, a number of machine learning tools were developed and applied to process more and more extensive data sets, including up to million of items and yielding sophisticated classification models. While this approach met with impressive efficiency in some cases, practical limitations stem from the high number of parameters that may be required by a model, resulting in increased cost and delay of decision making. Also, information relative to the specificity of local recruitment may be lost, hampering any simplification of universal models. Here, we explored the capacity of currently available artificial intelligence tools to classify patients found in a single health center on the basis of a limited number of parameters. As a model, the discrimination between systemic lupus erythematosus (SLE) and mixed connective tissue disease (MCTD) on the basis of thirteen biological parameters was studied with eight widely used classifiers. It is concluded that classification performance may be significantly improved by a knowledge-based selection of discriminating parameters.

An important goal of biological research is to explain and hopefully predict cell behavior from the molecular properties of cellular components. Accordingly, much work was done to build extensive “omic” datasets and develop theoretical methods, including computer simulation and network analysis to process as quantitatively as possible the parameters contained in these resources. Furthermore, substantial effort was made to standardize data presentation and make experimental results accessible to data scientists. However, the power and complexity of current experimental and theoretical tools make it more and more difficult to assess the capacity of gathered parameters to support optimal progress in our understanding of cell function. The purpose of this review is to focus on biomolecule interactions, the interactome, as a specific and important example, and examine the limitations of the explanatory and predictive power of parameters that are considered as suitable descriptors of molecular interactions. Recent experimental studies on important cell functions, such as adhesion and processing of environmental cues for decision-making, support the suggestion that it should be rewarding to complement standard binding properties such as affinity and kinetic constants, or even force dependence, with less frequently used parameters such as conformational flexibility or size of binding molecules.

How do cells process environmental cues to make decisions? This simple question is still generating much experimental and theoretical work, at the border of physics, chemistry and biology, with strong implications in medicine. The purpose of mechanobiology is to understand how biochemical and physical cues are turned into signals through mechanotransduction. Here, we review recent evidence showing that (i) mechanotransduction plays a major role in triggering signalling cascades following cell-neighbourhood interaction; (ii) the cell capacity to continually generate forces, and biomolecule properties to undergo conformational changes in response to piconewton forces, provide a molecular basis for understanding mechanotransduction; and (iii) mechanotransduction shapes the guidance cues retrieved by living cells and the information flow they generate. This includes the temporal and spatial properties of intracellular signalling cascades. In conclusion, it is suggested that the described concepts may provide guidelines to define experimentally accessible parameters to describe cell structure and dynamics, as a prerequisite to take advantage of recent progress in high-throughput data gathering, computer simulation and artificial intelligence, in order to build a workable, hopefully predictive, account of cell signalling networks.

The scanning of surrounding tissues by T lymphocytes to detect cognate antigens requires high speed, sensitivity and specificity. T-cell receptor (TCR) co-receptors such as CD8 increase detection performance, but the exact mechanism remains incompletely understood. Here, we used a laminar flow chamber to measure at the single molecule level the kinetics of bond formation and rupture between TCR- transfected CD8+ and CD8− Jurkat cells and surfaces coated with five peptide-exposing major histocompatibility antigens (pMHCs) of varying activating power. We also used interference reflection microscopy to image the spreading of these cells dropped on pMHC-exposing surfaces. CD8 did not influence the TCR–pMHC interaction during the first few seconds following cell surface encounter, but it promoted the subsequent spreading responses, suggesting that CD8 was involved in early activation rather than binding. Further, the rate and extent of spreading, but not the lag between contact and spreading initiation, depended on the pMHC. Elucidating T-lymphocyte detection strategy may help unravel underlying signaling networks.

The T cell receptor (TCR)-peptide-MHC (pMHC) interaction is the only antigen-specific interaction during T lymphocyte activation. Recent work suggests that formation of catch bonds is characteristic of activating TCR-pMHC interactions. However, whether this binding behavior is an intrinsic feature of the molecular bond, or a consequence of more complex multimolecular or cellular responses, remains unclear. We used a laminar flow chamber to measure, first, 2D TCR-pMHC dissociation kinetics of peptides of various activating potency in a cell-free system in the force range (6 to 15 pN) previously associated with catch-slip transitions and, second, 2D TCR-pMHC association kinetics, for which the method is well suited. We did not observe catch bonds in dissociation, and the off-rate measured in the 6- to 15-pN range correlated well with activation potency, suggesting that formation of catch bonds is not an intrinsic feature of the TCR-pMHC interaction. The association kinetics were better explained by a model with a minimal encounter duration rather than a standard on-rate constant, suggesting that membrane fluidity and dynamics may strongly influence bond formation.

Theoretical determination of intermolecular forces involves a cascade of calculations and approximations, which makes it very difficult to assess the validity of obtained results. This chapter provides a brief sketch of the available methods of studying intermolecular forces that were applied to biological adhesion or that seemed of potential interest in this domain. It reviews some basic results on interatomic or intermolecular forces in vacuum or in aqueous ionic solutions. The chapter describes some experimental methods of studying intermolecular forces. It considers sequentially long- and short-range interactions. The link between virial coefficients and intermolecular forces is provided by statistical mechanics. The liquid state theory provides a link between the thermodynamic properties of liquid and intermolecular forces. An important problem is the additivity of intermolecular potentials. The quantitative treatment of intermolecular forces at short and intermediate distances involves very heavy calculations that were made possible only with the availability of highspeed computers.

Leukocyte-mediated pulmonary inflammation is a key pathophysiological mechanism involved in acute respiratory distress syndrome (ARDS). Massive sequestration of leukocytes in the pulmonary microvasculature is a major triggering event of the syndrome. We therefore investigated the potential role of leukocyte stiffness and adhesiveness in the sequestration of leukocytes in microvessels.

Background: Antinuclear antibodies (ANA) are useful biomarkers for the diagnosis and the monitoring of rheumatic diseases. The American College of Rheumatology has stated that indirect immunofluorescence (IIF) analysis remains the gold standard for ANA screening. However, IIF is time consuming, subjective, not fully standardized and presents several issues for accreditation which is the process leading to ISO 15189 certification for medical laboratories. We propose an innovative tool for accreditation by using the quantitative evaluation of the automated image capture and analysis "ICARE" (Immunofluorescence for Computed Antinuclear antibody Rational Evaluation).Methods: We established the optimal screening dilution (1:160) and a fluorescence index (FI) cutoff for ICARE on a cohort of 91 healthy blood donors. Then, we evaluated performance of ICARE on a routine cohort of 236 patients. Precision parameters of ANA detection by IIF were evaluated according to ISO 15189.Results: ICARE showed an excellent concordance with visual evaluation (88%, Kappa = 0.76) and significantly discriminated between weak to moderate (1:160-1:320 titers) and high (>1:320 titers) ANA levels. A significant correlation was found between FI and ANA titers (Spearman's rho = 0.67; P < 0.0001). Using ICARE, we reported precision parameters such as repeatability (CV < 13.8%) and reproducibility (CV < 13.1%) as well as absence of inter-sample contamination for ANA detection by IIF according to ISO 15189 standards.Conclusions: ICARE offers a precious help for the accreditation of IIF qualitative methods. This innovative quantitative approach is in adequacy with the process of continuous improvement of the quality of clinical laboratories. (C) 2015 Elsevier B.V. All rights reserved.

Antibodies and B cell receptors often bind their antigen at cell-cell interface while both molecular species are surface-bound, which impacts bond kinetics and function. Despite the description of complex energy landscapes for dissociation kinetics which may also result in significantly different association kinetics, surface-bound molecule (2D) association kinetics usually remain described by an on-rate due to crossing of a single free energy barrier, and few experimental works have measured association kinetics under conditions implying force and two-dimensional relative ligand-receptor motion. We use a new laminar flow chamber to measure 2D bond formation with systematic variation of the distribution of encounter durations between antigen and antibody, in a range from 0.1 to 10 ms. Under physiologically relevant forces, 2D association is 100-fold slower than 3D association as studied by surface plasmon resonance assays. Supported by brownian dynamics simulations, our results show that a minimal encounter duration is required for 2D association; an energy landscape featuring a rough initial part might be a reasonable way of accounting for this. By systematically varying the temperature of our experiments, we evaluate roughness at 2 k B T , in the range of previously proposed rough parts of landscapes models during dissociation.