Biology subjects

Tangherloni, A.

Publications and source records attributed to Tangherloni, A..

7 recordsLinked to original sources

bioRxiv2026

Scaling recipes for single-cell RNA sequencing foundation models: when do scaling laws hold?

Deep learning models exhibit empirical scaling laws whereby performance changes predictably with model size, dataset size, and training compute. Although these relationships are well established in domains such as language and image modelling, their applicability to biological data remains unclear. Here, we investigate scaling behaviour in foundation models trained on large collec tions of single-cell transcriptomes. We show that pre-training loss decreases systematically with model capacity and training compute, exhibiting a power law dependence on model size. The strength and regularity of these trends differ between model formulations. We identify and quantify empirical relationships linking the optimal learning rate and depth-to-width ratio to model size and depth or compute. These results demonstrate that scaling principles extend to transcriptomic modelling. More broadly, they provide a quantitative framework for estimating the expected returns from additional resources and selecting suit able hyperparameters and architectures, thereby supporting the development of increasingly capable foundation models for omics data.

bioinformatics↗

bioRxiv2025

GENESIS: Generating scRNA-Seq data from Multiome Gene Expression

Single-cell technologies have significantly advanced our understanding of cellular heterogeneity by allowing the examination of individual cells at high resolution. Traditional single-cell RNA sequencing (scRNA-Seq) methods, which utilise whole cells, capture comprehensive RNA content. In contrast, emerging Multiome technologies, which simultaneously profile multiple omics such as gene expression (GEX) and chromatin accessibility, rely on nuclear RNA, potentially missing key cytoplasmic information. This discrepancy leads to substantial technical and biological differences between GEX and scRNA-Seq datasets, making it difficult to integrate data and perform downstream tasks like cell-type classification. To address this challenge, we introduce GENESIS (Gene Expression Normalisation and Enhancement for Single-cell Integrated Sequencing), a novel computational framework designed to transform GEX data from Multiome experiments into enhanced, scRNA-Seq like profiles. Utilising advanced generative models--including Variational Autoencoders, Generative Adversarial Networks, and a tailored VAE UNet architecture--GENESIS can generate high-quality data by modelling and compensating for the inherent differences between nuclear and cytoplasmic RNA. Our comprehensive evaluations show that GENESIS, particularly through the VAE UNet model, generates synthetic scRNA-Seq data that closely resembles the resolution and biological accuracy of whole-cell sequencing, improving downstream tasks, especially cell-type classification.

bioinformatics↗

bioRxiv2021

SMGen: A generator of synthetic models of biochemical reaction networks

Several software tools for the simulation and analysis of biochemical reaction networks have been developed in the last decades; however, assessing and comparing their computational performance in executing the typical tasks of Computational Systems Biology can be limited by the lack of a standardized benchmarking approach. To overcome these limitations, we propose here a novel tool, named SMGen, designed to automatically generate synthetic models of reaction networks that, by construction, are characterized by both features (e.g., system connectivity, reaction discreteness) and non trivial emergent dynamics of real biochemical networks. The generation of synthetic models in SMGen is based on the definition of an undirected graph consisting of a single connected component, which generally results in a computationally demanding task. To avoid any burden in the execution time, SMGen exploits a Main-Worker paradigm to speed up the overall process. SMGen is also provided with a user-friendly Graphical User Interface that allows the user to easily set up all the parameters required to generate a set of synthetic models with any user-defined number of reactions and species. We analysed the computational performance of SMGen by generating batches of symmetric and asymmetric Reaction-based Models (RBMs) of increasing size, showing how a different number of reactions and/or species affects the generation time. Our results show that when the number of reactions is higher than the number of species, SMGen has to identify and correct high numbers of errors during the creation process of the RBMs, a circumstance that increases the overall running time. Still, SMGen can create synthetic models with 512 species and reactions in less than 7 seconds. The open-source code of SMGen is available on GitLab: https://gitlab.com/sgr34/smgen.

systems biology↗

bioRxiv2021

FiCoS: a fine- and coarse-grained GPU-powered deterministic simulator for biochemical networks

Mathematical models of biochemical networks can largely facilitate the comprehension of the mechanisms at the basis of cellular processes, as well as the formulation of hypotheses that can be tested by means of targeted laboratory experiments. However, two issues might hamper the achievement of fruitful outcomes. On the one hand, detailed mechanistic models can involve hundreds or thousands of molecular species and their intermediate complexes, as well as hundreds or thousands of chemical reactions, a situation generally occurring in rule-based modeling. On the other hand, the computational analysis of a model typically requires the execution of a large number of simulations for its calibration or to test the effect of perturbations. As a consequence, the computational capabilities of modern Central Processing Units can be easily overtaken, possibly making the modeling of biochemical networks a worthless or ineffective effort. To the aim of overcoming the limitations of the current state-of-the-art simulation approaches, we present in this paper FiCoS, a novel "black-box" deterministic simulator that effectively realizes both a fine-grained and a coarse-grained parallelization on Graphics Processing Units. In particular, FiCoS exploits two different integration methods, namely, the Dormand-Prince and the Radau IIA, to efficiently solve both non-stiff and stiff systems of coupled Ordinary Differential Equations. We tested the performance of FiCoS against different deterministic simulators, by considering models of increasing size and by running analyses with increasing computational demands. FiCoS was able to dramatically speedup the computations up to 855x, showing to be a promising solution for the simulation and analysis of large-scale models of complex biological processes. Author summarySystems Biology is an interdisciplinary research area focusing on the integration of biological data with mathematical and computational methods in order to unravel and predict the emergent behavior of complex biological systems. The ultimate goal is the understanding of the complex mechanisms at the basis of biological processes, together with the formulation of novel hypotheses that can be then tested by means of laboratory experiments. In such a context, mechanistic models can be used to describe and investigate biochemical reaction networks by taking into account all the details related to their stoichiometry and kinetics. Unfortunately, these models can be characterized by hundreds or thousands of molecular species and biochemical reactions, making their simulation unfeasible with classic simulators running on Central Processing Units (CPUs). In addition, a large number of simulations might be required to calibrate the models and/or to test the effect of perturbations. In order to overcome the limitations imposed by CPUs, Graphics Processing Units (GPUs) can be effectively used to accelerate the simulations of these models. We thus designed and developed a novel GPU-based tool, called FiCoS, to speed-up the computational analyses typically required in Systems Biology.

systems biology↗

bioRxiv2020

ACDC: Automated Cell Detection and Counting for Time-lapse Fluorescence Microscopy

Advances in microscopy imaging technologies have enabled the visualization of live-cell dynamic processes using time-lapse microscopy imaging. However, modern methods exhibit several limitations related to the training phases and to time constraints, hindering their application in the laboratory practice. In this work, we present a novel method, named Automated Cell Detection and Counting (ACDC), designed for activity detection of fluorescent labeled cell nuclei in time-lapse microscopy. ACDC overcomes the limitations of the literature methods, by first applying bilateral filtering on the original image to smooth the input cell images while preserving edge sharpness, and then by exploiting the watershed transform and morphological filtering. Moreover, ACDC represents a feasible solution for the laboratory practice, as it can leverage multi-core architectures in computer clusters to efficiently handle large-scale imaging datasets. Indeed, our Parent-Workers implementation of ACDC allows to obtain up to a 3.7x speed-up compared to the sequential counterpart. ACDC was tested on two distinct cell imaging datasets to assess its accuracy and effectiveness on images with different characteristics. We achieved an accurate cell-count and nuclei segmentation without relying on large-scale annotated datasets, a result confirmed by the average Dice Similarity Coefficients of 76.84 and 88.64 and the Pearson coefficients of 0.99 and 0.96, calculated against the manual cell counting, on the two tested datasets.

bioinformatics↗

bioRxiv2020

Integrative Single-cell RNA-Seq and ATAC-Seq Analysis of Human Foetal Liver and Bone Marrow Haematopoiesis

Regulation of haematopoiesis during human development remains poorly defined. Here, we applied single-cell (sc)RNA-Seq and scATAC-Seq analysis to over 8,000 human immunophenotypic blood cells from foetal liver and bone marrow. We inferred their differentiation trajectory and identified three highly proliferative oligopotent progenitor populations downstream from haematopoietic stem cell/multipotent progenitors (HSC/MPPs). Along this trajectory, we observed opposing patterns of chromatin accessibility and differentiation that coincided with dynamic changes in the activity of distinct lineage-specific transcription factors. Integrative analysis of chromatin accessibility and gene expression revealed extensive epigenetic but not transcriptional priming of HSC/MPPs prior to their lineage commitment. Finally, we refined and functionally validated the sorting strategy for the HSC/MPPs and achieved around 90% enrichment. Our study provides a useful framework for future investigation of human developmental haematopoiesis in the context of blood pathologies and regenerative medicine.

cell biology↗

bioRxiv2019

scAEspy: a unifying tool based on autoencoders for the analysis of single-cell RNA sequencing data

BackgroundSingle-cell RNA sequencing (scRNA-Seq) experiments are gaining ground to study the molecular processes that drive normal development as well as the onset of different pathologies. Finding an effective and efficient low-dimensional representation of the data is one of the most important steps in the downstream analysis of scRNA-Seq data, as it could provide a better identification of known or putatively novel cell-types. Another step that still poses a challenge is the integration of different scRNA-Seq datasets. Though standard computational pipelines to gain knowledge from scRNA-Seq data exist, a further improvement could be achieved by means of machine learning approaches. ResultsAutoencoders (AEs) have been effectively used to capture the non-linearities among gene interactions of scRNA-Seq data, so that the deployment of AE-based tools might represent the way forward in this context. We introduce here scAEspy, a unifying tool that embodies: (1) four of the most advanced AEs, (2) two novel AEs that we developed on purpose, (3) different loss functions. We show that scAEspy can be coupled with various batch-effect removal tools to integrate data by different scRNA-Seq platforms, in order to better identify the cell-types. We benchmarked scAEspy against the most used batch-effect removal tools, showing that our AE-based strategies outperform the existing solutions. ConclusionsscAEspy is a user-friendly tool that enables using the most recent and promising AEs to analyse scRNA-Seq data by only setting up two user-defined parameters. Thanks to its modularity, scAEspy can be easily extended to accommodate new AEs to further improve the downstream analysis of scRNA-Seq data. Considering the relevant results we achieved, scAEspy can be considered as a starting point to build a more comprehensive toolkit designed to integrate multi single-cell omics.

bioinformatics↗