LCLuisa Cutillo

Luisa Cutillo

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Luisa Cutillo has a total of 181 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Universal Prediction of Molecular Weight Distribution for Entangled Linear Polymers from Linear Rheology Using Neural Networks

    by Robert J. Elliott, Luisa Cutillo, Johan Mattsson, Daniel J. Read

    We present a machine learning methodology for inferring the molecular weight distribution (MWD) of arbitrary polydisperse entangled linear polymers from their linear rheology. Using a state-of-the-art tube model, we generate large synthetic rheology datasets to train neural networks (NNs) to accurately predict MWDs from frequency-sweep rheology measurements. We take advantage of the universality of the dynamics of flexible polymers, where the shape of the relaxation spectrum is identical for polymers with different backbone chemistries but the same number of entanglements. We therefore use the NN to predict the distribution in the number of entanglements from normalised rheology data, and this distribution is subsequently converted to an MWD using the mean entanglement molecular weight. Our primary interest is in industrially relevant materials, so we focus on broad, highly polydisperse MWDs. However, we also introduce a classification scheme to determine, solely from the rheology, whether a sample is best described as polydisperse, monodisperse, or bidisperse, and deploy dedicated NNs for each of these cases. We present resulting predictions for a range of industrially relevant polymer chemistries, including commercial samples of polyethylene (HDPE and LLDPE), with good agreement with experimental gel permeation chromatography (GPC) data. An open-access GUI software tool is released alongside this work to enable easy adoption of our methodology in both academic and industrial settings.

  • Open Access

    Making multi-axis Gaussian graphical models scalable to millions of cells

    by Bailey Andrew, Erica L Harris, James A Poulter, David R Westhead, Luisa Cutillo

    Motivation: Networks underlie the generation and interpretation of many biological datasets: gene networks shed light on the regulatory structure of the genome, and cell networks can capture structure of the tumor micro-environment. However, most methods that learn such networks make the faulty “independence assumption”; to learn the gene network, they assume that no cell network exists. “Multi-axis” methods, which do not make this assumption, fail to scale beyond a few thousand cells or genes. This limits their applicability to only the smallest datasets. Results: We develop a multi-axis method, which learns conditional dependency networks, capable of processing million-cell datasets within minutes. This was previously impossible, and unlocks the use of such methods on modern scRNA-seq datasets, as well as more complex datasets. We apply the method to a new scRNA-seq dataset for neuronal cell development, and compare the result to an existing state of the art method, hdWGCNA. We demonstrate that the new method yields gene networks that have a more focused biological interpretation and that the simultaneously learned cell network has advantages over a conventional kNN-based clustering. Further, our method yields novel biological insights by identifying long non-coding RNAs that potentially have a role in neuronal development. Availability and implementation: Our methodology is available as a Python package GmGM on PyPI (https://pypi.org/project/GmGM/0.5.3/). The code for all experiments performed in this article is available on GitHub (https://github.com/BaileyAndrew/GmGM-Bioinformatics) and Zenodo (10.5281/zenodo.20384566).

  • Using neural networks to deduce polymer molecular weight distributions from linear rheology

    by Robert J. Elliott, Luisa Cutillo, Chinmay Das, Johan Mattsson, Daniel J. Read

    We present a methodology for inferring the molecular weight distribution (MWD) of polydisperse linear polymers from their linear rheology using machine learning techniques. Specifically, we use a state-of-the-art tube model to generate large datasets of artificially produced rheology data. These are used to train neural networks (NNs) to make accurate MWD predictions from frequency-sweep rheology measurements. We target distributions relevant to commercial polymers, so broad polydisperse MWDs are prioritized. To simplify the data format for the NN, we fit Maxwell modes to the rheology with predefined relaxation times and, hence, parameterize the rheology using the mode amplitudes; correspondingly, we propose MWD parameterization using the sum of several log-Gaussian subdistributions with logarithmically spaced mean molecular weights and identical dispersities. We assess the methodology’s performance by predicting MWDs using experimental polystyrene rheology data from the literature. Good agreement with gel permeation chromatography data is found where available, and where it is not, the prediction captures known molecular weight statistics (such as weight-average molecular weight and dispersity) even if the precise shape of the MWD is not known. The findings here lay the groundwork for future developments concerning the inversion of this tube model for other polymeric materials. The ability to infer the MWD from rheology would traditionally be prohibited by the mathematical complexity of state-of-the-art tube models, but we bypass this issue with our machine learning methodology.


  • Open Access

    University staff and student perspectives on competent and ethical use of AI: uncovering similarities and divergences

    by Manoj Ravi, Kashmir Kaur, Clare Wright, Matt Bawn, Luisa Cutillo

    We investigated the similarities and differences in understanding among UK-based university staff and students regarding AI literacy, in terms of competent and ethical use of AI tools. This study builds on existing research revealing both wide use of AI tools in higher education, but also a lack of shared understanding among stakeholder groups on what constitutes competent and ethical use of AI. This study is one of the first to combine insights from staff and students, illustrating specific concerns over AI competence and ethical implications in granular detail. The results reveal a significant disparity in the use of AI tools between students and staff, particularly in the adoption of text-based or conversational GenAI tools (cGenAI). Students reported extensive use of cGenAI tools for a range of tasks, while staff engagement was generally limited to brainstorming ideas or generating teaching tasks. Although the use of cGenAI is seen by most as AI competence, nuanced differences emerged between staff and student opinion depending on the application of the AI tool. Ethical issues in both groups were prominent, although staff reported more negative systemic concerns regarding inherent bias, concerns over transparency and data ownership. Over 90% of staff flagged the use of cGenAI for essay-generation as problematic, compared to 58% of students, primarily due to concerns regarding academic integrity. These differences point to the need for institutional guidelines and dialogue to address ethical concerns and align expectations across stakeholder groups to ensure the effective integration of AI literacy in higher education.


  • Open Access

    Gaussian Graphical Modelling Without Independence Assumptions for Uncentered Data

    by Bailey Andrew, David R. Westhead, Luisa Cutillo

    The independence assumption between random variables is a useful tool to increase the tractability of a modelling framework. However, this assumption can be too simplistic; failing to take dependencies into account can cause models to fail dramatically. The field of multi-axis graphical modelling (also called multi-way modelling, Kronecker-separable modelling) has seen growth over the past decade, but these models require that the data have zero mean. In the multi-axis case, inference is typically done in the single sample scenario, making mean inference impossible. In this paper, we demonstrate how the zero-mean assumption can cause egregious modelling errors for Kronecker-sum-decomposable Gaussian graphical models, as well as propose a relaxation to the zero-mean assumption that allows the avoidance of such errors. Specifically, we propose the "Kronecker-sum-structured mean" assumption, which leads to models with nonconvex-but-unimodal log-likelihoods that can be solved efficiently with coordinate descent.


  • Open Access

    robin2: accelerating single-cell data clustering evaluation

    by Valeria Policastro, Dario Righelli, Luisa Cutillo, Annamaria Carissimo

    Motivation: The rapid expansion of single-cell RNA sequencing (scRNA-seq) technologies has increased the need for robust and scalable clustering evaluation methods. To address these challenges, we developed robin2, an optimized version of our R package robin. It introduces enhanced computational efficiency, support for high-dimensional datasets, and harmonious integration with R’s base functionalities for robust network analysis. Results: robin2 offers improved functionality for clustering stability validation and enables systematic evaluation of community detection algorithms across various resolutions and pipelines. The application to Tabula Muris and PBMC scRNA-seq datasets confirmed its ability to identify biologically meaningful cell subpopulations with high statistical significance. The new version reduces computational time by 9-fold on large-scale datasets using parallel processing. Availability and implementation: The robin2 package is freely available on CRAN at https://CRAN.R-project.org/package=robin. Comprehensive documentation and a detailed analysis vignette are available on GitHub at https://drighelli.github.io/scrobinv2/index.html.


  • AI IN HIGHER EDUCATION: NUANCED UNDERSTANDINGS OF COMPETENCE, ETHICS AND EQUITY

    by Kashmir Kaur, Manoj Ravi, Clare Wright, Matt Bawn, Luisa Cutillo


  • Open Access

    Graphical Modelling without Independence Assumptions for Uncentered Data

    by Bailey Andrew, David R. Westhead, Luisa Cutillo

    The independence assumption is a useful tool to increase the tractability of one's modelling framework. However, this assumption does not match reality; failing to take dependencies into account can cause models to fail dramatically. The field of multi-axis graphical modelling (also called multi-way modelling, Kronecker-separable modelling) has seen growth over the past decade, but these models require that the data have zero mean. In the multi-axis case, inference is typically done in the single sample scenario, making mean inference impossible. In this paper, we demonstrate how the zero-mean assumption can cause egregious modelling errors, as well as propose a relaxation to the zero-mean assumption that allows the avoidance of such errors. Specifically, we propose the "Kronecker-sum-structured mean" assumption, which leads to models with nonconvex-but-unimodal log-likelihoods that can be solved efficiently with coordinate descent.

  • Open Access

    IDHwt glioblastomas can be stratified by their transcriptional response to standard treatment, with implications for targeted therapy

    by Georgette Tanner, Rhiannon Barrow, Shoaib Ajaib, Muna Al-Jabri, Nazia Ahmed, Steven Pollock, Martina Finetti, Nora Rippaus, Alexander F. Bruns, Khaja Syed, et al.

    Background: Glioblastoma (GBM) brain tumors lackingIDH1mutations (IDHwt) have the worst prognosis of all brain neoplasms. Patients receive surgery and chemoradiotherapy but tumors almost always fatally recur.Results: Using RNA sequencing data from 107 pairs of pre- and post-standard treatment locally recurrent IDHwt GBM tumors, we identify two responder subtypes based on longitudinal changes in gene expression. In two thirds of patients, a specific subset of genes is upregulated from primary to recurrence (Up responders), and in one third, the same genes are downregulated (Down responders), specifically in neoplastic cells. Characterization of the responder subtypes indicates subtype-specific adaptive treatment resistance mechanisms that are associated with distinct changes in the tumor microenvironment. In Up responders, recurrent tumors are enriched in quiescent proneural GBM stem cells and differentiated neoplastic cells, with increased interaction with the surrounding normal brain and neurotransmitter signaling, whereas Down responders commonly undergo mesenchymal transition. ChIP-sequencing data from longitudinal GBM tumors suggests that the observed transcriptional reprogramming could be driven by Polycomb-based chromatin remodeling rather than DNA methylation.Conclusions: We show that the responder subtype is cancer-cell intrinsic, recapitulated in in vitro GBM cell models, and influenced by the presence of the tumor microenvironment. Stratifying GBM tumors by responder subtype may lead to more effective treatment.