Biology subjects

Lio, P.

Publications and source records attributed to Lio, P..

At least 37 records · Page 2Linked to original sources

bioRxiv2024

gRNAde: Geometric Deep Learning for 3D RNA inverse design

Computational RNA design tasks are often posed as inverse problems, where sequences are designed based on adopting a single desired secondary structure without considering 3D conformational diversity. We introduce gRNAde, a geometric RNA design pipeline operating on 3D RNA backbones to design sequences that explicitly account for structure and dynamics. gRNAde uses a multi-state Graph Neural Network and autoregressive decoding to generates candidate RNA sequences conditioned on one or more 3D backbone structures where the identities of the bases are unknown. On a single-state fixed backbone re-design benchmark of 14 RNA structures from the PDB identified by Das et al. (2010), gRNAde obtains higher native sequence recovery rates (56% on average) compared to Rosetta (45% on average), taking under a second to produce designs compared to the reported hours for Rosetta. We further demonstrate the utility of gRNAde on a new benchmark of multi-state design for structurally flexible RNAs, as well as zero-shot ranking of mutational fitness landscapes in a retrospective analysis of a recent ribozyme. Experimental wet lab validation on 10 different structured RNA backbones finds that gRNAde has a success rate of 50% at designing pseudoknotted RNA structures, a significant advance over 35% for Rosetta. Open source code and tutorials are available at: github.com/chaitjo/geometric-rna-design

bioinformatics↗

bioRxiv2024

Learning and actioning general principles of cancer cell drug sensitivity

High-throughput screening platforms for the profiling of drug sensitivity of hundreds of cancer cell lines (CCLs) have generated large datasets that hold the potential to unlock targeted, anti-tumor therapies. In this study, we leveraged these datasets to create predictive models of cancer cells drug sensitivity. To this aim we trained explainable machine learning algorithms by employing cell line transcriptomics to predict the growth inhibitory potential of drugs. We used large language models (LLMs) to expand descriptions of the mechanisms of action (MOA) for each drug starting from available annotations, which were matched to the semantically closest pathways from reference knowledge bases. By leveraging this AI-curated resource, and the interpretability of our model, we demonstrated that pathways enriched for genes crucial for prediction often matched known drug-MOAs and essential genes, suggesting that our models learned the molecular determinants of drug response. Furthermore, we demonstrated that by incorporating only LLM-curated genes associated with MOAs, we enhanced the predictive accuracy of our drug models. To enhance translatability to a clinical setting, we employed a pipeline to align bulk RNAseq from CCLs, used for training the models, to those from patient samples, used for inference. We proved the effectiveness of our approach on TCGA samples, where patients best scoring drugs matched those prescribed for their cancer type. We further showed its usefulness by predicting and experimentally validating effective drugs for the patients of two highly lethal solid tumors, i.e. pancreatic cancer and glioblastoma. In summary, our method facilitates the inference and interpretation of cancer cell line drug sensitivity and holds potential to effectively translate them into new cancer therapeutics. Highlights-Interpretable drug-response prediction models were trained on large scale pharmacogenomics data sets (i.e. GDSC and PRISM). -Large language models were used to enhance the curation of biological pathways associated to drugs MOA -Unbiased interpretation of the models demonstrated learning of drug MOAs and gene essentiality -Inference of TCGA cohort samples recovered mono- and combination cancer drug prescriptions and indicate potential repurposing candidates. -Drug candidates predicted from bulk RNAseq samples of pancreatic cancer and glioblastoma were experimentally validated.

bioinformatics↗

bioRxiv2023

Conditional Protein Denoising Diffusion Generates Programmable Endonucleases

Deep learning-based methods for generating functional proteins address the growing need for novel biocatalysts, allowing for precise tailoring of functionalities to meet specific requirements. This emergence leads to the creation of highly efficient and specialized proteins with wide-ranging applications in scientific, technological, and biomedical domains. This study establishes a pipeline for protein sequence generation with a conditional protein diffusion model, namely CPDiffusion, to deliver diverse sequences of proteins with enhanced functions. CPDiffusion accommodates protein-specific conditions, such as secondary structure and highly conserved amino acids (AAs). Without relying on extensive training data, CPDiffusion effectively captures highly conserved residues and sequence features for a specific protein family. We applied CPDiffusion to generate artificial sequences of Argonaute (Ago) proteins based on the backbone structures of wild-type (WT) Kurthia massiliensis Ago (KmAgo) and Pyrococcus furiosus Ago (PfAgo), which are complex multi-domain programmable endonucleases. The generated sequences deviate by up to nearly 400 AAs from their WT templates. Experimental tests demonstrated that the majority of generated proteins show unambiguous activity in DNA cleavage for both KmAgo and PfAgo, with many of them exhibiting superior activity as compared to the WT. These findings underscore CPDiffusions remarkable success rate to generate novel sequences for proteins of complex structures and functions in a single step with enhanced activity. This approach facilitates the design of enzymes with multi-domain molecular structures and intricate functions through in silico generation and screening, all accomplished without any supervision from labeled data.

bioengineering↗

bioRxiv2023

Spatio-relational inductive biases in spatial cell-type deconvolution

Spatial transcriptomic technologies profile gene expression in-situ, facilitating the spatial characterisation of molecular phenomena within tissues, yet often at multi-cellular resolution. Computational approaches have been developed to infer fine-grained cell-type compositions across locations, but they frequently treat neighbouring spots independently of each other. Here we present GNN-C2L, a flexible deconvolution approach that leverages proximal inductive biases to propagate information along adjacent spots. In performance comparison on simulated and semisimulated datasets, GNN-C2L achieves increased deconvolution performance over spatial-agnostic variants. We believe that accounting for spatial inductive biases can yield improved characterisation of cell-type heterogeneity in tissues.

bioinformatics↗

bioRxiv2023

ElegansNet: a brief scientific report and initial experiments.

This research report introduces ElegansNet, a neural network that mimics real-world neuronal network circuitry, with the goal of better understanding the interplay between connectome topology and deep learning systems. The proposed approach utilizes the powerful representational capabilities of living beings neuronal circuitry to design and generate improved deep learning systems with a topology similar to natural networks. The Caenorhabditis elegans connectome is used as a reference due to its completeness, reasonable size, and functional neuron classes annotations. It is demonstrated that the connectome of simple organisms exhibits specific functional relationships between neurons, and once transformed into learnable tensor networks and integrated into modern architectures, it offers bio-plausible structures that efficiently solve complex tasks. The performance of the models is demonstrated against randomly wired networks and compared to artificial networks ranked on global benchmarks. In the first case, ElegansNet outperforms randomly wired networks. Interestingly, ElegansNet models show slightly similar performance with only those based on the Watts-Strogatz small-world property. When compared to state-of-the-art artificial neural networks, such as transformers or attention-based autoencoders, ElegansNet outperforms well-known deep learning and traditional models in both supervised image classification tasks and unsupervised hand-written digits reconstruction, achieving top-1 accuracy of 99.99% on Cifar10 and 99.84% on MNIST Unsup on the validation sets.

neuroscience↗

bioRxiv2023

Fate-mapping lymphocyte clones and their progenies from induced antigen-signals identifies temporospatial behaviours of T cells mediating tolerance

Tissue homeostasis is maintained by the behaviours of lymphocyte clones responding to antigenic triggers in the face of pathogen, environmental, and developmental challenges. Current methodologies for tracking the behaviour of specific lymphocytes identify clones of a defined antigen-receptor--antigen binding affinity. However, lymphocytes can receive antigenic signals from undefined or endogenous antigens, and the strength of each signal, even for the same lymphocyte, varies with accessory signalling, across tissues and across time. We present a novel fate-mapping mouse, that, by tracking lymphocyte clones and their progenies from induced antigen signals, overcomes these hurdles and provides novel insights into the maintenance of tissue homeostasis. We demonstrate the systems use by investigating the maintenance of localised T cell tolerance in tumour immunity. In a murine tumour model, our system reveals how Tregs differentiate to a reversible, tolerance inducing state within the tumour, and recirculate, while CD8+ T cells failing to recirculate, differentiate to an increasingly exhausted, tolerant state in the tumour. These contrasting T cell behaviours provide means by which immunity can tolerate a particular anatomical niche while maintaining systemic clonal protection. Our system can thus explore lymphocyte behaviours that cannot be tracked by previous methods and will therefore provide novel insights into the fundamental mechanisms underlying immunitys role in tissue homeostasis.

immunology↗

bioRxiv2022

Hypergraph factorisation for multi-tissue gene expression imputation

AO_SCPLOWBSTRACTC_SCPLOWIntegrating gene expression across scales and tissues is crucial for understanding the biological mechanisms that drive disease and characterise homeostasis. However, traditional multi-tissue integration methods cannot handle uncollected tissues or rely on genotype information, which is subject to privacy concerns and often unavailable. To address these challenges, we present HYFA (Hypergraph Factorisation), a novel method for joint imputation of multi-tissue and cell-type gene expression. HYFA imputes tissue-specific gene expression via a specialised graph neural network operating on a hypergraph of individuals, metagenes, and tissues. HYFA is genotype- agnostic, supports a variable number of collected tissues per individual, and imposes strong inductive biases to leverage the shared regulatory architecture of tissues. In performance comparison on data from the Genotype Tissue Expression project, HYFA achieves superior performance over existing transcriptome imputation methods, especially when multiple reference tissues are available. Through transfer learning on a paired single-nucleus RNA-seq (snRNA-seq) dataset, we further show that HYFA can accurately resolve cell-type signatures from bulk gene expression, highlighting the methods ability to leverage gene expression programs underlying cell-type identity, even in tissues that were never observed in the training set. Using Gene Set Enrichment Analysis, we find that the metagenes learned by HYFA capture information about known biological pathways. Notably, the HYFA-imputed dataset can be used to identify regulatory genetic variations (eQTLs), with substantial gains over the original incomplete dataset. Our framework can accelerate effective and scalable integration of tissue and cell-type gene expression biorepositories.

bioinformatics↗

bioRxiv2022

ERnet: a tool for the semantic segmentation and quantitative analysis of endoplasmic reticulum topology for video-rate super-resolution imaging

The topology of endoplasmic reticulum (ER) network is highly regulated by various cellular and environmental stimuli and affects major functions such as protein quality control and the cells response to metabolic changes. The ability to quantify the dynamical changes of the ER structures in response to cellular perturbations is crucial for the development of novel therapeutic approaches against ER associated diseases, such as hereditary spastic paraplegias and Niemann Pick Disease type C. However, the rapid movement and small spatial dimension of ER networks make this task challenging. Here, we combine video-rate super-resolution imaging with a state-of-the-art semantic segmentation method capable of automatically classifying sheet and tubular ER domains inside individual cells. Data are skeletonised and represented by connectivity graphs to enable the precise and efficient quantification and comparison of the network connectivity from different complex ER phenotypes. The method, called ERnet, is powered by a Vision Transformer architecture, and integrates multi-head self-attention and channel attention into the model for adaptive weighting of frames in the time domain. We validated the performance of ERnet by measuring different ER morphology changes in response to genetic or metabolic manipulations. Finally, as a means to test the applicability and versatility of ERnet, we showed that ERnet can be applied to images from different cell types and also taken from different imaging setups. Our method can be deployed in an automatic, high-throughput, and unbiased fashion to identify subtle changes in cellular phenotypes that can be used as potential diagnostics for propensity to ER mediated disease, for disease progression, and for response to therapy.

bioengineering↗

bioRxiv2022

Decoding Surface Fingerprints for Protein-Ligand Interactions

AO_SCPLOWBSTRACTC_SCPLOWSmall molecules have been the preferred modality for drug development and therapeutic interventions. This molecular format presents a number of advantages, e.g. long half-lives and cell permeability, making it possible to access a wide range of therapeutic targets. However, finding small molecules that engage "hard-to-drug" protein targets specifically and potently remains an arduous process, requiring experimental screening of extensive compound libraries to identify candidate leads. The search continues with further optimization of compound leads to meet the required potency and toxicity thresholds for clinical applications. Here, we propose a new computational workflow for high-throughput fragment-based screening and binding affinity prediction where we leverage the available protein-ligand complex structures using a state-of-the-art protein surface embedding framework (dMaSIF). We developed a tool capable of finding suitable ligands and fragments for a given protein pocket solely based on protein surface descriptors, that capture chemical and geometric features of the target pocket. The identified fragments can be further combined into novel ligands. Using the structural data, our ligand discovery pipeline learns the signatures of interactions between surface patches and small pharmacophores. On a query target pocket, the algorithm matches known target pockets and returns either potential ligands or identifies multiple ligand fragments in the binding site. Our binding affinity predictor is capable of predicting the affinity of a given protein-ligand pair, requiring only limited information about the ligand pose. This enables screening without the costly step of first docking candidate molecules. Our framework will facilitate the design of ligands based on the targets surface information. It may significantly reduce the experimental screening load and ultimately reveal novel chemical compounds for targeting challenging proteins.

bioinformatics↗

bioRxiv2021

REM: An Integrative Rule Extraction Methodology for Explainable Data Analysis in Healthcare

Deep learning models are receiving increasing attention in clinical decision-making, however the lack of explainability impedes their deployment in day-to-day clinical practice. We propose REM, an explainable methodology for extracting rules from deep neural networks and combining them with rules from non-deep learning models. This allows integrating machine learning and reasoning for investigating basic and applied biological research questions. We evaluate the utility of REM in two case studies for the predictive tasks of classifying histological and immunohistochemical breast cancer subtypes from genotype and phenotype data. We demonstrate that REM efficiently extracts accurate, comprehensible rulesets from deep neural networks that can be readily integrated with rulesets obtained from tree-based approaches. REM provides explanation facilities for predictions and enables the clinicians to validate and calibrate the extracted rulesets with their domain knowledge. With these functionalities, REM caters for a novel and direct human-in-the-loop approach in clinical decision-making.

bioinformatics↗

bioRxiv2020

CellVGAE: An unsupervised scRNA-seq analysis workflow with graph attention networks

AO_SCPLOWBSTRACTC_SCPLOWCurrently, single-cell RNA sequencing (scRNA-seq) allows high-resolution views of individual cells, for libraries of up to (tens of) thousands of samples. In this study, we introduce the use of graph neural networks (GNN) in the unsupervised study of scRNA-seq data, namely for dimensionality reduction and clustering. Motivated by the success of non-neural graph-based techniques in bioinformatics, as well as the now common feedforward neural networks being applied to scRNA-seq measurements, we develop an architecture based on a variational graph autoencoder with graph attention layers that works directly on the connectivity of cells. With the help of three case studies, we show that our model, named CellVGAE, can be effectively used for exploratory analysis, even on challenging datasets, by extracting meaningful features from the data and providing the means to visualise and interpret different aspects of the model. Furthermore, we evaluate the dimensionality reduction and clustering performance on 9 well-annotated datasets, where we compare with leading neural and non-neural techniques. CellVGAE outperforms competing methods in all 9 scenarios. Finally, we show that CellVGAE is more interpretable than existing architectures by analysing the graph attention coefficients. The software and code to generate all the figures are available at https://github.com/davidbuterez/CellVGAE.

bioinformatics↗

bioRxiv2020

From infection to immunity: understanding the response to SARS-CoV2 through in-silico modeling

BackgroundImmune system conditions of the patient is a key factor in COVID-19 infection survival. A growing number of studies have focused on immunological determinants to develop better biomarkers for therapies. AimThe dynamics of the insurgence of immunity is at the core of the both SARS-CoV-2 vaccine development and therapies. This paper addresses a fundamental question in the management of the infection: can we describe the insurgence (and the span) of immunity in COVID-19? The in-silico model developed here answers this question at individual (personalized) and population levels. We simulate the immune response to SARS-CoV-2 and analyze the impact of infecting viral load, affinity to the ACE2 receptor and age in the artificially infected population on the course of the disease. MethodsWe use a stochastic agent-based immune simulation platform to construct a virtual cohort of infected individuals with age-dependent varying degree of immune competence. We use a parameter setting to reproduce known inter-patient variability and general epidemiological statistics. ResultsWe reproduce in-silico a number of clinical observations and we identify critical factors in the statistical evolution of the infection. In particular we evidence the importance of the humoral response over the cytotoxic response and find that the antibody titers measured after day 25 from the infection is a prognostic factor for determining the clinical outcome of the infection. Our modeling framework uses COVID-19 infection to demonstrate the actionable effectiveness of simulating the immune response at individual and population levels. The model developed is able to explain and interpret observed patterns of infection and makes verifiable temporal predictions. Within the limitations imposed by the simulated environment, this work proposes in a quantitative way that the great variability observed in the patient outcomes in real life can be the mere result of subtle variability in the infecting viral load and immune competence in the population. In this work we i) show the power of model predictions, ii) identify the clinical end points that could be more suitable for computational modeling of COVID-19 immune response, iii) define the resolution and amount of data required to empower this class of models for translational medicine purposes and, iv) we exemplify how computational modeling of immune response provides an important view to discuss hypothesis and design new experiments, in particular paving the way to further investigations about the duration of vaccine-elicited immunity especially in the view of the blundering effect of immunesenescence.

bioinformatics↗

bioRxiv2020

A Deep Graph Neural Network Architecture for Modelling Spatio-temporal Dynamics in resting-stating functional MRI Data

Resting-state functional magnetic resonance imaging (rs-fMRI) has been successfully employed to understand the organisation of the human brain. For rs-fMRI analysis, the brain is typically parcellated into regions of interest (ROIs) and modelled as a graph where each ROI is a node and pairwise correlation between ROI blood-oxygen-level-dependent (BOLD) time series are edges. Recently, graph neural networks (GNNs) have seen a surge in popularity due to their successes in modelling unstructured relational data. The latest developments with GNNs, however, have not yet been fully exploited for the analysis of rs-fMRI data, particularly with regards to its spatio-temporal dynamics. Herein we present a novel deep neural network architecture, combining both GNNs and temporal convolutional networks (TCNs), which is able to learn from the spatial and temporal components of rs-fMRI data in an end-to-end fashion. In particular, this corresponds to intra-feature learning (i.e., learning temporal dynamics with TCNs) as well as inter-feature learning (i.e., leveraging spatial interactions between ROIs with GNNs). We evaluate our model with an ablation study using 35,159 samples from the UK Biobank rs-fMRI database. We also demonstrate explainability features of our architecture which map to realistic neurobiological insights. We hope our model could lay the groundwork for future deep learning architectures focused on leveraging the inherently and inextricably spatio-temporal nature of rs-fMRI data.

neuroscience↗

bioRxiv2020

Graphein - a Python Library for Geometric Deep Learning and Network Analysis on Protein Structures

Geometric deep learning has well-motivated applications in the context of biology, a domain where relational structure in datasets can be meaningfully leveraged. Currently, efforts in both geometric deep learning and, more broadly, deep learning applied to biomolecular tasks have been hampered by a scarcity of appropriate datasets accessible to domain specialists and machine learning researchers alike. However, there has been little exploration of how to best to integrate and construct geometric representations of these datatypes. To address this, we introduce Graphein as a turn-key tool for transforming raw data from widely-used bioinformatics databases into machine learning-ready datasets in a high-throughput and flexible manner. Graphein is a Python library for constructing graph and surface-mesh representations of protein structures and biological interaction networks for computational analysis. Graphein provides utilities for data retrieval from widely-used bioinformatics databases for structural data, including the Protein Data Bank, the recently-released AlphaFold Structure Database, and for biomolecular interaction networks from STRINGdb, BioGrid, TRRUST and RegNetwork. The library interfaces with popular geometric deep learning libraries: DGL, PyTorch Geometric and PyTorch3D though remains framework agnostic as it is built on top of the PyData ecosystem to enable inter-operability with scientific computing tools and libraries. Graphein is designed to be highly flexible, allowing the user to specify each step of the data preparation, scalable to facilitate working with large protein complexes and interaction graphs, and contains useful pre-processing tools for preparing experimental files. Graphein facilitates network-based, graph-theoretic and topological analyses of structural and interaction datasets in a high-throughput manner. As example workflows, we make available two new protein structure-related datasets, previously unused by the geometric deep learning community. We envision that Graphein will facilitate developments in computational biology, graph representation learning and drug discovery. Availability and implementationGraphein is written in Python. Source code, example usage and tutorials, datasets, and documentation are made freely available under the MIT License at the following URL: graphein.ai

bioinformatics↗

bioRxiv2020

Population GNNs for Brain Age Prediction

Many common neurological and neurodegenerative disorders, such as Alzheimers disease, dementia and multiple sclerosis, have been associated with abnormal patterns of apparent ageing of the brain. Discrepancies between the estimated brain age and the actual chronological age (brain age gaps) can be used to understand the biological pathways behind the ageing process, assess an individuals risk for various brain disorders and identify new personalised treatment strategies. By flexibly integrating minimally preprocessed neuroimaging and non-imaging modalities into a population graph data structure, we train two types of graph neural network (GNN) architectures to predict brain age in a clinically relevant fashion as well as investigate their robustness to noisy inputs and graph sparsity. The multimodal population graph approach has the potential to learn from the entire cohort of healthy and affected subjects of both sexes at once, capturing a wide range of con-founding effects and detecting variations in brain age trends between different sub-populations of subjects.

neuroscience↗

bioRxiv2020

Gene Expression Imputation with Generative Adversarial Imputation Nets

A question of fundamental biological significance is to what extent the expression of a subset of genes can be used to recover the full transcriptome, with important implications for biological discovery and clinical application. To address this challenge, we present GAIN-GTEx, a method for gene expression imputation based on Generative Adversarial Imputation Networks. In order to increase the applicability of our approach, we leverage data from GTEx v8, a reference resource that has generated a comprehensive collection of transcriptomes from a diverse set of human tissues. We compare our model to several standard and state-of-the-art imputation methods and show that GAIN-GTEx is significantly superior in terms of predictive performance and runtime. Furthermore, our results indicate strong generalisation on RNA-Seq data from 3 cancer types across varying levels of missingness. Our work can facilitate a cost-effective integration of large-scale RNA biorepositories into genomic studies of disease, with high applicability across diverse tissue types.

bioinformatics↗

bioRxiv2020

Multilayer modelling and analysis of the humantranscriptome

Here, we performed a comprehensive intra-tissue and inter-tissue network analysis of the human transcriptome. We generated an atlas of communities in co-expression networks in 49 tissues (GTEx v8), evaluated their tissue specificity, and investigated their methodological implications. UMAP embeddings of gene expression from the communities (representing nearly 18% of all genes) robustly identified biologically-meaningful clusters. Methodologically, integration of the communities into a transcriptome-wide association study of C-reactive protein (CRP) in 361,194 individuals in the UK Biobank identified genetically-determined expression changes associated with CRP and led to considerably improved performance. Furthermore, a deep learning framework applied to the communities in nearly 11,000 tumours profiled by The Cancer Genome Atlas across 33 different cancer types learned biologically-meaningful latent spaces, representing metastasis (p < 2.2 x 10-16) and stemness (p < 2.2 x 10-16). Our study provides a rich genomic resource to catalyse research into inter-tissue regulatory mechanisms and their downstream phenotypic consequences.

genomics↗

bioRxiv2020

PhylSim: A New Phylogenetic Tool for Modeling Trait Evolution and Speciation

We present a new software tool in R, the PhylSim package, which allows the user to simulate trait evolution on a phylogeny, while varying the speciation rate and evolutionary model over the course of the simulation. In particular, the user can specify any number of regimes, with a different speciation rate for each regime, or set the speciation rate to vary when the value of a trait exceeds a certain threshold. The evolutionary model can also be varied as many times as necessary over the course of the simulation, to account for traits tending toward different optima at different periods in evolutionary history. We illustrate the use of the package with an example, a simulation of the adaptive radiation of Antarctic notothenioids in the Southern Ocean.

bioinformatics↗