Biology subjects

Chierici, M.

Publications and source records attributed to Chierici, M..

7 recordsLinked to original sources

bioRxiv2025

Toward Reliable Synthetic Omics: Statistical Distances for Generative Models Evaluation

BackgroundSynthetic data generation is emerging as an approach to overcome the limitations of real-world data scarcity in omics studies, especially in precision medicine and oncology. Omics datasets, with their high dimensionality and relatively small sample sizes, often lead to overfitting, especially in deep learning models. Generative models offer a promising way to generate realistic synthetic data preserving the original data distribution. However, there is still no objective consensus on how to evaluate their performance. In this study, we set out to validate generative networks for transcriptomics data generation by using statistical distances as robust evaluation metrics. ResultsWe observe that statistical distances enable simultaneous evaluation of global and local data fidelity of generated synthetic data. Because these distances satisfy the properties of true metrics, they also enable formal hypothesis testing to assess whether generative models have in fact converged or are merely approaching the reference distribution. Crucially, optimizing for these distances was found to implicitly select models maximizing other widely used metrics of generative performance, providing evidence of their broad applicability. Overall, our findings indicate that the adoption of these metrics can play a key role in guiding the development of generative models across a wide range of domains.

bioinformatics↗

bioRxiv2024

Explainable deep neural networks for predicting sample phenotypes from single-cell transcriptomics

Recent advances in single-cell RNA-Seq (scRNA-Seq) technologies have revolutionized our ability to gather molecular insights into different phenotypes, such as diseases, at the level of individual cells. The analysis of the resulting data poses significant challenges due to their sparsity and large volume, and proper statistical methods are required to analyze and extract information from scRNA-Seq datasets. Sample classification based on gene expression data has proven effective and valuable for precision medicine applications. However, standard classification schemas are often not suitable for scRNA-Seq due to its unique characteristics, and new algorithms are required to effectively analyze and classify samples at the single-cell level. In this article, we introduce singleDeep, an end-to-end pipeline that streamlines the analysis of scRNA-Seq data training deep neural networks, enabling robust prediction and characterization of sample phenotypes. To validate the effectiveness of singleDeep, we applied it to make predictions on scRNA-Seq datasets from different conditions, including systemic lupus erythematosus and Alzheimers disease. Our results demonstrate strong diagnostic performance, validated both internally and externally. Moreover, compared with traditional machine learning methods applied to pseudobulk data, singleDeep consistently outperformed these approaches. In addition to prediction accuracy, singleDeep provides valuable insights into cell types and gene importance estimation for phenotypic characterization. This functionality provided additional and valuable information in our use cases. For instance, we corroborated that some interferon signature genes are consistently relevant for autoimmunity across all immune cell types in lupus. On the other hand, we discovered that genes linked to dementia have relevant roles in specific brain cell populations, such as APOE in astrocytes.

bioinformatics↗

bioRxiv2024

Generative Models Validation via Manifold Recapitulation Analysis

Comparing empirical distributions is central to generative model evaluation, hypothesis testing and data augmentation in high-dimensional biological data. Established methods such as energy distance summarize each point's relationship to the opposing distribution through a single expected distance, providing sensitivity to location shifts. We introduce Signature Distance (SD), a statistical distance that compares empirical distributions through the mean absolute difference of their sorted pointwise distance profiles. SD is a structural generalization of energy distance and matches its quadratic pairwise-distance cost, with an additional sorting step. In controlled experiments and on TCGA pan-cancer transcriptomic data, we show that (1) SD detects density changes with greater sensitivity than energy distance in the tested scale-contraction scenarios; (2) per-point mean-distance and signature-profile landscapes reveal the geometric mechanisms behind their different penalties; (3) linearly interpolated biological samples that receive no increased penalty from energy distance are penalized by SD; (4) SD provides a direct differentiable potential energy for model-free Langevin data expansion, with a bootstrap resampling protocol to assess the stopping epoch; and (5) SD is directly usable as a differentiable generative training loss. Code to reproduce all experiments is available at github.com/lazzaronico/signature-distance.

bioinformatics↗

bioRxiv2021

Transcriptomics data availability and reusability in the transition from microarray to next-generation sequencing

Over the last two decades, molecular biology has been changed by the introduction of high-throughput technologies. Data sharing requirements have prompted the establishment of persistent data archives. A standardized approach for recording and managing these data was first proposed in the Minimal Information About a Microarray Experiment (MIAME) guidelines. The Minimal Information about a high throughput nucleotide Sequencing Experiment (MINSEQE) proposal was introduced in 2008 as a logical extension of the guidelines to next-generation sequencing (NGS) technologies used for transcriptome analysis. We present a historical snapshot of the data-sharing situation focusing on transcriptomics data from both microarray and RNA-sequencing experiments published between 2009 and 2013, a period during which RNA-seq studies became increasingly popular for transcriptome analysis. We assess how much data from RNA-seq based experiments is actually available in persistent data archives, compared to data derived from microarray based experiments, and evaluate how these types of data differ. Based on this analysis, we provide recommendations to improve RNA-seq data availability, reusability, and reproducibility.

bioinformatics↗

bioRxiv2020

Integrative Network Fusion: a multi-omics approach in molecular profiling

Recent technological advances and international efforts, such as The Cancer Genome Atlas (TCGA), have made available several pan-cancer datasets encompassing multiple omics layers with detailed clinical information in large collection of samples. The need has thus arisen for the development of computational methods aimed at improving cancer subtyping and biomarker identification from multi-modal data. Here we apply the Integrative Network Fusion (INF) pipeline, which combines multiple omics layers exploiting Similarity Network Fusion (SNF) within a machine learning predictive framework. INF includes a feature ranking scheme (rSNF) on SNF-integrated features, used by a classifier over juxtaposed multi-omics features (juXT). In particular, we show instances of INF implementing Random Forest (RF) and linear Support Vector Machine (LSVM) as the classifier, and two baseline RF and LSVM models are also trained on juXT. A compact RF model, called rSNFi, trained on the intersection of top-ranked biomarkers from the two approaches juXT and rSNF is finally derived. All the classifiers are run in a 10x5-fold cross-validation schema to warrant reproducibility, following the guidelines for an unbiased Data Analysis Plan by the US FDA-led initiatives MAQC/SEQC. INF is demonstrated on four classification tasks on three multi-modal TCGA oncogenomics datasets. Gene expression, protein abundances and copy number variants are used to predict estrogen receptor status (BRCA-ER, N=381) and breast invasive carcinoma subtypes (BRCA-subtypes, N=305), while gene expression, miRNA expression and methylation data is used as predictor layers for acute myeloid leukemia and renal clear cell carcinoma survival (AML-OS, N=157; KIRC-OS, N=181). In test, INF achieved similar Matthews Correlation Coefficient (MCC) values and 97% to 83% smaller feature sizes (FS), compared with juXT for BRCA-ER (MCC: 0.83 vs 0.80; FS: 56 vs 1801) and BRCA-subtypes (0.84 vs 0.80; 302 vs 1801), improving KIRC-OS performance (0.38 vs 0.31; 111 vs 2319). INF predictions are generally more accurate in test than one-dimensional omics models, with smaller signatures too, where transcriptomics consistently play the leading role. Overall, the INF framework effectively integrates multiple data levels in oncogenomics classification tasks, improving over the performance of single layers alone and naive juxtaposition, and provides compact signature sizes1.

bioinformatics↗

bioRxiv2019

Integrating deep and radiomics features in cancer bioimaging

Almost every clinical specialty will use artificial intelligence in the future. The first area of practical impact is expected to be the rapid and accurate interpretation of image streams such as radiology scans, histo-pathology slides, ophthalmic imaging, and any other bioimaging diagnostic systems, enriched by clinical phenotypes used as outcome labels or additional descriptors. In this study, we introduce a machine learning framework for automatic image interpretation that combines the current pattern recognition approach (\"radiomics\") with Deep Learning (DL). As a first application in cancer bioimaging, we apply the framework for prognosis of locoregional recurrence in head and neck squamous cell carcinoma (N=298) from Computed Tomography (CT) and Positron Emission Tomography (PET) imaging. The DL architecture is composed of two parallel cascades of Convolutional Neural Network (CNN) layers merging in a softmax classification layer. The network is first pretrained on head and neck tumor stage diagnosis, then finetuned on the prognostic task by internal transfer learning. In parallel, radiomics features (e.g., shape of the tumor mass, texture and pixels intensity statistics) are derived by predefined feature extractors on the CT/PET pairs. We compare and mix deep learning and radiomics features into a unifying classification pipeline (RADLER), where model selection and evaluation are based on a data analysis plan developed in the MAQC initiative for reproducible biomarkers. On the multimodal CT/PET cancer dataset, the mixed deep learning/radiomics approach is more accurate than using only one feature type, or image mode. Further, RADLER significantly improves over published results on the same data.

bioinformatics↗

bioRxiv2018

Evaluating reproducibility of AI algorithms in digital pathology with DAPPER

Artificial Intelligence is exponentially increasing its impact on healthcare. As deep learning is mastering computer vision tasks, its application to digital pathology is natural, with the promise of aiding in routine reporting and standardizing results across trials. Deep learning features inferred from digital pathology scans can improve validity and robustness of current clinico-pathological features, up to identifying novel histological patterns, e.g. from tumor infiltrating lymphocytes. In this study, we examine the issue of evaluating accuracy of predictive models from deep learning features in digital pathology, as an hallmark of reproducibility. We introduce the DAPPER framework for validation based on a rigorous Data Analysis Plan derived from the FDAs MAQC project, designed to analyse causes of variability in predictive biomarkers. We apply the framework on models that identify tissue of origin on 787 Whole Slide Images from the Genotype-Tissue Expression (GTEx) project. We test 3 different deep learning architectures (VGG, ResNet, Inception) as feature extractors and three classifiers (a fully connected multilayer, Support Vector Machine and Random Forests) and work with 4 datasets (5, 10, 20 or 30 classes), for a total 53000 tiles at 512 x 512 resolution. We analyze accuracy and feature stability of the machine learning classifiers, also demonstrating the need for random features and random labels diagnostic tests to identify selection bias and risks for reproducibility. Further, we use the deep features from the VGG model from GTEx on the KIMIA24 dataset for identification of slide of origin (24 classes) to train a classifier on 1060 annotated tiles and validated on 265 unseen ones. The DAPPER software, including its deep learning backbone pipeline and the HINT (Histological Imaging - Newsy Tiles) benchmark dataset derived from GTEx, is released as a basis for standardization and validation initiatives in AI for Digital Pathology.\n\nAuthor summaryIn this study, we examine the issue of evaluating accuracy of predictive models from deep learning features in digital pathology, as an hallmark of reproducibility. It is indeed a top priority that reproducibility-by-design gets adopted as standard practice in building and validating AI methods in the healthcare domain. Here we introduce DAPPER, a first framework to evaluate deep features and classifiers in digital pathology, based on a rigorous data analysis plan originally developed in the FDAs MAQC initiative for predictive biomarkers from massive omics data. We apply DAPPER on models trained to identify tissue of origin from the HINT benchmark dataset of 53000 tiles from 787 Whole Slide Images in the Genotype-Tissue Expression (GTEx) project. We analyze accuracy and feature stability of different deep learning architectures (VGG, ResNet and Inception) as feature extractors and classifiers (a fully connected multilayer, SVMs and Random Forests) on up to 20 classes. Further, we use the deep features from the VGG model (trained on HINT) on the 1300 annotated tiles of the KIMIA24 dataset for identification of slide of origin (24 classes). The DAPPER software is available together with the HINT benchmark dataset.

bioinformatics↗