Data engineering
Shared metadata for data-centric materials science
Abstract The expansive production of data in materials science, their widespread sharing and repurposing requires educated support and stewardship. In order to ensure that this need helps rather than hinders scientific work, the implementation of the FAIR-data principles (Findable, Accessible, Interoperable, and Reusable) must not be too narrow. Besides, the wider materials-science community ought to agree on the strategies to tackle the challenges that are specific to its data, both from computations and experiments. In this paper, we present the result of the discussions held at the workshop on “Shared Metadata and Data Formats for Big-Data Driven Materials Science”. We start from an operative definition of metadata, and the features that a FAIR-compliant metadata schema should have. We will mainly focus on computational materials-science data and propose a constructive approach for the FAIRification of the (meta)data related to ground-state and excited-states calculations, potential-energy sampling, and generalized workflows. Finally, challenges with the FAIRification of experimental (meta)data and materials-science ontologies are presented together with an outlook of how to meet them. Authors Luca M. Ghiringhelli, Carsten Baldauf, Tristan Bereau, Sandor Brockhauser, Christian Carbogno, Javad Chamanara, Stefano Cozzini, Stefano Curtarolo, Claudia Draxl, Shyam Dwaraknath, Ádám Fekete, James Kermode, Christoph T. Koch, Markus Kühbach, Alvin Noe Ladines, Patrick Lambrix, Maja-Olivia Himmer, Sergey V. Levchenko, Micael Oliveira, Adam Michalchuk, Ronald E. Miller, Berk Onat, Pasquale Pavone, Giovanni Pizzi, Benjamin Regler, Gian-Marco Rignanese, Jörg Schaarschmidt, Markus Scheidgen, Astrid Schneidewind, Tatyana Sheveleva, Chuanxun Su, Denis Usvyat, Omar Valsson, Christof Wöll & Matthias Scheffler Journal Scientific Data Publication Date 14/09/2023 Consult the publication
An Unsupervised Machine Learning Method Stratifies Chronic Lymphocytic Leukemia Patients in Novel Categories with Different Risk of Early Treatment
Abstract: Novel scoring systems have been developed in recent years to improve the accuracy of prognostication from historical clinical staging systems (Rai, Binet) for chronic lymphocytic leukemia (CLL). Most of them, however, rely on discretized and dichotomic values of the various biomarkers to infer prognosis. Here we analyzed the immunophenotypic and (immuno)genetic profiles in a wide CLL cohort by applying unsupervised machine learning methods elaborating prognostic factors as continuous variables, to identify novel relationships and interactions likely missed in conventional models. Authors Francesca Cuturello, Federico Pozzo, Edith Natalia Villegas Garcia, Francesca Maria Rossi, Massimo Degan, Paola Nanni, Ilaria Cattarossi, Eva Zaina, Paola Varaschin, Alessandra Braida, Michele Berton, Laura Zannier, Filippo Vit, Erika Tissino, Tamara Bittolo, Roberta Laureana, Giovanni D’Arena, Luca Laurenti, Agostino Tafuri, Jacopo Olivieri, Francesco Zaja, Annalisa Chiarenza, Maria Ilaria Del Principe, Riccardo Bomben, Antonella Zucchetto, Stefano Cozzini, Alessio Ansuini, Alberto Cazzaniga, Valter Gattei Journal Blood Publication date 15/11/2022 Consult the pubblication
Adversarial Attacks on Protein Language Models
Abstract: Deep Learning models for protein structure prediction, such as AlphaFold2, leverage Transformer architectures and their attention mechanism to capture structural and functional properties of amino acid sequences. Despite the high accuracy of predictions, biologically insignificant perturbations of the input sequences, or even single point mutations, can lead to substantially different 3d structures. On the other hand, protein language models are often insensitive to biologically relevant mutations that induce misfolding or dysfunction (e.g. missense mutations). Precisely, predictions of the 3d coordinates do not reveal the structure-disruptive effect of these mutations. Therefore, there is an evident inconsistency between the biological importance of mutations and the resulting change in structural prediction. Inspired by this problem, we introduce the concept of adversarial perturbation of protein sequences in continuous embedding spaces of protein language models. Our method relies on attention scores to detect the most vulnerable amino acid positions in the input sequences. Adversarial mutations are biologically diverse from their references and are able to significantly alter the resulting 3d structures. Authors Ginevra Carbone, Francesca Cuturello, Luca Bortolussi, Alberto Cazzaniga Journal Machine Learning for Structural Biology Workshop, NeurIPS 2022. Publication date 25/10/2022 Consult the pubblication
DPCfam: unsupervised protein family classification by Density Peak Clustering of large sequence datasets
Abstract: As the UniProt database approaches the 200 million entries’ mark, the vast majority of proteins it contains lack any experimental validation of their functions. In this context, the identification of homologous relationships between proteins remains the single most widely applicable tool for generating functional and structural hypotheses in silico. Although many databases exist that classify proteins and protein domains into homologous families, large sections of the sequence space remain unassigned. Authors Elena Tea Russo, Federico Barone, Alex Bateman, Stefano Cozzini, Marco Punta, Alessandro Laio Journal PLOS Computational Biology Publication date 19/10/2022 Consult the pubblication
Higher rank motivic Donaldson–Thomas invariants of 𝔸3 via wall-crossing, and asymptotics
Abstract We compute, via motivic wall-crossing, the generating function of virtual motives of the Quot scheme of points on 𝔸3, generalising to higher rank a result of Behrend–Bryan–Szendrői. We show that this motivic partition function converges to a Gaussian distribution, extending a result of Morrison. Authors Alberto Cazzaniga, Dimbinaina Ralaivaosaona, Andrea T. Ricolfi Journal Mathematical Proceedings Publication Date 05/05/2022 Consult the publication
Framed motivic Donaldson–Thomas invariants of small crepant resolutions
Abstract For an arbitrary integer 𝑟 ≥1, we compute r-framed motivic DT and PT invariants of small crepant resolutions of toric Calabi–Yau 3-folds, establishing a “higher rank” version of the motivic DT/PT wall-crossing formula. This generalises the work of Morrison and Nagao. Our formulae, in particular their relationship with the 𝑟 =1 theory, fit nicely in the current development of higher rank refined DT invariants. Authors Alberto Cazzaniga, Andrea T. Ricolfi Journal Mathematische Nachrichten Publication Date 12/04/2022 Consult the publication
Deep artificial neural network for prediction of atrial fibrillation through the analysis of 12‐leads standard ECG
Abstract Atrial Fibrillation (AF) is a heart’s arrhythmia which, despite being often asymptomatic, represents an important risk factor for stroke, therefore being able to predict AF at the electrocardiogram exam, would be of great impact on actively targeting patients at high risk. In the present work we use Convolution Neural Networks to analyze ECG and predict Atrial Fibrillation starting from realistic datasets, i.e. considering fewer ECG than other studies and extending the maximal distance between ECG and AF diagnosis. We achieved 75.5% (0.75) AUC firstly increasing our dataset size by a shifting technique and secondarily using the dilation parameter of the convolution neural network. In addition we find that, contrarily to what is commonly used by clinicians reporting AF at the exam, the most informative leads for the task of predicting AF are D1 and avR. Similarly, we find that the most important frequencies to check are in the range of 5-20 Hz. Finally, we develop a net able to manage at the same time the electrocardiographic signal together with the electronic health record, showing that integration between different sources of data is a profitable path. In fact, the 2.8% gain of such net brings us to a 78.6% (std 0.77) AUC. In future works we will deepen both the integration of sources and the reason why we claim avR is the most informative lead. Authors A. Scagnetto, G. Barbati, I. Gandin, C. Cappelletto, G. Baj, A. Cazzaniga, F. Cuturello, A. Ansuini, L. Bortolussi, A. Di Lenarda Journal Arxiv Preprint Publication Date 14/01/2022 Consult the publication
Framed sheaves on projective space and Quot schemes
Abstract: We prove that, given integers m≥3, r≥1 and n≥0, the moduli space of torsion free sheaves on Pm with Chern character (r,0,…,0,−n) that are trivial along a hyperplane D⊂Pm is isomorphic to the Quot scheme QuotAm(O⊕r,n) of 0-dimensional length n quotients of the free sheaf O⊕r on Am. The proof goes by comparing the two tangent-obstruction theories on these moduli s Authors Alberto Cazzaniga, Andrea T. Ricolfi Journal Mathematische Zeitschrift Publication date 28/06/2021 Consult the pubblication
Speeding‐up pruning for Artificial Neural Networks: Introducing Accelerated Iterative Magnitude Pruning
Abstract: In recent years, Artificial Neural Networks (ANNs) pruning has become the focal point of many researches, due to the extreme overparametrization of such models. This has urged the scientific world to investigate methods for the simplification of the structure of weights in ANNs, mainly in an effort to reduce time for both training and inference. Frankle and Carbin [1], and later Renda, Frankle, and Carbin [2] introduced and refined an iterative pruning method which is able to effectively prune the network of a great portion of its parameters with little to no loss in performance. On the downside, this method requires a large amount of time for its application, since, for each iteration, the network has to be trained for (almost) the same amount of epochs of the unpruned network. In this work, we show that, for a limited setting, if targeting high overall sparsity rates, this time can be effectively reduced for each iteration, save for the last one, by more than 50%, while yielding a final product (i.e., final pruned network) whose performance is comparable to the ANN obtained using the existing method. Authors: Marco Zullich, Eric Medvet; Felice Andrea Pellegrino; Alessio Ansuini Journal: 2020 25th International Conference on Pattern Recognition (ICPR) Publication date: 05/05/2021 Consult the publication
SOMEnv: An R package for mining environmental monitoring datasets by Self‐Organizing Map and k‐means algorithms with a graphical user interface
Abstract: The Self-Organizing Map (SOM) algorithm belongs to the family of artificial neural networks. It is an unsupervised method that requires no a priori knowledge regarding experimental data classification. Further, it can deal with large datasets and non-linear problems, providing powerful visualization features for outcome exploration on 2D maps. For environmental pollution assessments other unsupervised techniques are widely used, such as principal component and hierarchical cluster analyses, but their application for mining large datasets and properly visualizing the results is limited, making them difficult to use for handling of large datasets obtained by high frequency environmental monitoring. This study presents an R package (SOMEnv) that allows non-expert users to elaborate by SOM algorithm environmental variables (pollutants and/or chemical physical properties) recorded with high frequency for a long monitoring period. Additionally, SOMEnv can also be used for elaborating small datasets derived from uneven sampling. All the calculations and outcome visualizations can be done using a graphical user interface (GUI), meaning that experience in R software coding is not necessary, and only a basic knowledge regarding the employed algorithm is needed to interpret the results. The benefits of the SOMEnv package are that (i) both the software environment and tool are freely available; (ii) it is able to handle large datasets; (iii) it provides heuristic rules for SOM initialization; (iv) it has a built-in GUI for performing calculations and visualizing the results. Moreover, it comes with a wide range of visualizations, several of which are dedicated to high frequency data monitoring. An example of application is presented. The package is freely available on the Comprehensive R Archive Network (CRAN) repository. Authors Sabina Licen, Marco Franzon, Tommaso Rodani, Pierluigi Barbieri Journal Microchemical Journal Publication date 31/12/2020 Consult the pubblication
Investigating Similarity Metrics for Convolutional Neural Networks in the Case of Unstructured Pruning
Abstract: Deep Neural Networks (DNNs) are essential tools of modern science and technology. The current lack of explainability of their inner workings and of principled ways to tame their architectural complexity triggered a lot of research in recent years. There is hope that, by making sense of representations in their hidden layers, we could collect insights on how to reduce model complexity—without performance degradation—by pruning useless connections. It is natural then to ask the following question: how similar are representations in pruned and unpruned models? Even small insights could help in finding principled ways to design good lightweight models, enabling significant savings of computation, memory, time and energy. In this work, we investigate empirically this problem on a wide spectrum of similarity measures, network architectures and datasets. We find that the results depend critically on the similarity measure used and we discuss briefly the origin of these differences, concluding that further investigations are required in order to make substantial advances. Authors: Alessio Ansuini, Eric Medvet, Felice Andrea Pellegrino, Marco Zullich Journal: International Conference on Pattern Recognition Applications and Methods (ICPRAM) Publication date: 23/12/2020 Consult the publication
Hierarchical nucleation in deep neural networks
Abstract Deep convolutional networks (DCNs) learn meaningful representations where data that share the same abstract characteristics are positioned closer and closer. Understanding these representations and how they are generated is of unquestioned practical and theoretical interest. In this work we study the evolution of the probability density of the ImageNet dataset across the hidden layers in some stateof-the-art DCNs. We find that the initial layers generate a unimodal probability density getting rid of any structure irrelevant for classification. In subsequent layers density peaks arise in a hierarchical fashion that mirrors the semantic hierarchy of the concepts. Density peaks corresponding to single categories appear only close to the output and via a very sharp transition which resembles the nucleation process of a heterogeneous liquid. This process leaves a footprint in the probability density of the output layer where the topography of the peaks allows reconstructing the semantic relationships of the categories. Authors Diego Doimo, Aldo Glielmo, Alessio Ansuini, Alessandro Laio Journal NIPS’20: Proceedings of the 34th International Conference on Neural Information Processing Systems Publication date 06/12/2020 Consult the publication