AnacletoLAB collaborates with several research groups in Computational Biology, Medicine and Molecular Biology in Europe and in the United States, as we believe interdisciplinary collaboration is essential to effectively tackle relevant bio-medical problems with Artificial Intelligence methods and techniques.

We collaborated or are collaborating with:

  • Jackson Laboratory for Genomic Medicine, Farmington, CT, USA
  • Department of Computer Science, Bioinformatics Centre for Systems and Synthetic Biology, Royal Holloway, University of London
  • Berlin Institute of Health, Charitè Universitatsmedizin, Berlin
  • Institute of Medical Genetics and Applied Genomics at the University Hospital Tübingen, Germany
  • Wellcome Trust Sanger Institute and the European Bioinformatics Institute (EBI) of Hinxton, UK
  • Artificial Intelligence department of the University of Granada, Spain
  • Computer Science Dept of Aalto University, Helsinki, Finland
  • Division of Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA, USA
  • Department of Medical Informatics and Clinical Epidemiology, Oregon Health & Science University, Portland, USA
  • Queen Mary University of London
  • European Center for Living Technologies, Venice
  • Other national research groups both in the medical field (National Cancer Institute (INT), and S. Raffaele Hospital of Milan, National Institute of Molecular Genetics) and Computer Science (University of Pisa, Palermo and Cagliari).


European PRACE project “ParBigMen: ParSMURF application to Big genomic and epigenomic data for the detection of pathogenic variants in Mendelian diseases”, (2020-2021)

This project funded by the European Union aims at discovering pathogenic variants associated with genetic diseases, using Machine Learning and andvanced High Performance Computing methods. To this end we will use HPC resources from SuperMUC-NG, a HPC cluster ranked in the top 10 supercomputers in the world.

EU Collaborative Doctoral Partnership in Genomics and Bioinformatics (2020-2025)

This joint doctoral program between the PhD School of Computer Science of UNIMI and the European Union Joint Research Center (JRC) of Ispra is co-funded by the European Commission.

The program is aimed at training researchers in the field of Genomics and Bioinformatics, able both to carry out innovative research in these scientific disciplines and to scientifically support the European Commission in making decisions about European policies for Genomics, Bioinformatics and Data Analytics in Health-care.

Finding-MS (2019-2022)

This project is funded through the European ERA-PerMed Joint Transnational Call (JTC) 2018 on "Research projects on Personalized Medicine: smart combinations for pre-clinical and clinical research with data and ICT solutions ".

The project is in collaboration with the S.Raffaele Hospital of Milan, the CNR - Institute for Bio-medical Technologies, the Center Hospitalier Universitaire de Toulouse and geneXplain, a German bioinformatics company (2019-2022). The overall aim of the project is to assess the genetic, epi-genetic and environmental factors underlying Multiple Sclerosis and to construct predictive models to support the prognosis and the the therapeutic treatment of patients. Our contribution consists in the development of machine learning methods to predict disease activity and to switch from 1st-line to 2nd-line drugs for Multiple Sclerosis.

Multicriteria Data Structures and Algorithms: from compressed to learned indexes,and beyond (2019-2022)

This PRIN project, funded by MIUR, is coordinated by the University of Pisa, and involves also University of Palermo and University of Piemonte Orientale.

The main aim of the project consists in the design and development of novel Multicriteria Data Structures and Algorithms to successfully meet the needs of efficiently storing, retrieving and analyzing massive datasets, originated by very different sources.

The multicriteria feature refers to the fact that we seamlessly integrate, via a principled optimization approach, modern compressed data structures with new, revolutionary, data structures learned from the input data by using proper machine-learning tools. The goal of the optimization is to select, among a family of properly designed data structures, the one that best fits the multiple constraints imposed by its context of use. In this project, we will lay down the theoretical and algorithmic-engineering foundations of this novel research area, which has the potential of supporting innovative data-analysis tools and data-intensive applications, including applications in bioinformatics and computational genomics.

Developing machine learning methods for the prioritization of regulatory variants in human disease (2018-2020)

This project, in collaboration with the Berlin Institute of Health is funded by MIUR (Italy) and DAAD (Germany) and its aim is to develop advanced machine learning methods for the detection of regulatory variants associated with human diseases and for the prediction of tissue-specific regulatory regions in the human genome.

RegNet: Deep Neural Networks for genome-wide regulatory region prediction (2019-2020)

This project is funded by ELIXIR. ELIXIR is funded by the European Union (H2020) and by the Innovative Medicine Initiative and represents one of the main European hub for supporting supercomputing and data management in bioinformatics. In this project we use the Maroni supercomputer for the genome-wide prediction of regulatory regions.

Machine Learning and Big Data analysis for Computational Biology (2019-2020)

This project is funded by University of Milano.

The aim of the project is the development of machine learning methods designed for applications in Genomic Medicine and other areas of Computational Biology, as well as the the design and implementation of high-performance Computing Tools for relevant applications in Bioinformatics.

Development of innovative computational techniques for integrated credit management and support for their collection (2020)

This project if funded by Area s.r.l., an Italian company, leader in credit management.

The research project consists in the analysis and study of innovative methodological and technological solutions to improve the acquisition and processing of data relating to the collection of credits, generated by both public administrations and private entities. Through the cataloging in an integrated database of debit position data, it will be possible to apply machine learning techniques to characterize and quantitatively measure the creditworthiness of the users, in order to efficiently organize the collection activities.

Computational methods and techniques to support the activity of debt collection agencies (2020)

This project if funded by Area s.r.l., an Italian company, leader in credit management.

The objective of this project consists in the preliminary study of computational methods for the storage and efficient management of big data relating to the debts of public and private subjects and for the prediction of the solvency of debtors with machine learning techiques.

ParStoBig: ParSMURF Scaling to Big Data (2019)

The Partnership for Advanced Computing in Europe (PRACE) Research Infrastructure provides a persistent world-class high-performance computing service for scientists and researchers from academia and industry in Europe.

ParStoBig is a preliminary grant whose objective is to show the reliability and the scalability of our parSMURF parallel system, in order to obtain a full PRACE grant.

The main objectives of the project are the following:

1) Application of parSMURF to big omics data, where a large number of features will be investigated and used to predict pathogenic variants. We expect to obtain breakthrough models able to achieve a significant advance in state-of-the-art prediction of pathogenic variants in Mendelian and complex genetic diseases.

2) The release of a highly parallel parSMURF application able to scale with big data and to fully exploit high-performance Computing architectures for relevant prediction problems in the context of Personalized and Precision Medicine

HyperGeV: Detection of Deleterious Genetic Variation through Hyper-ensemble Methods (2016-2018)

Funded by CINECA and Regione Lombardia through the LISA (Interdisciplinary Laboratory for Advanced Simulation) project.

The objective of this project is to provide a first parallel implementation of HyperSMURF, a hyper-ensemble of random forests able to deal with highly imbalanced genomic data. This parallel version of HyperSMURF will be applied to the detection of genetic variants associated with rare genetic diseases.

HPC-SoMuC: Development of Innovative HPC Methods for the Detection of Somatic Mutations in Cancer (2017-2018)

Funded by CINECA and Regione Lombardia through the LISA project.

The aim of this project is the development of machine learning methods able to exploit parallel computational techniques and develop easy-to-use software tools to handle the huge amount of genomic information today available for the detection of somatic point mutations in cancer.

A composite predictive model of response to Fingolimod (2016-2018)

This project, funded by the Italian Multiple Sclerosis Foundation, is lead by the Genetics Laboratory of the Complex Neurological Diseases of the S. Raffaele Hospital in Milan. Using the clinical and genotypic data of S. Raffaele we developed a predictive model for the patient response to the Fingolimod, a second level drug for the treatment of Multiple Sclerosis. The genetic biomarkers associated with the response to the Fingolimod drug, identified by the data of S. Raffaele and our predictive model, are currently being patented.