Computer Laboratory

pl

left: talk on Data ownership & Collective Awareness in the AI era, given at MYDATA 2019 Helsinki; middle: work; right: relax

(Here photos on Cambridge exam "lifestyle")

(Here after teaching kids how to code)

Pietro Liò

I am Full Professor at the department of Computer Science and Technology of the University of Cambridge and I am a member of the Artificial Intelligence group. I am a member of the Cambridge Centre for AI in Medicine.
My research interest focuses on developing Artificial Intelligence and Computational Biology models to understand diseases complexity and address personalised and precision medicine. Current focus is on Graph Neural Network modeling.

I have a MA from Cambridge, a PhD in Complex Systems and Non Linear Dynamics (School of Informatics, dept of Engineering of the University of Firenze, Italy) and a PhD in (Theoretical) Genetics (University of Pavia, Italy).
Other Affliations: I am member of CAMBRIDGE CENTRE FOR AI IN MEDICINE - the Integrate Cancer Medicine Institute,  the committee of MPhil in Computational Biology (Stakeholder Group for the CCBI) , steering committee of Cambridge BIG dataVPH-UK (Virtual Physiological Human), Fellow and member of the Council of Clare Hall College , I am member of Ellis, the European Lab for Learning & Intelligent Systems, I am member of the Academia Europaea; I am listed in www.topitalianscientists.org/Top_italian_scientists_VIA-Academy.aspx
 
 

Admin: member of Complaint Officer/Examination Review Committee (Cambridge University); reviewer of 4 MPhils (Newcastle University), steering committee VPH-UK.
I am happy to receive enquiries for PhD applications. I have successfully completed the equality and diversity essentials.
Office: FC20; tel: +44 (0)1223-763604; E_mail: Pietro.Lio at  cl.cam.ac.uk


Data Integration, cross-modality, evidence synthesis, Machine Learning in medicine


the figure below shows a variety of plots from different papers on deep learning (see at the bottom) focusing on data integration. Data integration is essential to extract all the information, including causality, about a certain subject.
pl
(Various Deep Learning Approaches for data integration: arXiv:1909.06442; arXiv:1907.05628; arXiv:1905.08721; arXiv:1905.06515; arXiv:1905.00534; arXiv:1904.06316; Medical Imaging 2019: Image Processing 10949, 109491L; arXiv:1901.03906; arXiv:1901.03419; BioRxiv, 801605; arXiv:1809.10341; International Conference on Theory and Application of Diagrams, 390-398; Bioinformatics 34 (17), 2944-2950; Nature communications 8 (1), 2045)

Methods Integration: relationship between computational modeling and machine learning

The figure below shows on the right, examples of modeling techniques ( a computational/mathematical model is a representation of the essential aspects of an existing system (or a system to be constructed) which presents knowledge of that system in usable form' (Eykhoff, 1974). On the left there are methodologies, implemented in software, to analyse Big data, showing the ability to automatically learn and improve from experience without being explicitly programmed. At the bottom some relevant publications from the group.
pl
(adapted from Bartocci and Liò, Computational Modeling, Formal Analysis, and Tools for Systems Biology, Plos Computational Biology; also MLCSB 2018: 121-141; NeuroImage 189: 276-287 (2019), CoRR abs/1906.09807 (2019); BMC Bioinformatics 19(1): 439:1-439:18 (2018);CoRR abs/1812.03715 (2018); BMC Bioinformatics 17(S-4): 83 (2016); Mol. BioSyst., 2011, 7, 2796-2803; ACRI 2008: 354-361; Front. Genet., 14 June 2018 | https://doi.org/10.3389/fgene.2018.00206; Bioinformatics 14(8): 726-733 (1998); Fundam. Inform. 171(1-4): 367-392 (2020); BioRxiv, 801605 2019 )


Recent papers, almost full list on Google Scholar or from this pdf

Papers on research on Covid19:

A machine learning model to identify early stage symptoms of SARS-Cov-2 infected patients (Expert Systems with Applications)

Pathogenetic profiling of COVID-19 and SARS-like viruses (Briefings in bioinformatics)


Modeling Social Groups, Policies and Cognitive Behavior in COVID-19 Epidemic Phases. Basic Scenarios (Substantia)


The Computational Patient has Diabetes and a COVID (arxiv)


Forecasting ultra-early intensive care strain from COVID-19 in England (medxiv)


Recent papers accepted at Neurips 2020

On Second Order Behaviour in Augmented Neural ODEs

Path Integral Based Convolution and Pooling for Graph Neural Networks

Principal Neighbourhood Aggregation for Graph Nets

Constraining Variational Inference with Geometric Jensen-Shannon Divergence

Other recent papers:

Petar Veličković, William Fedus, William L. Hamilton, Pietro Lio', Yoshua Bengio, R Devon Hjelm Deep Graph Infomax. https://arxiv.org/abs/1809.10341

Haider S. at al. Pathway-Based Subnetworks Enable Cross-Disease Biomarker Discovery. In press on Nature Communications.

Editing a Springer Book on Automated Reasoning in Systems Biology and Medicine with Paolo Zuliani
J. Despeyroux, A. Felty, P. Lio’, C. Olarte A Logical Framework for Modelling Breast tumorigenesis. submitted to International Symposium on Molecular Logic and Computational Synthetic Biology.

Hui Xiao, Krzysztof Bartoszek and Pietro Lio'. Multi-omic analysis of signaling factors in inflammatory comorbidities. BMC Bioinformatics (in press)

Ioana Bica, Petar Velickovi ́c, Hui Xiao and Pietro Lio' (2018) Multi-omics data integration using cross-modal neural networks ESANN 2018 proceedings, European Symposium on Artificial Neural Networks, Computational  Intelligence  and Machine Learning.  Bruges (Belgium), 25-27 April 2018

Di Stefano et al, Social Dynamics Modeling of Chrono-nutrition. Plos Comput. Biology  https://doi.org/10.1371/journal.pcbi.1006714

Edgar Liberis Petar Velickovic, Pietro Sormanni, Michele Vendruscolo and Pietro Lio' (2018) Parapred: Antibody Paratope Prediction using Convolutional and Recurrent Neural Networks. Bioinformatics 2018 Apr 16. doi: 10.1093/bioinformatics/bty305.

Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio', Yoshua Bengio Graph Attention Networks. accepted at ICLR 2018

Scatà M, Di Stefano A, La Corte A, Lio' P. (2018) Quantifying the propagation of distress and mental disorders in social networks. Sci Rep. 2018 Mar 22;8(1):5005. doi: 10.1038/s41598-018-23260-2.

Duo Wang, Mateja Jamnik, Pietro Lio' (2018)  Investigating diagrammatic reasoning with deep
neural networks. Accepted at Diagrams 2018

Bianchi L, Lio' P. Opportunities for community awareness platforms in personal genomics and bioinformatics education. Brief Bioinform. 2017 Nov 1;18(6):1082-1090. doi: 10.1093/bib/bbw078


Awards

2020 - AIAI2020 Best student paper  (16th AIAI 2020 : 16th Artificial Intelligence Applications and Innovations), Crete
2018 - BITS Bioinformatics Italian Society- Torino
bits
2016: The paper “Bioaccumulation modelling and sensitivity analysis for discovering key players in contaminated food webs: The case study of PCBs in the Adriatic Sea” (M. Taffi first author) has won the 2016 BYRA first prize at ISEM (The International Society for Ecological Modelling Global Conference) 2016 and the MCED (Modelling Complex Ecological Dynamics) 2016 Award second prize.
 
2018 - Visiting professor at the University of Padova.
2013 - Lagrange Fellowship (ISI, Universita' Piemonte Orientale).

2012 - Best Paper (Computing with Metabolic Machines) at Turing 100 in Manchester (first author Claudio Angione)
2011 - 3rd prize awarded by the European Commission (sponsored by ERCIM) for the  "Methodological bridges for complex systems" (with E. Merelli and N. Paoletti) at the FET 11, 2011  - Future and Emerging Technologies Conference ('Science Beyond Fiction') conference  - Budapest