Dottore di ricerca

ciclo: XXXV

supervisore: Aris Anagnostopoulos
co-supervisore: Paolo Tieri

Titolo della tesi: Toward Explainable Biomedical Deep Learning

Deep learning has been extensively utilized in the domains of bioinformatics and chemoinformatics, yielding compelling results. However, neural networks have predominantly been regarded as black boxes, characterized by internal mechanisms that hinder interpretability due to the highly nonlinear functions they learn. In the biomedical field, this lack of interpretability is undesirable, as it is imperative for scientists to comprehend the reasons behind the occurrence of specific diseases or the molecular properties that make a compound effective against a particular target protein. Consequently, the inherent closure of those models keeps their results far from being trusted. To address this issue and make deep learning suitable for bioinformatics and chemoinformatics tasks, there is the urge to develop techniques for explainable artificial intelligence (XAI). These techniques should be capable of measuring the significance of input features for predictions or determining the strength of their interactions. The ability to provide explanations must be integrated into the biomedical deep learning pipeline, which utilizes available data sources to uncover new insights regarding potentially disease-associated genes, thereby facilitating the repurposing and development of new drugs. In line with this objective, this thesis focuses on the development of innovative explainability techniques for neural networks and demonstrates their effective applications in bioinformatics and medicinal chemistry. The devised models find their place in the pipeline, wherein each component of the protocol generates effective and explainable results. These results span from the discovery of disease genes to the repurposing and development of drugs. However, deep learning lives in synergy with classical machine learning models and network-based algorithms, which remain relevant in this field and, therefore, hold a place within this thesis. Moreover, they offer the basis for proper training of deep learning models and pave the way for the development of XAI techniques for neural networks. The proposed work demonstrates how XAI can benefit biomedicine, proving deep learning to be a powerful tool to solve biomedical problems and that the obtained results can be explained. This contributes to the delivery of not only accurate but also trustworthy results, fulfilling the need for explainability of medical doctors, geneticists, and scientists in the life sciences and leading toward a fully explainable biomedical deep learning pipeline.

Produzione scientifica

11573/1709034 - 2024 - Protocol to explain support vector machine predictions via exact Shapley value computation
Mastropietro, Andrea; Bajorath, Jürgen - 01a Articolo in rivista
rivista: STAR PROTOCOLS (: New York: Cell Press Elsevier Inc) pp. - - issn: 2666-1667 - wos: (0) - scopus: 2-s2.0-85189875857 (0)

11573/1687346 - 2023 - XGDAG: explainable gene–disease associations via graph neural networks
Mastropietro, Andrea; De Carlo, Gianluca; Anagnostopoulos, Aris - 01a Articolo in rivista
rivista: BIOINFORMATICS ([Oxford] : Oxford University Press) pp. - - issn: 1367-4811 - wos: WOS:001047635500011 (2) - scopus: 2-s2.0-85168221756 (2)

11573/1691795 - 2023 - Calculation of exact Shapley values for explaining support vector machine models using the radial basis function kernel
Mastropietro, Andrea; Feldmann, Christian; Bajorath, Jürgen - 01a Articolo in rivista
rivista: SCIENTIFIC REPORTS (London: Springer Nature London: Nature Publishing Group) pp. 19561- - issn: 2045-2322 - wos: (0) - scopus: 2-s2.0-85176220589 (2)

11573/1691854 - 2023 - Learning characteristics of graph neural networks predicting protein–ligand affinities
Mastropietro, Andrea; Pasculli, Giuseppe; Bajorath, Jürgen - 01a Articolo in rivista
rivista: NATURE MACHINE INTELLIGENCE (London: Nature Research, 2019-) pp. - - issn: 2522-5839 - wos: WOS:001101937000001 (3) - scopus: 2-s2.0-85176461869 (9)

11573/1668281 - 2023 - NIAPU: Network-Informed Adaptive Positive-Unlabeled learning for disease gene identification
Stolfi, Paola; Mastropietro, Andrea; Pasculli, Giuseppe; Vergni, Davide; Tieri, Paolo - 01a Articolo in rivista
rivista: BIOINFORMATICS (-Oxford : Oxford University Press, 1998-) pp. - - issn: 1367-4803 - wos: (0) - scopus: 2-s2.0-85148307362 (5)

11573/1665431 - 2022 - PROCONSUL: PRObabilistic exploration of CONnectivity Significance patterns for disease modULe discovery
Luca, Riccardo De; Carfora, Marco; Blanco, Gonzalo; Mastropietro, Andrea; Petti, Manuela; Tieri, Paolo - 04b Atto di convegno in volume
congresso: 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (Las Vegas; USA)
libro: Proceedings - 2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022 - (978-1-6654-6819-0; 978-1-6654-6820-6)

11573/1661039 - 2022 - Protocol to explain graph neural network predictions using an edge-centric Shapley value-based approach
Mastropietro, Andrea; Pasculli, Giuseppe; Bajorath, Jürgen - 01a Articolo in rivista
rivista: STAR PROTOCOLS (: New York: Cell Press Elsevier Inc) pp. - - issn: 2666-1667 - wos: WOS:001058452300008 (3) - scopus: 2-s2.0-85142483416 (3)

11573/1652545 - 2022 - EdgeSHAPer: Bond-Centric Shapley Value-Based Explanation Method for Graph Neural Networks
Mastropietro, Andrea; Pasculli, Giuseppe; Feldmann, Christian; Rodríguezpérez, Raquel; Bajorath, Jürgen - 01a Articolo in rivista
rivista: ISCIENCE ([Cambridge MA] : Cell Press Elsevier Inc.) pp. - - issn: 2589-0042 - wos: WOS:000888874800005 (10) - scopus: 2-s2.0-85138031675 (12)

Shahini, E.; Pasculli, G.; Mastropietro, A.; Stolfi, P.; Tieri, P.; Vergni, D.; Cozzolongo, R.; Giannelli, G.; Pesce, F. - 01h Abstract in rivista
rivista: DIGESTIVE AND LIVER DISEASE (-Roma: Editrice Gastroenterologica Italiana; Milano: Elsevier -Roma: Editrice Gastroenterologica Italiana. -Ospedaletto Pisa: Pacini) pp. S106- - issn: 1590-8658 - wos: WOS:000791821000096 (1) - scopus: (0)

11573/1650880 - 2022 - Network Proximity-Based Drug Repurposing Strategy for Early and Late Stages of Primary Biliary Cholangitis
Shahini, Endrit; Pasculli, Giuseppe; Mastropietro, Andrea; Stolfi, Paola; Tieri, Paolo; Vergni, Davide; Cozzolongo, Raffaele; Pesce, Francesco; Giannelli, Gianluigi - 01a Articolo in rivista
rivista: BIOMEDICINES (Basel : MDPI) pp. 1694- - issn: 2227-9059 - wos: WOS:000832261000001 (0) - scopus: 2-s2.0-85136347643 (1)

11573/1565282 - 2021 - Adaptive Positive-Unlabelled Learning via Markov Diffusion
Stolfi, Paola; Mastropietro, Andrea; Pasculli, Giuseppe; Tieri, Paolo; Vergni, Davide - 02a Capitolo o Articolo
libro: Computer Science and Machine Learning - ()

11573/1444275 - 2020 - A CNN approach for audio classification in construction sites
Maccagno, Alessandro; Mastropietro, Andrea; Mazziotta, Umberto; Scarpiniti, Michele; Lee, Yong-Cheol; Uncini, Aurelio - 04b Atto di convegno in volume
congresso: The 29th Italian Workshop on Neural Networks (WIRN 2019) (Vietri sul Mare (SA); Italy)
libro: Progresses in Artificial Intelligence and Neural Systems - (978-981-15-5092-8; 978-981-15-5093-5)

© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma