Dr Maria-Anna (Marianna) Trapotsi

In January 2022, Marianna joined our piRNA team to support our study of piRNA cluster evolution using machine learning and synteny-based approaches. She also took part in our ‘Camformers’ team in the DREAM challenge where she developed a TensorFlow version of our deep learning model.

Biography

Marianna holds a Master of Pharmacy and a Master of Science by Research in medicinal computational chemistry from the University of Hertfordshire. She also holds a PhD from the University of Cambridge, which focused on using heterogeneous information sources for understanding and predicting biological effects of compounds.

Research positions

Bioinformatician (Jan 2022 - Sep 2022)
Cancer Research UK Cambridge Institute, University of Cambridge, UK

PhD Candidate (Sep 2017 - Dec 2021)
Centre for Molecular Informatics Department of Chemistry, in Dr Andreas Bender group in collaboration with AstraZeneca, University of Cambridge, UK.

Qualifications

• PhD, University of Cambridge, UK
• MRes Medicinal Computational Chemistry, University of Hertfordshire, UK
• MPharm, University of Hertfordshire, UK

Honours and awards

• Fourth place in the DREAM 2022 challenge "Predicting gene expression using millions of random promoter sequences" (Sep 2022)

Key publications

• van Lopik J#, Alizada A, Trapotsi M-A, Hannon GJ, Bornelöv S#,§, Czech Nicholson B§ (2023) Unistrand piRNA clusters are an evolutionary conserved mechanism to suppress endogenous retroviruses across the Drosophila genus. bioRxiv 2023.02.27.530199.
• Trapotsi M-A, Mouchet E, Williams G, Monteverde T, Juhani K, Turkki R, Miljkovic F, Martinsson A, Mervin L, Pryde KR, Mullers E, Barrett I, Engkvist O, Bender A, Moreau K§ (2022) Cell morphological profiling enables high-throughput screening for PROteolysis TArgeting Chimera (PROTAC) phenotypic signature. ACS Chemical Biology 6;17(7):1733-44.
• Trapotsi M-A#, Hosseini-Gerami L#, Bender A§ (2022). Computational analyses of mechanism of action (MoA): data, methods and integration. RSC Chemical Biology 3(2), 170-200.
• Trapotsi M-A, Mervin LH, Afzal AM, Sturm N, Engkvist O, Barrett IP, Bender A§ (2021) Comparison of chemical structure and cell morphology information for multitask bioactivity predictions. Journal of Chemical Information and Modeling 61(3), 1444-1456.
• Mervin LH#,§, Trapotsi M-A#, Afzal AM, Barrett IP, Bender A, Engkvist O (2021). Probabilistic Random Forest improves bioactivity predictions close to the classification threshold by taking into account experimental uncertainty. Journal of Cheminformatics 13, 1-17.