Hello! I am a PhD candidate in Computing at Imperial College London, supervised by Michael Bronstein and Kirill Veselkov. My research focuses on the application of graph machine learning to biomedical problems, with a special emphasis on drug repositioning, combinatorial therapeutics and hyperfoods (i.e. molecules in foods with disease-beating properties) prediction.
I am also passionate about increasing the presence of minorities in STEM, a goal I work towards by regularly volunteering as an instructor in courses aimed at empowering girls and children from disadvantaged backgrounds to pursue careers in STEM.
Laponogov, I.*, Gonzalez, G.*, Shepherd, M., Qureshi, A., Veselkov, D., Charkoftaki, G., Vasiliou, V., Youssef, J., Bronstein, M., Veselkov, K. Human Genomics 15(1): 1. * equal contribution.
We introduce a network machine learning method to identify potential bioactive anti-COVID-19 molecules in foods based on their capacity to target the SARS-CoV-2-host gene-gene (protein-protein) interactome.
Borgas, P., Gonzalez, G., Veselkov, K., Mirnezami, R. World Journal of Clinical Oncology, 12(6), 482–499.
Meta-analysis studying the association of several food items (garlic, nuts, tomatoes, cruciferous vegetables and citrus fruits) and the risk cancer.
Gonzalez, G., Gong, S., Laponogov, I., Bronstein, M., Veselkov, K. Human Genomics, 15(1), 33.
Graph neural model for anticancer hyperfoods prediction
Gonzalez, G., Gong, S., Laponogov, I., Veselkov, K. and Bronstein, M. 2019 NeurIPS Graph Representation Learning Workshop.
We introduce a graph neural network model for the anticancer hyperfood prediction task.
Frasca, F*., Galeano, D.*,Gonzalez, G., Laponogov, I., Veselkov, K., Paccanaro, A. and Bronstein, M. 2019 NeurIPS Graph Representation Learning Workshop. * equal contribution
Here, we propose an interpretable model that learns disease self-representations for drug repositioning.
Veselkov, K., Gonzalez, G., Aljifri, S., Galea, D., Mirnezami, R., Youssef, J., Bronstein, M. and Laponogov, I. Nature Scientific Reports, 9(1).
We introduce a machine learning approach to predict molecules in food with anticancer properties ('anticancer hyperfoods').
Imperial College London, UK
Department of Computing, Faculty of Engineering
Imperial College London, UK
Master of Research, Data Science
Department of Surgery and Cancer, Faculty of Medicine
Polytechnic University of Madrid, Spain
Bachelor of Science, Biomedical Engineering
Top of the class
Teaching and co-supervisions
Co-supervision of master's projects
Yuxi Wang (2021). Drug combinations against colorectal cancer
Jason Qiu (2021). Combinatorial therapeutics against COVID-19
Marco Gallotta (2021). Drug combinations against lung cancer
Madelen Shepherd (2020). The COVID-19 pandemic and cancer – an opportunity for drug repurposing
Ahad Qureshi (2020). COVID-19 and Lung Cancer: Can we Kill Two Birds with One Stone
Spring term 2020. Deep Learning. Department of Computing, Imperial College London
Summer term 2019. Big Data and Machine Learning. Dyson School of Design Engineering, Imperial College London.
Outreach and voluntary positions
LOGML - Co-Organizer
May 2020 - Aug 2021
The London Geometry and Machine Learning workshop was a week-long event scheduled for July 2021, in which early career researchers worked on practical projects under the guidance of experienced mentors. The workshop also featured prominent researchers in the fields of geometry and machine learning, as well as a company and networking night.
ICL Women in Computing - Co-President
Oct 2019 - July 2021
ICL Women in Computing is a collective of students and researchers in the Department of Computing dedicated to promoting initiatives that aim to tackle the gender imbalance in computer science. The society's goals are to empower gender minorities and inspire the younger generation to pursue careers in STEM as well as creating a community open and welcoming of people of all genders.
As a Co-President I contributed by overseeing the work of the society, in planning events, liaising with contacts within and outside the department, and representing the society in general.
In2Science - Instructor
Jul 2020 - Aug 2020
Delivered webinar sessions on the topic of machine learning aimed at students from low-income backgrounds to empower them to achieve their potential and progress to STEM research intensive degrees.