top of page
IMG_5569-2.jpg

I joined Genentech/Roche in February 2023, after completing a PhD on graph deep learning for lead discovery advised by Michael Bronstein and Kirill Veselkov at Imperial College London. I am part of the Frontier Research team at Prescient/MLDD in Genentech Research and Early Development (gRED).

My expertise lies at the intersection of graph deep learning and causal inference and my focus is on (causal) graph deep learning for drug discovery/design, from the small-scale (e.g., proteins) to the large-scale (e.g., patient data) systems. I am particularly passionate about applying my knowledge to women’s health to catalyze breakthroughs in women-specific conditions such as endometriosis and preeclampsia.

​

​

Senior ML Scientist II
Prescient Design, Genentech

email ggonzalezp16[at]gmail[dot]com

LinkedIn  GScholar  Twitter

about

selected publications

On knowing a gene: A distributional hypothesis of gene function

        by Kwon, J. J., Pan, J., Gonzalez G., Hahn W. C., Zitnik M. In Cell Systems (2024)

 

Combinatorial prediction of therapeutic perturbations using causally-inspired neural networks

        by Gonzalez G., Herath I., Veselkov K., Bronstein M., Zitnik M. In biorxiv (2024)

​

Towards Training GNNs using Explanation Directed Message Passing

        by Giunchiglia V., Varun Shukla C., Gonzalez G., Agarwal, C. In Learning on Graphs Conference (2022)

​

Network machine learning maps phytochemically rich “Hyperfoods” to fight COVID-19

by Laponogov, I.*, Gonzalez, G.*, Shepherd, M., Qureshi, A., Veselkov, D., Charkoftaki, G., Vasiliou, V., Youssef, J., Bronstein, M., Veselkov, K., * equal contribution.​ In Human Genomics (2021). ​

​

​

Phytochemically rich dietary components and the risk of colorectal cancer: A systematic review and meta-analysis of observational studies.

by Borgas, P., Gonzalez, G., Veselkov, K., Mirnezami, R. In World Journal of Clinical Oncology (2021).

​

​

​

Predicting anticancer hyperfoods with graph convolutional networks

by Gonzalez, G., Gong, S., Laponogov, I., Bronstein, M., Veselkov, K. In Human Genomics (2021). ​

​

​

Graph Attentional Autoencoder for Anticancer Hyperfood Prediction

by Gonzalez, G., Gong, S.,  Laponogov, I., Veselkov, K. and Bronstein, M. In NeurIPS Graph Representation Learning Workshop (2019). ​

​

education

2021 - 2023

Visiting PhD, Harvard Medical School, US

​

2018 - 2023

PhD Computing. Imperial College London, UK

​

2017 - 2018

MRes Data Science. Imperial College London, UK

​

2013 - 2017

BSc Biomedical Engineering. Polytechnic University of Madrid, Spain

teaching

Imperial College London

​

Fall term 2021

GTA for Machine Learning, Faculty of Medicine.

 

Summer term 2021

Instructor for workshop: Big Data and the ’Dark Matter’ of COVID, Faculty of Medicine.

​

Spring term 2020

GAT for Deep Learning, Faculty of Engineering.

​​

Summer term 2019

GTA for Big Data and Machine Learning, Faculty of Engineering.

​

 

Non-profit organizations

​

Summer 2020

In2Science instructor, Machine Learning sessions to encourage Year 12 students to progress into STEM research-intensive degrees.

​

Fall 2018

CodeFirstGirls instructor, Web Programming in HTML, CSS, and JavaScript for girls with no experience in programming, to encourage them to pursue careers in STEM.

resumé

co-supervision
master's projects

2021

Emma Zhang. The overlap score of genetic targets of food and drug molecules predicts their synergistic anticancer effect.

​​

Yoyo Zhong. Exploring dietary bioactive compounds on colorectal cancer radiation response using random walk with restarts.

​​

Yuxi Wang. Drug combinations against colorectal cancer.

​​

Jason Qiu. Combinatorial therapeutics against COVID-19.

​​

Marco Gallotta. Drug combinations against lung cancer.

​​

2020

Madelen Shepherd. The COVID-19 pandemic and cancer – an opportunity for drug repurposing.

​​

Ahad Qureshi. COVID-19 and Lung Cancer: Can we Kill Two Birds with One Stone.

contact

outreach

LOGML - co-organizer

2020 - 2021, 2023 - 2024

The London Geometry and Machine Learning workshop is a week-long event in which early career researchers worked on practical projects under the guidance of experienced mentors. The workshop also features prominent researchers in the fields of geometry and machine learning, as well as a company and networking night.

2019 - 2021

Co-organized talks, workshops, and weekly activities for female and gender-minority PhD and staff members in the department of Computing. Led WiC Entrepreneur initiative to promote entrepreneurship among female students and staff members in the department of computing.

bottom of page