Our project aims to address the critical issue of sex representation in biological research. Sex differences play a pivotal role in disease progression and treatment responses, yet female representation has long been neglected in scientific studies. Our hypothesis is that projects with higher funding are more likely to include both male and female subjects, as they can afford the additional costs associated with larger sample sizes. To test this hypothesis, we will analyze data from the Community Research and Development Information Service (CORDIS) database, focusing on projects funded under FP7 and Horizon 2020 programs. By employing a pre-trained BERT language model, we will quantitatively and qualitatively extract sex-related data from associated research publications. This comprehensive analysis spanning 14 years will assess sex representation in biological research and reveal any changes due to equity measures implemented by the European Commission sex representation due to equity measures implemented by the European Commission. Join our project at Biohackathon Germany 2023 and contribute to a more inclusive and equitable future for biological research

Project leads: Victoria Ruiz Serra (BSC) & Beatrix Urda (BSC)