Publications
Systema: a framework for evaluating genetic perturbation response prediction beyond systematic variation
Predicting transcriptional responses to genetic perturbations is challenging in functional genomics. While recent methods aim to infer effects of untested perturbations, their true predictive power remains unclear. Here, we show that current methods struggle to generalize beyond systematic variation, the consistent transcriptional differences between perturbed and control cells arising from selection biases or confounders. […]
Viñas Torné, R. Wiatrak, M., Piran, Z., Fan, S., Jiang, L., Teichmann, S.A., Nitzan, M., Brbić, M.
In Nature Biotechnology, 2025.
A contextualised protein language model reveals the functional syntax of bacterial evolution
Bacteria have evolved a vast diversity of functions and behaviours which are currently incompletely understood and poorly predicted from DNA sequence alone. To understand the syntax of bacterial evolution and discover genome-to-phenotype relationships, we curated over 1.3 million genomes spanning bacterial phylogenetic space, representing each as an ordered sequence of proteins which collectively were used to train a transformer-based, contextualised protein language model, Bacformer. […]
Wiatrak, M., Viñas Torné, R., Ntemourtsidou, M., Dinan, A., Abelson, D.C., Arora, D., Brbić, M., Weimann, A., Floto, R. A.
In biorXiv, 2025.
Sequence-based modelling of bacterial genomes enables accurate antibiotic resistance prediction
Rapid detection of antibiotic-resistant bacteria and understanding the mechanisms underlying antimicrobial resistance (AMR) are major unsolved problems that pose significant threats to global public health. […]
Wiatrak, M., Weimann, A., Dinan, A., Brbić, M., Floto, R. A.
In biorXiv, 2024.
On Masked Language Models for Contextual Link Prediction
In the real world, many relational facts require context; for instance, a politician holds a given elected position only for a particular timespan. […]
Brayne, A., Wiatrak, M., Corneil D.
In ACL 2022 workshop on Deep Learning Inside Out (DeeLIO).
Directed graph embeddings in pseudo-riemannian manifolds
The inductive biases of graph representation learning algorithms are often encoded in the background geometry of their embedding space. […]
Sim, A., Wiatrak, M., Brayne, A., Creed, P., Paliwal, S.
In ICML 2021.
Simple hierarchical multi-task neural end-to-end entity linking for biomedical text
Recognising and linking entities is a crucial first step to many tasks in biomedical text analysis, such as relation extraction and target identification. […]
Wiatrak, M., Iso-Sipilä, J.
In EMNLP 2021 workshop on Health Text Mining and Information Analysis (LOUHI).
Stabilizing generative adversarial networks: A survey
Generative Adversarial Networks (GANs) are a type of generative model which have received much attention due to their ability to model complex real-world data. Despite their recent successes, the process of training GANs remains challenging […]
Wiatrak, M., Albrecht, S.V., Nystrom, A.
In arXiv, 2020.