7 citations · 23 across the 8 of their papers we have counts for
6 papers · 1 filter
MassSpecGym in the Wild: Uncovering and Correcting Evaluation Pitfalls in AI-Driven Molecule Discovery
Hongxuan Liu, Roman Bushuiev, Ivy Lightheart +12
Reliable benchmarking is critical for developing machine learning models for tandem mass spectrometry (MS/MS) based molecule discovery. Subtle issues in experimental design and mod…
De novo generation of functional terpene synthases using TpsGPT
Hamsini Ramanathan, Roman Bushuiev, Matouš Soldát +5
Terpene synthases (TPS) are a key family of enzymes responsible for generating the diverse terpene scaffolds that underpin many natural products, including front-line anticancer dr…
Generalization Beyond Benchmarks: Evaluating Learnable Protein-Ligand Scoring Functions on Unseen Targets
Jakub Kopko, David Graber, Saltuk Mustafa Eyrilmez +4
As machine learning becomes increasingly central to molecular design, it is vital to ensure the reliability of learnable protein-ligand scoring functions on novel protein targets.…
One protein is all you need
Anton Bushuiev, Roman Bushuiev, Olga Pimenova +9
Generalization beyond training data remains a central challenge in machine learning for biology. A common way to enhance generalization is self-supervised pre-training on large dat…
Revealing data leakage in protein interaction benchmarks
Anton Bushuiev, Roman Bushuiev, Jiri Sedlar +4
In recent years, there has been remarkable progress in machine learning for protein-protein interactions. However, prior work has predominantly focused on improving learning algori…
Learning to design protein-protein interactions with enhanced generalization
Anton Bushuiev, Roman Bushuiev, Petr Kouba +8
Discovering mutations enhancing protein-protein interactions (PPIs) is critical for advancing biomedical research and developing improved therapeutics. While machine learning appro…