Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 1
Encontrada(s) 1 página(s)

Dipòsit Digital de Documents de la UAB
Publicación Capítulo o parte de un libro (BookPart)

Efficient Peptide MRM Transition Prediction via Convolutional Hashing

  • Adàlia, Ramon|||0009-0004-9458-1922
  • Sanjuan Gómez, Gemma|||0000-0003-1406-3320
  • Margalef, Tomàs|||0000-0001-6384-7389
  • Zamora, Ismael|||0000-0002-7700-0354
We present a novel method for predicting multiple reaction monitoring (MRM) transitions for peptides in targeted proteomics. Our approach employs a hash-based representation inspired by convolutional neural networks, efficiently encoding peptide fragments as sparse count vectors that capture local sequence context. Using gradient-boosted decision trees, our method achieves mean Hits@5 scores of 3.4318 (hash-based) and 3.5405 (hybrid model with target frequency), significantly outperforming baselines. Transpiling trained models into Zig enables exceptional computational efficiency, with low memory usage (1180 kB) and a throughput of 388-451 peptides/second even on mobile devices, enabling lightweight, high-speed processing for scalable peptide MRM transition prediction in high-throughput proteomics workflows.