Google Research

Peptide-Spectra Matching with Weak Supervision

  • Sam Schoenholz
  • Sean Hackett
  • Laura Deming
  • Eugene Melamud
  • Andrew Dai
  • Navdeep Jaitly
  • Fiona McAllister
  • Jonathon O'Brien
  • George Dahl
  • Bryson Bennett
  • Daphne Koller
arXiv (2018)


As in many other scientific domains, we face a fundamental problem when using machine learning to identify proteins from mass spectrometry data: large ground truth datasets mapping inputs to correct outputs are extremely difficult to obtain. Instead, we have access to imperfect hand-coded models crafted by domain experts. In this paper, we apply deep neural networks to an important step of the protein identification problem, the pairing of mass spectra with short sequences of amino acids called peptides. We train our model to differentiate between top scoring results from a state-of-the art classical system and hard-negative second and third place results. Our resulting model is much better at identifying peptides with spectra than the model used to generate its training data. In particular, we achieve a 43% improvement over standard matching methods and a 10% improvement over a combination of the matching method and an industry standard cross-spectra reranking tool. Importantly, in a more difficult experimental regime that reflects current challenges facing biologists, our advantage over the previous state-of-theart grows to 15% even after reranking. We believe this approach will generalize to other challenging scientific problems.

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work