paper-with-me

홈 › Papers

MS2MetGAN: Latent-space adversarial training for metabolite-spectrum matching in MS/MS database search

2026-03-07 · Meng Tsai, Alexzander Dwyer, Estelle Nuckels, Yingfeng Wang arxiv

Database search is a widely used approach for identifying metabolites from tandem mass spectra (MS/MS). In this strategy, an experimental spectrum is matched against a user-specified database of candidate metabolites, and candidates are ranked such that true metabolite-spectrum matches receive the highest scores. Machine-learning methods have been widely incorporated into database-search-based identification tools and have substantially improved performance. To further improve identification accuracy, we propose a new framework for generating negative training samples. The framework first uses autoencoders to learn latent representations of metabolite structures and MS/MS spectra, thereby recasting metabolite-spectrum matching as matching between latent vectors. It then uses a GAN to generate latent vectors of decoy metabolites and constructs decoy metabolite-spectrum matches as negative samples for training. Experimental results show that our tool, MS2MetGAN, achieves better overall performance than existing metabolite identification methods.

📄 PDF Abstract BibTeX arXiv:2603.13342

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Robust Learning on Noisy Graphs via Latent Space Constraints with External Knowledge

2025-07-07 · Chunhui Gu, Mohammad Sadegh Nasr, James P. Long, Kim-Anh Do 외 arxiv

Graph Neural Networks (GNNs) often struggle with noisy edges. We propose Latent Space Constrained Graph Neural Networks (LSC-GNN) to incorporate external "clean" links and guide embeddings of a noisy target graph. We tra…

Probabilistic Approach for Evaluating Metabolite Sample Integrity

2015-06-14

The success of metabolomics studies depends upon the "fitness" of each biological sample used for analysis: it is critical that metabolite levels reported for a biological sample represent an accurate snapshot of the stu…

feature selection

Causal Discovery for Gene Regulatory Network Prediction

2023-01-03 · Jacob Rast

Biological systems and processes are networks of complex nonlinear regulatory interactions between nucleic acids, proteins, and metabolites. A natural way in which to represent these interaction networks is through the u…

Causal DiscoveryPrediction

The enzyme cost of given metabolic flux distributions, as a function of logarithmic metabolite levels, is convex

2015-01-11

Enzyme costs play a major role in the choice of metabolic routes, both in evolution and bioengineering. Given desired fluxes, necessary enzyme levels can be estimated based on known rate laws and on a principle of minima…

Data-driven Synthesis of Magnetic Resonance Spectroscopy Data using a Variational Autoencoder

2026-02-28 · Dennis M. J. van de Sande, Julian P. Merkofer, Sina Amirrajab, Mitko Veta 외 arxiv

The development of deep learning methods for magnetic resonance spectroscopy (MRS) is often hindered by limited availability of large, high-quality training datasets. While physics-based simulations are commonly used to …