The Language of Elution: Autoregressive Prediction of the Next Feature in Untargeted LC-HRMS Lipidomics

• URL: http://arxiv.org/abs/2606.05225v1
• Date: Tue, 02 Jun 2026 10:42:17 GMT
• Title: The Language of Elution: Autoregressive Prediction of the Next Feature in Untargeted LC-HRMS Lipidomics
• Abstract summary: Training on 15,242 features from four clinical lipidomics cohorts (342 plasma samples; SCIEX TripleTOF 6600+, Waters CSH C18)<n>LSTM reaches 98.4% top-1 accuracy (99.99% top-5; mean absolute error 3.6 Da) and the Transformer 98.0%.<n>These results establish that elution sequences are highly predictable and lay the groundwork for predictive MS/MS acquisition to improve annotation coverage in metabolomics.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Untargeted liquid chromatography-high-resolution mass spectrometry (LC-HRMS) detects thousands of molecular features per sample, yet only 2-20% receive confident structural annotations. A root cause of this "dark metabolome" is that tandem MS/MS acquisition is reactive: instruments select precursors only after ions appear, blind to what elutes next. We reframe chromatographic elution as an autoregressive sequence prediction task. Because reversed-phase elution order is governed by hydrophobicity, successive features form a physically constrained sequence, like tokens in language. We discretize the mass-to-charge (m/z) axis into 110 bins and train long short-term memory (LSTM) and Transformer models to predict the next eluting m/z bin from five annotation-free per-token features: m/z bin, mass defect, retention-time gap, polarity, and intensity rank. Trained on 15,242 features from four clinical lipidomics cohorts (342 plasma samples; SCIEX TripleTOF 6600+, Waters CSH C18), the LSTM reaches 98.4% top-1 accuracy (99.99% top-5; mean absolute error 3.6 Da) and the Transformer 98.0%. Ablation shows autoregressive context accounts for 55.5 percentage points while no single feature contributes more than 0.2 pp: the sequential pattern, not molecular properties, drives prediction. Models transfer across instruments sharing the method (r=0.999 on an independent Agilent 6530 dataset) but fail under a different column chemistry (5.1% top-1) or polarity mode (2.6%), confirming method- and mode-specificity. Fine-tuning on as few as two to five quality-control injections recovers held-out accuracy from 2.6% to nearly 50%, so cross-condition deployment needs minimal calibration. These results establish that elution sequences are highly predictable and lay the groundwork for predictive MS/MS acquisition to improve annotation coverage in untargeted metabolomics.

Related papers

• Graph Diffusion Residuals for Control-Function Instrumental Variables [82.39671985893028]
  High-capacity first stages can interpolate treatment and leave too little residual information for the outcome equation.<n>We study Adaptive Anisotropic Instrumental Heat Flow (A-IHF), a deterministic graph-diffusion residual extractor for flexible control functions.<n>A-IHF treats treatment as a signal on a graph of first-stage features, uses pilot diffusion to detect large treatment jumps, attenuates conductance across those jumps, and computes the generated control with a sparse graph resolvent.
  arXiv  Detail & Related papers  (2026-06-12T17:02:53Z)
• Multimodality Stacking with Blockwise missing values and application to the PIONeeR biomarkers study for prediction of resistance to immunotherapy [0.0]
  We introduce Multimodality Stacking with Blockwise missing values (MSB), a late-fusion framework for survival analysis.<n>MSB independently models modality-specific features before aggregating predictions via a cross-validated stacking meta-learner.<n>MSB was validated on the PIONeeR study to predict progression-free survival in lung cancer patients.
  arXiv  Detail & Related papers  (2026-05-24T12:48:38Z)
• From Theory to Decision Rule: Calibrating the Noisy-Label Crossover for Vision-Language Model Weak Supervision Across Three Medical-Imaging Benchmarks [41.99844472131922]
  We provide a benchmark calibration for foundation-model weak labels.<n>The crossover predicted by theory appears at ng100 on PCAM, 20-50 on ISIC, and 250-500 on NIH-CXR.<n>A structured-vs-random noise sign flip on NIH-CXR shows that the rate-only formulation of the bound is incomplete.
  arXiv  Detail & Related papers  (2026-05-23T23:15:07Z)
• Agentic Discovery of Cryomicroneedle Formulations [4.138244144792088]
  We report an AI-assisted, closed-loop workflow for cryomicroneedle cryoprotectant discovery.<n>A curated dataset of 198 mesenchymal stem-cell cryopreservation formulations was converted into 21 ingredient features.<n>The best validated formulation achieved 95.15% post-thaw viability with low DMSO, ectoin, ethylene glycol, and fetal bovine serum.
  arXiv  Detail & Related papers  (2026-05-19T11:09:46Z)
• FlashMol: High-Quality Molecule Generation in as Few as Four Steps [33.25994871049577]
  FlashMol is an ultra-fast molecule generative model producing high-quality molecular conformations in as few as 4 steps.<n>Experiments on QM9 and GEOM-DRUG datasets demonstrate that FlashMol matches and even surpasses the original 1000-step teacher.
  arXiv  Detail & Related papers  (2026-05-07T23:04:24Z)
• Edge-specific signal propagation on mature chromophore-region 3D mechanism graphs for fluorescent protein quantum-yield prediction [0.3058685580689604]
  We present a chromophore-centred mechanism graph algorithm for Fluorescent protein quantum yield prediction.<n>Each PDB structure is converted into a typed 3D residue graph, registered to a mature-CRO state.<n>Because each feature encodes a contact channel, seed signal and target CRO region, interpretation is intrinsic rather than post hoc.
  arXiv  Detail & Related papers  (2026-05-07T17:51:41Z)
• Residual Koopman Spectral Profiling for Predicting and Preventing Transformer Training Instability [40.24077350481118]
  Training divergence in transformers wastes compute, yet practitioners discover instability only after expensive runs begin.<n>Our study of Residual Koopman Spectral Profiling (RKSP) provides such an estimate.<n>Our central diagnostic, the near-unit spectral mass, quantifies the fraction of modes concentrated near the unit circle, which captures instability risk.
  arXiv  Detail & Related papers  (2026-02-26T13:33:25Z)
• Breaking the Modality Barrier: Generative Modeling for Accurate Molecule Retrieval from Mass Spectra [60.08608779794957]
  We propose GLMR, a Generative Language Model-based Retrieval framework.<n>In the pre-retrieval stage, a contrastive learning-based model identifies top candidate molecules as contextual priors for the input mass spectrum.<n>In the generative retrieval stage, these candidate molecules are integrated with the input mass spectrum to guide a generative model in producing refined molecular structures.
  arXiv  Detail & Related papers  (2025-11-09T07:25:53Z)
• Feature Selection and Regularization in Multi-Class Classification: An Empirical Study of One-vs-Rest Logistic Regression with Gradient Descent Optimization and L1 Sparsity Constraints [0.0]
  Multi-class wine classification presents fundamental trade-offs between model accuracy, feature dimensionality, and interpretability.<n>This paper presents a comprehensive empirical study of One-vs-Rest logistic regression on the UCI Wine dataset.
  arXiv  Detail & Related papers  (2025-10-16T08:47:05Z)
• Language Models Enable Data-Augmented Synthesis Planning for Inorganic Materials [1.6163129903911515]
  Off-the-shelf models, such as GPT-4.1, Gemini 2.0 Flash and Llama 4 Maverick, achieve a Top-1 precursor-prediction accuracy of up to 53.8 %.<n>We employ language models to generate 28,548 synthetic reaction recipes, which we combine with literature-mined examples to pretrain a transformer-based model, SyntMTE.
  arXiv  Detail & Related papers  (2025-06-14T15:55:05Z)
• Learning Flexible Forward Trajectories for Masked Molecular Diffusion [35.326540193307345]
  Masked diffusion models (MDMs) have achieved notable progress in modeling discrete data, while their potential in molecular generation remains underexplored.<n>We introduce the surprising result that naively applying standards MDMs severely degrades the performance.<n>We propose Masked Element-wise Learnable Diffusion (MELD) that orchestrates per-element corruption trajectories to avoid collision between distinct molecular graphs.
  arXiv  Detail & Related papers  (2025-05-22T15:30:17Z)
• Interpretable cancer cell detection with phonon microscopy using multi-task conditional neural networks for inter-batch calibration [39.759100498329275]
  We present a conditional neural network framework to simultaneously achieve inter-batch calibration. We validate our approach by training and validating on different experimental batches. We extend our model to reconstruct denoised signals, enabling physical interpretation of salient features indicating disease state.
  arXiv  Detail & Related papers  (2024-03-26T12:20:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.