Carafe2 enables high quality in silico spectral library generation for timsTOF data-independent acquisition proteomics

Wen, B.; Paez, J. S.; Hsu, C.; Canzani, D.; Chang, A. T.; Shulman, N.; MacLean, B. X.; Berg, M. D.; Villen, J.; Fondrie, W.; Pino, L.; MacCoss, M. J.; Noble, W. S.

doi:10.64898/2026.03.27.714846

bioRxiv · 10.64898/2026.03.27.714846

Carafe2 enables high quality in silico spectral library generation for timsTOF data-independent acquisition proteomics

Wen, B.·Paez, J. S.·Hsu, C.·Canzani, D.·Chang, A. T.·Shulman, N.·MacLean, B. X.·Berg, M. D.·Villen, J.·Fondrie, W.·Pino, L.·MacCoss, M. J.·Noble, W. S.

View original source ↗Export metadata ↓

Abstract

Data-independent acquisition (DIA) proteomics enables reproducible and systematic peptide detection and quantification, and trapped ion mobility spectrometry (TIMS) on the timsTOF platform further improves DIA by synchronizing ion mobility separation with quadrupole precursor sampling. Analyzing the highly multiplexed spectra generated by DIA typically relies on spectral libraries, and fully leveraging the additional ion mobility dimension requires these libraries to include accurate retention time, fragment ion intensity, and ion mobility annotations. Existing in silico spectral library generation tools either lack ion mobility support entirely or rely on models trained on data-dependent acquisition (DDA) data, that can introduce a mismatch that may not capture unique experiment-specific biases when applied to each respective timsTOF dataset. Carafe is a software tool that uses deep learning models to generate high-quality, experiment-specific in silico libraries by training directly on DIA data. In this study, we extend Carafe to generate libraries for timsTOF DIA data, which involves fine-tuning retention time (RT), fragment ion intensity, and ion mobility prediction models using timsTOF DIA data. Carafe2 operates directly on native timsTOF raw data (Bruker .d directories) without the need for data conversion. We demonstrate the performance of Carafe2 across a wide range of DIA applications, including global proteome, phosphoproteome, and plasma proteome datasets. Comparing Carafe2 fine-tuned RT, fragment ion intensity, and ion mobility prediction models with pretrained DDA models, we find that Carafe2 models outperform pretrained models on a variety of DIA datasets. We then demonstrate the utility of in silico libraries generated by Carafe2 for peptide detection on several different types of timsTOF DIA datasets by comparing with the libraries generated with DDA-trained AlphaPeptDeep models, DIA-NN built-in models, and empirical spectral libraries generated from DDA experiments.

Explore related subjects

bioinformatics Preprint

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Wen, B., Paez, J. S., Hsu, C., Canzani, D., Chang, A. T., Shulman, N., MacLean, B. X., Berg, M. D., Villen, J., Fondrie, W., Pino, L., MacCoss, M. J., Noble, W. S.. 2026-03-31. Carafe2 enables high quality in silico spectral library generation for timsTOF data-independent acquisition proteomics. https://doi.org/10.64898/2026.03.27.714846

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

Targeted finetuning enables co-folding models to learn ligand-induced protein conformational states

Advances in protein structure prediction have enabled all-atom protein-ligand co-folding models that predict bound conformations directly from sequence and small-molecule structure. However, these models often fail to generalize to novel binding sites or alternative protein conformational states, limiting their utility for chemical biology and drug discovery. Here we show this limitation reflects training data bias rather than architectural constraints and can be overcome through targeted finetuning. Using ten previously unseen X-ray structures of Werner (WRN) helicase from a drug discovery program, we finetune Boltz-1 to learn both an allosteric binding site and a large conformational change locking the enzyme in an inactive state, while preserving accuracy on the ATP-bound state. The finetuned model generalizes to different chemical series and transfers the conformational logic across RecQ-family helicases in a binding-site sequence-dependent manner. This approach provides a blueprint for adapting foundation models as new structural and mechanistic data emerge, enabling co-folding networks to capture ligand-induced conformational switches and binding poses absent from their training data but central to biological regulation and therapeutic intervention.

bioinformatics↗

bioRxiv2026

Benchmarking single-cell foundation models for aging biology

Single cell foundation models (scFMs) provide representations of cellular states, but their utility across biological questions in aging research remains unclear. We established a benchmark of cellular representations for aging research, evaluating ten general-purpose scFMs, three aging-specific models and conventional methods across five biological questions using more than 2.5 million single cell transcriptomes. Using frozen pretrained representations, Geneformer performed best among scFMs for chronological age prediction and age pseudotime concordance, although 2,000 highly variable genes achieved higher mean performance. Several scFMs captured positive molecular age shifts across three disease contexts, consistent with reported aging-associated changes. SCimilarity performed well for rare cellular state identification across out-of-distribution datasets, exceeding aging specific models and conventional baselines. At the gene level, scGPT showed the highest recovery of reference TF target interactions, including aging-related regulatory hubs. Overall, scFMs supported diverse aging analyses, but performance depended on the biological question, highlighting their utility for rare cellular state identification and regulatory analysis.

bioinformatics↗

bioRxiv2026

CryoMV: Structure-Prior-Guided Modeling and Real-Particle Validation of Continuous Conformational Transitions in Cryo-EM

Continuous protein conformations are essential for understanding fundamental biological processes and supporting drug discovery. Although cryo-EM can resolve individual states at high resolution, recovering continuous heterogeneity from 2D particle images remains challenging. High noise, motion blur, and limited structural priors make it difficult to accurately generate and validate high-resolution continuous conformations using raw particle data. Here, we introduce cryoMV, a framework that integrates structure-prior-guided modeling with real-particle validation for continuous conformational transitions. CryoMV uses reference density maps to establish structural anchors and motion priors, models candidate transition paths between selected conformations, and transfers the learned representation to raw 2D cryo-EM particle images. Each candidate conformation is subsequently evaluated using the estimated particle poses and contrast transfer functions. Supported conformations are reconstructed through raw particle back-projection and assessed using canonical half-maps and Fourier shell correlation. On EMPIAR-10516 and EMPIAR-10345, cryoMV achieves excellent performance in terms of robustness, verifiability, and reconstruction resolution. By incorporating structure-prior modeling and evidence from the raw particles, cryoMV offers an explicit mechanism for assessing whether generated conformations are supported by experimental data and provides a practical approach to reducing model-induced artifacts in continuous cryo-EM heterogeneity analysis.

bioinformatics↗