Imputation of cancer proteomics data with a deep model that learns from many datasets.

Missing values are a major challenge in the analysis of mass spectrometry proteomics data. Missing values hinder reproducibility, decrease statistical power for identifying differentially expressed (DE) proteins and make it challenging to analyze low-abundance proteins. We present Lupine, a deep learning-based method for imputing, or estimating, missing values in tandem mass tag (TMT) proteomics data. Lupine is, to our knowledge, the first imputation method that is designed to learn jointly from many datasets, and we provide evidence that this approach leads to more accurate predictions. We validated Lupine by applying it to TMT data from >1,000 cancer patient samples spanning ten cancer types from the Clinical Proteomics Tumor Atlas Consortium (CPTAC). Lupine outperforms the state of the art for TMT imputation, identifies more DE proteins than other methods, corrects for TMT batch effects, and learns a meaningful representation of proteins and patient samples. Lupine is implemented as an open source Python package.

Evaluating Proteomics Imputation Methods with Improved Criteria.

Quantitative measurements produced by tandem mass spectrometry proteomics experiments typically contain a large proportion of missing values. Missing values hinder reproducibility, reduce statistical power, and make it difficult to compare across samples or experiments. Although many methods exist for imputing missing values, in practice, the most commonly used methods are among the worst performing. Furthermore, previous benchmarking studies have focused on relatively simple measurements of error such as the mean-squared error between imputed and held-out values. Here we evaluate the performance of commonly used imputation methods using three practical, "downstream-centric" criteria. These criteria measure the ability to identify differentially expressed peptides, generate new quantitative peptides, and improve the peptide lower limit of quantification. Our evaluation comprises several experiment types and acquisition strategies, including data-dependent and data-independent acquisition. We find that imputation does not necessarily improve the ability to identify differentially expressed peptides but that it can identify new quantitative peptides and improve the peptide lower limit of quantification. We find that MissForest is generally the best performing method per our downstream-centric criteria. We also argue that existing imputation methods do not properly account for the variance of peptide quantifications and highlight the need for methods that do.

Therapy-Induced Evolution of Human Lung Cancer Revealed by Single-Cell RNA Sequencing.

Lung cancer, the leading cause of cancer mortality, exhibits heterogeneity that enables adaptability, limits therapeutic success, and remains incompletely understood. Single-cell RNA sequencing (scRNA-seq) of metastatic lung cancer was performed using 49 clinical biopsies obtained from 30 patients before and during targeted therapy. Over 20,000 cancer and tumor microenvironment (TME) single-cell profiles exposed a rich and dynamic tumor ecosystem. scRNA-seq of cancer cells illuminated targetable oncogenes beyond those detected clinically. Cancer cells surviving therapy as residual disease (RD) expressed an alveolar-regenerative cell signature suggesting a therapy-induced primitive cell-state transition, whereas those present at on-therapy progressive disease (PD) upregulated kynurenine, plasminogen, and gap-junction pathways. Active T-lymphocytes and decreased macrophages were present at RD and immunosuppressive cell states characterized PD. Biological features revealed by scRNA-seq were biomarkers of clinical outcomes in independent cohorts. This study highlights how therapy-induced adaptation of the multi-cellular ecosystem of metastatic cancer shapes clinical outcomes.