Skip to content
DraconiticResearch
Search Sources API
186,541 studies31 sourcesUpdated 42 min ago
Peer-reviewedCC BYBriefings in bioinformatics

Biologically informative not available deconvolution excavates hidden features in proteomics datasets.

  • Weiheng Guo1
  • Wenyi Jin1,2
  • Jieyi Zheng3
  • Jian Zhang4
  • Xikang Feng3
  • Lingxi Chen1
  • Liang Zhang1
4 affiliations
  1. 1Department of Biomedical Sciences, College of Biomedicine, City University of Hong Kong, Tat Chee Ave, Kowloon, Hong Kong SAR 999077, China.
  2. 2Department of Orthopaedics, Renmin Hospital of Wuhan University, Wuhan University, Zhangzhidong Road, Wuhan 430060, China.
  3. 3School of Software, Northwestern Polytechnical University, West Youyi Road, Xi'an 710072, China.
  4. 4Department of Pharmaceutical and Artificial-Intelligence Sciences, School of Medicine, Shanghai Jiao Tong University, South Chongqing Road, Shanghai 200025, China.
Read full textPDFDOICite

Abstract

Missing values [not available (NAs)] in proteomics arise from true absence/low abundance and technical factors. Conventional imputation often obscures disease signals by ignoring the biological information inherent in protein absence. We present biologically informative NA deconvolution (BIND), an adaptive neighborhood-based workflow that classifies NAs as biological or technical. BIND binarizes matrices to encode presence/absence and uses context-aware k-nearest neighbors with Gaussian kernels to deconvolve NA origins, enabling clustering, biomarker discovery, and an NA-weighted correlation for protein-protein interaction (PPI) inference. In a simulation derived from the CCLE949 dataset, BIND achieved an Area Under the Curve (AUC) of 0.93, with k = 10 and γ = 3 selected for subsequent Cancer Cell Line Encyclopedia (CCLE) analyses, and remained robust across biological-to-technical NA ratios ranging from 3:1 to 1:3. In hepatocellular carcinoma tissues (n = 248), BIND distinguished tumor from adjacent normal, identified candidate biomarkers, and detected cancer-specific PPIs enriched in spliceosome and DNA replication pathways. A public BIND web server offers interactive visualization and supports single-cell proteomics, enhancing accessibility. Overall, BIND transforms NA patterns from a liability into biologically informative features for clustering, endotype discovery, biomarker identification, and PPI analysis.

Related

  1. Biologically engineered vectors enable topical mRNA delivery for skin regeneration
    Julie Gérard, Héloïse Pilet, Charbel Bouez +6
    Communications BiologyPeer-reviewedCC BY 4.0Full text1 citedMolecular biology & gene regulationPMC
  2. Detailed Insight into the Chignolin Folding Process from Maximally Informative Low-Resolution Representations of Its Isocommittor Hypersurfaces.
    Alessia Guadagnin Pattaro, Roberto Menichetti, Raffaello Potestio
    Journal of chemical theory and computationPeer-reviewedCC BYFull textMolecular biology & gene regulationEurope PMC
  3. Studying Biologically Important Monovalent Cation Diffusion across Lipids Using Molecular Fe Redox Reporters in Hybrid Bilayer Membranes
    Hei Tung Yau, Zuo Hang Yu, Xiaoyong Mo +3
    ChemRxivPreprintCC BY-NC-NDFull textMolecular biology & gene regulationChemRxiv
  4. ReadsRatio: a facile method for cell type deconvolution with cross-platform applications
    Qiuyu Jing, Qiang Li, Shirley C. W. Chan +7
    Genome BiologyPeer-reviewedCC BY-NC-ND 4.0Molecular biology & gene regulationCrossref
  5. Characterization of Kluyveromyces marxianus Extracellular Vesicles as a New Potential Delivery System for Biologically Active Compounds
    Marta Rogalska, Katarzyna Kmita, Anna Katarzyna Wrońska +6
    International Journal of Molecular SciencesPeer-reviewedCC BY 4.0Full textMolecular biology & gene regulationCrossrefEurope PMC

Cite

BibTeXRIS
BibTeX
@article{guo2026biologically,
  title = {{Biologically informative not available deconvolution excavates hidden features in proteomics datasets.}},
  author = {Weiheng Guo and Wenyi Jin and Jieyi Zheng and Jian Zhang and Xikang Feng and Lingxi Chen and Liang Zhang},
  journal = {Briefings in bioinformatics},
  year = {2026},
  month = sep,
  doi = {10.1093/bib/bbag582},
  url = {https://europepmc.org/article/MED/42932842},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Biologically informative not available deconvolution excavates hidden features in proteomics datasets.
AU  - Weiheng Guo
AU  - Wenyi Jin
AU  - Jieyi Zheng
AU  - Jian Zhang
AU  - Xikang Feng
AU  - Lingxi Chen
AU  - Liang Zhang
PY  - 2026
DA  - 2026/09/01
JO  - Briefings in bioinformatics
DO  - 10.1093/bib/bbag582
UR  - https://europepmc.org/article/MED/42932842
AB  - Missing values [not available (NAs)] in proteomics arise from true absence/low abundance and technical factors. Conventional imputation often obscures disease signals by ignoring the biological information inherent in protein absence. We present biologically informative NA deconvolution (BIND), an adaptive neighborhood-based workflow that classifies NAs as biological or technical. BIND binarizes matrices to encode presence/absence and uses context-aware k-nearest neighbors with Gaussian kernels to deconvolve NA origins, enabling clustering, biomarker discovery, and an NA-weighted correlation for protein-protein interaction (PPI) inference. In a simulation derived from the CCLE949 dataset, BIND achieved an Area Under the Curve (AUC) of 0.93, with k = 10 and γ = 3 selected for subsequent Cancer Cell Line Encyclopedia (CCLE) analyses, and remained robust across biological-to-technical NA ratios ranging from 3:1 to 1:3. In hepatocellular carcinoma tissues (n = 248), BIND distinguished tumor from adjacent normal, identified candidate biomarkers, and detected cancer-specific PPIs enriched in spliceosome and DNA replication pathways. A public BIND web server offers interactive visualization and supports single-cell proteomics, enhancing accessibility. Overall, BIND transforms NA patterns from a liability into biologically informative features for clustering, endotype discovery, biomarker identification, and PPI analysis.
SN  - 1467-5463
SN  - 1477-4054
ER  -