Rongshan Yu

AbNovoBench benchmarks de novo sequencing algorithms for monoclonal antibodies using a large dataset and provides an online platform for antibody sequencing workflows.

DreamDIAlignR improves DIA proteomics analysis by integrating cross-run peptide data with deep learning and FDR control, increasing detected quantitatively changing proteins by 25.6% on a benchmark dataset.

CleverXMBD1 improves cell abundance quantification by using a confidence-based multi-positive and unlabeled loss function, outperforming existing methods across multiple datasets.

The paper evaluates deconvolution methods for inferring immune infiltration from bulk gene expression using a DREAM Challenge, finding that some community-contributed methods, especially deep learning-based ones, perform well.

This paper develops a rapid de novo sequencing workflow for COVID-19 neutralizing antibodies, achieving high accuracy in mixed antibody mixtures.

This paper introduces Fusion, a de novo assembler for antibody sequences, demonstrating high accuracy in reconstructing monoclonal and mixed antibody sequences from mass spectrometry data.

The paper identifies prognostic-associated subpopulations and develops recurrence risk signatures from scRNA-seq data of colorectal cancer using a rank-based framework.

Dear-DIAXMBD is a deep autoencoder method for analyzing DIA proteomics data, achieving superior performance across different species and instrument platforms.

DAISM-DNNXMBD improves cell type proportion estimation in bulk RNA-seq by using in silico data augmentation and deep neural networks, outperforming existing methods on real-world datasets.

DreamDIA-XMBD improves DIA proteomics analysis by using deep representation features for better identification and quantification than existing methods.

IMCellXMBD improves cell identification and quantification in imaging mass cytometry by denoising, distinguishing cells from noise, and normalizing protein expression.

Dice-XMBD improves cell segmentation accuracy for imaging mass cytometry data compared to existing methods.

The paper develops a tool called IDEP to perform personalized differential expression analysis on cancer proteomes, showing it can identify patient-specific deregulated proteins more effectively than group-based methods.

ScaleQC provides a scalable lossy to lossless compression solution for NGS quality values, achieving efficient storage without re-encoding.

This study evaluates seven scRNA-seq data processing pipelines across nine datasets from five platforms, comparing their performance in runtime, resource use, and data consistency.