Junyan Lu
@junyanlu.bsky.social
Group leader at University Hospital Heidelberg
Former Postdoc at EMBL
Bioinformatician, Data scientists Computational mass-spectrometry, multi-omics, and precision oncology. He/Him
https://lu-group-ukhd.github.io/
Former Postdoc at EMBL
Bioinformatician, Data scientists Computational mass-spectrometry, multi-omics, and precision oncology. He/Him
https://lu-group-ukhd.github.io/
Across synthetic, semi-synthetic, and experimental serial dilution datasets, msBayesImpute consistently:
✅ Achieved the lowest imputation error
✅ Improved sample-wise normalization
✅ Delivered the highest accuracy in DE analysis across 9 methods
✅ Achieved the lowest imputation error
✅ Improved sample-wise normalization
✅ Delivered the highest accuracy in DE analysis across 9 methods
October 7, 2025 at 8:47 AM
Across synthetic, semi-synthetic, and experimental serial dilution datasets, msBayesImpute consistently:
✅ Achieved the lowest imputation error
✅ Improved sample-wise normalization
✅ Delivered the highest accuracy in DE analysis across 9 methods
✅ Achieved the lowest imputation error
✅ Improved sample-wise normalization
✅ Delivered the highest accuracy in DE analysis across 9 methods
Missing values in proteomics are often not missing at random (MNAR). Existing methods either assume MAR or oversimplify MNAR.
💡 msBayesImpute learns protein-specific dropout curves directly from the data using Bayesian matrix factorization + probabilistic dropout models.
💡 msBayesImpute learns protein-specific dropout curves directly from the data using Bayesian matrix factorization + probabilistic dropout models.
October 7, 2025 at 8:47 AM
Missing values in proteomics are often not missing at random (MNAR). Existing methods either assume MAR or oversimplify MNAR.
💡 msBayesImpute learns protein-specific dropout curves directly from the data using Bayesian matrix factorization + probabilistic dropout models.
💡 msBayesImpute learns protein-specific dropout curves directly from the data using Bayesian matrix factorization + probabilistic dropout models.