Towards a more accurate differential analysis of multiple imputed proteomics data with mi4limma

Marie Chion (1, 2) , Christine Carapito (2, 3, 4) , Frédéric Bertrand (5, 6)

1 IRMA - Institut de Recherche Mathématique Avancée
2 LSMBO - Laboratoire de Spectrométrie de Masse BioOrganique [Strasbourg]
3 FR ProFI - Fédération de Recherche nationale ProFI
4 IPHC - Institut Pluridisciplinaire Hubert Curien
5 LM2S - Laboratoire Modélisation et Sûreté des Systèmes
6 CEA Cadarache

Imputing missing values is common practice in label-free quantitative proteomics. Imputation replaces a missing value by a user-defined one. However, the imputation itself is not optimally considered downstream of the imputation process. In particular, imputed datasets are considered as if they had always been complete. The uncertainty due to the imputation is not properly taken into account. Hence, the mi4p package provides a more accurate statistical analysis of multiple-imputed datasets. A rigorous multiple imputation methodology is implemented, leading to a less biased estimation of parameters and their variability thanks to Rubin's rules. The imputation-based peptide's intensities' variance estimator is then moderated using

Mots clés: Label-free quantitative proteomics; Differential analysis; Missing values; Multiple imputation; Moderated t-testing

Domaines: Statistiques [stat]; Statistiques [math.ST]; Génomique, Transcriptomique et Protéomique [q-bio.GN]; Applications [stat.AP]

Marie Chion, Christine Carapito, Frédéric Bertrand. Towards a more accurate differential analysis of multiple imputed proteomics data with mi4limma. Statistical Analysis of Proteomic Data: Methods and Tools, 2022, ⟨10.1007/978-1-0716-1967-4_7⟩. ⟨hal-03442944⟩