open access publication

Preprint, 2023

Multiomics machine learning identifies inflammation molecular pathways in prodromal Alzheimer’s Disease

In: medRxiv, Page 2023.03.02.23286674, 10.1101/2023.03.02.23286674

Contributors (32)

Gómez-Pascual, Alicia (0000-0003-2348-9083) (Corresponding author) [1] [2] Naccache, Talel [3] Xu, Jin [4] Hooshmand, Kourosh (0000-0002-6970-5725) [2] Wretlind, Asger (0000-0001-6083-5227) [2] Gabrielli, Martina (0000-0003-4958-541X) [5] Lombardo, Marta Tiffany (0000-0002-2903-7515) [5] [6] Shi, Liu [7] Buckley, Noel John (0000-0003-1152-0653) [8] [9] Tijms, Betty Marije (0000-0002-2612-1797) [10] Vos, Stephanie J B (0000-0002-2045-9818) [11] Kate, Mara Ten [10] Engelborghs, Sebastiaan [12] [13] Sleegers, Kristel (0000-0002-0283-2332) [13] [14] Frisoni, Giovanni Battista (0000-0002-6419-1753) [15] [16] Wallin, Anders [17] Lleó, Alberto (0000-0002-2568-5478) [18] Popp, Julius (0000-0002-0068-0312) [19] [20] [21] Martinez-Lage, Pablo Campo (0000-0001-5404-9967) [22] Streffer, Johannes [23] Barkhof, Frederick (0000-0003-3543-3706) [24] [25] Zetterberg, Henrik (0000-0003-3930-4354) [17] [26] [27] Visser, Pieter Jelle (0000-0001-8008-9727) [10] [11] Lovestone, Simmon (0000-0003-0473-4565) [9] [28] Bertram, Lars (0000-0002-0108-124X) [29] [30] Nevado-Holgado, Alejo Jesus (0000-0001-9276-2720) [9] Gualerzi, Alice [31] Picciolini, Silvia [31] Proitsi, Petroula (0000-0002-2553-6974) [4] Verderio, Claudia (0000-0001-7216-5873) [5] Botía, Juan Antonio (0000-0002-6992-598X) [1] Legido-Quigley, Cristina (0000-0002-4018-214X) (Corresponding author) [2] [4]


  1. [1] University of Murcia
  2. [NORA names: Spain; Europe, EU; OECD]
  3. [2] Steno Diabetes Center
  4. [NORA names: Steno Diabetes Centers; Hospital; Denmark; Europe, EU; Nordic; OECD]
  5. [3] City, University of London
  6. [NORA names: United Kingdom; Europe, Non-EU; OECD]
  7. [4] King's College London
  8. [NORA names: United Kingdom; Europe, Non-EU; OECD]
  9. [5] Neuroscience Institute
  10. [NORA names: Italy; Europe, EU; OECD]


Abstract Mild Cognitive Impairment (MCI) is a phase that can precede Alzheimer’s Disease (AD). To better understand the molecular mechanisms underlying conversion from MCI to AD, we applied a battery of machine learning algorithms on 800 samples from the EMIF-AD MBD study. The cohort comprised participants diagnosed as 230 normal cognition (NC), 386 MCI (with longitudinal data on AD conversion or remaining stable) and 184 AD-type dementia. Data consisted of metabolites (n=540) and proteins (n=3630) measured in plasma coupled to clinical data (n=26). Multiclass models selected oleamide, MMSE and the priority language as the most confident features while MCI conversion models selected pTau, tTau and JPH3, CFP, SNCA and PI15 proteins. These proteins selected for MCI conversion have been previously associated with AD-related phenotype. Oleamide, a possible anti-inflammatory, prompted in-vitro experiments in rodent microglia. The results demonstrated that disease-associated microglia synthesize oleamide which were excreted in vesicles. In addition, plasma vesicles extracted from participants with AD showed elevated oleamide levels compared to controls (P<0.05). This study uncovered MCI conversion pathways that involve inflammation, neuronal regulation and protein degradation. Graphical abstract


ABSTRACT Mild cognitive impairment, AD-related phenotypes, AD-type dementia, Alzheimer's disease, CFP, JPH3, MCI conversion, MMSE, SNCA, addition, algorithm, batteries, clinical data, cognition, cognitive impairment, cohort, confident features, control, conversion, conversion model, conversion pathways, data, degradation, dementia, disease, experiments, features, impairment, inflammation, language, levels, machine, mechanism, metabolites, microglia, mild cognitive impairment, model, molecular mechanisms, molecular pathways, multiclass model, neuronal regulation, normal cognition, oleamide, pTau, participants, pathway, phase, phenotype, plasma, plasma vesicles, priority language, prodromal Alzheimer's disease, protein, protein degradation, regulation, results, rodent microglia, samples, study, tTau, vesicles


  • Department of Health and Social Care
  • Basque Government
  • European Research Council
  • Swedish Research Council
  • National Institute for Health and Care Research
  • Research Foundation - Flanders
  • Fundación Seneca
  • Vlaams Instituut voor Biotechnologie
  • South London and Maudsley NHS Foundation Trust
  • Lundbeck (Denmark)
  • European Commission