TY - JOUR

T1 - SEMORE

T2 - SEgmentation and MORphological fingErprinting by machine learning automates super-resolution data analysis

AU - Bender, Steen W.B.

AU - Dreisler, Marcus W.

AU - Zhang, Min

AU - Kæstel-Hansen, Jacob

AU - Hatzakis, Nikos S.

N1 - Funding Information: This work was supported by the Villum foundation center BIONEC (18333), the NNF challenge center for Optimised Oligo Escape and control of disease (NNF23OC0081287), the NNF center for 4D cellular dynamics (NNF22OC0075851), the Lundbeck foundation grant R346-2020-1759, Villum foundation Synergy grant (40578), and Carlsberg foundation grant CF21-0499. We are grateful to the group of Professor William Edward Louch for providing the experimental data sets of live-cell PALM of ryanodine receptors. N.S.H. is a member of the Integrative Structural Biology Cluster (ISBUC) at the University of Copenhagen and associate member of the Novo Nordisk Foundation Center for Protein Research, which is supported financially by the Novo Nordisk Foundation (NNF14CC0001). Publisher Copyright: © The Author(s) 2024.

PY - 2024

Y1 - 2024

N2 - The morphology of protein assemblies impacts their behaviour and contributes to beneficial and aberrant cellular responses. While single-molecule localization microscopy provides the required spatial resolution to investigate these assemblies, the lack of universal robust analytical tools to extract and quantify underlying structures limits this powerful technique. Here we present SEMORE, a semi-automatic machine learning framework for universal, system- and input-dependent, analysis of super-resolution data. SEMORE implements a multi-layered density-based clustering module to dissect biological assemblies and a morphology fingerprinting module for quantification by multiple geometric and kinetics-based descriptors. We demonstrate SEMORE on simulations and diverse raw super-resolution data: time-resolved insulin aggregates, and published data of dSTORM imaging of nuclear pore complexes, fibroblast growth receptor 1, sptPALM of Syntaxin 1a and dynamic live-cell PALM of ryanodine receptors. SEMORE extracts and quantifies all protein assemblies, their temporal morphology evolution and provides quantitative insights, e.g. classification of heterogeneous insulin aggregation pathways and NPC geometry in minutes. SEMORE is a general analysis platform for super-resolution data, and being a time-aware framework can also support the rise of 4D super-resolution data.

AB - The morphology of protein assemblies impacts their behaviour and contributes to beneficial and aberrant cellular responses. While single-molecule localization microscopy provides the required spatial resolution to investigate these assemblies, the lack of universal robust analytical tools to extract and quantify underlying structures limits this powerful technique. Here we present SEMORE, a semi-automatic machine learning framework for universal, system- and input-dependent, analysis of super-resolution data. SEMORE implements a multi-layered density-based clustering module to dissect biological assemblies and a morphology fingerprinting module for quantification by multiple geometric and kinetics-based descriptors. We demonstrate SEMORE on simulations and diverse raw super-resolution data: time-resolved insulin aggregates, and published data of dSTORM imaging of nuclear pore complexes, fibroblast growth receptor 1, sptPALM of Syntaxin 1a and dynamic live-cell PALM of ryanodine receptors. SEMORE extracts and quantifies all protein assemblies, their temporal morphology evolution and provides quantitative insights, e.g. classification of heterogeneous insulin aggregation pathways and NPC geometry in minutes. SEMORE is a general analysis platform for super-resolution data, and being a time-aware framework can also support the rise of 4D super-resolution data.

U2 - 10.1038/s41467-024-46106-0

DO - 10.1038/s41467-024-46106-0

M3 - Journal article

C2 - 38409214

AN - SCOPUS:85186188760

VL - 15

JO - Nature Communications

JF - Nature Communications

SN - 2041-1723

IS - 1

M1 - 1763

ER -