crossNN: an explainable framework for cross-platform DNA methylation-based classification of cancer
Abstract DNA methylation-based classification of brain tumors has emerged as a powerful and indispensable diagnostic technique. Initial implementations have used methylation microarrays for data generation, but different sequencing approaches are increasingly used. Most current classifiers, however, rely on a fixed methylation feature space, rendering them incompatible with other platforms, especially different flavors of DNA sequencing. Here, we describe crossNN, a neural network-based machine learning framework which can accurately classify tumor entities using DNA methylation profiles obtained from different platforms and with different epigenome coverage and sequencing depth. It outperforms other deep- and shallow machine learning models with respect to precision as well as simplicity and computational requirements while still being fully explainable. Validation in a large cohort of >1,900 tumors profiled using different microarray and sequencing platforms, including low-pass nanopore and targeted bisulfite sequencing, demonstrates the robustness and scalability of the model..
Medienart: |
Preprint |
---|
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
bioRxiv.org - (2024) vom: 27. Jan. Zur Gesamtaufnahme - year:2024 |
---|
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Yuan, Dongsheng [VerfasserIn] |
---|
Links: |
Volltext [kostenfrei] |
---|
Themen: |
---|
doi: |
10.1101/2024.01.22.24301523 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
XBI042271738 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | XBI042271738 | ||
003 | DE-627 | ||
005 | 20240128090549.0 | ||
007 | cr uuu---uuuuu | ||
008 | 240125s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1101/2024.01.22.24301523 |2 doi | |
035 | |a (DE-627)XBI042271738 | ||
035 | |a (biorXiv)10.1101/2024.01.22.24301523 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Yuan, Dongsheng |e verfasserin |0 (orcid)0009-0000-8819-3369 |4 aut | |
245 | 1 | 0 | |a crossNN: an explainable framework for cross-platform DNA methylation-based classification of cancer |
264 | 1 | |c 2024 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a Computermedien |b c |2 rdamedia | ||
338 | |a Online-Ressource |b cr |2 rdacarrier | ||
520 | |a Abstract DNA methylation-based classification of brain tumors has emerged as a powerful and indispensable diagnostic technique. Initial implementations have used methylation microarrays for data generation, but different sequencing approaches are increasingly used. Most current classifiers, however, rely on a fixed methylation feature space, rendering them incompatible with other platforms, especially different flavors of DNA sequencing. Here, we describe crossNN, a neural network-based machine learning framework which can accurately classify tumor entities using DNA methylation profiles obtained from different platforms and with different epigenome coverage and sequencing depth. It outperforms other deep- and shallow machine learning models with respect to precision as well as simplicity and computational requirements while still being fully explainable. Validation in a large cohort of >1,900 tumors profiled using different microarray and sequencing platforms, including low-pass nanopore and targeted bisulfite sequencing, demonstrates the robustness and scalability of the model. | ||
650 | 4 | |a Biology |7 (dpeaa)DE-84 | |
650 | 4 | |a 570 |7 (dpeaa)DE-84 | |
700 | 1 | |a Jugas, Robin |4 aut | |
700 | 1 | |a Pokorna, Petra |4 aut | |
700 | 1 | |a Sterba, Jaroslav |4 aut | |
700 | 1 | |a Slaby, Ondrej |4 aut | |
700 | 1 | |a Schmid, Simone |4 aut | |
700 | 1 | |a Siewert, Christin |4 aut | |
700 | 1 | |a Osberg, Brendan |4 aut | |
700 | 1 | |a Capper, David |4 aut | |
700 | 1 | |a Zeiner, Pia |4 aut | |
700 | 1 | |a Weber, Katharina |4 aut | |
700 | 1 | |a Harter, Patrick |4 aut | |
700 | 1 | |a Jabareen, Nabil |4 aut | |
700 | 1 | |a Mackowiak, Sebastian |4 aut | |
700 | 1 | |a Ishaque, Naveed |4 aut | |
700 | 1 | |a Eils, Roland |4 aut | |
700 | 1 | |a Lukassen, Sören |0 (orcid)0000-0001-7045-6327 |4 aut | |
700 | 1 | |a Euskirchen, Philipp |0 (orcid)0000-0002-9138-805X |4 aut | |
773 | 0 | 8 | |i Enthalten in |t bioRxiv.org |g (2024) vom: 27. Jan. |
773 | 1 | 8 | |g year:2024 |g day:27 |g month:01 |
856 | 4 | 0 | |u http://dx.doi.org/10.1101/2024.01.22.24301523 |z kostenfrei |3 Volltext |
912 | |a GBV_XBI | ||
951 | |a AR | ||
952 | |j 2024 |b 27 |c 01 |