A Multi-Cohort Gene Expression Classifier (ALLCatchR) Identifies B-Precursor ALL Subtypes and Their Developmental Trajectories across Age Groups

Beder, Thomas; Hansen, Björn Thore; Hartmann, Alina; Zimmermann, Johannes; Amelunxen, Eric; Kraft, Nadine; Walter, Wencke; Žaliová, Markéta; Antić, Željko; Chouvarine, Philippe; Bartsch, Lorenz; Bultmann, Miriam; Bendig, Sonja; Kässens, Jan Christian; Franzenburg, Sören; Kaleta, Christoph; Franke, André; Cario, Gunnar; Schrappe, Martin; Neumann, Martin; Goekbuget, Nicola; Bergmann, Anke; Trka, Jan; Haferlach, Claudia; Brüggemann, Monika; Baldus, Claudia D.; Bastian, Lorenz

doi:10.1182/blood-2022-163311

Cited by 1 publication

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…M&M performs comparable to existing, more classrestricted pediatric tumor classifiers When introducing a pan-cancer classifier, it is important to check whether it can compete with other classification algorithms without causing a performance drop. To this end, we compared M&M's results to three well-known and wellperforming pediatric tumor classifiers: ALLCatchR for B-ALL tumor subtypes, the DKFZ methylation classifier for CNS tumor types (CNS m ) and the DKFZ methylation classifier for sarcomas (SARC m ) 3,9,10 . To make the comparison robust, 100 different data subsets were generated by downsampling to 25% of the available samples.…”

Section: Mandm Misclassifications Are Infrequent Non-repetitive and I...mentioning

confidence: 99%

“…A methylation-profile based central nervous system (CNS) classifier, developed within the DKFZ in Heidelberg 3 , was shown to increase patient survival 8 . In recent years, several pediatric classifiers were developed, based on DNA-methylation or RNA-seq data 3,9,10 . Nevertheless, these classifiers only cover a subset of the existing tumor (sub)types within pediatric cancer.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

M&M: An RNA-seq based Pan-Cancer Classifier for Pediatric Tumors

Wallis,

Baker-Hernandez,

van Tuil

et al. 2024

Preprint

View full text Add to dashboard Cite

With many rare tumor types, acquiring the correct diagnosis is a challenging but crucial process in pediatric oncology. Here, we present M&M, a pan-cancer ensemble-based machine learning algorithm tailored towards inclusion of rare tumor types. The RNA-seq based algorithm can classify 52 different tumor types (precision∼99%, recall∼80%), plus the underlying 96 tumor subtypes (precision∼96%, recall∼70%). For low-confidence classifications, a comparable precision is achieved when including the three highest-scoring labels. M&M’s pan-cancer setup allows for easy clinical implementation, requiring only one classifier for all incoming diagnostic samples, including samples from different tumor stages and treatment statuses. Simultaneously, its performance is comparable to existing tumor- and tissue-specific classifiers. The introduction of an extensive pan-cancer classifier in diagnostics has the potential to increase diagnostic accuracy for many pediatric cancer cases, thereby contributing towards optimal patient survival and quality of life.

show abstract

Section: Mandm Misclassifications Are Infrequent Non-repetitive and I...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%