PT  - JOURNAL ARTICLE
AU  - Adriana Salcedo
AU  - Maxime Tarabichi
AU  - Alex Buchanan
AU  - Shadrielle M.G. Espiritu
AU  - Hongjiu Zhang
AU  - Kaiyi Zhu
AU  - Tai-Hsien Ou Yang
AU  - Ignaty Leshchiner
AU  - Dimitris Anastassiou
AU  - Yuanfang Guan
AU  - Gun Ho Jang
AU  - Kerstin Haase
AU  - Amit G. Deshwar
AU  - William Zou
AU  - Imaad Umar
AU  - Stefan Dentro
AU  - Jeff A. Wintersinger
AU  - Kami Chiotti
AU  - Jonas Demeulemeester
AU  - Clemency Jolly
AU  - Lesia Sycza
AU  - Minjeong Ko
AU  - PCAWG-11 Working Group
AU  - SMC-Het Participants
AU  - David C. Wedge
AU  - Quaid D. Morris
AU  - Kyle Ellrott
AU  - Peter Van Loo
AU  - Paul C. Boutros
TI  - Crowd-sourced benchmarking of single-sample tumour subclonal reconstruction
AID  - 10.1101/2022.06.14.495937
DP  - 2022 Jan 01
TA  - bioRxiv
PG  - 2022.06.14.495937
4099  - http://biorxiv.org/content/early/2022/06/15/2022.06.14.495937.short
4100  - http://biorxiv.org/content/early/2022/06/15/2022.06.14.495937.full
AB  - Tumours are dynamically evolving populations of cells. Subclonal reconstruction algorithms use bulk DNA sequencing data to quantify parameters of tumour evolution, allowing assessment of how cancers initiate, progress and respond to selective pressures. A plethora of subclonal reconstruction algorithms have been created, but their relative performance across the varying biological and technical features of real-world cancer genomic data is unclear. We therefore launched the ICGC-TCGA DREAM Somatic Mutation Calling -- Tumour Heterogeneity and Evolution Challenge. This seven-year community effort used cloud-computing to benchmark 31 containerized subclonal reconstruction algorithms on 51 simulated tumours. Each algorithm was scored for accuracy on seven independent tasks, leading to 12,061 total runs. Algorithm choice influenced performance significantly more than tumour features, but purity-adjusted read-depth, copy number state and read mappability were associated with performance of most algorithms on most tasks. No single algorithm was a top performer for all seven tasks and existing ensemble strategies were surprisingly unable to outperform the best individual methods, highlighting a key research need. All containerized methods, evaluation code and datasets are available to support further assessment of the determinants of subclonal reconstruction accuracy and development of improved methods to understand tumour evolution.Competing Interest StatementPCB sits on the Scientific Advisory Boards of Sage Bionetworks, Intersect Diagnostics Inc. and BioSymetrics Inc. AS is an employee and shareholder of Illumina Inc