{"id":"oscr:b:6K5ZZES0Z3YPT-R","url":"https://openscicode.org/b/oscr:b:6K5ZZES0Z3YPT-R","status":"current","doi":"10.1186/s13073-026-01650-w","since":"2026-11-14","page":"doi_10.1186_s13073-026-01650-w","repo":"github.com/clinicalepigeneticslaboratory/accs-workflows","commit":"f9e1692e02b064f370e94b97fdf0de8bc1681c4d","path":"4_models_training.py","swhid":"swh:1:cnt:bf958aa5f83e49399f672fc64698fa769a763419","lines":[49,99],"symbol":"train_models","paragraphs":[[13,"Methods › Models training and tuning"],[28,"Results › Simple ML models can outperform more complex algorithms"]],"method":"lexical-v1","origin":"machine","paper":"https://doi.org/10.1186/s13073-026-01650-w","swhid_qualified":"swh:1:cnt:bf958aa5f83e49399f672fc64698fa769a763419;origin=https://github.com/clinicalepigeneticslaboratory/accs-workflows;anchor=swh:1:rev:f9e1692e02b064f370e94b97fdf0de8bc1681c4d;path=/4_models_training.py;lines=49-99","reader":"https://openscicode.org/paper/doi_10.1186_s13073-026-01650-w/?path=4_models_training.py#L49-L99","citation":"Code block oscr:b:6K5ZZES0Z3YPT-R (https://openscicode.org/b/oscr:b:6K5ZZES0Z3YPT-R)\n4_models_training.py, lines 49 to 99, in github.com/clinicalepigeneticslaboratory/accs-workflows (https://github.com/clinicalepigeneticslaboratory/accs-workflows), commit f9e1692e02b064f370e94b97fdf0de8bc1681c4d.\nPaper: https://doi.org/10.1186/s13073-026-01650-w\nSWHID: swh:1:cnt:bf958aa5f83e49399f672fc64698fa769a763419;origin=https://github.com/clinicalepigeneticslaboratory/accs-workflows;anchor=swh:1:rev:f9e1692e02b064f370e94b97fdf0de8bc1681c4d;path=/4_models_training.py;lines=49-99"}