Prediction model for drug response of acute myeloid leukemia patients

Trac, Quang Thinh; Pawitan, Yudi; Mou, Tian; Erkers, Tom; Östling, Päivi; Bohlin, Anna; Österroos, Albin; Vesterlund, Mattias; Jafari, Rozbeh; Siavelis, Ioannis; Bäckvall, Helena; Kiviluoto, Santeri; Orre, Lukas M.; Rantalainen, Mattias; Lehtiö, Janne; Lehmann, Sören; Kallioniemi, Olli; Vu, Trung Nghia

doi:10.1038/s41698-023-00374-z

Cited by 2 publications

(3 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For model building, we utilized all available data types, namely clinical, RNA, and Whole Exome sequencing, in isolation and all possible combinations. Our analysis showed similar overall performance compared to previous efforts [5]. Specifically, Quang et al [5] used a single hold-out approach to evaluate performance and reported a median correlation of 0.35.…”

Section: Discussionsupporting

confidence: 78%

“…Our analysis showed similar overall performance compared to previous efforts [5]. Specifically, Quang et al [5] used a single hold-out approach to evaluate performance and reported a median correlation of 0.35. Even though they used information from the Whole Exome and RNA sequencing data, they utilized only the RNA sequencing as input in the training process.…”

Section: Discussionsupporting

confidence: 78%

“…The training data for DRUML comprises proteomics and phosphoproteomics data from 48 different cell lines, and they assessed its performance using data from 53 cellular models obtained from 12 independent research facilities. Trac et al[5] developed MDREAM (Monotherapy Drug Response prediction for AML) using integrated omics data. MDREAM underwent training and initial validation utilizing the BeatAML cohort.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Machine Learning for Predicting Therapeutic Outcomes in Acute Myeloid Leukemia Patients

Karathanasis,

Papasavva,

Oulas

et al. 2024

Preprint

View full text Add to dashboard Cite

Background and ObjectiveThe standard of care inAcute Myeloid Leukemiapatients has remained essentially unchanged for nearly 40 years. Due to the complicated mutational patterns within and between individual patients and a lack of targeted agents for most mutational events, implementing individualized treatment for AML has proven difficult. We reanalysed theBeatAML datasetemployingMachine Learning algorithms. The BeatAML project entails patients extensively characterized at the molecular and clinical levels and linked to drug sensitivity outputs. Our approach capitalizes on the molecular and clinical data provided by theBeatAML datasetto predict theex vivodrug sensitivity for the 122 drugs evaluated by the project.MethodsWe utilized ElasticNet, which produces fully interpretable models, in combination with a two-step training protocol that allowed us to narrow down computations. We automated the genes’ filtering step by employing two metrics, and we evaluated all possible data combinations to identify the best training configuration settings per drug.ResultsWe report a Pearson correlation across all drugs of 0.36 when clinical and RNA sequencing data were combined, with the best-performing models reaching a Pearson correlation of 0.67. When we trained using the datasets in isolation, we noted that RNA Sequencing data (Pearson: 0.36) attained three times the predictive power of whole exome sequencing data (Pearson: 0.11), with clinical data falling somewhere in between (Pearson 0.26). Lastly, we present a paradigm of clinical significance. We used our models’ prediction as ahealth management scoreto rank an individual’s expected response to treatment. We identified 78 patients out of 89 (88%) that the proposed drug was more potent than the administered one based on theirex vivodrug sensitivity data.ConclusionsIn conclusion, our reanalysis of the BeatAML dataset using Machine Learning algorithms demonstrates the potential for individualized treatment prediction in Acute Myeloid Leukemia patients, addressing the longstanding challenge of treatment personalization in this disease. By leveraging molecular and clinical data, our approach yields promising correlations between predicted drug sensitivity and actual responses, highlighting a significant step forward in improving therapeutic outcomes for AML patients.HighlightsMachine learning can predict response to treatment in Acute Myeloid Leukemia patients.RNA sequencing data are more informative than whole exome sequencing and clinical data in predicting drug response in Acute Myeloid Leukemia patients.Drug response predictions could be used as a health management score to rank the individual’s expected response to treatment.We identified a more potent drug than the administered one for 88% (78 out of 89) of the patients examined.

show abstract

Section: Discussionsupporting

confidence: 78%

Section: Discussionsupporting

confidence: 78%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning for Predicting Therapeutic Outcomes in Acute Myeloid Leukemia Patients

Karathanasis,

Papasavva,

Oulas

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Prognosis and treatment in acute myeloid leukemia: a comprehensive review

Debnath,

Nath

2024

Egypt J Med Hum Genet

View full text Add to dashboard Cite

Acute myeloid leukemia (AML) is a heterogeneous disorder that is characterized by clonal expansion of immature "blast cells" in the bone marrow and peripheral circulation, resulting in bone marrow failure and inefficient erythropoiesis. The identification of numerous recurrent genetic mutations such as NPM1, CEBPA, and FLT3-ITD has stratified AML into favorable, intermediate, and adverse-risk groups, respectively, along with a cytogenetic profile that carries a considerably different prognosis among these groups. For post-induction treatment, cytogenetics and genetic mutation testing continue to be vital prognostic tools. Despite advancements, including an increased understanding of biology and new drug targets, the cornerstone of treatment still consists of a combination of cytarabine- and anthracycline-based regimens. The majority of patients eventually relapse and die of the disease, especially the elderly population. This review describes the prognosis of different molecular markers and the major recent advancements in the treatment of AML.

show abstract

Prediction model for drug response of acute myeloid leukemia patients

Cited by 2 publications

References 51 publications

Machine Learning for Predicting Therapeutic Outcomes in Acute Myeloid Leukemia Patients

Machine Learning for Predicting Therapeutic Outcomes in Acute Myeloid Leukemia Patients

Prognosis and treatment in acute myeloid leukemia: a comprehensive review

Contact Info

Product

Resources

About