Clinical recommendations for Acute Myeloid Leukemia (AML) classification and risk-stratification remain heavily reliant on cytogenetic findings at diagnosis, which are present in <50% of patients. Using comprehensive molecular profiling data from 3,653 patients we characterize and validate 16 molecular classes describing 100% of AML patients. Each class represents diverse biological AML subgroups, and is associated with distinct clinical presentation, likelihood of response to induction chemotherapy, risk of relapse and death over time. Secondary AML-2, emerges as the second largest class (24%), associates with high-risk disease, poor prognosis irrespective of flow Minimal Residual Disease (MRD) negativity, and derives significant benefit from transplantation. Guided by class membership we derive a 3-tier risk-stratification score that re-stratifies 26% of patients as compared to standard of care. This results in a unified framework for disease classification and risk-stratification in AML that relies on information from cytogenetics and 32 genes. Last, we develop an open-access patient-tailored clinical decision support tool.

The mechanisms of action of and resistance to trastuzumab deruxtecan (T-DXd), an anti-HER2–drug conjugate for breast cancer treatment, remain unclear. The phase 2 DAISY trial evaluated the efficacy of T-DXd in patients with HER2-overexpressing (n = 72, cohort 1), HER2-low (n = 74, cohort 2) and HER2 non-expressing (n = 40, cohort 3) metastatic breast cancer. In the full analysis set population (n = 177), the confirmed objective response rate (primary endpoint) was 70.6% (95% confidence interval (CI) 58.3–81) in cohort 1, 37.5% (95% CI 26.4–49.7) in cohort 2 and 29.7% (95% CI 15.9–47) in cohort 3. The primary endpoint was met in cohorts 1 and 2. Secondary endpoints included safety. No new safety signals were observed. During treatment, HER2-expressing tumors (n = 4) presented strong T-DXd staining. Conversely, HER2 immunohistochemistry 0 samples (n = 3) presented no or very few T-DXd staining (Pearson correlation coefficient r = 0.75, P = 0.053). Among patients with HER2 immunohistochemistry 0 metastatic breast cancer, 5 of 14 (35.7%, 95% CI 12.8–64.9) with ERBB2 expression below the median presented a confirmed objective response as compared to 3 of 10 (30%, 95% CI 6.7–65.2) with ERBB2 expression above the median. Although HER2 expression is a determinant of T-DXd efficacy, our study suggests that additional mechanisms may also be involved. (ClinicalTrials.gov identifier NCT04132960.)

The availability of patient cohorts with several types of omics data opens new perspectives for exploring the disease’s underlying biological processes and developing predictive models. It also comes with new challenges in computational biology in terms of integrating high-dimensional and heterogeneous data in a fashion that captures the interrelationships between multiple genes and their functions. Deep learning methods offer promising perspectives for integrating multi-omics data. In this paper, we review the existing integration strategies based on autoencoders and propose a new customizable one whose principle relies on a two-phase approach. In the first phase, we adapt the training to each data source independently before learning cross-modality interactions in the second phase. By taking into account each source’s singularity, we show that this approach succeeds at taking advantage of all the sources more efficiently than other strategies. Moreover, by adapting our architecture to the computation of Shapley Additive explanations, our model can provide interpretable results in a multi-source setting. Using multiple omics sources from different TCGA cohorts, we demonstrate the performance of the proposed method for cancer on test cases for several tasks, such as the classification of tumor types and breast cancer subtypes, as well as survival outcome prediction. We show through our experiments the great performances of our architecture on seven different datasets with various sizes and provide some interpretations of the results obtained. Our code is available on (https://github.com/HakimBenkirane/CustOmics).

Metastatic relapse after treatment is the leading cause of cancer mortality, and known resistance mechanisms are missing for most treatments administered to patients. To bridge this gap, we analyze a pan-cancer cohort (META-PRISM) of 1,031 refractory metastatic tumors profiled via whole-exome and transcriptome sequencing. META-PRISM tumors, particularly prostate, bladder, and pancreatic types, displayed the most transformed genomes compared to primary untreated tumors. Standard-of-care resistance biomarkers were identified only in lung and colon cancers - 9.6% of META-PRISM tumors, indicating that too few resistance mechanisms have received clinical validation. In contrast, we verified the enrichment of multiple investigational and hypothetical resistance mechanisms in treated compared to non-treated patients, thereby confirming their putative role in treatment resistance. Additionally, we demonstrated that molecular markers improve six-month survival prediction, particularly in patients with advanced breast cancer. Our analysis establishes the utility of META-PRISM cohort for investigating resistance mechanisms and performing predictive analyses in cancer.