Biology subjects

Rantalainen, M.

Publications and source records attributed to Rantalainen, M..

3 recordsLinked to original sources

bioRxiv2024

Pathway activation model for personalized prediction of drug synergy

Targeted monotherapies for cancer often fail due to inherent or acquired drug resistance. By aiming at multiple targets simultaneously, drug combinations can produce synergistic interactions that increase drug effectiveness and reduce resistance. Computational models based on the integration of omics data have been used to identify synergistic combinations, but predicting drug synergy remains a challenge. Here, we introduce DIPx, an algorithm for personalized prediction of drug synergy based on biologically motivated tumor- and drug-specific pathway activation scores (PASs). We trained and validated DIPx in the AstraZeneca-Sanger (AZS) DREAM Challenge dataset using two separate test sets: Test Set 1 comprised the combinations already present in the training set, while Test Set 2 contained combinations absent from the training set, thus indicating the models ability to handle novel combinations. The Spearman correlation coefficients between predicted and observed drug synergy were 0.50 (95% CI: 0.47-0.53) in Test Set 1 and 0.26 (95% CI: 0.22-0.30) in Test Set 2, compared to 0.38 (95% CI: 0.34-0.42) and 0.18 (95% CI: 0.16-0.20), respectively, for the best performing method in the Challenge. We show evidence that higher synergy is associated with higher functional interaction between the drug targets, and this functional interaction information is captured by PAS. We illustrate the use of PAS to provide a potential biological explanation in terms of activated pathways that mediate the synergistic effects of combined drugs. In summary, DIPx can be a useful tool for personalized prediction of drug synergy and exploration of activated pathways related to the effects of combined drugs.

bioinformatics↗

bioRxiv2023

Ensembles for improved detection of invasive breast cancer in histological images

Accurate detection of invasive breast cancer (IC) can provide decision support to pathologists as well as improve downstream computational analyses, where detection of IC is a first step. Tissue containing IC is characterized by the presence of specific morphological features, which can be learned by convolutional neural networks (CNN). Here, we compare the use of a single CNN model versus an ensemble of several base models with the same CNN architecture, and we evaluate prediction performance as well as variability across ensemble based model predictions. Two in-house datasets comprising 587 WSI are used to train an ensemble of ten InceptionV3 models whose consensus is used to determine the presence of IC. A novel visualization strategy was developed to communicate ensemble agreement spatially. Performance was evaluated in an internal test set with 118 WSIs, and in an additional external dataset (TCGA breast cancer) with 157 WSI. We observed that the ensemble-based strategy outperformed the single CNN-model alternative with respect to accuracy on tile level in 89% of all WSIs in the test set. The overall accuracy was 0.92 (DICE coefficient, 0.90) for the ensemble model, and 0.85 (DICE coefficient, 0.83) for the single CNN alternative in the internal test set. For TCGA the ensemble outperformed the single CNN in 96.8% of the WSI, with an accuracy of 0.87 (DICE coefficient 0.89), the single model provides an accuracy of 0.75 (DICE coefficient 0.78) The results suggest that an ensemble-based modeling strategy for breast cancer invasive cancer detection consistently outperforms the conventional single model alternative. Furthermore, visualization of the ensemble agreement and confusion areas provide direct visual interpretation of the results. High performing cancer detection can provide decision support in the routine pathology setting as well as facilitate downstream computational analyses.

bioinformatics↗

bioRxiv2018

Cell-free DNA profiling of metastatic prostate cancer reveals microsatellite instability, structural rearrangements and clonal hematopoiesis

BackgroundThere are multiple existing and emerging therapeutic avenues for metastatic prostate cancer, with a common denominator, which is the need for predictive biomarkers. Circulating tumor DNA (ctDNA) has the potential to cost-efficiently accelerate precision medicine trials to improve clinical efficacy and diminish costs and toxicity. However, comprehensive ctDNA profiling in metastatic prostate cancer to date has been limited.\n\nMethodsA combination of targeted- and low-pass whole genome sequencing was performed on plasma cell-free DNA and matched white blood cell germline DNA in 364 blood samples from 217 metastatic prostate cancer patients.\n\nResultsctDNA was detected in 85.9% of baseline samples, correlated to line of therapy and was mirrored by circulating tumor cell enumeration of synchronous blood samples. Comprehensive profiling of the androgen receptor (AR) revealed a continuous increase in the fraction of patients with intra-AR structural variation, from 15.4% during first line mCRPC therapy to 45.2% in fourth line, indicating a continuous evolution of AR during the course of the disease. Patients displayed frequent alterations in DNA repair deficiency genes (18.0%). Additionally, the microsatellite instability phenotype was identified in 3.81% of eligible samples ([≥]0.1 ctDNA fraction). Sequencing of non-repetitive intronic- and exonic regions of PTEN, RB1 and TP53 detected biallelic inactivation in 47.5%, 20.3% and 44.1% of samples with [≥]0.2 ctDNA fraction, respectively. Only one patient carried a clonal high-impact variant without a detectable second hit. Intronic high-impact structural variation was twice as common as exonic mutations in PTEN and RB1. Finally, 14.6% of patients presented false positive variants due to clonal hematopoiesis, commonly ignored in commercially available assays.\n\nConclusionsctDNA profiles appear to mirror the genomic landscape of metastatic prostate cancer tissue and may cost-efficiently provide somatic information in clinical trials designed to identify predictive biomarkers. However, intronic sequencing of the interrogated tumor suppressors challenge the ubiquitous focus on coding regions and is vital, together with profiling of synchronous white blood cells, to minimize erroneous assignments which in turn may confound results and impede true associations in clinical trials.

genomics↗