Robinson, A. D. | Search bioRxiv

bioRxiv2023

Data-driven biomarkers outperform theory-based biomarkers in predicting stroke motor outcomes

Chronic motor impairments are a leading cause of disability after stroke. Previous studies have predicted motor outcomes based on the degree of damage to predefined structures in the motor system, such as the corticospinal tract. However, such theory-based approaches may not take full advantage of the information contained in clinical imaging data. The present study uses data-driven approaches to predict chronic motor outcomes after stroke and compares the accuracy of these predictions to previously-identified theory-based biomarkers. Using a cross-validation framework, regression models were trained using lesion masks and motor outcomes data from 789 stroke patients (293 female/496 male) from the ENIGMA Stroke Recovery Working Group (age 64.9{+/-}18.0 years; time since stroke 12.2{+/-}0.2 months; normalised motor score 0.7{+/-}0.5 (range [0,1]). The out-of-sample prediction accuracy of two theory-based biomarkers was assessed: lesion load of the corticospinal tract, and lesion load of multiple descending motor tracts. These theory-based prediction accuracies were compared to the prediction accuracy from three data-driven biomarkers: lesion load of lesion-behaviour maps, lesion load of structural networks associated with lesion-behaviour maps, and measures of regional structural disconnection. In general, data-driven biomarkers had better prediction accuracy - as measured by higher explained variance in chronic motor outcomes - than theory-based biomarkers. Data-driven models of regional structural disconnection performed the best of all models tested (R2 = 0.210, p < 0.001), performing significantly better than predictions using the theory-based biomarkers of lesion load of the corticospinal tract (R2 = 0.132, p< 0.001) and of multiple descending motor tracts (R2 = 0.180, p < 0.001). They also performed slightly, but significantly, better than other data-driven biomarkers including lesion load of lesion-behaviour maps (R2 =0.200, p < 0.001) and lesion load of structural networks associated with lesion-behaviour maps (R2 =0.167, p < 0.001). Ensemble models - combining basic demographic variables like age, sex, and time since stroke - improved prediction accuracy for theory-based and data-driven biomarkers. Finally, combining both theory-based and data-driven biomarkers with demographic variables improved predictions, and the best ensemble model achieved R2 = 0.241, p < 0.001. Overall, these results demonstrate that models that predict chronic motor outcomes using data-driven features, particularly when lesion data is represented in terms of structural disconnection, perform better than models that predict chronic motor outcomes using theory-based features from the motor system. However, combining both theory-based and data-driven models provides the best predictions.

neuroscience↗

bioRxiv2019

Therapeutically actionable PAK4 is amplified, overexpressed and involved in bladder cancer progression

Muscle-invasive bladder carcinomas (MIBCs) are aggressive genitourinary malignancies. Disease incidence and survival rates vary based on aggressiveness and treatment options. Metastatic urothelial carcinoma of the bladder is generally incurable by current chemotherapy and leads to early mortality. For a minority ([~]20%) of patients, T-cell checkpoint inhibitors provide durable benefits following prior platinum therapy. Recent studies have identified molecular subtypes of MIBCs with different sensitivities to frontline therapy, suggesting heterogeneity in these tumors and pointing to the importance of molecular characterization of MIBCs to provide effective treatment. We have performed multi-omic profiling of the kinome to identify therapeutic targets that are overexpressed in a subset of BLCAs. Our analyses revealed amplification and overexpression of P21 (RAC1) activated kinase 4 (PAK4) in a subset of BLCAs. For these tumors, multiplex kinase assay profiling identified corresponding PAK4 target substrates. By performing experiments using cultured bladder cancer cells, we confirmed the role of PAK4 in BLCA cell proliferation and invasion. Furthermore, our studies showed that a PAK4 inhibitor was effective in curtailing growth of BLCA cells. Transcriptomic analyses identified elevated expression of another kinase, Protein Tyrosine Kinase 6 (PTK6), upon treatment with a PAK4 inhibitor. Similarly, RNA interference of PAK4 led to elevated expression of PTK6. Treatment with a combination of kinase inhibitors (vandetanib and dasatinib) showed enhanced sensitivity compared to either drug alone. Thus, PAK4 may be therapeutically actionable for a subset of MIBC patients with amplified and/or overexpressed PAK4 in their tumors. Our results also indicate that combined inhibition of PAK4 and PTK6 may overcome resistance to PAK4. These observations warrant clinical investigations with selected BLCA patients.

cancer biology↗