Systematic Living Evidence for Clinical Trials (SyLECT): a data-driven framework for drug selection in clinical trials in motor neuron disease
Wong, C.; Cardinali, A.; Liao, J.; Selvaraj, B. T.; Baxter, P.; Carter, R. N.; Longden, J.; Graham, R. E.; Dakin, R. S.; Pal, S.; Chataway, J.; Swingler, R.; Hardingham, G. E.; Carragher, N.; Chandran, S.; Macleod, M.; the ReLiSyR-MND consortium,
Show abstract
Despite many promising preclinical studies and decades of clinical trials, there remains a paucity of effective disease-modifying drugs in motor neuron disease. We aimed to develop a systematic and structured data-driven framework to identify, evaluate and prioritise candidate drugs for clinical trials, specifically for the Motor Neuron Disease-Systematic Multi-Arm Adaptive Randomised Trial (MND-SMART; NCT040302870). We developed the Systematic Living Evidence for Clinical Trials (SyLECT) platform as a modular framework integrating emerging data from different domains to inform prioritisation of candidate drugs. Current domains incorporated include published clinical, animal in vivo, and in vitro literature; in house in vitro high throughput drug screening; pathway and network analysis; and pharmacological, feasibility and clinical trial data from drug, chemical, and clinical trial databases. In this approach, we first identify a list of candidate drugs from these domains then select drugs for further consideration based on drug properties, feasibility, and expert opinion. For prioritised drugs we then generate, evaluate, and synthesise further evidence from across data domains. Using automated workflows and interactive web applications, we produce snapshot "living evidence summaries" to inform expert panel decisions on prioritisation of candidate drugs for MND-SMART. The third drug selected for MND-SMART and the first using this framework is amantadine. We demonstrated the feasibility of a systematic data-driven framework to inform prioritisation of candidate drugs for clinical trials in motor neuron disease, with potential for wider application across diseases where there is unmet clinical need. Key messagesO_ST_ABSWhat is already known on this topicC_ST_ABS- Despite extensive preclinical research and clinical trials for disease-modifying treatments in motor neuron disease, translational success remains elusive. - Advances in research across biological domains presents a wealth of data to guide prioritisation of candidate drugs for clinical trials. What this study adds- This study demonstrates the feasibility of using a systematic, modular, data-driven framework to inform prioritisation of candidate drugs for an adaptive platform trial in motor neuron disease. How this study might affect research, practice or policy- The framework could be applied to inform prioritisation of drugs for clinical trials in other diseases, especially adaptive platform trials in neurodegenerative diseases.
Matching journals
The top 12 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- CATALYST trial protocol: A multicentre, open-label, phase II, multi-arm trial for an early and accelerated evaluation of the potential treatments for COVID-19 in hospitalised adults 93%
- RESEARCH PROTOCOL: Large-scale evidence generation and evaluation across a network of databases for type 2 diabetes mellitus 90%
- An overview of global monitoring systems for the side effects and adverse events associated with medicinal cannabis use: A scoping review using a systematic approach 90%
Similar papers in this journal
- Machine learning guided association of adverse drug reactions with in vitro target-based pharmacology 94%
- Randomised Controlled Trial of Intravenous Nafamostat Mesylate in COVID pneumonitis: Phase 1b/2a Experimental Study to Investigate Safety, Pharmacokinetics and Pharmacodynamics 91%
- A systematic review of interleukin-2-based immunotherapies in clinical trials for cancer and autoimmune diseases 90%
Similar papers in this journal
Similar papers in this journal
- Repurposing Therapeutics for COVID-19: Rapid Prediction of Commercially available drugs through Machine Learning and Docking 93%
- Protocol for a seamless phase 2A-phase 2B randomized double-blind placebo-controlled trial to evaluate the safety and efficacy of benfotiamine in patients with early Alzheimer’s disease (BenfoTeam) 92%
- Combining explainable machine learning, demographic and multi-omic data to identify precision medicine strategies for inflammatory bowel disease 92%
Similar papers in this journal
- A randomized sham-controlled trial of transcranial and intranasal photobiomodulation in Japanese patients with mild cognitive impairment and mild dementia due to Alzhimer’s disease: a protocol 90%
- A Phase II study to evaluate the safety and efficacy of prasinezumab in early Parkinson’s disease (PASADENA): rationale, design and baseline data 90%
- Safe Non-opioid and Non-barbiturate containing Acute Medication Combinations in Headache: An Exhaustive Approach Based on DrugBank Database 89%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.