By clicking “Accept All”, you agree to the storing of cookies on your device to enhance site navigation, analyze site usage, and assist in our marketing efforts. View our Privacy Policy for more information.
Oncology drug development today is an ideal environment for the application of Artificial Intelligence. Lantern is developing our unique platform, RADR®, to help in the process of developing, rescuing and revitalizing targeted compounds in the fight against cancer, and to personalize cancer treatments.
Oncology drug development today is an ideal environment for the application of A.I. Lantern is developing our unique platform, RADR®, to help in the process of developing, rescuing and revitalizing targeted compounds in the fight against cancer, and to personalize cancer treatments.
.png)
RADR®, or Response Algorithm for Drug Positioning & Rescue, is Lantern’s proprietary integrated data analytics, experimental biology, biotechnology, and machine-learning-based platform. RADR® is used primarily to predict the potential response patients will have to Lantern’s drugs and to other drugs that are being reviewed and analyzed by Lantern.
RADR® is also being used to help define and develop combination strategies among drugs in development and those that are approved for a range of oncology indications. RADR® uses transcriptome data, genomic data and drug sensitivity data from a wide range of curated sources that are continually being analyzed, monitored and updated. Our RADR® platform is core to our drug development approach for identifying the desired project candidates to in-license and develop.
Our RADR® platform is enabled through access to, and analysis of, a number of key datasets: (i) publicly available databases, (ii) data from commercial clinical studies and trials, and (iii) our proprietary data generated from ex vivo 3D tumor models specific to drug-tumor interactions. We incorporate automated supervised machine learning strategies along with big data analytics, statistics and systems biology to facilitate identification of new correlations of genetic biomarkers with drug activity.
The value of the platform architecture is derived from its validation through the analysis of over
100+ billion oncology-specific clinical and preclinical data points, more than 200+ advanced ML algorithms, and over 130,000+ patient records from 8,163+ datasets.
RADR® has now surpassed 100 billion data points, facilitating increased drug and cancer type-specific biomarker identification, the discovery of new indications, and the identification of additional drug candidates to build out our product pipeline towards advances in cancer therapy.
Our artificial intelligence-based machine learning approach combines six automated modules that work sequentially to derive drug and tumor-specific complex biomarker panels. These six modules include: Data Ingest, Data Processing and Curation, Feature Selection, Prediction, Hypothesis Generation, Validation & Feedback, and Patient Stratification & Clinical Trial Design.
Multi-omics data is received from large, public oncology data sources and private partner data sources. Lantern’s proprietary data is included here as well.
This step includes data cleaning, transformation, normalization, and integration without compromising the original quality of data – datasets are reviewed by internal KOLs to ascertain relevance and quality. Data is standardized across patient samples, and connections are made that link preclinical models to patient samples and clinical data.
RADR® -A.I. performs proprietary gene filtering via biological, statistical and machine learning-based methods to extract biologically relevant and statistically significant biomarkers and genomic features. Findings are benchmarked against published literature and data.
An automated artificial intelligence algorithm uses filtered gene sets to build, tune and test the algorithm in an iterative process that selects an optimal model having highest testing accuracy. This module will also generate 50-200 drug tumor-specific candidate biomarkers.
Data mining and Machine Learning pipelines lead to hypothesis generation, which guides additional preclinical research in the lab, which produces more data. This data can be used to validate hypotheses, which are then added back to the system, thus improving the accuracy of our predictions.
Our final, tuned model uses available patient data on candidate biomarkers to predict medical drug response and stratifies patients as responders, partial responders, or non-responders. Response prediction informs both companion diagnostic (CDx) development and clinical trial design for advancements in experimental medicine.
