Lantern Pharma: transforming oncology drug development with AI
Lantern Pharma: transforming oncology drug development with AI
A clinical stage pharma at the intersection of Artificial Intelligence, Genomics and Machine Learning
Lantern Pharma
Lantern Pharma (@LanternPharma) is a clinical stage biopharmaceutical company using its proprietary RADR®, an AI and ML platform, to transform the cost and timeline of oncology drug discovery and development.
RADR® (or Response Algorithm for Drug Positioning & Rescue) is Lantern’s proprietary integrated data analytics, experimental biology, biotechnology and ML-based platform, used primarily to predict the potential response the patients will have to new drugs that the company is developing.
In particular, RADR uses transcriptome data, genomic data and drug sensitivity data from a wide range of curated sources that are continually being analysed, monitored and updated, for identifying the desired candidates to in-license and develop. These curated sources are:
publicly available databases,
data from commercial clinical studies and trials, and
Lantern’s proprietary data generated from ex vivo 3D tumour models specific to drug-tumour interactions.
Very briefly, by incorporating automated supervised ML strategies along with big data analytics, statistics and systems biology they facilitate identification of new correlations 🔮 of genetic biomarkers with drug activity.
For example, Lantern Pharma’s precision medicine approach, called the 5M.AI Biomarker Approach (RADR is a key component of 5M.AI), consists of five broad modules. In particular, at the first stage patient data from clinical trials are analysed. At the second stage, lab genomic analysis of patient samples and genetic models are performed. Then data analytics and ML algorithms predict ⚖ meaningful biomarkers and responders at the third stage. And finally, predictive biomarkers are identified (fourth stage), that would eventually allow to identify, at the last stage, subgroups of responders that express the specific predictive biomarkers for specific drug treatments (Lantern Pharma: precision medicine pioneers).
The value of the PADR platform architecture being used is derived from its validation through the analysis of over:
18+ billion oncology-specific clinical and preclinical data points,
more than 154 drug-tumour interactions, and
over 130,000 patient records from 17 databases, one of which is their internal database.
For now, RADR has surpassed 18 billion data points and during 2022 they expect to reach over 25 billion data points, and also grow the methods and algorithms powering the analysis and insights of their RADR platform.
In general, the PADR platform combines six automated modules that work sequentially to derive drug and biomarker panels. These modules are:
Data Ingest: During this step, multi-omics data received from large, public oncology data sources and private partner data sources, as well as Lantern’s proprietary data are analysed.
Data Processing and Curation: This step includes data cleaning, transformation, normalisation and integration without compromising the original quality of data. Data is standardised across patient samples, and connections are made that link preclinical models to patient samples and clinical data.
Feature Selection: During the third step, RADR performs proprietary gene filtering via biological, statistical and ML-based methods to extract biologically relevant and statistically significant biomarkers and genomic features. Findings are then benchmarked against published literature and data.
Prediction: An automated AI 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 tumour-specific candidate biomarkers.
Hypothesis Generation, Validation & Feedback: Data mining and ML 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.
Patient Stratification & Clinical Trial Design: Finally, tuned models use available patient data on candidate biomarkers to predict medical drug response and stratify patients as responders, partial responders, or non-responders. Response prediction informs both companion diagnostic development and clinical trial design for advancements in experimental medicine.
Lantern Pharma Oncology Pipeline
Lantern’s current portfolio 💻💊🔬💉📑 consists of four drug candidates and an ADC (Antibody-Drug Conjugate) program across 9 cancer indications. Let’s see now these four candidates:
LP-100
LP-100 (Irofulven) or 6-hydroxymethylacylfulvene exploits cancer cells’ deficiency in DNA repair mechanisms. LP-100 is a mono-functional covalent DNA binder that inhibits DNA synthesis and replication, affects cell cycle and induces apoptosis. (Lantern Pharma: precision medicine pioneers)
Right now, LP-100 (in combination with prednisolone a steroid medication used to treat certain types of allergies, inflammatory conditions, autoimmune disorders, and cancers) is being tested in a genomic-signature guided phase 2 clinical trial in Denmark for patients with metastatic castration resistant prostate cancer (mCRPC). Moreover, recent opportunities have also been identified for the potential use of LP-100 in cancers with DNA repair deficiencies, including potential to treat bladder and prostate cancer patients who have a mutation in the ERCC2/3 genes (DNA repair genes).
LP-300
LP-300 or Disodium 2,2’-dithio-bis-ethane sulfonate originally branded as Tavocept®, is a small molecule entity with cysteine modifying activity on selected proteins (i.e. ALK, Anaplastic lymphoma kinase), and additionally modulating protein function of different targets (EGFR, MET and ROS1) simultaneously. Is considered a potential first-in-class combination agent for NSCLC (Non-Small Cell Lung Cancer) since it has chemo-enhancing and nephro-protective effects.
Initially, a phase III clinical trial was conducted in which patients with advanced lung adenocarcinoma received LP-300 in combination with chemotherapy cisplatin, paclitaxel or docetaxel. And although the study did not meet endpoints in the overall patient population, retrospective analysis demonstrated that the addition of LP-300 significantly increased overall survival in a specific subset of never-smoker patients.
Accordingly, Lantern is now repositioning LP-300 (in combination with carboplatin and pemetrexed) as a potential combination therapy for never-smoking NSCLC patients with histologically defined adenocarcinoma.
Currently, there is no approved therapy specifically for the growing indication of never-smokers (or non-smokers) with NSCLC, and LP-300 with both chemo-protective and chemosensitising activity has the potential to increase overall survival and alleviate toxicities from primary chemotherapy in front line, second line or salvage therapy in newly diagnosed, relapsed, metastatic or advanced NSCLC.
LP-184
LP-184 (hydroxyureamethylacylfulvene) is a small molecule drug candidate and a “next generation” alkylating agent with an ability to cross the blood-brain barrier. It is highly potent and synthetically lethal in cancers harbouring defects in multiple DNA damage repair and recombination pathways.
In particular, LP-184 is selectively lethal in tumours over-expressing PTGR1 (Prostaglandin Reductase 1) and deficient in DNA damage repair pathways, both of which occur frequently in multiple tumour types.
As a matter of fact, LP-184 demonstrated a remarkable efficacy against a range of cell lines, both in vivo and ex vivo models, and also validated by in-silico predictions generated by RADR. Therefore, LP-184 will be developed for many targeted oncology indications such as: pancreatic, CNS Cancers - Glioblastoma, CNS Cancers - ATRT (aggressive form of cancer and is difficult to cure), Bladder and other Pediatric cancers.
Just this week, @LanternPharma presented positive preclinical data on the in vitro efficacy of LP-184 in brain metastases (#METS) at the @AACR meeting (#CancerResearch). Check out their abstract for more 🕵🏻 here: https://bit.ly/3O7PRyG
LP-284
LP-284 belongs to the new generation of acylfulvenes (a class of cytotoxic semi-synthetic derivatives of illudin, a natural product that can be extracted from the jack o'lantern mushroom 🍄 Omphalotus olearius), a family of naturally derived anti-cancer drug candidates, and is the stereoisomer (enantiomer) of their drug candidate LP-184.
In comparison to the two other acylfulvenes LP-100 and LP-184 studied by Lantern Pharma, LP-284 has distinct anti-tumour activities in a variety of hematological cancers including lymphoma, multiple myeloma and leukemia.
So far, in early preclinical studies LP-284 has shown nanomolar potency in several hematological cell lines and is also being explored for use as a combination therapy with spironolactone (potassium-sparing diuretic).
Collaborations
The company has for now the following world-class scientific 👬👫👭 collaborations:
With Fox Chase Cancer Center, focused on advancing the development of LP-184 in pancreatic cancer.
With Georgetown University, for advancing prostate cancer drug development of LP-184, a next-generation targeted DNA-damaging agent.
With Johns Hopkins, and they just announced positive preclinical data in glioblastoma (GBM) with drug candidate LP-184.
With National Cancer Institute to aid precision oncology research and treatments.
With Danish Cancer Society Research Center to support clinical development of drug candidates LP-100 and LP-184, in solid tumours
And with UT Health San Antonio to expand into additional pediatric cancers.
For more about the science behind Lantern ✍🏻👀👁 visit “The Science Behind Lantern Pharma”, a list of Lantern’s numerous publications and posters.
Lantern (NASDAQ: $LTRN) so far has raised 💰 about $97 million in the public markets and right now partners with academic institutions, companies and non-profits that have:
Large genomic cancer data sets 🗄
Novel cancer cell lines, organoid and PDX (patient-derived xenografts) models
Access to patient tumour samples, and
Innovative and big data approaches to solve complex problems 🔐🔒🔓
Finally, a word from Lantern’s CEO and President Panna Sharma (@therealpanna) :
"We are in the golden age of A.I. where we are able to significantly impact the speed and precision at which we develop new drugs".
Until next time,
