Lantern Pharma has signed a research collaboration with Bielefeld University for the development of novel antibody-drug conjugates (ADCs) with high therapeutic and anti-tumor potential.
The partners will be using Lantern’s proprietary Response Algorithm for Drug Positioning and Rescue (RADR®) artificial intelligence (AI) and machine learning (ML) platform , to rapidly develop novel cryptophycin-antibody drug conjugates (ADCs), which represent an exciting class of potent and highly targeted drug candidates.[1][2][3]
The platform technology was developed to integrate data from pre-clinical and clinical data sources, like CellMinerCDB, [4] the Cancer Genome Atlas (TCGA) (TCGA), [5] the Catalogue of Somatic Mutations in Cancer (COSMIC), [6] Gene Omnibus (GEO),[7][8] patient data, and publications to generate insights for preclinical and clinical research.
The collaboration will leverage insights from Lantern’s recently developed RADR® AI ADC module in combination with research from Professor Norbert Sewald, Ph.D., the principal investigator for Bielefeld and leader of Magicbullet::reloaded, a European consortium focused on developing novel drug delivery mechanisms, including ADCs.
Sewald is Professor of Organic and Bioorganic Chemistry at Bielefeld University in Bielefeld, Germany. His research group’s focus includes the development of antibody-drug and peptide-drug conjugates, the isolation and total synthesis of natural products, the chemical modification of bioactive peptides, and the biocatalytic halogenation of amino acids, peptides, and proteins.
RADR®
“RADR® is an integral component for de-risking and powering the progression of Lantern’s drug programs, and our recent advances in moving from program identification through preclinical development have occurred at speeds rarely seen in oncology drug discovery and development,” said Panna Sharma, Lantern’s Chief Executive Officer and President.
The rapidly growing global ADC market is currently valued at over $4.0 billion and is projected to reach $14.0 billion by 2027. There are currently 12 ADCs that have been approved by the US Food and Drug Administration (FDA) for the treatment of cancer and approximately 37 ADCs in current late-stage oncology trials.
“Globally, the expansion of RADR®’s ADC capabilities will not only build on its demonstrated ability to identify synergistic and effective combinations of antibodies and small molecules, but will also facilitate new high-value ADC-focused business development opportunities and collaborations,” Sharma continued.
The advancement of RADR®‘s product development roadmap will be accelerated using RADR®‘s library of over 200+ advanced algorithms and automated ML pipelines. According to experts, this AI strategy will enable the large-scale analysis of thousands of high-performing model features through their SHapley Additive exPlanation (SHAP) scores and can efficiently identify key genes and pathways that are mechanistically important to drug resistance, quality of patient outcomes, and improved delivery of ADC drug payloads. These features can add potential value to ADC programs and prioritize ADC targets. Additionally, this powerful strategy can be leveraged to inform downstream ADC design by identifying ADC components that, when used together, have a high probability of synergy that can lead to therapeutic response.
De-risking ADC drug candidates
This AI-guided strategy has the potential to de-risk the ADC drug development process, while simultaneously enhancing the creation of effective and targeted ADCs.
Lantern’s RADR® platform excels at automated, large-scale, biological, and response network analysis, yielding correlations that can be leveraged in both target identification and drug response prediction.
The biology-driven AI drug development approach, which leverages over 25 billion oncology focused data points across thousands of data sets, can be used in augmentation with existing structural and bond analysis methodologies to further de-risk ADC drug candidates. This AI-driven approach using RADR® is expected to deliver an improved understanding of potential clinical indications and patient stratification approaches for ADC development.
Paving the way
Outcomes from the collaboration are expected to pave the way for next-generation ADCs and other drug conjugates that are designed using AI and that can be developed with potentially higher efficacy, at a faster pace, and with significantly reduced costs.
The initial aim of the collaboration will be to synthesize and evaluate novel ADCs linked to cryptophycins, which are promising anti-tumor molecules, in part because of their potency at ultra-low, picomolar, concentrations. The cryptophycin-ADCs will be tested across multiple cancer cell lines and initial results are expected during 2023.
”We have ample experience in structure-activity relationships of cryptophycins as well in the synthesis of ADCs and small molecule-drug conjugates (SMDCs). Teaming up with top researchers from European academia and industry in the consortium of Magicbullet::reloaded further reinforced this capacity. We now look forward to the collaboration with Lantern,” Sewald said.
“Cryptophycins are an exciting family of highly potent heterocyclic peptides from Cyanobacteria that have demonstrated antitumor potency and can inhibit tumor growth by strongly interfering with microtubule stability and assembly,” stated Kishor Bhatia, Ph.D., Lantern’s Chief Scientific Officer.
“Sewald and his group are experts in the synthesis of cryptophycin derivatives and have established extensive groundwork to support the targeted ADC delivery of cryptophycins. By leveraging our RADR® platform’s AI ADC development module and partnering with Dr. Sewald, we expect to be able to select and advance cryptophycin-ADCs towards the clinic with better targeting and therapeutic efficacy for patients with advanced cancers with limited therapeutic options,” continued Dr. Bhatia.
Ongoing development
After the initial aims of the collaboration are completed, Lantern plans to leverage its AI ADC development module, which is fully integrated into RADR®, to launch multiple ADCs that can leverage cryptophycins or other promising payloads. Lantern also expects to use the AI ADC development module with other collaborators, both academic and commercial, to develop promising ADC candidates for launch into targeted clinical trials.
Under the terms of the collaboration, Sewald and his team will synthesize, optimize, and provide initial testing of the cryptophycin-ADCs. Lantern is also receiving an exclusive and worldwide option to license intellectual property (IP) from Bielefeld University related to the collaboration and IP generated from the collaboration.
Reference
[1] McDermott J, Sturtevant D, Kathad U, Varma S, Zhou J, Kulkarni A, Biyani N, et al. Artificial intelligence platform, RADR®, aids in the discovery of DNA damaging agent for the ultra-rare cancer Atypical Teratoid Rhabdoid Tumors. Front. Drug Discov., 11 October 2022; Volume 2 – 2022 | DOI 10.3389/fddsv.2022.1033395
[2] Verma VA, Pillow TH, DePalatis L, Li G, Phillips GL, Polson AG, Raab HE, Spencer S, Zheng B. The cryptophycins as potent payloads for antibody drug conjugates. Bioorg Med Chem Lett. 2015 Feb 15;25(4):864-8. doi: 10.1016/j.bmcl.2014.12.070. Epub 2015 Jan 2. PMID: 25613677.
[3] Lai Q, Wu M, Wang R, Lai W, Tao Y, Lu Y, Wang Y, Yu L, Zhang R, Peng Y, Jiang X, Fu Y, Wang X, Zhang Z, Guo C, Liao W, Zhang Y, Kang T, Chen H, Yao Y, Gou L, Yang J. Cryptophycin-55/52 based antibody-drug conjugates: Synthesis, efficacy, and mode of action studies. Eur J Med Chem. 2020 Aug 1;199:112364. doi: 10.1016/j.ejmech.2020.112364. Epub 2020 Apr 30. PMID: 32402935.
[4] Rajapakse VN, Luna A, Yamade M, Loman L, Varma S, Sunshine M, Iorio F, Sousa FG, Elloumi F, Aladjem MI, Thomas A, Sander C, Kohn KW, Benes CH, Garnett M, Reinhold WC, Pommier Y. CellMinerCDB for Integrative Cross-Database Genomics and Pharmacogenomics Analyses of Cancer Cell Lines. iScience. 2018 Dec 21;10:247-264. doi: 10.1016/j.isci.2018.11.029. Epub 2018 Dec 12. PMID: 30553813; PMCID: PMC6302245.
[5] Tomczak K, Czerwińska P, Wiznerowicz M. The Cancer Genome Atlas (TCGA): an immeasurable source of knowledge. Contemp Oncol (Pozn). 2015;19(1A):A68-77. doi: 10.5114/wo.2014.47136. PMID: 25691825; PMCID: PMC4322527.
[6] Tate JG, Bamford S, Jubb HC, Sondka Z, Beare DM, Bindal N, Boutselakis H, Cole CG, Creatore C, Dawson E, Fish P, Harsha B, Hathaway C, Jupe SC, Kok CY, Noble K, Ponting L, Ramshaw CC, Rye CE, Speedy HE, Stefancsik R, Thompson SL, Wang S, Ward S, Campbell PJ, Forbes SA. COSMIC: the Catalogue Of Somatic Mutations In Cancer. Nucleic Acids Res. 2019 Jan 8;47(D1):D941-D947. doi: 10.1093/nar/gky1015. PMID: 30371878; PMCID: PMC6323903.
[7] Edgar R, Domrachev M, Lash AE. Gene Expression Omnibus: NCBI gene expression and hybridization array data repository. Nucleic Acids Res. 2002 Jan 1;30(1):207-10. doi: 10.1093/nar/30.1.207. PMID: 11752295; PMCID: PMC99122.
[8] Barrett T, Wilhite SE, Ledoux P, Evangelista C, Kim IF, Tomashevsky M, Marshall KA, Phillippy KH, Sherman PM, Holko M, Yefanov A, Lee H, Zhang N, Robertson CL, Serova N, Davis S, Soboleva A. NCBI GEO: archive for functional genomics data sets–update. Nucleic Acids Res. 2013 Jan;41(Database issue):D991-5. doi: 10.1093/nar/gks1193. Epub 2012 Nov 27. PMID: 23193258; PMCID: PMC3531084.
Featured image: Licensed under the Unsplash+ License
