Target Identification and Prioritization: Blood Cancer

Blood cancers, which affect the blood, bone marrow and lymphatic system, pose unique treatment challenges compared to solid tumors.  Despite the availability of chemotherapy, delivering an adequate dosage to the tumor site through systematic administration proves challenging. This difficulty necessitates higher dosages to maintain therapeutic efficacy, inadvertently leading to patient side effects and the development of drug resistance, underscoring the critical need for improved targeted therapies. 

There are three main types of blood cancer: leukemia, multiple myeloma and lymphoma.¹ Collectively, these blood cancers accounted for around 185,000 cases and 58,000 deaths in the U.S. in 2022.² In this use case, we zero in on potential targets for Diffuse Large B Cell Lymphoma (DLBCL), the most prevalent Non-Hodgkin Lymphoma for which 30-40% patients are refractory or relapsing.³

By machine-reading the literature, Causaly uncovered over 6,000 targets for DLBCL, supported by over  27,000 documents. Interestingly, around 750 targets have been reported to be involved in DLBCL disease progression.  

For greater confidence in the viability of a target, the results can be narrowed down to those investigated in preclinical studies. This enabled the identification of approximately 400 targets involved in DLBCL progression.  

Further refinement of targets by relationship type allows the directionality of a target-disease relationship to be deduced. According to Causaly, more than 150 targets were shown to upregulate DLBCL progression. Less than half of these targets have been reported in primary data in the last 5 years.  

Causaly’s advanced filtering capabilities allow the prioritization of targets by novelty, the number of publications, and the strength of the evidence for the role of the target in disease pathophysiology: 

Blood cancer treatments are hampered by poor drug delivery, requiring high dosages leading to toxic side effects and drug resistance. There is a pressing need for improved therapeutics. By leveraging AI, drug discovery teams can expedite the identification and prioritization of credible targets, paving the way for the exploration of novel therapeutic avenues.