Using Artificial Intelligence to Uncover Novel Therapeutic Targets in Hematology/Oncology

Abstract ID 100128 Poster Board 250 Hematology/Oncology models: We developed 42 machine learning models using Knowledge Graphs (KGML), informed by data from Pharos (1), based on major resources like DepMap (2), Reactome (3), and STRING (4). Focused on 41 blood cancers, we utilized cancer-specific positive genes and 440 shared negative genes, using metapath and XGBoost (5). Analysis of the top 500 genes from each model revealed 3,842 genes strongly linked to cancers, with 519 classified as "Tchem," i.e., small molecule modulators are known (6). We focused on Tchem proteins given the notion that small molecules perturbing these proteins are already known, which accelerates drug discovery. "Druggable" targets: Four separate, 1SVM (one-class support vector machine) and XGBoost KGML models were built using mode-of-action drug targets (6) (also called Tclin; N = 704) as input. This 42nd model evaluates the likelihood that a gene shares the characteristics of Tclin targets ("druggable") using aggregated probabilities across the 4 models. Main Findings: Of the 519 Tchem genes, 132 have "Tclin-like" probability above 50%. The top five "druggable targets" are GAPDH, AKT1, HRAS, TLR4 and TP53, respectively; their role in cancer is well studied. Our focus then shifted to genes that have no known cancer associations, as evaluated by the DISEASES platform (7) - see Table 1. Two G-protein coupled receptor genes, LPAR5 and ADORA3, appear to be uniquely associated with primary bone diffuse large B cell lymphoma, and with acute leukaemic transformation of myeloproliferative neoplasm, respectively. PLD1 (an enzyme) is associated with B cell prolymphocytic leukemia. Additional studies are required to elucidate their role in these malignancies. Our work illustrates how machine learning can be used to uncover overlooked, but potentially promising drug targets for leukemias, lymphomas and myelomas. References 1. Kelleher KJ, Sheils TK, Mathias SL, Yang JJ, Metzger VT, Siramshetty VB, et al. Nucleic Acids Res. 2023; 51:D1405–16. 2. Tsherniak A, Vazquez F, Montgomery PG, Weir BA, Kryukov G, Cowley GS, et al. Cell. 2017; 170:564–76.e16. 3. Gillespie M, Jassal B, Stephan R, Milacic M, Rothfels K, Senff-Ribeiro A, et al. Nucleic Acids Res. 2022; 50:D687–92. 4. Szklarczyk D, Kirsch R, Koutrouli M, Nastou K, Mehryary F, Hachilif R, et al. Nucleic Acids Res. 2023; 51:D638–46. 5. Binder J, Ursu O, Bologa C, Jiang S, Maphis N, Dadras S, et al. Commun Biol. 2022; 5:125. 6. Oprea TI, Bologa CG, Brunak S, Campbell A, Gan GN, Gaulton A, et al. Nat Rev Drug Discov. 2018; 17:317–32. 7. Grissa D, Junge A, Oprea TI, Jensen LJ. Database. 2022; 2022:baac019.