Abstract LB066: Machine learning algorithm for drug discovery targeting new co-transcription factors of HIF1A

Abstract

Abstract Hypoxia-inducible factor 1 alpha (HIF1A) activation drives cellular adaption to low oxygen stress in malignant and non-malignant cells. HIF1A transcriptionally regulates many genes in key processes like angiogenesis and metastasis, facilitating the cell’s survival. Interestingly, HIF1A is able to carry out its regulatory functions by forming protein-protein interactions with its co-transcription factors. Since low oxygen conditions are frequently present in cancerous cells, we predict that these co-transcription factors could serve as new cancer therapeutic targets. Our recent work has thus focused on identifying motifs in HIF1A ChIP-Seq sequences and discovering novel HIF1A co-transcription factors. In this study, we leveraged cutting-edge deep learning methods, including a hybrid convolutional neural network (CNN) and recurrent neural network (RNN) based motif-discovery model, and discovered several novel motifs. We also look to predict potential therapeutic drugs against the identified co-transcription factors using a machine-learning drug discovery model that evaluates therapies based on their half-maximal inhibitory concentration (IC50). We have so far found several small molecules that could adequately modulate the activity of the identified co-transcription factors. Our results could lead to new therapeutic approaches against HIF1A-dependent cancers such as colon, breast, gastric, lung, brain, and prostate. Citation Format: Yuxiang Zhang, Saidi Wang, Haiyan Hu, Xiaoman Li. Machine learning algorithm for drug discovery targeting new co-transcription factors of HIF1A [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 2 (Clinical Trials and Late-Breaking Research); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(8_Suppl):Abstract nr LB066.