Abstract
In line with recent advances in neural drug design and sensitivity prediction, we propose a novel architecture for interpretable prediction of anticancer compound sensitivity using a multimodal attention-based convolutional encoder. Our model is based on the three key pillars of drug sensitivity: compounds' structure in the form of a SMILES sequence, gene expression profiles of tumors, and prior knowledge on intracellular interactions from protein-protein interaction networks. We demonstrate that our multiscale convolutional attention-based encoder significantly outperforms a baseline model trained on Morgan fingerprints and a selection of encoders based on SMILES, as well as the previously reported state-of-the-art for multimodal drug sensitivity prediction (R2 = 0.86 and RMSE = 0.89). Moreover, the explainability of our approach is demonstrated by a thorough analysis of the attention weights. We show that the attended genes significantly enrich apoptotic processes and that the drug attention is strongly correlated with a standard chemical structure similarity index. Finally, we report a case study of two receptor tyrosine kinase (RTK) inhibitors acting on a leukemia cell line, showcasing the ability of the model to focus on informative genes and submolecular regions of the two compounds. The demonstrated generalizability and the interpretability of our model testify to its potential for in silico prediction of anticancer compound efficacy on unseen cancer cells, positioning it as a valid solution for the development of personalized therapies as well as for the evaluation of candidate compounds in de novo drug design.
Highlights
We presented an attention-based multimodal neural approach for explainable drug sensitivity prediction using a combination of (1) SMILES string encoding of drug compounds, (2) transcriptomics of cancer cells, and (3) intracellular interactions incorporated into a protein−protein interaction (PPI) network
In an extensive comparative study of SMILES sequence encoders, we Article demonstrated that using the raw SMILES string of drug compounds, we were able to surpass the predictive performance reached by a baseline model utilizing Morgan fingerprints
We showed that the attention-based SMILE encoder architectures, especially the newly proposed multiscale convolutional attentive (MCA), performed the best while producing results that were verifiably explainable
Summary
There is strong evidence that the response to anticancer therapy is highly dependent on the tumor genomic and transcriptomic makeup, resulting in heterogeneity in patient clinical response to anticancer drugs.[5] This varied clinical response has led to the promise of personalized (or precision) medicine in cancer, where molecular biomarkers, e.g., the expression of specific genes, obtained from a patient’s tumor profiling may be used to choose a personalized therapy These challenges highlight a need across both pharmaceutical and healthcare industries for multimodal quantitative methods that can jointly exploit disparate sources of knowledge with the goal of characterizing the link between the molecular structure of compounds, the genetic and epigenetic alterations of the biological samples, and drug response.[6] In this work, we present a multimodal approach that enables us to tackle the aforementioned challenges. Our contextual attention mechanism emerges as the key component of our proposed SMILES encoder, as it helps validate our findings by explaining the model’s inner working and reasoning process, many of which are in agreement with domainknowledge on biochemistry of cancer cells
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
