PaccMann: a web service for interpretable anticancer compound sensitivity prediction

Abstract

The identification of new targeted and personalized therapies for cancer requires the fast and accurate assessment of the drug efficacy of potential compounds against a particular biomolecular sample. It has been suggested that the integration of complementary sources of information might strengthen the accuracy of a drug efficacy prediction model. Here, we present a web-based platform for the Prediction of AntiCancer Compound sensitivity with Multimodal Attention-based Neural Networks (PaccMann). PaccMann is trained on public transcriptomic cell line profiles, compound structure information and drug sensitivity screenings, and outperforms state-of-the-art methods on anticancer drug sensitivity prediction. On the open-access web service (https://ibm.biz/paccmann-aas), users can select a known drug compound or design their own compound structure in an interactive editor, perform in-silico drug testing and investigate compound efficacy on publicly available or user-provided transcriptomic profiles. PaccMann leverages methods for model interpretability and outputs confidence scores as well as attention heatmaps that highlight the genes and chemical sub-structures that were more important to make a prediction, hence facilitating the understanding of the model’s decision making and the involved biochemical processes. We hope to serve the community with a toolbox for fast and efficient validation in drug repositioning or lead compound identification regimes.

Computational Investigation Identified Potential Chemical Scaffolds for Heparanase as Anticancer Therapeutics

“…Deep learning models have progressed recently to predict the inhibitory activity of the compounds. PaccMann (accessed on 12 May 2021, ) is one such web-based drug sensitivity platform designed to utilize multimodal attention-based neural networks [ 66 ]. Moreover, PaccMann is an effective validation toolbox used for drug repurposing approaches and has an R 2 value of 0.86 along with an RMSE (root mean square error) value of 0.89, highlighting the strong correlations between the resultant data generated by the server and the experimentally estimated values.…”

Designing Novel Compounds for the Treatment and Management of RET-Positive Non-Small Cell Lung Cancer—Fragment Based Drug Design Strategy

“…In the current investigation, the sensitivity of the compounds was evaluated using a multimodal neural network-based tool named ‘PaccMann’. This tool utilizes the key pillar information of the compounds such as SMILES sequence, prior information on the intracellular interactions, and gene expression profiles of tumors to predict the sensitivity of compounds against various cancer cell lines with high accuracy [ 36 ].…”

PaccMannRL: De novo generation of hit-like anticancer molecules from transcriptomic data via reinforcement learning

“…In the first stage, the models are trained independently; one VAE is trained on gene expression data (in the following called profile VAE or just PVAE) from TCGA , and another VAE (in the following called SMILES VAE or just SVAE) is trained on bioactive small molecules from ChEMBL (Bento et al, 2013) (see Figure 1C). As a critic, we use PaccMann, a multimodal drug sensitivity prediction model developed and validated in our previous work Cadow et al, 2020). In the second stage, the encoder of the profile VAE is combined with the decoder of the molecule VAE and exposed to a joint retraining that is optimized using a policy gradient regime with a reward coming from the critic module.…”