Dataset Information

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

ABSTRACT: Summary With the advent of deep generative models in computational chemistry, in-silico drug design is undergoing an unprecedented transformation. Although deep learning approaches have shown potential in generating compounds with desired chemical properties, they disregard the cellular environment of target diseases. Bridging systems biology and drug design, we present a reinforcement learning method for de novo molecular design from gene expression profiles. We construct a hybrid Variational Autoencoder that tailors molecules to target-specific transcriptomic profiles, using an anticancer drug sensitivity prediction model (PaccMann) as reward function. Without incorporating information about anticancer drugs, the molecule generation is biased toward compounds with high predicted efficacy against cell lines or cancer types. The generation can be further refined by subsidiary constraints such as toxicity. Our cancer-type-specific candidate drugs are similar to cancer drugs in drug-likeness, synthesizability, and solubility and frequently exhibit the highest structural similarity to compounds with known efficacy against these cancer types. Graphical abstract Highlights • A conditional generative model for de novo design of anticancer hit molecules is devised• Drug sensitivity and toxicity models steer the molecule design via reinforcement learning• Molecules are designed to target individual transcriptomic profiles of cell lines• Targeted, hit-like molecules are generated more frequently, even for unseen cell lines• In silico, the molecules exhibit similar physicochemical properties to real cancer drugs Complex System Biology; Systems Biology; Transcriptomics; Computer Science

SUBMITTER: Born J

PROVIDER: S-EPMC8022157 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:A plethora of AI-based techniques now exists to conduct de novo molecule generation that can devise molecules conditioned towards a particular endpoint in the context of drug design. One popular approach is using reinforcement learning to update a recurrent neural network or language-based de novo molecule generator. However, reinforcement learning can be inefficient, sometimes requiring up to 105 molecules to be sampled to optimize more complex objectives, which poses a limitation when using computationally expensive scoring functions like docking or computer-aided synthesis planning models. In this work, we propose a reinforcement learning strategy called Augmented Hill-Climb based on a simple, hypothesis-driven hybrid between REINVENT and Hill-Climb that improves sample-efficiency by addressing the limitations of both currently used strategies. We compare its ability to optimize several docking tasks with REINVENT and benchmark this strategy against other commonly used reinforcement learning strategies including REINFORCE, REINVENT (version 1 and 2), Hill-Climb and best agent reminder. We find that optimization ability is improved ~ 1.5-fold and sample-efficiency is improved ~ 45-fold compared to REINVENT while still delivering appealing chemistry as output. Diversity filters were used, and their parameters were tuned to overcome observed failure modes that take advantage of certain diversity filter configurations. We find that Augmented Hill-Climb outperforms the other reinforcement learning strategies used on six tasks, especially in the early stages of training or for more difficult objectives. Lastly, we show improved performance not only on recurrent neural networks but also on a reinforcement learning stabilized transformer architecture. Overall, we show that Augmented Hill-Climb improves sample-efficiency for language-based de novo molecule generation conditioning via reinforcement learning, compared to the current state-of-the-art. This makes more computationally expensive scoring functions, such as docking, more accessible on a relevant timescale.

Project description:In polypharmacology drugs are required to bind to multiple specific targets, for example to enhance efficacy or to reduce resistance formation. Although deep learning has achieved a breakthrough in de novo design in drug discovery, most of its applications only focus on a single drug target to generate drug-like active molecules. However, in reality drug molecules often interact with more than one target which can have desired (polypharmacology) or undesired (toxicity) effects. In a previous study we proposed a new method named DrugEx that integrates an exploration strategy into RNN-based reinforcement learning to improve the diversity of the generated molecules. Here, we extended our DrugEx algorithm with multi-objective optimization to generate drug-like molecules towards multiple targets or one specific target while avoiding off-targets (the two adenosine receptors, A1AR and A2AAR, and the potassium ion channel hERG in this study). In our model, we applied an RNN as the agent and machine learning predictors as the environment. Both the agent and the environment were pre-trained in advance and then interplayed under a reinforcement learning framework. The concept of evolutionary algorithms was merged into our method such that crossover and mutation operations were implemented by the same deep learning model as the agent. During the training loop, the agent generates a batch of SMILES-based molecules. Subsequently scores for all objectives provided by the environment are used to construct Pareto ranks of the generated molecules. For this ranking a non-dominated sorting algorithm and a Tanimoto-based crowding distance algorithm using chemical fingerprints are applied. Here, we adopted GPU acceleration to speed up the process of Pareto optimization. The final reward of each molecule is calculated based on the Pareto ranking with the ranking selection algorithm. The agent is trained under the guidance of the reward to make sure it can generate desired molecules after convergence of the training process. All in all we demonstrate generation of compounds with a diverse predicted selectivity profile towards multiple targets, offering the potential of high efficacy and low toxicity.

Project description:BackgroundDynamic transcriptional regulation is critical for an organism's response to environmental signals and yet remains elusive to capture. Such transcriptional regulation is mediated by master transcription factors (TF) that control large gene regulatory networks. Recently, we described a dynamic mode of TF regulation named "hit-and-run". This model proposes that master TF can interact transiently with a set of targets, but the transcription of these transient targets continues after the TF dissociation from the target promoter. However, experimental evidence validating active transcription of the transient TF-targets is still lacking.ResultsHere, we show that active transcription continues after transient TF-target interactions by tracking de novo synthesis of RNAs made in response to TF nuclear import. To do this, we introduced an affinity-labeled 4-thiouracil (4tU) nucleobase to specifically isolate newly synthesized transcripts following conditional TF nuclear import. Thus, we extended the TARGET system (Transient Assay Reporting Genome-wide Effects of Transcription factors) to include 4tU-labeling and named this new technology TARGET-tU. Our proof-of-principle example is the master TF Basic Leucine Zipper 1 (bZIP1), a central integrator of metabolic signaling in plants. Using TARGET-tU, we captured newly synthesized mRNAs made in response to bZIP1 nuclear import at a time when bZIP1 is no longer detectably bound to its target. Thus, the analysis of de novo transcripomics demonstrates that bZIP1 may act as a catalyst TF to initiate a transcriptional complex ("hit"), after which active transcription by RNA polymerase continues without the TF being bound to the gene promoter ("run").ConclusionOur findings provide experimental proof for active transcription of transient TF-targets supporting a "hit-and-run" mode of action. This dynamic regulatory model allows a master TF to catalytically propagate rapid and broad transcriptional responses to changes in environment. Thus, the functional read-out of de novo transcripts produced by transient TF-target interactions allowed us to capture new models for genome-wide transcriptional control.

Dataset Information

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets