GENERA: A Combined Genetic/Deep-Learning Algorithm for Multiobjective Target-Oriented De Novo Design

PMODiff: Physics-Informed Multi-Objective Optimization Diffusion Model for Protein-Specific 3D Molecule Generation

3D generative models have shown great potential in structure-based drug design for generating ligands tailored to specific protein binding pockets. However, existing methods primarily emphasize ligand-target geometric interactions and binding affinity prediction, often overlooking intrinsic physicochemical principles driving protein-ligand interactions as well as critical pharmaceutical properties, such as drug-likeness and synthetic accessibility. To address these limitations, PMODiff (Physics-Informed Multi-Objective Optimization Diffusion Model) integrates a physics-informed component into the denoising phase, minimizing protein-ligand interaction energy modeled by a simplified Lennard-Jones potential, thus generating conformations aligned with essential physicochemical constraints. In addition, pretrained networks guide the sampling process toward ligands exhibiting high affinity, favorable drug-likeness, and synthetic accessibility, thus addressing multiobjective optimization challenges in practical drug development. Experimental results on the CrossDocked2020 data set indicate that PMODiff generates more realistic 3D structures with higher binding affinity, achieving an average Vina Score of -7.44. This performance represents a 13% improvement over existing methods, highlighting the potential of PMODiff for more comprehensive drug design.

Transformer Decoder Learns from a Pretrained Protein Language Model to Generate Ligands with High Affinity

The drug discovery process can be significantly accelerated by using deep learning methods to suggest molecules with druglike features and, more importantly, that are good candidates to bind specific proteins of interest. We present a novel deep learning generative model, Prot2Drug, that learns to generate ligands binding specific targets leveraging (i) the information carried by a pretrained protein language model and (ii) the ability of transformers to capitalize the knowledge gathered from thousands of protein-ligand interactions. The embedding unveils the receipt to follow for designing molecules binding a given protein, and Prot2Drug translates such instructions by using the syntax of the molecular language generating novel compounds which are predicted to have favorable physicochemical properties and high affinity toward specific targets. Moreover, Prot2Drug reproduced numerous known interactions between compounds and proteins used for generating them and suggested novel protein targets for known compounds, indicating potential drug repurposing strategies. Remarkably, Prot2Drug facilitates the design of promising ligands even for protein targets with limited or no information about their ligands or 3D structure.

Navigating a 1E+60 Chemical Space of Peptide/Peptoid Oligomers

Herein we report a virtual library of 1E+60 members, a common estimate for the total size of the drug-like chemical space. The library is obtained from 100 commercially available peptide and peptoid building blocks assembled into linear or cyclic oligomers of up to 30 units, forming molecules within the size range of peptide drugs and potentially accessible by solid-phase synthesis. We demonstrate ligand-based virtual screening (LBVS) using the peptide design genetic algorithm (PDGA), which evolves a population of 50 members to resemble a given target molecule using molecular fingerprint similarity as fitness function. Target molecules are reached in less than 10,000 generations. Like in many journeys, the value of the chemical space journey using PDGA lies not in reaching the target but in the journey itself, here by encountering non-obvious analogs. We also show that PDGA can be used to generate median molecules and analogs of non-peptide target molecules.

Progress in the application of artificial intelligence in molecular generation models based on protein structure

The molecular generation models based on protein structures represent a cutting-edge research direction in artificial intelligence-assisted drug discovery. This article aims to comprehensively summarize the research methods and developments by analyzing a series of novel molecular generation models predicated on protein structures. Initially, we categorize the molecular generation models based on protein structures and highlight the architectural frameworks utilized in these models. Subsequently, we detail the design and implementation of protein structure-based molecular generation models by introducing different specific examples. Lastly, we outline the current opportunities and challenges encountered in this field, intending to offer guidance and a referential framework for developing and studying new models in related fields in the future.

Mothra: Multiobjective de novo Molecular Generation Using Monte Carlo Tree Search

In the field of drug discovery, identifying compounds that satisfy multiple criteria, such as target protein affinity, pharmacokinetics, and membrane permeability, is challenging because of the vast chemical space. Until now, multiobjective optimization via generative models has often involved linear combinations of different reward functions. Linear combinations solve multiobjective optimization problems by turning multiobjective optimization into a single-objective task and causing problems with weighting for each objective. Herein, we propose a scalable multiobjective molecular generative model developed using deep learning techniques. This model integrates the capabilities of recurrent neural networks for molecular generation and Pareto multiobjective Monte Carlo tree search to determine the optimal search direction. Through this integration, our model can generate compounds using enhanced evaluation functions that include important aspects like target protein affinity, drug similarity, and toxicity. The proposed model addresses the limitations of previous linear combination methods, and its effectiveness is demonstrated via extensive experimentation. The improvements achieved in the evaluation metrics underscore the potential utility of our approach toward drug discovery applications. In addition, we provide the source code for our model such that researchers can easily access and use our framework in their own investigations. The source code and pretrained model for Mothra, developed in this study, along with the Docker image for the Pareto front explorer and compound picker, designed to streamline the selection and visualization of optimal chemical compounds, are released under the GNU General Public License v3.0 and available at https://github.com/sekijima-lab/Mothra.

Augmenting genetic algorithms with machine learning for inverse molecular design

Evolutionary and machine learning methods have been successfully applied to the generation of molecules and materials exhibiting desired properties. The combination of these two paradigms in inverse design tasks can yield powerful methods that explore massive chemical spaces more efficiently, improving the quality of the generated compounds. However, such synergistic approaches are still an incipient area of research and appear underexplored in the literature. This perspective covers different ways of incorporating machine learning approaches into evolutionary learning frameworks, with the overall goal of increasing the optimization efficiency of genetic algorithms. In particular, machine learning surrogate models for faster fitness function evaluation, discriminator models to control population diversity on-the-fly, machine learning based crossover operations, and evolution in latent space are discussed. The further potential of these synergistic approaches in generative tasks is also assessed, outlining promising directions for future developments.

Enabling target-aware molecule generation to follow multi objectives with Pareto MCTS

Target-aware drug discovery has greatly accelerated the drug discovery process to design small-molecule ligands with high binding affinity to disease-related protein targets. Conditioned on targeted proteins, previous works utilize various kinds of deep generative models and have shown great potential in generating molecules with strong protein-ligand binding interactions. However, beyond binding affinity, effective drug molecules must manifest other essential properties such as high drug-likeness, which are not explicitly addressed by current target-aware generative methods. In this article, aiming to bridge the gap of multi-objective target-aware molecule generation in the field of deep learning-based drug discovery, we propose ParetoDrug, a Pareto Monte Carlo Tree Search (MCTS) generation algorithm. ParetoDrug searches molecules on the Pareto Front in chemical space using MCTS to enable synchronous optimization of multiple properties. Specifically, ParetoDrug utilizes pretrained atom-by-atom autoregressive generative models for the exploration guidance to desired molecules during MCTS searching. Besides, when selecting the next atom symbol, a scheme named ParetoPUCT is proposed to balance exploration and exploitation. Benchmark experiments and case studies demonstrate that ParetoDrug is highly effective in traversing the large and complex chemical space to discover novel compounds with satisfactory binding affinities and drug-like properties for various multi-objective target-aware drug discovery tasks.

Evolutionary Multiobjective Molecule Optimization in an Implicit Chemical Space

Optimization techniques play a pivotal role in advancing drug development, serving as the foundation of numerous generative methods tailored to efficiently design optimized molecules derived from existing lead compounds. However, existing methods often encounter difficulties in generating diverse, novel, and high-property molecules that simultaneously optimize multiple drug properties. To overcome this bottleneck, we propose a multiobjective molecule optimization framework (MOMO). MOMO employs a specially designed Pareto-based multiproperty evaluation strategy at the molecular sequence level to guide the evolutionary search in an implicit chemical space. A comparative analysis of MOMO with five state-of-the-art methods across two benchmark multiproperty molecule optimization tasks reveals that MOMO markedly outperforms them in terms of diversity, novelty, and optimized properties. The practical applicability of MOMO in drug discovery has also been validated on four challenging tasks in the real-world discovery problem. These results suggest that MOMO can provide a useful tool to facilitate molecule optimization problems with multiple properties.

Unleashing the power of generative AI in drug discovery

Artificial intelligence (AI) is revolutionizing drug discovery by enhancing precision, reducing timelines and costs, and enabling AI-driven computer-aided drug design. This review focuses on recent advancements in deep generative models (DGMs) for de novo drug design, exploring diverse algorithms and their profound impact. It critically analyses the challenges that are intricately interwoven into these technologies, proposing strategies to unlock their full potential. It features case studies of both successes and failures in advancing drugs to clinical trials with AI assistance. Last, it outlines a forward-looking plan for optimizing DGMs in de novo drug design, thereby fostering faster and more cost-effective drug development.

DeLA-DrugSelf: Empowering multi-objective de novo design through SELFIES molecular representation

In this paper, we introduce DeLA-DrugSelf, an upgraded version of DeLA-Drug [J. Chem. Inf. Model. 62 (2022) 1411-1424], which incorporates essential advancements for automated multi-objective de novo design. Unlike its predecessor, which relies on SMILES notation for molecular representation, DeLA-DrugSelf employs a novel and robust molecular representation string named SELFIES (SELF-referencing Embedded String). The generation process in DeLA-DrugSelf not only involves substitutions to the initial string representing the starting query molecule but also incorporates insertions and deletions. This enhancement makes DeLA-DrugSelf significantly more adept at executing data-driven scaffold decoration and lead optimization strategies. Remarkably, DeLA-DrugSelf explicitly addresses the SELFIES-related collapse issue, considering only collapse-free compounds during generation. These compounds undergo a rigorous quality metrics evaluation, highlighting substantial advancements in terms of drug-likeness, uniqueness, and novelty compared to the molecules generated by the previous version of the algorithm. To evaluate the potential of DeLA-DrugSelf as a mutational operator within a genetic algorithm framework for multi-objective optimization, we employed a fitness function based on Pareto dominance. Our objectives focused on target-oriented properties aimed at optimizing known cannabinoid receptor 2 (CB2R) ligands. The results obtained indicate that DeLA-DrugSelf, available as a user-friendly web platform (https://www.ba.ic.cnr.it/softwareic/delaself/), can effectively contribute to the data-driven optimization of starting bioactive molecules based on user-defined parameters.

CONSMI: Contrastive Learning in the Simplified Molecular Input Line Entry System Helps Generate Better Molecules

In recent years, the application of deep learning in molecular de novo design has gained significant attention. One successful approach involves using SMILES representations of molecules and treating the generation task as a text generation problem, yielding promising results. However, the generation of more effective and novel molecules remains a key research area. Due to the fact that a molecule can have multiple SMILES representations, it is not sufficient to consider only one of them for molecular generation. To make up for this deficiency, and also motivated by the advancements in contrastive learning in natural language processing, we propose a contrastive learning framework called CONSMI to learn more comprehensive SMILES representations. This framework leverages different SMILES representations of the same molecule as positive examples and other SMILES representations as negative examples for contrastive learning. The experimental results of generation tasks demonstrate that CONSMI significantly enhances the novelty of generated molecules while maintaining a high validity. Moreover, the generated molecules have similar chemical properties compared to the original dataset. Additionally, we find that CONSMI can achieve favorable results in classifier tasks, such as the compound-protein interaction task.

On the difficulty of validating molecular generative models realistically: a case study on public and proprietary data

While a multitude of deep generative models have recently emerged there exists no best practice for their practically relevant validation. On the one hand, novel de novo-generated molecules cannot be refuted by retrospective validation (so that this type of validation is biased); but on the other hand prospective validation is expensive and then often biased by the human selection process. In this case study, we frame retrospective validation as the ability to mimic human drug design, by answering the following question: Can a generative model trained on early-stage project compounds generate middle/late-stage compounds de novo? To this end, we used experimental data that contains the elapsed time of a synthetic expansion following hit identification from five public (where the time series was pre-processed to better reflect realistic synthetic expansions) and six in-house project datasets, and used REINVENT as a widely adopted RNN-based generative model. After splitting the dataset and training REINVENT on early-stage compounds, we found that rediscovery of middle/late-stage compounds was much higher in public projects (at 1.60%, 0.64%, and 0.21% of the top 100, 500, and 5000 scored generated compounds) than in in-house projects (where the values were 0.00%, 0.03%, and 0.04%, respectively). Similarly, average single nearest neighbour similarity between early- and middle/late-stage compounds in public projects was higher between active compounds than inactive compounds; however, for in-house projects the converse was true, which makes rediscovery (if so desired) more difficult. We hence show that the generative model recovers very few middle/late-stage compounds from real-world drug discovery projects, highlighting the fundamental difference between purely algorithmic design and drug discovery as a real-world process. Evaluating de novo compound design approaches appears, based on the current study, difficult or even impossible to do retrospectively.Scientific Contribution This contribution hence illustrates aspects of evaluating the performance of generative models in a real-world setting which have not been extensively described previously and which hopefully contribute to their further future development.