Jul 2026· Turkish Journal of Engineering· 0 citations· 23 references
TL;DR
Atomica is presented, a web-based engineering-intelligence platform designed to integrate AI-driven molecular generation with reproducible cheminformatics validation and bioactivity-context retrieval in a single workflow that bridges algorithmic molecular generation and applied, collaboration-ready drug-discovery workflows.
Abstract
Drug discovery remains constrained by high development costs (often exceeding USD 2.6 billion per approved drug) and long timelines (typically 10-15 years), with substantial late-stage attrition. We present Atomica, a web-based engineering-intelligence platform designed to integrate AI-driven molecular generation with reproducible cheminformatics validation and bioactivity-context retrieval in a single workflow. Atomica uses a server-mediated architecture to orchestrate MolMIM-based generation, descriptor and rule-based filtering, and PubChem record enrichment while avoiding client-side credential exposure. Molecule quality is assessed using explicit quantitative criteria, including validity, uniqueness, novelty, QED, synthetic accessibility (SA), LogP, and constraint success rate under user-defined similarity thresholds. The platform operationalizes constrained generation as a sampling-and-ranking process in descriptor space rather than a physics-based simulation, and it reports accepted versus rejected candidates to address invalid-output risk transparently. A representative end-to-end case workflow demonstrates practical candidate prioritization from seed structure input through filtering and evidence enrichment. Atomica is implemented with a typed, modular service layer and documented reproducibility controls (versioned dependencies, defined benchmarking protocol, and repeatable evaluation settings). This work contributes an integrated and scientifically auditable framework that bridges algorithmic molecular generation and applied, collaboration-ready drug-discovery workflows.
Drug discovery is a time-consuming and resource-intensive process with a development period of more than ten years and a clinical attrition rate of more than 90%. Despite its contributions to rational drug design, computer-aided drug design has been constrained by limited scalability, overreliance on molecular descriptors, and incomplete modeling of complex biological systems. The emergence of artificial intelligence (AI) has transformed this landscape. AI-based drug discovery platforms have shifted the paradigm from a narrow focus to a comprehensive platform that covers target identification using graph-based drug-target interaction models. Additionally, deep-learning-based docking techniques, such as GNINA and AtomNet, de novo design approaches, such as REINVENT and RANC, and multi-task ADMET predictors, such as ADMETlab 2.0, are all parts of the AI-based drug discovery platform. In addition, AlphaFold has recently predicted more than 200 million protein structures, substantially expanding the pool of accessible drug targets. This review focuses on the AI-based approaches for target discovery, virtual screening, molecular generation, lead optimization, retro-synthesis, and structural modeling while also addressing issues of dataset bias, reproducibility, and real-world applicability. In this review, we discuss the emerging trends of AI-based drug discovery computational tools, which might change the face of medicinal chemistry. This review provides a balanced overview of AI-based drug discovery, including the limitations and challenges, to provide a framework to move this emerging field of science to a more robust, reproducible and clinically applicable platform.
Ryena Dhir, Pitam Ghosh, D. Sharma et al.· RSC Advances· 0 citations
A state-aware functional classifier (SAFC) is developed that integrates molecular dynamics derived receptor ensembles, ensemble docking and protein ligand interaction graphs that provides dynamics-aware functional activity rankings for generated molecules that were partly complementary to docking, drug-likeness and synthetic accessibility scores.
H. Kumar, Zheng-Xiao Yang, Yankai Yu et al.· bioRxiv· 0 citations
Artificial intelligence is revolutionizing drug discovery by accelerating target identification, molecular design, virtual screening, and toxicity prediction, while tackling longstanding challenges like high costs and lengthy timelines in traditional pipelines. This review explores recent AI innovations—such as AlphaFold for protein structure prediction, generative models for de novo drug design, and graph neural networks for drug repurposing—alongside real-world case studies from companies like Exscientia, Insilico Medicine, and BenevolentAI, which have produced clinical candidates like DSP-1181 and rentosertib. Despite these advances, key hurdles persist, including data quality issues, model interpretability, synthetic feasibility for complex molecules, and integration with experimental workflows, underscoring the need for explainable AI, better datasets, and ethical frameworks to bridge research gaps. Looking ahead, hybrid AI-experimental approaches and collaborations between pharma giants and AI startups promise to deliver safer, more personalized therapies faster.
P. Jadhav, R. Pingale, Kanchan Gajanan Gawai et al.· International journal for ad...· 0 citations
An operational, end-to-end workflow that explicitly connects computational predictions to medicinal chemistry decision points is provided, addressing a critical gap between computational prediction and clinical translation.
Antonio Lavecchia· Medicinal research reviews (...· 0 citations
Discovery of novel therapeutic small molecules remains one of the most challenging tasks in pharmaceutical research, as it is described by high attrition rates, well over $2 billion per candidate, and timelines often surpassing a decade. Generative AI has transformative potential to probe the enormous chemical space estimated at 1060 drug-like molecules, but current computational approaches are fragmented across multiple tools and require enterprise-grade hardware, thus creating a sort of "computational divide" that excludes many academic groups and smaller laboratories. We introduce in this study a unified end-to-end Generative AI Assistant, specifically designed for constrained hardware environments, optimized to run on widely available consumer-grade GPUs like the NVIDIA GTX 1650 with 4 GB VRAM. With our system, we integrated a lightweight LSTM-based generative model using SELFIES tokenization to ensure 100% syntactic validity, a multi-task XGBoost classifier for toxicity prediction across 12 biological assays, hybrid property prediction with molecular fingerprints, and an API-based module for 3D protein structure prediction via ESMFold. Using benchmark testing, we have established a robust performance level with a reliable convergence of our generative model in conjunction with an overall decrease in training loss from 2.15 to 1.19 and a stable validation loss of 1.43, as well as a weighted average AUC of 0.790 for our toxicity classifier. Toxic-class recall significantly increased after threshold tuning, improving the framework's appropriateness for early-stage safety screening applications. In addition, the analysis of chemical space validates the model's ability to generate previously unexplored novel molecules that possess desirable drug-like characteristics (mean LogP = 2.04) and to enhance safety, we are integrating both ML-based toxicity screening and a rule-based PAINS filtering into a novel hybrid prototype. As an additional contribution to overall accessibility, we also developed and tested a CPU fallback feature to allow for automatic fallback of the generative model in instances of hardware incompatibility. Together these contributions enable the efficient and cost-effective democratization of modern drug discovery workflows on affordable hardware (93% reduction in infrastructure costs) without sacrificing the scientific integrity or predictive capability of our developed models.
This review emphasizes the influence of new AI platforms like AlphaFold3, molecular interactions are structurally optimized (MISATO), and ZairaChem on the discovery of oncology drugs and examines how AI reconciles chemical design with pharmacological feasibility.
Mohsin Ali, Muhammad Ali Tajwar, Farid Ahmed et al.· Medicinal research reviews (...· 0 citations