Explore the vast range of titles available.

The efficacy of aprotinin combinations with selected antiviral-drugs treatment of influenza virus and coronavirus (SARS-CoV-2) infection was studied in mice models of influenza pneumonia and COVID-19. The high efficacy of the combinations in reducing virus titer in lungs and body weight loss and in increasing the survival rate were demonstrated. This preclinical study can be considered a confirmatory step before introducing the combinations into clinical assessment.

Human coronaviruses (CoV) cause respiratory infections that range from mild to severe. CoVs are a large family of viruses with considerable genetic heterogeneity and a multitude of viral types, making preventing and treating these viruses difficult. Comprehensive treatments that inhibit CoV infections fulfill a pressing medical need and may be immensely valuable in managing emerging and endemic CoV infections. As the main protease (M pro ) is highly conserved across many CoVs, this protease has been identified as a route for broad CoV inhibition. We utilize the advanced generative chemistry platform Chemistry42 for de novo molecular design and obtained novel small-molecule, non-peptide-like inhibitors targeting the SARS-CoV-2 M pro . ISM3312 is identified as an irreversible, covalent M pro inhibitor from extensive virtual screening and structure-based optimization efforts. ISM3312 exhibits low off-target risk and outstanding antiviral activity against multiple human coronaviruses, including SARS-CoV-2, MERS-CoV, 229E, OC43, NL63, and HKU1 independent of P-glycoprotein (P-gp) inhibition. Furthermore, ISM3312 shows significant inhibitory effects against Nirmatrelvir-resistant M pro mutants, suggesting ISM3312 may contribute to reduced viral escape in these settings. Incorporating ISM3312 and Nirmatrelvir into antiviral strategy could improve preparedness and reinforce defenses against future coronavirus threats. A novel covalent inhibitor, ISM3312, targets the main protease of multiple human coronaviruses, including drug-resistant strains, and shows broad antiviral activity. It offers a promising therapeutic strategy against current and future coronavirus threats.

We have developed a deep generative model, generative tensorial reinforcement learning (GENTRL), for de novo small-molecule design. GENTRL optimizes synthetic feasibility, novelty, and biological activity. We used GENTRL to discover potent inhibitors of discoidin domain receptor 1 (DDR1), a kinase target implicated in fibrosis and other diseases, in 21 days. Four compounds were active in biochemical assays, and two were validated in cell-based assays. One lead candidate was tested and demonstrated favorable pharmacokinetics in mice. A machine learning model allows the identification of new small-molecule kinase inhibitors in days.

Human coronaviruses (CoV) cause respiratory infections that range from mild to severe. CoVs are a large family of viruses with considerable genetic heterogeneity and a multitude of viral types, making preventing and treating these viruses difficult. Comprehensive treatments that inhibit CoV infections fulfill a pressing medical need and may be immensely valuable in managing emerging and endemic CoV infections. As the main protease (M ) is highly conserved across many CoVs, this protease has been identified as a route for broad CoV inhibition. We utilize the advanced generative chemistry platform Chemistry42 for de novo molecular design and obtained novel small-molecule, non-peptide-like inhibitors targeting the SARS-CoV-2 M . ISM3312 is identified as an irreversible, covalent M inhibitor from extensive virtual screening and structure-based optimization efforts. ISM3312 exhibits low off-target risk and outstanding antiviral activity against multiple human coronaviruses, including SARS-CoV-2, MERS-CoV, 229E, OC43, NL63, and HKU1 independent of P-glycoprotein (P-gp) inhibition. Furthermore, ISM3312 shows significant inhibitory effects against Nirmatrelvir-resistant M mutants, suggesting ISM3312 may contribute to reduced viral escape in these settings. Incorporating ISM3312 and Nirmatrelvir into antiviral strategy could improve preparedness and reinforce defenses against future coronavirus threats.

Baloxavir marboxil (BXM) is approved for treating uncomplicated influenza. The active metabolite baloxavir acid (BXA) inhibits cap-dependent endonuclease activity of the influenza virus polymerase acidic protein (PA), which is necessary for viral transcription. Treatment-emergent E23G or E23K (E23G/K) PA substitutions have been implicated in reduced BXA susceptibility, but their effect on virus fitness and transmissibility, their synergism with other BXA resistance markers, and the mechanisms of resistance have been insufficiently studied. Accordingly, we generated point mutants of circulating seasonal influenza A(H1N1)pdm09 and A(H3N2) viruses carrying E23G/K substitutions. Both substitutions caused 2- to 13-fold increases in the BXA EC 50 . EC 50 s were higher with E23K than with E23G and increased dramatically (138- to 446-fold) when these substitutions were combined with PA I38T, the dominant BXA resistance marker. E23G/K-substituted viruses exhibited slightly impaired replication in MDCK and Calu-3 cells, which was more pronounced with E23K. In ferret transmission experiments, all viruses transmitted to direct-contact and airborne-transmission animals, with only E23K+I38T viruses failing to infect 100% of animals by airborne transmission. E23G/K genotypes were predominantly stable during transmission events and through five passages in vitro. Thermostable PA–BXA interactions were weakened by E23G/K substitutions and further weakened when combined with I38T. In silico modeling indicated this was caused by E23G/K altering the placement of functionally important Tyr24 in the endonuclease domain, potentially decreasing BXA binding but at some cost to the virus. These data implicate E23G/K, alone or combined with I38T, as important markers of reduced BXM susceptibility, and such mutants could emerge and/or transmit among humans.

The exploration and mapping of chemical space remain a central challenge in modern drug discovery. Traditional compound libraries and databases cover only a minute fraction of this space, limiting the discovery of novel, bioactive, and patentable chemotypes. Here, we present a unique dataset containing approximately 110 M molecular structures of potential NLRP3 inhibitors enabled by the LEGION ( Latent Enumeration, Generation, Integration, Optimization, and Navigation ) workflow, which integrates generative AI, AI-guided screening within the Chemistry42 platform and auxiliary cheminformatics tools to enable large-scale exploration of chemical space around specific drug targets. Using the structural data of NLRP3 co-crystals, a clinically relevant target, LEGION combined ligand- and structure-based design strategies, in-house algorithms for 3D pharmacophore-aware scaffold extraction, and distinct library enumeration methods to identify over 34,000 unique scaffolds, which can be multiplied into a dataset of 123B molecular structures within the provided code. The resulting dataset of unprecedented size proved effective for scaffold hopping, chemical space navigation, and supporting intellectual property applications by generating structurally diverse and synthetically accessible structures.

Recent progress has expanded the use of large language models (LLMs) in drug discovery, including synthesis planning. However, objective evaluation of retrosynthesis performance remains limited. Existing benchmarks and metrics typically rely on published synthetic procedures and Top-K accuracy based on single ground-truth, which does not capture the open-ended nature of real-world synthesis planning. We propose a new benchmarking framework for single-step retrosynthesis that evaluates both general-purpose and chemistry-specialized LLMs using ChemCensor, a novel metric for chemical plausibility. By emphasizing plausibility over exact match, this approach better aligns with human synthesis planning practices. We also introduce CREED, a novel dataset comprising millions of ChemCensor-validated reaction records for LLM training, and use it to train a model that improves over the LLM baselines under this benchmark.

General-purpose large language models (LLMs) that rely on in-context learning do not reliably deliver the scientific understanding and performance required for drug discovery tasks. Simply increasing model size or introducing reasoning tokens does not yield significant performance gains. To address this gap, we introduce the MMAI Gym for Science, a one-stop shop molecular data formats and modalities as well as task-specific reasoning, training, and benchmarking recipes designed to teach foundation models the 'language of molecules' in order to solve practical drug discovery problems. We use MMAI Gym to train an efficient Liquid Foundation Model (LFM) for these applications, demonstrating that smaller, purpose-trained foundation models can outperform substantially larger general-purpose or specialist models on molecular benchmarks. Across essential drug discovery tasks - including molecular optimization, ADMET property prediction, retrosynthesis, drug-target activity prediction, and functional group reasoning - the resulting model achieves near specialist-level performance and, in the majority of settings, surpasses larger models, while remaining more efficient and broadly applicable in the domain.

Chemistry42 is a software platform for de novo small molecule design that integrates Artificial Intelligence (AI) techniques with computational and medicinal chemistry methods. Chemistry42 is unique in its ability to generate novel molecular structures with predefined properties validated through in vitro and in vivo studies. Chemistry42 is a core component of Insilico Medicine Pharma.ai drug discovery suite that also includes target discovery and multi-omics data analysis (PandaOmics) and clinical trial outcomes predictions (InClinico).

Chemistry42 is a software platform for de novo small molecule design that integrates Artificial Intelligence (AI) techniques with computational and medicinal chemistry methods. Chemistry42 is unique in its ability to generate novel molecular structures with predefined properties validated through in vitro and in vivo studies. Chemistry42 is a core component of Insilico Medicine Pharma.ai drug discovery suite that also includes target discovery and multi-omics data analysis (PandaOmics) and clinical trial outcomes predictions (InClinico).