Machine learning interatomic potentials (MLIPs) promise quantum-level accuracy at classical force field speeds, but their performance hinges on the quality and diversity of training data. An efficient and fully automated approach to sample chemical reaction space without relying on human intuition, addressing a critical gap in MLIP development is presented. The method combines the speed of tight-binding calculations with selective high-level refinement, generating diverse datasets that capture both equilibrium and reactive regions of potential energy surfaces. By employing single-ended growing string and nudged elastic band methods, reaction pathways previously underrepresented in MLIP training sets, particularly near transition states are systematically explored. This approach yields datasets with rich structural and chemical diversity, essential for robust MLIP development. Open-source code is provided for the entire workflow, facilitating the integration of the approach into existing MLIP development pipelines.

Artificial intelligence (AI) is reshaping biomedical research by providing scalable computational frameworks suited to the complexity of biological systems. Central to this revolution are bio/chemical language models, including large language models, which are reconceptualizing molecular structures as a form of 'language' amenable to advanced computational techniques. Here we critically examine the role of these models in biology and chemistry, tracing their evolution from molecular representation to molecular generation and optimization. This review covers key molecular representation strategies for both biological macromolecules and small organic compounds-ranging from protein and nucleotide sequences to single-cell data, string-based chemical formats, graph-based encodings and three-dimensional point clouds-highlighting their respective advantages and inherent limitations in AI applications. The discussion further explores core model architectures, such as bidirectional encoder representations from transformers-like encoders, generative pretrained transformer-like decoders and encoder-decoder transformers, alongside their sophisticated pretraining strategies such as self-supervised learning, multitask learning and retrieval-augmented generation. Key biomedical applications, spanning protein structure and function prediction, de novo protein design, genomic analysis, molecular property prediction, de novo molecular design, reaction prediction and retrosynthesis, are explored through representative studies and emerging trends. Finally, the review considers the emerging landscape of agentic and interactive AI systems, showcasing briefly their potential to automate and accelerate scientific discovery while addressing critical technical, ethical and regulatory considerations that will shape the future trajectory of AI in biomedicine.

Transcription factors specifically bind to their consensus sequence motifs and regulate transcription efficiency. Transcription factors are also able to non-specifically contact the phosphate backbone of DNA through electrostatic interaction. The homeodomain of Meis1 TALE human transcription factor (Meis1-HD) recognizes its target DNA sequences via two DNA contact regions, the L1-α1 region and the α3 helix (specific binding mode). This study demonstrates that the non-specific binding mode of Meis1-HD is the energetically favored process during DNA binding, achieved by the interaction of the L1-α1 region with the phosphate backbone. An NMR dynamics study suggests that non-specific binding might set up an intermediate structure which can then rapidly and easily find the consensus region on a long section of genomic DNA in a facilitated binding process. Structural analysis using NMR and molecular dynamics shows that key structural distortions in the Meis1-HD-DNA complex are induced by various single nucleotide mutations in the consensus sequence, resulting in decreased DNA binding affinity. Collectively, our results elucidate the detailed molecular mechanism of how Meis1-HD recognizes single nucleotide mutations within its consensus sequence: (i) through the conformational features of the α3 helix; and (ii) by the dynamic features (rigid or flexible) of the L1 loop and the α3 helix. These findings enhance our understanding of how single nucleotide mutations in transcription factor consensus sequences lead to dysfunctional transcription and, ultimately, human disease.

MicroRNA-dependent mRNA decay plays an important role in gene silencing by facilitating posttranscriptional and translational repression. Inspired by this intrinsic nature of microRNA-mediated mRNA cleavage, here, we describe a microRNA-targeting mRNA as a switch platform called mRNA bridge mimetics to regulate the translocation of proteins. We applied the mRNA bridge mimetics platform to Cas9 protein to confer it the ability to translocate into the nucleus via cleavage of the nuclear export signal. This system performed programmed gene editing in vitro and in vivo. Combinatorial treatment with cisplatin and miR-21-EZH2 axis-targeting CRISPR Self Check-In improved sensitivity to chemotherapeutic drugs in vivo. Using the endogenous microRNA-mediated mRNA decay mechanism, our platform is able to remodel a cell's natural biology to allow the entry of precise drugs into the nucleus, devoid of non-specific translocation. The mRNA bridge mimetics strategy is promising for applications in which the reaction must be controlled via intracellular stimuli and modulates Cas9 proteins to ensure safe genome modification in diseased conditions.

Machine learning interatomic potentials (MLIPs) promise quantum-level accuracy at classical force field speeds, but their performance hinges on the quality and diversity of training data. An efficient and fully automated approach to sample chemical reaction space without relying on human intuition, addressing a critical gap in MLIP development is presented. The method combines the speed of tight-binding calculations with selective high-level refinement, generating diverse datasets that capture both equilibrium and reactive regions of potential energy surfaces. By employing single-ended growing string and nudged elastic band methods, reaction pathways previously underrepresented in MLIP training sets, particularly near transition states are systematically explored. This approach yields datasets with rich structural and chemical diversity, essential for robust MLIP development. Open-source code is provided for the entire workflow, facilitating the integration of the approach into existing MLIP development pipelines.

Artificial intelligence (AI) is reshaping biomedical research by providing scalable computational frameworks suited to the complexity of biological systems. Central to this revolution are bio/chemical language models, including large language models, which are reconceptualizing molecular structures as a form of 'language' amenable to advanced computational techniques. Here we critically examine the role of these models in biology and chemistry, tracing their evolution from molecular representation to molecular generation and optimization. This review covers key molecular representation strategies for both biological macromolecules and small organic compounds-ranging from protein and nucleotide sequences to single-cell data, string-based chemical formats, graph-based encodings and three-dimensional point clouds-highlighting their respective advantages and inherent limitations in AI applications. The discussion further explores core model architectures, such as bidirectional encoder representations from transformers-like encoders, generative pretrained transformer-like decoders and encoder-decoder transformers, alongside their sophisticated pretraining strategies such as self-supervised learning, multitask learning and retrieval-augmented generation. Key biomedical applications, spanning protein structure and function prediction, de novo protein design, genomic analysis, molecular property prediction, de novo molecular design, reaction prediction and retrosynthesis, are explored through representative studies and emerging trends. Finally, the review considers the emerging landscape of agentic and interactive AI systems, showcasing briefly their potential to automate and accelerate scientific discovery while addressing critical technical, ethical and regulatory considerations that will shape the future trajectory of AI in biomedicine.

Transcription factors specifically bind to their consensus sequence motifs and regulate transcription efficiency. Transcription factors are also able to non-specifically contact the phosphate backbone of DNA through electrostatic interaction. The homeodomain of Meis1 TALE human transcription factor (Meis1-HD) recognizes its target DNA sequences via two DNA contact regions, the L1-α1 region and the α3 helix (specific binding mode). This study demonstrates that the non-specific binding mode of Meis1-HD is the energetically favored process during DNA binding, achieved by the interaction of the L1-α1 region with the phosphate backbone. An NMR dynamics study suggests that non-specific binding might set up an intermediate structure which can then rapidly and easily find the consensus region on a long section of genomic DNA in a facilitated binding process. Structural analysis using NMR and molecular dynamics shows that key structural distortions in the Meis1-HD-DNA complex are induced by various single nucleotide mutations in the consensus sequence, resulting in decreased DNA binding affinity. Collectively, our results elucidate the detailed molecular mechanism of how Meis1-HD recognizes single nucleotide mutations within its consensus sequence: (i) through the conformational features of the α3 helix; and (ii) by the dynamic features (rigid or flexible) of the L1 loop and the α3 helix. These findings enhance our understanding of how single nucleotide mutations in transcription factor consensus sequences lead to dysfunctional transcription and, ultimately, human disease.

MicroRNA-dependent mRNA decay plays an important role in gene silencing by facilitating posttranscriptional and translational repression. Inspired by this intrinsic nature of microRNA-mediated mRNA cleavage, here, we describe a microRNA-targeting mRNA as a switch platform called mRNA bridge mimetics to regulate the translocation of proteins. We applied the mRNA bridge mimetics platform to Cas9 protein to confer it the ability to translocate into the nucleus via cleavage of the nuclear export signal. This system performed programmed gene editing in vitro and in vivo. Combinatorial treatment with cisplatin and miR-21-EZH2 axis-targeting CRISPR Self Check-In improved sensitivity to chemotherapeutic drugs in vivo. Using the endogenous microRNA-mediated mRNA decay mechanism, our platform is able to remodel a cell's natural biology to allow the entry of precise drugs into the nucleus, devoid of non-specific translocation. The mRNA bridge mimetics strategy is promising for applications in which the reaction must be controlled via intracellular stimuli and modulates Cas9 proteins to ensure safe genome modification in diseased conditions.

Designing efficient synthetic routes for a target molecule remains a major challenge in organic synthesis. Atom environments are ideal, stand-alone, chemically meaningful building blocks providing a high-resolution molecular representation. Our approach mimics chemical reasoning, and predicts reactant candidates by learning the changes of atom environments associated with the chemical reaction. Through careful inspection of reactant candidates, we demonstrate atom environments as promising descriptors for studying reaction route prediction and discovery. Here, we present a new single-step retrosynthesis prediction method, viz. RetroTRAE, being free from all SMILES-based translation issues, yields a top-1 accuracy of 58.3% on the USPTO test dataset, and top-1 accuracy reaches to 61.6% with the inclusion of highly similar analogs, outperforming other state-of-the-art neural machine translation-based methods. Our methodology introduces a novel scheme for fragmental and topological descriptors to be used as natural inputs for retrosynthetic prediction tasks.

Predicting immunoglobulin-antigen (Ig-Ag) binding remains a significant challenge due to the paucity of experimentally-resolved complexes and the limited accuracy of de novo Ig structure prediction. We introduce IgPose, a generalizable framework for Ig-Ag pose identification and scoring, built on a generative data-augmentation pipeline. To mitigate data scarcity, we constructed the Structural Immunoglobulin Decoy Database (SIDD), a comprehensive repository of high-fidelity synthetic decoys. IgPose integrates equivariant graph neural networks, ESM-2 embeddings, and gated recurrent units to synergistically capture both geometric and evolutionary features. We implemented interface-focused k-hop sampling with biologically guided pooling to enhance generalization across diverse interfaces. The framework comprises two sub-networks--IgPoseClassifier for binding pose discrimination and IgPoseScore for DockQ score estimation--and achieves robust performance on curated internal test sets and the CASP-16 benchmark compared to physics and deep learning baselines. IgPose serves as a versatile computational tool for high-throughput antibody discovery pipelines by providing accurate pose filtering and ranking. IgPose is available on GitHub (https://github.com/arontier/igpose).

MOTIVATION: Predicting immunoglobulin-antigen (Ig-Ag) binding remains a significant challenge due to the paucity of experimentally resolved complexes and the limited accuracy of de novo Ig structure prediction. RESULTS: We introduce IgPose, a generalizable framework for Ig-Ag pose identification and scoring, built on a generative data-augmentation pipeline. To mitigate data scarcity, we constructed the Structural Immunoglobulin Decoy Database (SIDD), a comprehensive repository of high-fidelity synthetic decoys. IgPose integrates equivariant graph neural networks, ESM-2 embeddings, and gated recurrent units to synergistically capture both geometric and evolutionary features. We implemented interface-focused k-hop sampling with biologically guided pooling to enhance generalization across diverse interfaces. The framework comprises two sub-networks-IgPoseClassifier for binding pose discrimination and IgPoseScore for DockQ score estimation-and achieves robust performance on curated internal test sets and the CASP-16 benchmark compared to physics and deep learning baselines. IgPose serves as a versatile computational tool for high-throughput antibody discovery pipelines by providing accurate pose filtering and ranking. AVAILABILITY AND IMPLEMENTATION: IgPose is available on GitHub (https://github.com/arontier/igpose).

Virtual screening is a critical step in computer-aided drug discovery. As synthetic databases and reaction schemes expand, the number of synthesizable compounds grows, making efficient screening essential. The success of ultra-large-scale virtual screening hinges on two factors: accuracy in binding affinity prediction and speed. We previously developed AK-Score2 for accurate protein-ligand binding prediction and V-Dock for estimating docking scores. Here, we present Docking of Millions (DoM), an ultra-large-scale virtual screening system integrating both methods. Iterative learning of V-Dock to approximate AK-Score2-based affinities accelerates screening by eliminating the need to dock all compounds, saving time and resources. In benchmarking, screening 5 million compounds against DDR1, c-kit, ASK1, NSD1, CREBBP, and PDE5, DoM consumed only 319 h on average, 12% of full library screening time. Also, it achieved an average retrieval rate of 89% in the top 100 compounds. Inhibition assays identified that 1 out of 27 and 4 out of 31 molecules suppressed ASK1 and DDR1 activity by more than 50% at 10 μM. Further validation of selected compounds identified that the lowest IC50 values are 1.96 μM and 788 nM for ASK1 and DDR1, respectively. These findings demonstrate DoM as a practical and efficient platform for real-world drug discovery.

(CACHE) challenged computational teams to identify chemically novel ligands targeting the macrodomain 1 of SARS-CoV-2 Nsp3, a promising coronavirus drug target. Twenty-three groups deployed diverse design strategies to collectively select 1739 ligand candidates. While over 85% of the designed molecules were chemically novel, the best experimentally confirmed hits were structurally similar to previously published compounds. Confirming a trend observed in CACHE #1 and #2, two of the best-performing workflows used compounds selected by physics-based computational screening methods to train machine learning models able to rapidly screen large chemical libraries, while four others used exclusively physics-based approaches. Three pharmacophore searches and one fragment growing strategy were also part of the seven winning workflows. While active molecules discovered by CACHE #3 participants largely mimicked the adenine ring of the endogenous substrate, ADP-ribose, preserving the canonical chemotype commonly observed in previously reported Nsp3-Mac1 ligands, they still provide novel structure-activity relationship insights that may inform the development of future antivirals. Collectively, these results show that multiple molecular design strategies can efficiently converge on similar potent molecules.