CovalentInDB 2.0: an updated comprehensive database for structure-based and ligand-based covalent inhibitor design and screening.

The rational design of targeted covalent inhibitors (TCIs) has emerged as a powerful strategy in drug discovery, known for its ability to achieve strong binding affinity and prolonged target engagement. However, the development of covalent drugs is often challenged by the need to optimize both covalent warhead and non-covalent interactions, alongside the limitations of existing compound libraries. To address these challenges, we present CovalentInDB 2.0, an updated online database designed to support covalent drug discovery. This updated version includes 8303 inhibitors and 368 targets, supplemented by 3445 newly added cocrystal structures, providing detailed analyses of non-covalent interactions. Furthermore, we have employed an AI-based model to profile the ligandability of 144 864 cysteines across the human proteome. CovalentInDB 2.0 also features the largest covalent virtual screening library with 2 030 192 commercially available compounds and a natural product library with 105 901 molecules, crucial for covalent drug screening and discovery. To enhance the utility of these compounds, we performed structural similarity analysis and drug-likeness predictions. Additionally, a new user data upload feature enables efficient data contribution and continuous updates. CovalentInDB 2.0 is freely accessible at http://cadd.zju.edu.cn/cidb/.

Discovery of Potent Covalent CRM1 Inhibitors Via a Customized Structure-Based Virtual Screening Pipeline and Bioassays.

CRM1 (chromosomal region maintenance 1, also referred to as exportin 1 or XPO1) plays a crucial role in maintaining the appropriate nuclear levels of tumor suppressor proteins (TSPs), growth regulatory proteins (GRPs), and antiapoptotic proteins, thereby contributing significantly to their anticancer effects. Dysregulation of CRM1-mediated nuclear transport, observed in a range of cancers such as colon cancer as well as autoimmune diseases, highlights its significance in various disease processes. In this paper, we employed a customized structure-based virtual screening campaign to search for novel covalent CRM1 inhibitors and purchased 50 potentially active compounds for in vitro bioassays. Among these candidates, AN-988 displayed a notably higher binding affinity (KD = 615 nM) toward CRM1, as determined by the biolayer interferometry (BLI) assay. Furthermore, AN-988 exhibited a strong suppression of colorectal cancer cell proliferation and remarkable anti-inflammatory effects. Notably, AN-988 induced cell apoptosis and cell cycle arrest in a time- and dose-dependent manner by effectively inhibiting the translocation of FOXO3a from the nucleus to the cytosol, thereby preserving the activity of FOXO3a. Collectively, our study identified AN-988 as a promising CRM1 inhibitor, underscoring its potential as a preclinical colon cancer therapy candidate.

Characterizing the Cooperative Effect of PROTAC Systems with End-Point Binding Free Energy Calculation.

Proteolytic targeting chimeras (PROTACs), as an emerging type of drug, function by proximity-based modalities that narrow the distance between a target protein and the E3 ubiquitin ligase to facilitate the ubiquitination labeling of the target protein for degradation. Although it is evidenced that the cooperativity of the PROTAC ternary interaction is one of the key factors affecting the degradation rate of a target protein, PROTAC design utilizing this indicator is still challenging because of the complicated/flexible interactions in a target-PROTAC-E3 ternary system. Therefore, developing reliable and practicable computational methods is of great interest for PROTAC design. Hence, in this study, we investigate the feasibility of using the end-point binding free energy calculation method, represented by molecular mechanics/Poisson-Boltzmann (generalized-Born) surface area (MM/PB(GB)SA), for characterizing cooperativity (including the stabilization and hook effects) of the PROTAC systems. The result shows that MM/GBSA is a good predictor in characterizing these effects under a relatively long molecular dynamics adjustment (50-100 ns) and low dielectric constant (εin = 1), with the Pearson correlation coefficient (rp) > 0.5 and 0.6 for the stabilization and hook effect, respectively. This study provides a feasible strategy for characterizing the cooperativity of the PROTAC systems, facilitating the rational design of PROTAC molecules.

In-depth theoretical modeling to explore the mechanism of TPX-0131 overcoming lorlatinib resistance to ALKL1196M/G1202R mutation.

A number of anaplastic lymphoma kinase (ALK) inhibitors have been clinically approved, with lorlatinib, particularly as a third-generation drug, demonstrating efficacy against various drug-resistant ALK single mutations. However, continued clinical use of lorlatinib has led to the emergence of ALK double mutations conferring resistance to lorlatinib, notably ALKL1196M/G1202R. TPX-0131 is a potential fourth-generation ALK inhibitor currently under development. TPX-0131 demonstrates a broader spectrum of activity against ALK-resistant mutations, efficiently inhibiting 26 single-point mutations and various double/triple mutations, including solvent front mutations and gatekeeper mutations. In this study, for the first time, a comprehensive elucidation of the molecular mechanisms by which TPX-0131 overcomes lorlatinib resistance to ALKL1196M/G1202R through modeling, MD simulations, free energy calculations, and US simulations. The results indicate that the interactions between lorlatinib and key residues at the hinge region are disturbed by L1196M/G1202R double mutation, leading to the disruption of important hydrogen bonding between Glu1197 and lorlatinib. For TPX-0131, the L1196M/G1202R mutation enhances electrostatic and van der Waals interactions, causing significant conformational changes primarily in the hinge region, G-loop, and ß-strands. The tight binding of TPX-0131 to residues Arg1202, Met1199 and Arg1120 contribute significantly to overcoming lorlatinib resistance in ALKL1196M/G1202R mutant. These research results are expected to offer insights into the mechanism of TPX-0131 in treating ALKG1202R/L1196M-induced NSCLC resistance and optimizing of ALK inhibitors.

Discovery of Thiadiazoleamide Derivatives as Potent, Selective, and Orally Available Antagonists Disrupting Androgen Receptor Homodimer.

Androgen receptor (AR) is an important therapeutic target for prostate cancer (PCa) treatment, but prolonged use of AR antagonists has led to variant drug-resistant mutations. Since all marketed AR antagonists target the ligand binding pocket (LBP) of AR, to mitigate cross-resistance, a new drug pocket named Dimer Interface Pocket was discovered and a novel AR antagonist M17-B15 was identified. M17-B15 showed strong in vitro efficacy against PCa but had poor pharmacokinetic properties in vivo. In this study, through rational design and structure-activity relationship exploration, a series of thiadiazoleamide derivatives represented by N29 (IC50 = 0.018 µM) were identified with dominant AR antagonistic activity and remarkable anti-PCa activity in vitro. Furthermore, N29 effectively inhibited a series of typical drug-resistant AR mutants. The improved oral bioavailability of N29 facilitated its efficacy via oral administration, significantly inhibiting LNCaP xenograft tumor in vivo, presenting a promising therapeutic application for PCa.

PROTAC-DB 3.0: an updated database of PROTACs with extended pharmacokinetic parameters.

Proteolysis-targeting chimera (PROTAC) is an emerging therapeutic technology that leverages the ubiquitin-proteasome system to target protein degradation. Due to its event-driven mechanistic characteristics, PROTAC has the potential to regulate traditionally non-druggable targets. Recently, AI-aided drug design has accelerated the development of PROTAC drugs. However, the rational design of PROTACs remains a considerable challenge. Here, we present an updated online database, PROTAC-DB 3.0. In this third version, we have expanded the database to include 6111 PROTACs (87% increase compared to the 2.0 version). Additionally, the database now contains 569 warheads (small molecules targeting the protein), 2753 linkers, and 107 E3 ligands (small molecules recruiting E3 ligases). The number of target-PROTAC-E3 ternary complex structures has also increased to 959. Recognizing the importance of druggability in PROTAC design, we have incorporated pharmacokinetic data to PROTAC-DB 3.0. To enhance user experience, we have added features for sorting based on molecular similarity and literature publication date. PROTAC-DB 3.0 is accessible at http://cadd.zju.edu.cn/protacdb/.

Unlocking comprehensive molecular design across all scenarios with large language model and unordered chemical language.

Molecular generation stands at the forefront of AI-driven technologies, playing a crucial role in accelerating the development of small molecule drugs. The intricate nature of practical drug discovery necessitates the development of a versatile molecular generation framework that can tackle diverse drug design challenges. However, existing methodologies often struggle to encompass all aspects of small molecule drug design, particularly those rooted in language models, especially in tasks like linker design, due to the autoregressive nature of large language model-based approaches. To empower a language model for a wider range of molecular design tasks, we introduce an unordered simplified molecular-input line-entry system based on fragments (FU-SMILES). Building upon this foundation, we propose FragGPT, a universal fragment-based molecular generation model. Initially pretrained on extensive molecular datasets, FragGPT utilizes FU-SMILES to facilitate efficient generation across various practical applications, such as de novo molecule design, linker design, R-group exploration, scaffold hopping, and side chain optimization. Furthermore, we integrate conditional generation and reinforcement learning (RL) methodologies to ensure that the generated molecules possess multiple desired biological and physicochemical properties. Experimental results across diverse scenarios validate FragGPT's superiority in generating molecules with enhanced properties and novel structures, outperforming existing state-of-the-art models. Moreover, its robust drug design capability is further corroborated through real-world drug design cases.

RLpMIEC: High-Affinity Peptide Generation Targeting Major Histocompatibility Complex-I Guided and Interpreted by Interaction Spectrum-Navigated Reinforcement Learning.

Major histocompatibility complex (MHC) plays a vital role in presenting epitopes (short peptides from pathogenic proteins) to T-cell receptors (TCRs) to trigger the subsequent immune responses. Vaccine design targeting MHC generally aims to find epitopes with a high binding affinity for MHC presentation. Nevertheless, to find novel epitopes usually requires high-throughput screening of bulk peptide database, which is time-consuming, labor-intensive, more unaffordable, and very expensive. Excitingly, the past several years have witnessed the great success of artificial intelligence (AI) in various fields, such as natural language processing (NLP, e.g., GPT-4), protein structure prediction and engineering (e.g., AlphaFold2), and so on. Therefore, herein, we propose a deep reinforcement-learning (RL)-based generative algorithm, RLpMIEC, to quantitatively design peptide targeting MHC-I systems. Specifically, RLpMIEC combines the energetic spectrum (namely, the molecular interaction energy component, MIEC) based on the peptide-MHC interaction and the sequence information to generate peptides with strong binding affinity and precise MIEC spectra to accelerate the discovery of candidate peptide vaccines. RLpMIEC performs well in all the generative capability evaluations and can generate peptides with strong binding affinities and precise MIECs and, moreover, with high interpretability, demonstrating its powerful capability in participation for accelerating peptide-based vaccine development.

Multi-modal deep learning enables efficient and accurate annotation of enzymatic active sites.

Annotating active sites in enzymes is crucial for advancing multiple fields including drug discovery, disease research, enzyme engineering, and synthetic biology. Despite the development of numerous automated annotation algorithms, a significant trade-off between speed and accuracy limits their large-scale practical applications. We introduce EasIFA, an enzyme active site annotation algorithm that fuses latent enzyme representations from the Protein Language Model and 3D structural encoder, and then aligns protein-level information with the knowledge of enzymatic reactions using a multi-modal cross-attention framework. EasIFA outperforms BLASTp with a 10-fold speed increase and improved recall, precision, f1 score, and MCC by 7.57%, 13.08%, 9.68%, and 0.1012, respectively. It also surpasses empirical-rule-based algorithm and other state-of-the-art deep learning annotation method based on PSSM features, achieving a speed increase ranging from 650 to 1400 times while enhancing annotation quality. This makes EasIFA a suitable replacement for conventional tools in both industrial and academic settings. EasIFA can also effectively transfer knowledge gained from coarsely annotated enzyme databases to smaller, high-precision datasets, highlighting its ability to model sparse and high-quality databases. Additionally, EasIFA shows potential as a catalytic site monitoring tool for designing enzymes with desired functions beyond their natural distribution.

Highly Accurate and Efficient Deep Learning Paradigm for Full-Atom Protein Loop Modeling with KarmaLoop.

Protein loop modeling is a challenging yet highly nontrivial task in protein structure prediction. Despite recent progress, existing methods including knowledge-based, ab initio, hybrid, and deep learning (DL) methods fall substantially short of either atomic accuracy or computational efficiency. To overcome these limitations, we present KarmaLoop, a novel paradigm that distinguishes itself as the first DL method centered on full-atom (encompassing both backbone and side-chain heavy atoms) protein loop modeling. Our results demonstrate that KarmaLoop considerably outperforms conventional and DL-based methods of loop modeling in terms of both accuracy and efficiency, with the average RMSDs of 1.77 and 1.95 Å for the CASP13+14 and CASP15 benchmark datasets, respectively, and manifests at least 2 orders of magnitude speedup in general compared with other methods. Consequently, our comprehensive evaluations indicate that KarmaLoop provides a state-of-the-art DL solution for protein loop modeling, with the potential to hasten the advancement of protein engineering, antibody-antigen recognition, and drug design.

Large Language Model-Based Natural Language Encoding Could Be All You Need for Drug Biomedical Association Prediction.

Analyzing drug-related interactions in the field of biomedicine has been a critical aspect of drug discovery and development. While various artificial intelligence (AI)-based tools have been proposed to analyze drug biomedical associations (DBAs), their feature encoding did not adequately account for crucial biomedical functions and semantic concepts, thereby still hindering their progress. Since the advent of ChatGPT by OpenAI in 2022, large language models (LLMs) have demonstrated rapid growth and significant success across various applications. Herein, LEDAP was introduced, which uniquely leveraged LLM-based biotext feature encoding for predicting drug-disease associations, drug-drug interactions, and drug-side effect associations. Benefiting from the large-scale knowledgebase pre-training, LLMs had great potential in drug development analysis owing to their holistic understanding of natural language and human topics. LEDAP illustrated its notable competitiveness in comparison with other popular DBA analysis tools. Specifically, even in simple conjunction with classical machine learning methods, LLM-based feature representations consistently enabled satisfactory performance across diverse DBA tasks like binary classification, multiclass classification, and regression. Our findings underpinned the considerable potential of LLMs in drug development research, indicating a catalyst for further progress in related fields.

Design and synthesis of 7-membered lactam fused hydroxypyridinones as potent metal binding pharmacophores (MBPs) for inhibiting influenza virus PAN endonuclease.

Since influenza virus RNA polymerase subunit PAN is a dinuclear Mn2+ dependent endonuclease, metal-binding pharmacophores (MBPs) with Mn2+ coordination has been elucidated as a promising strategy to develop PAN inhibitors for influenza treatment. However, few attentions have been paid to the relationship between the optimal arrangement of the donor atoms in MBPs and anti-influenza A virus (IAV) efficacy. Given that, the privileged hydroxypyridinones fusing a seven-membered lactam ring with diverse side chains, chiral centers or cyclic systems were designed and synthesized. A structure-activity relationship study resulted in a hit compound 16l (IC50 = 2.868 ± 0.063 µM against IAV polymerase), the seven-membered lactam ring of which was fused a pyrrolidine ring. Further optimization of the hydrophobic binding groups on 16l afforded a lead compound (R, S)-16s, which exhibited a 64-fold more potent inhibitory activity (IC50 = 0.045 ± 0.002 µM) toward IAV polymerase. Moreover, (R, S)-16s demonstrated a potent anti-IAV efficacy (EC50 = 0.134 ± 0.093 µM) and weak cytotoxicity (CC50 = 15.35 µM), indicating the high selectivity of (R, S)-16s. Although the lead compound (R, S)-16s exhibited a little weaker activity than baloxavir, these findings illustrated the utility of a metal coordination-based strategy in generating novel MBPs with potent anti-influenza activity.

Retrosynthesis prediction with an iterative string editing model.

Retrosynthesis is a crucial task in drug discovery and organic synthesis, where artificial intelligence (AI) is increasingly employed to expedite the process. However, existing approaches employ token-by-token decoding methods to translate target molecule strings into corresponding precursors, exhibiting unsatisfactory performance and limited diversity. As chemical reactions typically induce local molecular changes, reactants and products often overlap significantly. Inspired by this fact, we propose reframing single-step retrosynthesis prediction as a molecular string editing task, iteratively refining target molecule strings to generate precursor compounds. Our proposed approach involves a fragment-based generative editing model that uses explicit sequence editing operations. Additionally, we design an inference module with reposition sampling and sequence augmentation to enhance both prediction accuracy and diversity. Extensive experiments demonstrate that our model generates high-quality and diverse results, achieving superior performance with a promising top-1 accuracy of 60.8% on the standard benchmark dataset USPTO-50 K.

AttABseq: an attention-based deep learning prediction method for antigen-antibody binding affinity changes based on protein sequences.

The optimization of therapeutic antibodies through traditional techniques, such as candidate screening via hybridoma or phage display, is resource-intensive and time-consuming. In recent years, computational and artificial intelligence-based methods have been actively developed to accelerate and improve the development of therapeutic antibodies. In this study, we developed an end-to-end sequence-based deep learning model, termed AttABseq, for the predictions of the antigen-antibody binding affinity changes connected with antibody mutations. AttABseq is a highly efficient and generic attention-based model by utilizing diverse antigen-antibody complex sequences as the input to predict the binding affinity changes of residue mutations. The assessment on the three benchmark datasets illustrates that AttABseq is 120% more accurate than other sequence-based models in terms of the Pearson correlation coefficient between the predicted and experimental binding affinity changes. Moreover, AttABseq also either outperforms or competes favorably with the structure-based approaches. Furthermore, AttABseq consistently demonstrates robust predictive capabilities across a diverse array of conditions, underscoring its remarkable capacity for generalization across a wide spectrum of antigen-antibody complexes. It imposes no constraints on the quantity of altered residues, rendering it particularly applicable in scenarios where crystallographic structures remain unavailable. The attention-based interpretability analysis indicates that the causal effects of point mutations on antibody-antigen binding affinity changes can be visualized at the residue level, which might assist automated antibody sequence optimization. We believe that AttABseq provides a fiercely competitive answer to therapeutic antibody optimization.

DrugFlow: An AI-Driven One-Stop Platform for Innovative Drug Discovery.

Artificial intelligence (AI)-aided drug design has demonstrated unprecedented effects on modern drug discovery, but there is still an urgent need for user-friendly interfaces that bridge the gap between these sophisticated tools and scientists, particularly those who are less computer savvy. Herein, we present DrugFlow, an AI-driven one-stop platform that offers a clean, convenient, and cloud-based interface to streamline early drug discovery workflows. By seamlessly integrating a range of innovative AI algorithms, covering molecular docking, quantitative structure-activity relationship modeling, molecular generation, ADMET (absorption, distribution, metabolism, excretion and toxicity) prediction, and virtual screening, DrugFlow can offer effective AI solutions for almost all crucial stages in early drug discovery, including hit identification and hit/lead optimization. We hope that the platform can provide sufficiently valuable guidance to aid real-word drug design and discovery. The platform is available at https://drugflow.com.

TransfIGN: A Structure-Based Deep Learning Method for Modeling the Interaction between HLA-A*02:01 and Antigen Peptides.

The intricate interaction between major histocompatibility complexes (MHCs) and antigen peptides with diverse amino acid sequences plays a pivotal role in immune responses and T cell activity. In recent years, deep learning (DL)-based models have emerged as promising tools for accelerating antigen peptide screening. However, most of these models solely rely on one-dimensional amino acid sequences, overlooking crucial information required for the three-dimensional (3-D) space binding process. In this study, we propose TransfIGN, a structure-based DL model that is inspired by our previously developed framework, Interaction Graph Network (IGN), and incorporates sequence information from transformers to predict the interactions between HLA-A*02:01 and antigen peptides. Our model, trained on a comprehensive data set containing 61,816 sequences with 9051 binding affinity labels and 56,848 eluted ligand labels, achieves an area under the curve (AUC) of 0.893 on the binary data set, better than state-of-the-art sequence-based models trained on larger data sets such as NetMHCpan4.1, ANN, and TransPHLA. Furthermore, when evaluated on the IEDB weekly benchmark data sets, our predictions (AUC = 0.816) are better than those of the recommended methods like the IEDB consensus (AUC = 0.795). Notably, the interaction weight matrices generated by our method highlight the strong interactions at specific positions within peptides, emphasizing the model's ability to provide physical interpretability. This capability to unveil binding mechanisms through intricate structural features holds promise for new immunotherapeutic avenues.

Exploring the activation mechanism of metabotropic glutamate receptor 2.

Homomeric dimerization of metabotropic glutamate receptors (mGlus) is essential for the modulation of their functions and represents a promising avenue for the development of novel therapeutic approaches to address central nervous system diseases. Yet, the scarcity of detailed molecular and energetic data on mGlu2 impedes our in-depth comprehension of their activation process. Here, we employ computational simulation methods to elucidate the activation process and key events associated with the mGlu2, including a detailed analysis of its conformational transitions, the binding of agonists, Gi protein coupling, and the guanosine diphosphate (GDP) release. Our results demonstrate that the activation of mGlu2 is a stepwise process and several energy barriers need to be overcome. Moreover, we also identify the rate-determining step of the mGlu2's transition from the agonist-bound state to its active state. From the perspective of free-energy analysis, we find that the conformational dynamics of mGlu2's subunit follow coupled rather than discrete, independent actions. Asymmetric dimerization is critical for receptor activation. Our calculation results are consistent with the observation of cross-linking and fluorescent-labeled blot experiments, thus illustrating the reliability of our calculations. Besides, we also identify potential key residues in the Gi protein binding position on mGlu2, mGlu2 dimer's TM6-TM6 interface, and Gi α5 helix by the change of energy barriers after mutation. The implications of our findings could lead to a more comprehensive grasp of class C G protein-coupled receptor activation.

Combining Transition Path Sampling with Data-Driven Collective Variables through a Reactivity-Biased Shooting Algorithm.

Rare event sampling is a central problem in modern computational chemistry research. Among the existing methods, transition path sampling (TPS) can generate unbiased representations of reaction processes. However, its efficiency depends on the ability to generate reactive trial paths, which in turn depends on the quality of the shooting algorithm used. We propose a new algorithm based on the shooting success rate, i.e., reactivity, measured as a function of a reduced set of collective variables (CVs). These variables are extracted with a machine learning approach directly from TPS simulations, using a multitask objective function. Iteratively, this workflow significantly improves the shooting efficiency without any prior knowledge of the process. In addition, the optimized CVs can be used with biased enhanced sampling methodologies to accurately reconstruct the free energy profiles. We tested the method on three different systems: a two-dimensional toy model, conformational transitions of alanine dipeptide, and hydrolysis of acetyl chloride in bulk water. In the latter, we integrated our workflow with an active learning scheme to learn a reactive machine learning-based potential, which allowed us to study the mechanism and free energy profile with an ab initio-like accuracy.

ChemFH: an integrated tool for screening frequent false positives in chemical biology and drug discovery.

High-throughput screening rapidly tests an extensive array of chemical compounds to identify hit compounds for specific biological targets in drug discovery. However, false-positive results disrupt hit compound screening, leading to wastage of time and resources. To address this, we propose ChemFH, an integrated online platform facilitating rapid virtual evaluation of potential false positives, including colloidal aggregators, spectroscopic interference compounds, firefly luciferase inhibitors, chemical reactive compounds, promiscuous compounds, and other assay interferences. By leveraging a dataset containing 823 391 compounds, we constructed high-quality prediction models using multi-task directed message-passing network (DMPNN) architectures combining uncertainty estimation, yielding an average AUC value of 0.91. Furthermore, ChemFH incorporated 1441 representative alert substructures derived from the collected data and ten commonly used frequent hitter screening rules. ChemFH was validated with an external set of 75 compounds. Subsequently, the virtual screening capability of ChemFH was successfully confirmed through its application to five virtual screening libraries. Furthermore, ChemFH underwent additional validation on two natural products and FDA-approved drugs, yielding reliable and accurate results. ChemFH is a comprehensive, reliable, and computationally efficient screening pipeline that facilitates the identification of true positive results in assays, contributing to enhanced efficiency and success rates in drug discovery. ChemFH is freely available via https://chemfh.scbdd.com/.