ADMETlab 3.0: an updated comprehensive online ADMET prediction platform enhanced with broader coverage, improved performance, API functionality and decision support.

ADMETlab 3.0 is the second updated version of the web server that provides a comprehensive and efficient platform for evaluating ADMET-related parameters as well as physicochemical properties and medicinal chemistry characteristics involved in the drug discovery process. This new release addresses the limitations of the previous version and offers broader coverage, improved performance, API functionality, and decision support. For supporting data and endpoints, this version includes 119 features, an increase of 31 compared to the previous version. The updated number of entries is 1.5 times larger than the previous version with over 400 000 entries. ADMETlab 3.0 incorporates a multi-task DMPNN architecture coupled with molecular descriptors, a method that not only guaranteed calculation speed for each endpoint simultaneously, but also achieved a superior performance in terms of accuracy and robustness. In addition, an API has been introduced to meet the growing demand for programmatic access to large amounts of data in ADMETlab 3.0. Moreover, this version includes uncertainty estimates in the prediction results, aiding in the confident selection of candidate compounds for further studies and experiments. ADMETlab 3.0 is publicly for access without the need for registration at: https://admetlab3.scbdd.com.

Learning with uncertainty to accelerate the discovery of histone lysine-specific demethylase 1A (KDM1A/LSD1) inhibitors.

Machine learning including modern deep learning models has been extensively used in drug design and screening. However, reliable prediction of molecular properties is still challenging when exploring out-of-domain regimes, even for deep neural networks. Therefore, it is important to understand the uncertainty of model predictions, especially when the predictions are used to guide further experiments. In this study, we explored the utility and effectiveness of evidential uncertainty in compound screening. The evidential Graphormer model was proposed for uncertainty-guided discovery of KDM1A/LSD1 inhibitors. The benchmarking results illustrated that (i) Graphormer exhibited comparative predictive power to state-of-the-art models, and (ii) evidential regression enabled well-ranked uncertainty estimates and calibrated predictions. Subsequently, we leveraged time-splitting on the curated KDM1A/LSD1 dataset to simulate out-of-distribution predictions. The retrospective virtual screening showed that the evidential uncertainties helped reduce false positives among the top-acquired compounds and thus enabled higher experimental validation rates. The trained model was then used to virtually screen an independent in-house compound set. The top 50 compounds ranked by two different ranking strategies were experimentally validated, respectively. In general, our study highlighted the importance to understand the uncertainty in prediction, which can be recognized as an interpretable dimension to model predictions.

Knowledge-based BERT: a method to extract molecular features like computational chemists.

Molecular property prediction models based on machine learning algorithms have become important tools to triage unpromising lead molecules in the early stages of drug discovery. Compared with the mainstream descriptor- and graph-based methods for molecular property predictions, SMILES-based methods can directly extract molecular features from SMILES without human expert knowledge, but they require more powerful algorithms for feature extraction and a larger amount of data for training, which makes SMILES-based methods less popular. Here, we show the great potential of pre-training in promoting the predictions of important pharmaceutical properties. By utilizing three pre-training tasks based on atom feature prediction, molecular feature prediction and contrastive learning, a new pre-training method K-BERT, which can extract chemical information from SMILES like chemists, was developed. The calculation results on 15 pharmaceutical datasets show that K-BERT outperforms well-established descriptor-based (XGBoost) and graph-based (Attentive FP and HRGCN+) models. In addition, we found that the contrastive learning pre-training task enables K-BERT to 'understand' SMILES not limited to canonical SMILES. Moreover, the general fingerprints K-BERT-FP generated by K-BERT exhibit comparative predictive power to MACCS on 15 pharmaceutical datasets and can also capture molecular size and chirality information that traditional binary fingerprints cannot capture. Our results illustrate the great potential of K-BERT in the practical applications of molecular property predictions in drug discovery.

Out-of-the-box deep learning prediction of quantum-mechanical partial charges by graph representation and transfer learning.

Accurate prediction of atomic partial charges with high-level quantum mechanics (QM) methods suffers from high computational cost. Numerous feature-engineered machine learning (ML)-based predictors with favorable computability and reliability have been developed as alternatives. However, extensive expertise effort was needed for feature engineering of atom chemical environment, which may consequently introduce domain bias. In this study, SuperAtomicCharge, a data-driven deep graph learning framework, was proposed to predict three important types of partial charges (i.e. RESP, DDEC4 and DDEC78) derived from high-level QM calculations based on the structures of molecules. SuperAtomicCharge was designed to simultaneously exploit the 2D and 3D structural information of molecules, which was proved to be an effective way to improve the prediction accuracy of the model. Moreover, a simple transfer learning strategy and a multitask learning strategy based on self-supervised descriptors were also employed to further improve the prediction accuracy of the proposed model. Compared with the latest baselines, including one GNN-based predictor and two ML-based predictors, SuperAtomicCharge showed better performance on all the three external test sets and had better usability and portability. Furthermore, the QM partial charges of new molecules predicted by SuperAtomicCharge can be efficiently used in drug design applications such as structure-based virtual screening, where the predicted RESP and DDEC4 charges of new molecules showed more robust scoring and screening power than the commonly used partial charges. Finally, two tools including an online server (http://cadd.zju.edu.cn/deepchargepredictor) and the source code command lines (https://github.com/zjujdj/SuperAtomicCharge) were developed for the easy access of the SuperAtomicCharge services.

Domestic cat nose functions as a highly efficient coiled parallel gas chromatograph.

The peripheral structures of mammalian sensory organs often serve to support their functionality, such as alignment of hair cells to the mechanical properties of the inner ear. Here, we examined the structure-function relationship for mammalian olfaction by creating an anatomically accurate computational nasal model for the domestic cat (Felis catus) based on high resolution microCT and sequential histological sections. Our results showed a distinct separation of respiratory and olfactory flow regimes, featuring a high-speed dorsal medial stream that increases odor delivery speed and efficiency to the ethmoid olfactory region without compromising the filtration and conditioning purpose of the nose. These results corroborated previous findings in other mammalian species, which implicates a common theme to deal with the physical size limitation of the head that confines the nasal airway from increasing in length infinitely as a straight tube. We thus hypothesized that these ethmoid olfactory channels function as parallel coiled chromatograph channels, and further showed that the theoretical plate number, a widely-used indicator of gas chromatograph efficiency, is more than 100 times higher in the cat nose than an "amphibian-like" straight channel fitting the similar skull space, at restful breathing state. The parallel feature also reduces airflow speed within each coil, which is critical to achieve the high plate number, while feeding collectively from the high-speed dorsal medial stream so that total odor sampling speed is not sacrificed. The occurrence of ethmoid turbinates is an important step in the evolution of mammalian species that correlates to their expansive olfactory function and brain development. Our findings reveal novel mechanisms on how such structure may facilitate better olfactory performance, furthering our understanding of the successful adaptation of mammalian species, including F. catus, a popular pet, to diverse environments.

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.

Assessing the performance of MM/PBSA and MM/GBSA methods. 10. Prediction reliability of binding affinities and binding poses for RNA-ligand complexes.

Ribonucleic acid (RNA)-ligand interactions play a pivotal role in a wide spectrum of biological processes, ranging from protein biosynthesis to cellular reproduction. This recognition has prompted the broader acceptance of RNA as a viable candidate for drug targets. Delving into the atomic-scale understanding of RNA-ligand interactions holds paramount importance in unraveling intricate molecular mechanisms and further contributing to RNA-based drug discovery. Computational approaches, particularly molecular docking, offer an efficient way of predicting the interactions between RNA and small molecules. However, the accuracy and reliability of these predictions heavily depend on the performance of scoring functions (SFs). In contrast to the majority of SFs used in RNA-ligand docking, the end-point binding free energy calculation methods, such as molecular mechanics/generalized Born surface area (MM/GBSA) and molecular mechanics/Poisson Boltzmann surface area (MM/PBSA), stand as theoretically more rigorous approaches. Yet, the evaluation of their effectiveness in predicting both binding affinities and binding poses within RNA-ligand systems remains unexplored. This study first reported the performance of MM/PBSA and MM/GBSA with diverse solvation models, interior dielectric constants (εin) and force fields in the context of binding affinity prediction for 29 RNA-ligand complexes. MM/GBSA is based on short (5 ns) molecular dynamics (MD) simulations in an explicit solvent with the YIL force field; the GBGBn2 model with higher interior dielectric constant (εin = 12, 16 or 20) yields the best correlation (Rp = -0.513), which outperforms the best correlation (Rp = -0.317, rDock) offered by various docking programs. Then, the efficacy of MM/GBSA in identifying the near-native binding poses from the decoys was assessed based on 56 RNA-ligand complexes. However, it is evident that MM/GBSA has limitations in accurately predicting binding poses for RNA-ligand systems, particularly compared with notably proficient docking programs like rDock and PLANTS. The best top-1 success rate achieved by MM/GBSA rescoring is 39.3%, which falls below the best results given by docking programs (50%, PLNATS). This study represents the first evaluation of MM/PBSA and MM/GBSA for RNA-ligand systems and is expected to provide valuable insights into their successful application to RNA targets.

Computational Fluid Dynamics and Its Potential Applications for the ENT Clinician.

This article is an examination of computational fluid dynamics in the field of otolaryngology, specifically rhinology. The historical development and subsequent application of computational fluid dynamics continues to enhance our understanding of various sinonasal conditions and surgical planning in the field today. This article aims to provide a description of computational fluid dynamics, the methods for its application, and the clinical relevance of its results. Consideration of recent research and data in computational fluid dynamics demonstrates its use in nonhistological disease pathology exploration, accompanied by a large potential for surgical guidance applications. Additionally, this article defines in lay terms the variables analyzed in the computational fluid dynamic process, including velocity, wall shear stress, area, resistance, and heat flux.

Hyperbolic relational graph convolution networks plus: a simple but highly efficient QSAR-modeling method.

Accurate predictions of druggability and bioactivities of compounds are desirable to reduce the high cost and time of drug discovery. After more than five decades of continuing developments, quantitative structure-activity relationship (QSAR) methods have been established as indispensable tools that facilitate fast, reliable and affordable assessments of physicochemical and biological properties of compounds in drug-discovery programs. Currently, there are mainly two types of QSAR methods, descriptor-based methods and graph-based methods. The former is developed based on predefined molecular descriptors, whereas the latter is developed based on simple atomic and bond information. In this study, we presented a simple but highly efficient modeling method by combining molecular graphs and molecular descriptors as the input of a modified graph neural network, called hyperbolic relational graph convolution network plus (HRGCN+). The evaluation results show that HRGCN+ achieves state-of-the-art performance on 11 drug-discovery-related datasets. We also explored the impact of the addition of traditional molecular descriptors on the predictions of graph-based methods, and found that the addition of molecular descriptors can indeed boost the predictive power of graph-based methods. The results also highlight the strong anti-noise capability of our method. In addition, our method provides a way to interpret models at both the atom and descriptor levels, which can help medicinal chemists extract hidden information from complex datasets. We also offer an HRGCN+'s online prediction service at https://quantum.tencent.com/hrgcn/.

Do we need different machine learning algorithms for QSAR modeling? A comprehensive assessment of 16 machine learning algorithms on 14 QSAR data sets.

Although a wide variety of machine learning (ML) algorithms have been utilized to learn quantitative structure-activity relationships (QSARs), there is no agreed single best algorithm for QSAR learning. Therefore, a comprehensive understanding of the performance characteristics of popular ML algorithms used in QSAR learning is highly desirable. In this study, five linear algorithms [linear function Gaussian process regression (linear-GPR), linear function support vector machine (linear-SVM), partial least squares regression (PLSR), multiple linear regression (MLR) and principal component regression (PCR)], three analogizers [radial basis function support vector machine (rbf-SVM), K-nearest neighbor (KNN) and radial basis function Gaussian process regression (rbf-GPR)], six symbolists [extreme gradient boosting (XGBoost), Cubist, random forest (RF), multiple adaptive regression splines (MARS), gradient boosting machine (GBM), and classification and regression tree (CART)] and two connectionists [principal component analysis artificial neural network (pca-ANN) and deep neural network (DNN)] were employed to learn the regression-based QSAR models for 14 public data sets comprising nine physicochemical properties and five toxicity endpoints. The results show that rbf-SVM, rbf-GPR, XGBoost and DNN generally illustrate better performances than the other algorithms. The overall performances of different algorithms can be ranked from the best to the worst as follows: rbf-SVM > XGBoost > rbf-GPR > Cubist > GBM > DNN > RF > pca-ANN > MARS > linear-GPR ≈ KNN > linear-SVM ≈ PLSR > CART ≈ PCR ≈ MLR. In terms of prediction accuracy and computational efficiency, SVM and XGBoost are recommended to the regression learning for small data sets, and XGBoost is an excellent choice for large data sets. We then investigated the performances of the ensemble models by integrating the predictions of multiple ML algorithms. The results illustrate that the ensembles of two or three algorithms in different categories can indeed improve the predictions of the best individual ML algorithms.

MG-BERT: leveraging unsupervised atomic representation learning for molecular property prediction.

MOTIVATION: Accurate and efficient prediction of molecular properties is one of the fundamental issues in drug design and discovery pipelines. Traditional feature engineering-based approaches require extensive expertise in the feature design and selection process. With the development of artificial intelligence (AI) technologies, data-driven methods exhibit unparalleled advantages over the feature engineering-based methods in various domains. Nevertheless, when applied to molecular property prediction, AI models usually suffer from the scarcity of labeled data and show poor generalization ability. RESULTS: In this study, we proposed molecular graph BERT (MG-BERT), which integrates the local message passing mechanism of graph neural networks (GNNs) into the powerful BERT model to facilitate learning from molecular graphs. Furthermore, an effective self-supervised learning strategy named masked atoms prediction was proposed to pretrain the MG-BERT model on a large amount of unlabeled data to mine context information in molecules. We found the MG-BERT model can generate context-sensitive atomic representations after pretraining and transfer the learned knowledge to the prediction of a variety of molecular properties. The experimental results show that the pretrained MG-BERT model with a little extra fine-tuning can consistently outperform the state-of-the-art methods on all 11 ADMET datasets. Moreover, the MG-BERT model leverages attention mechanisms to focus on atomic features essential to the target property, providing excellent interpretability for the trained model. The MG-BERT model does not require any hand-crafted feature as input and is more reliable due to its excellent interpretability, providing a novel framework to develop state-of-the-art models for a wide range of drug discovery tasks.

From Black Boxes to Actionable Insights: A Perspective on Explainable Artificial Intelligence for Scientific Discovery.

The application of Explainable Artificial Intelligence (XAI) in the field of chemistry has garnered growing interest for its potential to justify the prediction of black-box machine learning models and provide actionable insights. We first survey a range of XAI techniques adapted for chemical applications and categorize them based on the technical details of each methodology. We then present a few case studies to illustrate the practical utility of XAI, such as identifying carcinogenic molecules and guiding molecular optimizations, in order to provide chemists with concrete examples of ways to take full advantage of XAI-augmented machine learning for chemistry. Despite the initial success of XAI in chemistry, we still face the challenges of developing more reliable explanations, assuring robustness against adversarial actions, and customizing the explanation for different applications and needs of the diverse scientific community. Finally, we discuss the emerging role of large language models like GPT in generating natural language explanations and discusses the specific challenges associated with them. We advocate that addressing the aforementioned challenges and actively embracing new techniques may contribute to establishing machine learning as an indispensable technique for chemistry in this digital era.

ADMETlab 2.0: an integrated online platform for accurate and comprehensive predictions of ADMET properties.

Because undesirable pharmacokinetics and toxicity of candidate compounds are the main reasons for the failure of drug development, it has been widely recognized that absorption, distribution, metabolism, excretion and toxicity (ADMET) should be evaluated as early as possible. In silico ADMET evaluation models have been developed as an additional tool to assist medicinal chemists in the design and optimization of leads. Here, we announced the release of ADMETlab 2.0, a completely redesigned version of the widely used AMDETlab web server for the predictions of pharmacokinetics and toxicity properties of chemicals, of which the supported ADMET-related endpoints are approximately twice the number of the endpoints in the previous version, including 17 physicochemical properties, 13 medicinal chemistry properties, 23 ADME properties, 27 toxicity endpoints and 8 toxicophore rules (751 substructures). A multi-task graph attention framework was employed to develop the robust and accurate models in ADMETlab 2.0. The batch computation module was provided in response to numerous requests from users, and the representation of the results was further optimized. The ADMETlab 2.0 server is freely available, without registration, at https://admetmesh.scbdd.com/.

DeepChargePredictor: a web server for predicting QM-based atomic charges via state-of-the-art machine-learning algorithms.

SUMMARY: High-level quantum mechanics (QM) methods are no doubt the most reliable approaches for the prediction of atomic charges, but it usually needs very large computational resources, which apparently hinders the use of high-quality atomic charges in large-scale molecular modeling, such as high-throughput virtual screening. To solve this problem, several algorithms based on machine-learning (ML) have been developed to fit high-level QM atomic charges. Here, we proposed DeepChargePredictor, a web server that is able to generate the high-level QM atomic charges for small molecules based on two state-of-the-art ML algorithms developed in our group, namely AtomPathDescriptor and DeepAtomicCharge. These two algorithms were seamlessly integrated into the platform with the capability to predict three kinds of charges (i.e. RESP, AM1-BCC and DDEC) widely used in structure-based drug design. Moreover, we have comprehensively evaluated the performance of these charges generated by DeepChargePredictor for large-scale drug design applications, such as end-point binding free energy calculations and virtual screening, which all show reliable or even better performance compared with the baseline methods. AVAILABILITY AND IMPLEMENTATION: The data in the article can be obtained on the web page http://cadd.zju.edu.cn/deepchargepredictor/publication. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Correction: Taste of time: A porous-medium model for human tongue surface with implications for early taste perception.

[This corrects the article DOI: 10.1371/journal.pcbi.1007888.].

Exploring Low-Toxicity Chemical Space with Deep Learning for Molecular Generation.

Creating a wide range of new compounds that not only have ideal pharmacological properties but also easily pass long-term toxicity evaluation is still a challenging task in current drug discovery. In this study, we developed a conditional generative model by combining a semisupervised variational autoencoder (SSVAE) with an MGA toxicity predictor. Our aim is to generate molecules with low toxicity, good drug-like properties, and structural diversity. For multiobjective optimization, we have developed a method with hierarchical constraints on the toxicity space of small molecules to generate drug-like small molecules, which can also minimize the effect on the diversity of generated results. The evaluation results of the metrics indicate that the developed model has good effectiveness, novelty, and diversity. The generated molecules by this model are mainly distributed in low-toxicity regions, which suggests that our model can efficiently constrain the generation of toxic structures. In contrast to simply filtering toxic ones after generation, the low-toxicity molecular generative model can generate molecules with structural diversity. Our strategy can be used in target-based drug discovery to improve the quality of generated molecules with low-toxicity, drug-like, and highly active properties.

ALipSol: An Attention-Driven Mixture-of-Experts Model for Lipophilicity and Solubility Prediction.

Lipophilicity (logD) and aqueous solubility (logSw) play a central role in drug development. The accurate prediction of these properties remains to be solved due to data scarcity. Current methodologies neglect the intrinsic relationships between physicochemical properties and usually ignore the ionization effects. Here, we propose an attention-driven mixture-of-experts (MoE) model named ALipSol, which explicitly reproduces the hierarchy of task relationships. We adopt the principle of divide-and-conquer by breaking down the complex end point (logD or logSw) into simpler ones (acidic pKa, basic pKa, and logP) and allocating a specific expert network for each subproblem. Subsequently, we implement transfer learning to extract knowledge from related tasks, thus alleviating the dilemma of limited data. Additionally, we substitute the gating network with an attention mechanism to better capture the dynamic task relationships on a per-example basis. We adopt local fine-tuning and consensus prediction to further boost model performance. Extensive evaluation experiments verify the success of the ALipSol model, which achieves RMSE improvement of 8.04%, 2.49%, 8.57%, 12.8%, and 8.60% on the Lipop, ESOL, AqSolDB, external logD, and external logS data sets, respectively, compared with Attentive FP and the state-of-the-art in silico tools. In particular, our model yields more significant advantages (Welch's t-test) for small training data, implying its high robustness and generalizability. The interpretability analysis proves that the atom contributions learned by ALipSol are more reasonable compared with the vanilla Attentive FP, and the substitution effects in benzene derivatives agreed well with empirical constants, revealing the potential of our model to extract useful patterns from data and provide guidance for lead optimization.

Identification of Genetic Variations and Candidate Genes Responsible for Stalk Sugar Content and Agronomic Traits in Fresh Corn via GWAS across Multiple Environments.

The stem and leaves of fresh corn plants can be used as green silage or can be converted to biofuels, and the stalk sugar content and yield directly determine the application value of fresh corn. To identify the genetic variations and candidate genes responsible for the related traits in fresh corn, the genome-wide scan and genome-wide association analysis (GWAS) were performed. A total of 32 selective regions containing 172 genes were detected between sweet and waxy corns. Using the stalk sugar content and seven other agronomic traits measured in four seasons over two years, the GWAS identified ninety-two significant single nucleotide polymorphisms (SNPs). Most importantly, seven SNPs associated with the stalk sugar content were detected across multiple environments, which could explain 13.68-17.82% of the phenotypic variation. Accessions differing in genotype for certain significant SNPs showed significant variation in the stalk sugar content and other agronomic traits, and the expression levels of six important candidate genes were significantly different between two materials with different stalk sugar content. The genetic variations and candidate genes provide valuable resources for future studies of the molecular mechanism of the stalk sugar content and establish the foundation for molecular marker-assisted breeding of fresh corn.

Computational Fluid Dynamic Modeling Reveals Nonlinear Airway Stress during Trachea Development.

Normative trachea dimensions and aerodynamic information during development was collected to establish clinical benchmarks and showed that airway development seems to outpace respiratory demands. Infants and toddlers' trachea exhibit higher aerodynamic stress that significantly decreases by teenage years. This implies large airway pathology in younger children may have a more substantial clinical impact.

Taste of time: A porous-medium model for human tongue surface with implications for early taste perception.

Most sensory systems are remarkable in their temporal precision, reflected in such phrases as "a flash of light" or "a twig snap". Yet taste is complicated by the transport processes of stimuli through the papilla matrix to reach taste receptors, processes that are poorly understood. We computationally modeled the surface of the human tongue as a microfiber porous medium and found that time-concentration profiles within the papilla zone rise with significant delay that well match experimental ratings of perceived taste intensity to a range of sweet and salty stimuli for both rapid pulses and longer sip-and-hold exposures. Diffusivity of these taste stimuli, determined mostly by molecular size, correlates greatly with time and slope to reach peak intensity: smaller molecular size may lead to quicker taste perception. Our study demonstrates the novelty of modeling the human tongue as a porous material to drastically simplify computational approaches and that peripheral transport processes may significantly affect the temporal profile of taste perception, at least to sweet and salty compounds.