Is the mouse nose a miniature version of a rat nose? A computational comparative study.

BACKGROUND AND OBJECTIVE: Although the mouse is a widely used animal model in biomedical research, there are few published studies on its nasal aerodynamics, potentially due to its small size. It is not appropriate to assume that mice and rats' nasal structure and airflow characteristics are the same because the ratio of nasal surface area to nasal volume and body weight is much higher in a mouse than in a rat. The aim of this work is to use anatomically accurate image-based computational fluid dynamic modeling to quantitatively reveal the characteristics of mouse nasal airflow and mass transport that haven't been detailed before and find key differences to that of rat nose, which will deepen our understanding of the mouse's physiological functions. METHODS: We created an anatomically accurate 3D computational nasal model of a B6 mouse using postmortem high-resolution micro-CT scans and simulated the airflow distribution and odor transport patterns under restful breathing conditions. The deposition pattern of airborne particles was also simulated and validated against experimental data. In addition, we calculated the gas chromatograph efficiency of odor transport in the mouse employing the theoretical plate concept and compared it with previous studies involving cat and rat models. RESULTS: Similar to the published rat model, respiratory and olfactory flow regimes are clearly separated in the mouse nasal cavity. A high-speed dorsal medial (DM) stream was observed, which enhances the delivery speed and efficiency of odor to the ethmoid (olfactory) recess (ER). The DM stream split into axial and secondary paths in the ER. However, the secondary flow in the mouse is less extensive than in the rat. The gas chromatograph efficiency calculations suggest that the rat may possess a moderately higher odorant transport efficiency than that of the mouse due to its more complex ethmoid recess structure and extensive secondary flow. However, the mouse's nasal structure seems to adapt better to varying airflow velocity. CONCLUSIONS: Due to the inherent structural disparities, the rat and mouse models exhibit moderate differences in airflow and mass transport patterns, potentially impacting their olfaction and other behavioral habits.

Sweet corn association panel and genome-wide association analysis reveal loci for chilling-tolerant germination.

Sweet corn is highly susceptible to the deleterious effects of low temperatures during the initial stages of growth and development. Employing a 56K chip, high-throughput single-nucleotide polymorphism (SNP) sequencing was conducted on 100 sweet corn inbred lines. Subsequently, six germination indicators-germination rate, germination index, germination time, relative germination rate, relative germination index, and relative germination time-were utilized for genome-wide association analysis. Candidate genes were identified via comparative analysis of homologous genes in Arabidopsis and rice, and their functions were validated using quantitative real-time polymerase chain reaction (qRT-PCR). The results revealed 35,430 high-quality SNPs, 16 of which were significantly correlated. Within 50 kb upstream and downstream of the identified SNPs, 46 associated genes were identified, of which six were confirmed as candidate genes. Their expression patterns indicated that Zm11ΒHSDL5 and Zm2OGO likely play negative and positive regulatory roles, respectively, in the low-temperature germination of sweet corn. Thus, we determined that these two genes are responsible for regulating the low-temperature germination of sweet corn. This study contributes valuable theoretical support for improving sweet corn breeding and may aid in the creation of specific germplasm resources geared toward enhancing low-temperature tolerance in sweet corn.

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.

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.

Enhancing Generic Reaction Yield Prediction through Reaction Condition-Based Contrastive Learning.

Deep learning (DL)-driven efficient synthesis planning may profoundly transform the paradigm for designing novel pharmaceuticals and materials. However, the progress of many DL-assisted synthesis planning (DASP) algorithms has suffered from the lack of reliable automated pathway evaluation tools. As a critical metric for evaluating chemical reactions, accurate prediction of reaction yields helps improve the practicality of DASP algorithms in the real-world scenarios. Currently, accurately predicting yields of interesting reactions still faces numerous challenges, mainly including the absence of high-quality generic reaction yield datasets and robust generic yield predictors. To compensate for the limitations of high-throughput yield datasets, we curated a generic reaction yield dataset containing 12 reaction categories and rich reaction condition information. Subsequently, by utilizing 2 pretraining tasks based on chemical reaction masked language modeling and contrastive learning, we proposed a powerful bidirectional encoder representations from transformers (BERT)-based reaction yield predictor named Egret. It achieved comparable or even superior performance to the best previous models on 4 benchmark datasets and established state-of-the-art performance on the newly curated dataset. We found that reaction-condition-based contrastive learning enhances the model's sensitivity to reaction conditions, and Egret is capable of capturing subtle differences between reactions involving identical reactants and products but different reaction conditions. Furthermore, we proposed a new scoring function that incorporated Egret into the evaluation of multistep synthesis routes. Test results showed that yield-incorporated scoring facilitated the prioritization of literature-supported high-yield reaction pathways for target molecules. In addition, through meta-learning strategy, we further improved the reliability of the model's prediction for reaction types with limited data and lower data quality. Our results suggest that Egret holds the potential to become an essential component of the next-generation DASP tools.

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.

How Does Oxymetazoline Change Nasal Aerodynamics and Symptomatology in Patients with Turbinate Hypertrophy?

OBJECTIVES: Oxymetazoline relieves nasal obstructive symptoms via vasoconstriction, however, the changes in nasal structures and aerodynamics that impact symptoms the most remain unclear. METHODS: This prospective, longitudinal, and single blinded cohort study applied Computational Fluid Dynamic (CFD) modeling based on CT scans at baseline and post-oxymetazoline on 13 consecutive patients with chronic nasal obstruction secondary to inferior turbinate hypertrophy from a tertiary medical center. To account for placebo effect, a sham saline spray was administered with subject blindfolded prior to oxymetazoline, with 30 min rest in between. Nasal Obstruction Symptom Evaluation (NOSE) and unilateral Visual Analogue Scale (VAS) scores of nasal obstructions were collected at baseline, after sham, and 30 min after oxymetazoline. RESULTS: Both VAS and NOSE scores significantly improved from baseline to post-oxymetazoline (NOSE: 62.3 ± 12.4 to 31.5 ± 22.5, p < 0.01; VAS: 5.27 ± 2.63 to 3.85 ± 2.59, p < 0.05), but not significantly from baseline to post-sham. The anatomical effects of oxymetazoline were observed broadly throughout the entire length of the inferior and middle turbinates (p < 0.05). Among many variables that changed significantly post-oxymetazoline, only decreased nasal resistance (spearman r = 0.4, p < 0.05), increased regional flow rates (r = -0.3 to -0.5, p < 0.05) and mucosal cooling heat flux (r = -0.42, p < 0.01) in the inferior but not middle turbinate regions, and nasal valve Wall Shear Stress (WSS r = -0.43, p < 0.05) strongly correlated with symptom improvement. CONCLUSION: Oxymetazoline broadly affects the inferior and middle turbinates, however, symptomatic improvement appears to be driven more by global nasal resistance and regional increases in airflow rate, mucosal cooling, and WSS, especially near the head of the inferior turbinate. LEVEL OF EVIDENCE: 3: Well-designed, prospective, single blinded cohort trial. Laryngoscope, 134:1100-1106, 2024.

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.

A flexible data-free framework for structure-based de novo drug design with reinforcement learning.

Contemporary structure-based molecular generative methods have demonstrated their potential to model the geometric and energetic complementarity between ligands and receptors, thereby facilitating the design of molecules with favorable binding affinity and target specificity. Despite the introduction of deep generative models for molecular generation, the atom-wise generation paradigm that partially contradicts chemical intuition limits the validity and synthetic accessibility of the generated molecules. Additionally, the dependence of deep learning models on large-scale structural data has hindered their adaptability across different targets. To overcome these challenges, we present a novel search-based framework, 3D-MCTS, for structure-based de novo drug design. Distinct from prevailing atom-centric methods, 3D-MCTS employs a fragment-based molecular editing strategy. The fragments decomposed from small-molecule drugs are recombined under predefined retrosynthetic rules, offering improved drug-likeness and synthesizability, overcoming the inherent limitations of atom-based approaches. Leveraging multi-threaded parallel simulations combined with a real-time energy constraint-based pruning strategy, 3D-MCTS achieves remarkable efficiency. At a fixed computational cost, it outperforms other state-of-the-art (SOTA) methods by producing molecules with enhanced binding affinity. Furthermore, its fragment-based approach ensures the generation of more dependable binding conformations, exhibiting a success rate 43.6% higher than that of other SOTAs. This advantage becomes even more pronounced when handling targets that significantly deviate from the training dataset. 3D-MCTS is capable of achieving thirty times more hits with high binding affinity than traditional virtual screening methods, which demonstrates the superior ability of 3D-MCTS to explore chemical space. Moreover, the flexibility of our framework makes it easy to incorporate domain knowledge during the process, thereby enabling the generation of molecules with desirable pharmacophores and enhanced binding affinity. The adaptability of 3D-MCTS is further showcased in metalloprotein applications, highlighting its potential across various drug design scenarios.

Generic Interpretable Reaction Condition Predictions with Open Reaction Condition Datasets and Unsupervised Learning of Reaction Center.

Effective synthesis planning powered by deep learning (DL) can significantly accelerate the discovery of new drugs and materials. However, most DL-assisted synthesis planning methods offer either none or very limited capability to recommend suitable reaction conditions (RCs) for their reaction predictions. Currently, the prediction of RCs with a DL framework is hindered by several factors, including: (a) lack of a standardized dataset for benchmarking, (b) lack of a general prediction model with powerful representation, and (c) lack of interpretability. To address these issues, we first created 2 standardized RC datasets covering a broad range of reaction classes and then proposed a powerful and interpretable Transformer-based RC predictor named Parrot. Through careful design of the model architecture, pretraining method, and training strategy, Parrot improved the overall top-3 prediction accuracy on catalysis, solvents, and other reagents by as much as 13.44%, compared to the best previous model on a newly curated dataset. Additionally, the mean absolute error of the predicted temperatures was reduced by about 4 °C. Furthermore, Parrot manifests strong generalization capacity with superior cross-chemical-space prediction accuracy. Attention analysis indicates that Parrot effectively captures crucial chemical information and exhibits a high level of interpretability in the prediction of RCs. The proposed model Parrot exemplifies how modern neural network architecture when appropriately pretrained can be versatile in making reliable, generalizable, and interpretable recommendation for RCs even when the underlying training dataset may still be limited in diversity.

Neurologic and psychiatric features of impending neurodegeneration in iRBD.

Introduction: Idiopathic rapid eye movement (REM) sleep behavior disorder (iRBD) is linked to Parkinson's disease and other alpha-synucleinopathies, but various subsets of iRBD may not carry equal risk (i.e., those with depression are at higher risk than those without). Here, we prospectively focus on neurologic and psychiatric aspects of subjects with iRBD, in an attempt to determine what factors are prominent in those who undergo phenoconversion as opposed to those who do not. Methods: We analyzed data from the "REM Sleep Behavior Disorder Associations with Parkinson's Disease Study (RAPiDS)" cohort both at baseline and then at follow-up evaluations (1 to 3 years later) utilizing several neurologic batteries, including the Movement Disorder Society's Unified Parkinson's Disease Rating Scale (MDS-UPDRS), the Montreal Cognitive Assessment (MoCA), the Questionnaire for Impulsive-Compulsive Disorders in Parkinson's Disease (QUIP), the 10-M Walk Test (10MWT), and the Epworth Sleepiness Scale. Determination of phenoconversion was ascertained from physical examination and medical chart review from the initial evaluation onward. Results: Of those who completed both evaluations, there were 33 subjects with iRBD, with an average age of 63.1 ± 12.8 years, with 9 women and 24 men. Of these, 8 (24%) iRBD subjects developed neurodegenerative illness, and demonstrated multiple areas of neurologic and psychiatric signs and symptoms, such as speech and movement problems as well as anxiety and depression. Conclusions: Our data adds to the literature regarding risk of phenoconversion in those with iRBD. Further study will be needed, but it is clear that not all subjects with iRBD present the same risk for neurodegeneration.

MF-SuP-pKa: Multi-fidelity modeling with subgraph pooling mechanism for pKa prediction.

Acid-base dissociation constant (pKa) is a key physicochemical parameter in chemical science, especially in organic synthesis and drug discovery. Current methodologies for pKa prediction still suffer from limited applicability domain and lack of chemical insight. Here we present MF-SuP-pKa (multi-fidelity modeling with subgraph pooling for pKa prediction), a novel pKa prediction model that utilizes subgraph pooling, multi-fidelity learning and data augmentation. In our model, a knowledge-aware subgraph pooling strategy was designed to capture the local and global environments around the ionization sites for micro-pKa prediction. To overcome the scarcity of accurate pKa data, low-fidelity data (computational pKa) was used to fit the high-fidelity data (experimental pKa) through transfer learning. The final MF-SuP-pKa model was constructed by pre-training on the augmented ChEMBL data set and fine-tuning on the DataWarrior data set. Extensive evaluation on the DataWarrior data set and three benchmark data sets shows that MF-SuP-pKa achieves superior performances to the state-of-the-art pKa prediction models while requires much less high-fidelity training data. Compared with Attentive FP, MF-SuP-pKa achieves 23.83% and 20.12% improvement in terms of mean absolute error (MAE) on the acidic and basic sets, respectively.

How Good Are Current Docking Programs at Nucleic Acid-Ligand Docking? A Comprehensive Evaluation.

Nucleic acid (NA)-ligand interactions are of paramount importance in a variety of biological processes, including cellular reproduction and protein biosynthesis, and therefore, NAs have been broadly recognized as potential drug targets. Understanding NA-ligand interactions at the atomic scale is essential for investigating the molecular mechanism and further assisting in NA-targeted drug discovery. Molecular docking is one of the predominant computational approaches for predicting the interactions between NAs and small molecules. Despite the availability of versatile docking programs, their performance profiles for NA-ligand complexes have not been thoroughly characterized. In this study, we first compiled the largest structure-based NA-ligand binding data set to date, containing 800 noncovalent NA-ligand complexes with clearly identified ligands. Based on this extensive data set, eight frequently used docking programs, including six protein-ligand docking programs (LeDock, Surflex-Dock, UCSF Dock6, AutoDock, AutoDock Vina, and PLANTS) and two specific NA-ligand docking programs (rDock and RLDOCK), were systematically evaluated in terms of binding pose and binding affinity predictions. The results demonstrated that some protein-ligand docking programs, specifically PLANTS and LeDock, produced more promising or comparable results compared with the specialized NA-ligand docking programs. Among the programs evaluated, PLANTS, rDock, and LeDock showed the highest performance in binding pose prediction, and their top-1 and best root-mean-square deviation (rmsd) success rates were as follows: PLANTS (35.93 and 76.05%), rDock (27.25 and 72.16%), and LeDock (27.40 and 64.37%). Compared with the moderate level of binding pose prediction, few programs were successful in binding affinity prediction, and the best correlation (Rp = -0.461) was observed with PLANTS. Finally, further comparison with the latest NA-ligand docking program (NLDock) on four well-established data sets revealed that PLANTS and LeDock outperformed NLDock in terms of binding pose prediction on all data sets, demonstrating their significant potential for NA-ligand docking. To the best of our knowledge, this study is the most comprehensive evaluation of popular molecular docking programs for NA-ligand systems.

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.

Chemistry-intuitive explanation of graph neural networks for molecular property prediction with substructure masking.

Graph neural networks (GNNs) have been widely used in molecular property prediction, but explaining their black-box predictions is still a challenge. Most existing explanation methods for GNNs in chemistry focus on attributing model predictions to individual nodes, edges or fragments that are not necessarily derived from a chemically meaningful segmentation of molecules. To address this challenge, we propose a method named substructure mask explanation (SME). SME is based on well-established molecular segmentation methods and provides an interpretation that aligns with the understanding of chemists. We apply SME to elucidate how GNNs learn to predict aqueous solubility, genotoxicity, cardiotoxicity and blood-brain barrier permeation for small molecules. SME provides interpretation that is consistent with the understanding of chemists, alerts them to unreliable performance, and guides them in structural optimization for target properties. Hence, we believe that SME empowers chemists to confidently mine structure-activity relationship (SAR) from reliable GNNs through a transparent inspection on how GNNs pick up useful signals when learning from data.

Accumulation Rule of Sugar Content in Corn Stalk.

The primary parts of corn stalks are the leaves and the stems, which comprise the cortex and the pith. Corn has long been cultivated as an grain crops, and now it is a primary global source of sugar, ethanol, and biomass-generated energy. Even though increasing the sugar content in the stalk is an important breeding goal, progress has been modest in many breeding researchers. Accumulation is the gradual rise in quantity when new additions are made. The challenging characteristics of such sugar content in corn stalks are below the protein, bio-economy, and mechanical injury. Hence, in this research, plant water-content-enabled micro-Ribonucleic acids (PWC-miRNAs) were designed to increase the sugar content in corn stalks following an accumulation rule. High-throughput sequencing of the transcriptome, short RNAs, and coding RNAs was performed here; leaf and stem degradation from two early-maturing Corn genotypes revealed new information on miRNA-associated gene regulation in corn during the sucrose accumulation process. For sugar content in corn stalk, PWC-miRNAs were used to establish the application of the accumulation rule for data-processing monitoring throughout. Through simulation, management, and monitoring, the condition is accurately predicted, providing a new scientific and technological means to improve the efficiency of the construction of sugar content in corn stalks. The experimental analysis of PWC-miRNAs outperforms sugar content in terms of performance, accuracy, prediction ratio, and evaluation. This study aims to provide a framework for increasing the sugar content of corn stalk.

MetalProGNet: a structure-based deep graph model for metalloprotein-ligand interaction predictions.

Metalloproteins play indispensable roles in various biological processes ranging from reaction catalysis to free radical scavenging, and they are also pertinent to numerous pathologies including cancer, HIV infection, neurodegeneration, and inflammation. Discovery of high-affinity ligands for metalloproteins powers the treatment of these pathologies. Extensive efforts have been made to develop in silico approaches, such as molecular docking and machine learning (ML)-based models, for fast identification of ligands binding to heterogeneous proteins, but few of them have exclusively concentrated on metalloproteins. In this study, we first compiled the largest metalloprotein-ligand complex dataset containing 3079 high-quality structures, and systematically evaluated the scoring and docking powers of three competitive docking tools (i.e., PLANTS, AutoDock Vina and Glide SP) for metalloproteins. Then, a structure-based deep graph model called MetalProGNet was developed to predict metalloprotein-ligand interactions. In the model, the coordination interactions between metal ions and protein atoms and the interactions between metal ions and ligand atoms were explicitly modelled through graph convolution. The binding features were then predicted by the informative molecular binding vector learned from a noncovalent atom-atom interaction network. The evaluation on the internal metalloprotein test set, the independent ChEMBL dataset towards 22 different metalloproteins and the virtual screening dataset indicated that MetalProGNet outperformed various baselines. Finally, a noncovalent atom-atom interaction masking technique was employed to interpret MetalProGNet, and the learned knowledge accords with our understanding of physics.

Kinome-wide polypharmacology profiling of small molecules by multi-task graph isomorphism network approach.

Prediction of the interactions between small molecules and their targets play important roles in various applications of drug development, such as lead discovery, drug repurposing and elucidation of potential drug side effects. Therefore, a variety of machine learning-based models have been developed to predict these interactions. In this study, a model called auxiliary multi-task graph isomorphism network with uncertainty weighting (AMGU) was developed to predict the inhibitory activities of small molecules against 204 different kinases based on the multi-task Graph Isomorphism Network (MT-GIN) with the auxiliary learning and uncertainty weighting strategy. The calculation results illustrate that the AMGU model outperformed the descriptor-based models and state-of-the-art graph neural networks (GNN) models on the internal test set. Furthermore, it also exhibited much better performance on two external test sets, suggesting that the AMGU model has enhanced generalizability due to its great transfer learning capacity. Then, a naïve model-agnostic interpretable method for GNN called edges masking was devised to explain the underlying predictive mechanisms, and the consistency of the interpretability results for 5 typical epidermal growth factor receptor (EGFR) inhibitors with their structure‒activity relationships could be observed. Finally, a free online web server called KIP was developed to predict the kinome-wide polypharmacology effects of small molecules (http://cadd.zju.edu.cn/kip).

Nicosulfuron stress on the glyoxalase system and endogenous hormone content in sweet maize seedlings.

To reduce the harmful effects of nicosulfuron on sweet corn, the physiological regulation mechanism of sweet corn detoxification was studied. This study analyzed the effects of nicosulfuron stress on the glyoxalase system, hormone content, and key gene expression of nicosulfuron-tolerant "HK301" and nicosulfuron-sensitive "HK320" sweet corn seedling sister lines. After spraying nicosulfuron, the methylglyoxal (MG) content in HK301 increased first and then decreased. Glyoxalase I (GlyI) and glyoxalase II (GlyII) activities, non-enzymatic glutathione (GSH), and the glutathione redox state glutathione/(glutathione + glutathione disulfide) (GSH/(GSH + GSSG)) showed a similar trend as the MG content. Abscisic acid (ABA), gibberellin (GA), and zeatin nucleoside (ZR) also increased first and then decreased, whereas the auxin (IAA) increased continuously. In HK301, all indices after spraying nicosulfuron were significantly greater than those of the control. In HK320, MG accumulation continued to increase after nicosulfuron spraying and GlyI and GlyII activities, and GSH first increased and then decreased after 1 day of stress. The indicators above were significantly greater than the control. The GSH/(GSH + GSSG) ratio showed a decreasing trend and was significantly smaller than the control. Furthermore, ABA and IAA continued to increase, and the GA and ZR first increased and then decreased. Compared with HK320, HK301 significantly upregulated the transcription levels of GlyI and GlyII genes in roots, stems, and leaves. Comprehensive analysis showed that sweet maize seedlings improved their herbicide resistance by changing the glyoxalase system and regulating endogenous hormones. The results provide a theoretical basis for further understanding the response mechanism of the glyoxalase system and the regulation characteristics of endogenous hormones in maize under nicosulfuron stress.

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.