Polymer colloidal motors with photodynamic-regulated propulsion.

Artificial colloidal motors capable of converting various external energy into mechanical motion, have emerged as attractive photosensitizer (PS) nanocarriers with good deliverability for photodynamic therapy. However, photoactivated 3O2-to-1O2 transformation as the most crucial energy transfer of the photodynamic process itself is still challenging to convert into autonomous transport. Herein, we report on PS-loaded thiophane-containing semiconducting conjugated polymer (SCP)-based polymer colloidal motors with asymmetric geometry for photodynamic-regulated propulsion in the liquid. The asymmetrical presence of the SCP phases within the colloidal motors would lead to significant differences in the 3O2-to-1O2 transformation and 1O2 release manners between asymmetrical polymer phases, spontaneously creating asymmetrical osmotic pressure gradients across the nanoparticles for powering the self-propelled motion under photodynamic regulation. This photoactivated energy-converting behavior can be also combined with the photothermal conversion of the SCP phases to create two energy gradients exerting diffusiophoretic/thermophoretic force on the colloidal motors for achieving multimode synergistic propulsion. This unique motile feature endows the light-driven PS nanocarriers with good permeability against various physiological barriers in the tumor microenvironment for enhancing antitumor efficacy, showing great potential in phototherapy.

ISTransbase: an online database for inhibitor and substrate of drug transporters.

Drug transporters, integral membrane proteins found throughout the human body, play critical roles in physiological and biochemical processes through interactions with ligands, such as substrates and inhibitors. The extensive and disparate data on drug transporters complicate understanding their complex relationships with ligands. To address this challenge, it is essential to gather and summarize information on drug transporters, inhibitors and substrates, and simultaneously develop a comprehensive and user-friendly database. Current online resources often provide fragmented information and have limited coverage of drug transporter substrates and inhibitors, highlighting the need for a specialized, comprehensive and openly accessible database. ISTransbase addresses this gap by amassing a substantial amount of data from literature, government documents and open databases. It includes 16 528 inhibitors and 4465 substrates of 163 drug transporters from 18 different species, resulting in a total of 93 841 inhibitor records and 51 053 substrate records. ISTransbase provides detailed insights into drug transporters and their inhibitors/substrates, encompassing transporter and molecule structure, transporter function and distribution, as well as experimental methods and results from transport or inhibition experiments. Furthermore, ISTransbase offers three search strategies that allow users to retrieve drugs and transporters based on multiple selectable constraints, as well as perform checks for drug-drug interactions. Users can also browse and download data. In summary, ISTransbase (https://istransbase.scbdd.com/) serves as a valuable resource for accurately and efficiently accessing information on drug transporter inhibitors and substrates, aiding researchers in exploring drug transporter mechanisms and assisting clinicians in mitigating adverse drug reactions Database URL: https://istransbase.scbdd.com/.

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.

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/.

HydrogelFinder: A Foundation Model for Efficient Self-Assembling Peptide Discovery Guided by Non-Peptidal Small Molecules.

Self-assembling peptides have numerous applications in medicine, food chemistry, and nanotechnology. However, their discovery has traditionally been serendipitous rather than driven by rational design. Here, HydrogelFinder, a foundation model is developed for the rational design of self-assembling peptides from scratch. This model explores the self-assembly properties by molecular structure, leveraging 1,377 self-assembling non-peptidal small molecules to navigate chemical space and improve structural diversity. Utilizing HydrogelFinder, 111 peptide candidates are generated and synthesized 17 peptides, subsequently experimentally validating the self-assembly and biophysical characteristics of nine peptides ranging from 1-10 amino acids-all achieved within a 19-day workflow. Notably, the two de novo-designed self-assembling peptides demonstrated low cytotoxicity and biocompatibility, as confirmed by live/dead assays. This work highlights the capacity of HydrogelFinder to diversify the design of self-assembling peptides through non-peptidal small molecules, offering a powerful toolkit and paradigm for future peptide discovery endeavors.

Enhancing Molecular Property Prediction through Task-Oriented Transfer Learning: Integrating Universal Structural Insights and Domain-Specific Knowledge.

Precisely predicting molecular properties is crucial in drug discovery, but the scarcity of labeled data poses a challenge for applying deep learning methods. While large-scale self-supervised pretraining has proven an effective solution, it often neglects domain-specific knowledge. To tackle this issue, we introduce Task-Oriented Multilevel Learning based on BERT (TOML-BERT), a dual-level pretraining framework that considers both structural patterns and domain knowledge of molecules. TOML-BERT achieved state-of-the-art prediction performance on 10 pharmaceutical datasets. It has the capability to mine contextual information within molecular structures and extract domain knowledge from massive pseudo-labeled data. The dual-level pretraining accomplished significant positive transfer, with its two components making complementary contributions. Interpretive analysis elucidated that the effectiveness of the dual-level pretraining lies in the prior learning of a task-related molecular representation. Overall, TOML-BERT demonstrates the potential of combining multiple pretraining tasks to extract task-oriented knowledge, advancing molecular property prediction in drug discovery.

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.

The present state and challenges of active learning in drug discovery.

Active learning (AL) is an iterative feedback process that efficiently identifies valuable data within vast chemical space, even with limited labeled data. This characteristic renders it a valuable approach to tackle the ongoing challenges faced in drug discovery, such as the ever-expanding explore space and the limitations of labeled data. Consequently, AL is increasingly gaining prominence in the field of drug development. In this paper, we comprehensively review the application of AL at all stages of drug discovery, including compounds-target interaction prediction, virtual screening, molecular generation and optimization, as well as molecular properties prediction. Additionally, we discuss the challenges and prospects associated with the current applications of AL in drug discovery.

Predicting Elimination of Small-Molecule Drug Half-Life in Pharmacokinetics Using Ensemble and Consensus Machine Learning Methods.

Half-life is a significant pharmacokinetic parameter included in the excretion phase of absorption, distribution, metabolism, and excretion. It is one of the key factors for the successful marketing of drug candidates. Therefore, predicting half-life is of great significance in drug design. In this study, we employed eXtreme Gradient Boosting (XGboost), randomForest (RF), gradient boosting machine (GBM), and supporting vector machine (SVM) to build quantitative structure-activity relationship (QSAR) models on 3512 compounds and evaluated model performance by using root-mean-square error (RMSE), R2, and mean absolute error (MAE) metrics and interpreted features by SHapley Additive exPlanation (SHAP). Furthermore, we developed consensus models through integrating four individual models and validated their performance using a Y-randomization test and applicability domain analysis. Finally, matched molecular pair analysis was used to extract the transformation rules. Our results revealed that XGboost outperformed other individual models (RMSE = 0.176, R2 = 0.845, MAE = 0.141). The consensus model integrating all four models continued to enhance prediction performance (RMSE = 0.172, R2 = 0.856, MAE = 0.138). We evaluated the reliability, robustness, and generalization ability via Y-randomization test and applicability domain analysis. Meanwhile, we utilized SHAP to interpret features and employed matched molecular pair analysis to extract chemical transformation rules that provide suggestions for optimizing drug structure. In conclusion, we believe that the consensus model developed in this study serve as a reliable tool to evaluate half-life in drug discovery, and the chemical transformation rules concluded in this study could provide valuable suggestions in drug discovery.

CPhaMAS: An online platform for pharmacokinetic data analysis based on optimized parameter fitting algorithm.

BACKGROUND AND OBJECTIVE: Clinical pharmacological modeling and statistical analysis software is an essential basic tool for drug development and personalized drug therapy. The learning curve of current basic tools is steep and unfriendly to beginners. The curve is even more challenging in cases of significant individual differences or measurement errors in data, resulting in difficulties in accurately estimating pharmacokinetic parameters by existing fitting algorithms. Hence, this study aims to explore a new optimized parameter fitting algorithm that reduces the sensitivity of the model to initial values and integrate it into the CPhaMAS platform, a user-friendly online application for pharmacokinetic data analysis. METHODS: In this study, we proposed an optimized Nelder-Mead method that reinitializes simplex vertices when trapped in local solutions and integrated it into the CPhaMAS platform. The CPhaMAS, an online platform for pharmacokinetic data analysis, includes three modules: compartment model analysis, non-compartment analysis (NCA) and bioequivalence/bioavailability (BE/BA) analysis. Our proposed CPhaMAS platform was evaluated and compared with existing WinNonlin. RESULTS: The platform was easy to learn and did not require code programming. The accuracy investigation found that the optimized Nelder-Mead method of the CPhaMAS platform showed better accuracy (smaller mean relative error and higher R2) in two-compartment and extravascular administration models when the initial value was set to true and abnormal values (10 times larger or smaller than the true value) compared with the WinNonlin. The mean relative error of the NCA calculation parameters of CPhaMAS and WinNonlin was <0.0001 %. When calculating BE for conventional, high-variability and narrow-therapeutic drugs. The main statistical parameters of the parameters Cmax, AUCt, and AUCinf in CPhaMAS have a mean relative error of <0.01% compared to WinNonLin. CONCLUSIONS: In summary, CPhaMAS is a user-friendly platform with relatively accurate algorithms. It is a powerful tool for analysing pharmacokinetic data for new drug development and precision medicine.

Sunlight-triggered prebiotic nanomotors for inhibition and elimination of pathogen and biofilm in aquatic environment.

Pathogen contamination in drinking water sources causes waterborne infectious diseases, seriously threatening human health. Nowadays, stimuli-responsive self-propelled nanomotors are appealing therapeutic agents for antibacterial therapy in vivo. However, achieving water disinfection using these nanobots is still a great challenge. Herein, we report on prebiotic galactooligosaccharide-based nanomotors for sunlight-regulated water disinfection. The nanomotors can utilize galactooligosaccharide-based N-nitrosamines as sunlight-responsive fuels for the spontaneous production of antibacterial nitric oxide. Such a solar-to-chemical energy conversion would power the nanomotors for self-diffusiophoresis, which could promote the diffusion of the nanomotors in water and their penetration in the biofilm, significantly enhancing the inhibition and elimination of the pathogens and their biofilms in aquatic environments. After water treatments, the prebiotic-based residual disinfectants can be selectively utilized by beneficial bacteria to effectively relieve safety risks to the environment and human health. The low-energy-cost, green and potent antibacterial nanobots show promising potential in water disinfection.

Enhancing Multi-species Liver Microsomal Stability Prediction through Artificial Intelligence.

Liver microsomal stability, a crucial aspect of metabolic stability, significantly impacts practical drug discovery. However, current models for predicting liver microsomal stability are based on limited molecular information from a single species. To address this limitation, we constructed the largest public database of compounds from three common species: human, rat, and mouse. Subsequently, we developed a series of classification models using both traditional descriptor-based and classic graph-based machine learning (ML) algorithms. Remarkably, the best-performing models for the three species achieved Matthews correlation coefficients (MCCs) of 0.616, 0.603, and 0.574, respectively, on the test set. Furthermore, through the construction of consensus models based on these individual models, we have demonstrated their superior predictive performance in comparison with the existing models of the same type. To explore the similarities and differences in the properties of liver microsomal stability among multispecies molecules, we conducted preliminary interpretative explorations using the Shapley additive explanations (SHAP) and atom heatmap approaches for the models and misclassified molecules. Additionally, we further investigated representative structural modifications and substructures that decrease the liver microsomal stability in different species using the matched molecule pair analysis (MMPA) method and substructure extraction techniques. The established prediction models, along with insightful interpretation information regarding liver microsomal stability, will significantly contribute to enhancing the efficiency of exploring practical drugs for development.

Predictors of amputation in patients with diabetic foot ulcers: a multi-centre retrospective cohort study.

PURPOSE: Investigating risk factors for amputation in patients with diabetic foot ulcer (DFU) and developing a nomogram prediction model. METHODS: We gathered case data of DFU patients from five medical institutions in Anhui Province, China. Following eligibility criteria, a retrospective case-control study was performed on data from 526 patients. RESULTS: Among the 526 patients (mean age: 63.32 ± 12.14), 179 were female, and 347 were male; 264 underwent amputation. Univariate analysis identified several predictors for amputation, including Blood type-B, Ambulation, history of amputation (Hx. Of amputation), Bacterial culture-positive, Wagner grade, peripheral arterial disease (PAD), and laboratory parameters (HbA1c, Hb, CRP, ALB, FIB, PLT, Protein). In the multivariate regression, six variables emerged as independent predictors: Blood type-B (OR = 2.332, 95%CI [1.488-3.657], p < 0.001), Hx. Of amputation (2.298 [1.348-3.917], p = 0.002), Bacterial culture-positive (2.490 [1.618-3.830], p <0.001), Wagner 3 (1.787 [1.049-3.046], p = 0.033), Wagner 4-5 (4.272 [2.444-7.468], p <0.001), PAD (1.554 [1.030-2.345], p = 0.036). We developed a nomogram prediction model utilizing the aforementioned independent risk factors. The model demonstrated a favorable predictive ability for amputation risk, as evidenced by its area under the receiver operating characteristics (ROC) curve of 0.756 and the well-fitted corrected nomogram calibration curve. CONCLUSION: Our findings underscore Blood type-B, Hx. Of amputation, Bacterial culture-positive, Wagner 3-5, and PAD as independent risk factors for amputation in DFU patients. The resultant nomogram exhibits substantial accuracy in predicting amputation occurrence. Timely identification of these risk factors can reduce DFU-related amputation rates.

Brown Adipose Tissue Promotes Autologous Fat Grafts Retention Possibly Through Inhibiting Wnt/ß-Catenin Pathway.

BACKGROUND: In plastic surgery, autologous fat grafts (AFG) play an important role because of their abundant supply, biocompatibility, and low rejection rate. However, the lower retention rate of fat grafts limits their widespread use. Brown adipose tissue (BAT) can promote angiogenesis and regulate the level of associated inflammation. This study explored whether BAT has a facilitative effect on fat graft retention. METHODS: We obtained white adipose tissue (WAT) from c57 mice and combined it with either BAT from c57 mice or phosphate-buffered saline (PBS) as a control. These mixtures were injected subcutaneously into the back of thymus-free nude mice. After 12 weeks, fat grafts were harvested, weighed, and analyzed. RESULTS: We found that the BAT-grafted group had higher mass retention, more mature adipocytes, and higher vascularity than the other group. Further analysis revealed that BAT inhibited M1 macrophages; down-regulated IL-6, IL-1ß, and TNF-ß; upregulated M2 macrophages and Vascular endothelial growth factor-A (VEGFA); and promoted adipocyte regeneration by inhibiting the Wnt/ß-catenin pathway, which together promoted adipose graft retention. CONCLUSION: The study demonstrated that BAT improved adipose graft retention by promoting angiogenesis, inhibiting tissue inflammation levels and the Wnt/ß-catenin pathway. LEVEL OF EVIDENCE III: This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266.

Exosomes Derived from Adipose Stem Cells Enhance Angiogenesis in Diabetic Wound Via miR-146a-5p/JAZF1 Axis.

Chronic trauma in diabetes is a leading cause of disability and mortality. Exosomes show promise in tissue regeneration. This study investigates the role of exosomes derived from adipose stem cells (ADSC-Exos) in angiogenesis. MiRNA-seq analysis revealed significant changes in 47 genes in human umbilical vein endothelial cells (HUVECs) treated with ADSC-Exos, with miR-146a-5p highly expressed. MiR-146a-5p mimics enhanced the pro-angiogenic effects of ADSC-Exos, while inhibitors had the opposite effect. JAZF1 was identified as a direct downstream target of miR-146a-5p through bioinformatics, qRT-PCR, and dual luciferase assay. Overexpress of JAZF1 resulted in decreased proliferation, migration, and angiogenic capacity of HUVECs, and reduced VEGFA expression. This study proposes that ADSC-Exos regulate angiogenesis partly via the miR-146a-5p/JAZF1 axis.

ChemMORT: an automatic ADMET optimization platform using deep learning and multi-objective particle swarm optimization.

Drug discovery and development constitute a laborious and costly undertaking. The success of a drug hinges not only good efficacy but also acceptable absorption, distribution, metabolism, elimination, and toxicity (ADMET) properties. Overall, up to 50% of drug development failures have been contributed from undesirable ADMET profiles. As a multiple parameter objective, the optimization of the ADMET properties is extremely challenging owing to the vast chemical space and limited human expert knowledge. In this study, a freely available platform called Chemical Molecular Optimization, Representation and Translation (ChemMORT) is developed for the optimization of multiple ADMET endpoints without the loss of potency (https://cadd.nscc-tj.cn/deploy/chemmort/). ChemMORT contains three modules: Simplified Molecular Input Line Entry System (SMILES) Encoder, Descriptor Decoder and Molecular Optimizer. The SMILES Encoder can generate the molecular representation with a 512-dimensional vector, and the Descriptor Decoder is able to translate the above representation to the corresponding molecular structure with high accuracy. Based on reversible molecular representation and particle swarm optimization strategy, the Molecular Optimizer can be used to effectively optimize undesirable ADMET properties without the loss of bioactivity, which essentially accomplishes the design of inverse QSAR. The constrained multi-objective optimization of the poly (ADP-ribose) polymerase-1 inhibitor is provided as the case to explore the utility of ChemMORT.

A Very Deep Graph Convolutional Network for 13C NMR Chemical Shift Calculations with Density Functional Theory Level Performance for Structure Assignment.

Nuclear magnetic resonance (NMR) chemical shift calculations are powerful tools for structure elucidation and have been extensively employed in both natural product and synthetic chemistry. However, density functional theory (DFT) NMR chemical shift calculations are usually time-consuming, while fast data-driven methods often lack reliability, making it challenging to apply them to computationally intensive tasks with a high requirement on quality. Herein, we have constructed a 54-layer-deep graph convolutional network for 13C NMR chemical shift calculations, which achieved high accuracy with low time-cost and performed competitively with DFT NMR chemical shift calculations on structure assignment benchmarks. Our model utilizes a semiempirical method, GFN2-xTB, and is compatible with a broad variety of organic systems, including those composed of hundreds of atoms or elements ranging from H to Rn. We used this model to resolve the controversial J/K ring junction problem of maitotoxin, which is the largest whole molecule assigned by NMR calculations to date. This model has been developed into user-friendly software, providing a useful tool for routine rapid structure validation and assignation as well as a new approach to elucidate the large structures that were previously unsuitable for NMR calculations.

Combined BET and MEK Inhibition synergistically suppresses melanoma by targeting YAP1.

Rationale: The response rate to the MEK inhibitor trametinib in BRAF-mutated melanoma patients is less than 30%, and drug resistance develops rapidly, but the mechanism is still unclear. Yes1-associated transcriptional regulator (YAP1) is highly expressed in melanoma and may be related to MEK inhibitor resistance. The purpose of this study was to investigate the mechanism of YAP1 in MEK inhibitor resistance in melanoma and to screen YAP1 inhibitors to further determine whether YAP1 inhibition reverses MEK inhibitor resistance. Methods: On the one hand, we analyzed paired melanoma and adjacent tissue samples using RNA-seq and found that the Hippo-YAP1 signaling pathway was the top upregulated pathway. On the other hand, we evaluated the transcriptomes of melanoma samples from patients before and after trametinib treatment and investigated the correlation between YAP1 expression and trametinib resistance. Then, we screened for inhibitors that repress YAP1 expression and investigated the mechanisms. Finally, we investigated the antitumor effect of YAP1 inhibition combined with MEK inhibition both in vitro and in vivo. Results: We found that YAP1 expression levels upon trametinib treatment in melanoma patients were correlated with resistance to trametinib. YAP1 was translocated into the nucleus after trametinib treatment in melanoma cells, which could render resistance to MEK inhibition. Thus, we screened for inhibitors that repress YAP1 expression and identified multiple bromodomain and extra-terminal (BET) inhibitors, including NHWD-870, as hits. BET inhibition repressed YAP1 expression by decreasing BRD4 binding to the YAP1 promoter. Consistently, YAP1 overexpression was sufficient to reverse the proliferation defect caused by BRD4 depletion. In addition, the BET inhibitor NHWD-870 acted synergistically with trametinib to suppress melanoma growth in vitro and in vivo. Conclusions: We identified a new vulnerability for MEK inhibitor-resistant melanomas, which activated Hippo pathway due to elevated YAP1 activity. Inhibition of BRD4 using BET inhibitors suppressed YAP1 expression and led to blunted melanoma growth when combined with treatment with the MEK inhibitor trametinib.

Comprehensive evaluation of molecule property prediction with ChatGPT.

The versatility of ChatGPT in performing a diverse range of tasks has elicited considerable interest on its potential applications within professional fields. Taking drug discovery as a testbed, this paper provides a comprehensive evaluation of ChatGPT's ability on molecule property prediction. The study focuses on three aspects: 1) Effects of different prompt settings, where we investigate the impact of varying prompts on the prediction outcomes of ChatGPT; 2) Comprehensive evaluation on molecule property prediction, where we conduct a comprehensive evaluation on 53 ADMET-related endpoints; 3) Analysis of ChatGPT's potential and limitations, where we make comparisons with models tailored for molecule property prediction, thus gaining a more accurate understanding of ChatGPT's capabilities and limitations in this area. Through comprehensive evaluation, we find that 1) With appropriate prompt settings, ChatGPT can attain satisfactory prediction outcomes that are competitive with specialized models designed for those tasks. 2) Prompt settings significantly affect ChatGPT's performance. Among all prompt settings, the strategy of selecting examples in few-shot has the greatest impact on results. Scaffold sampling greatly outperforms random sampling. 3) The capacity of ChatGPT to accomplish high-precision predictions is significantly influenced by the quality of examples provided, which may constrain its practical applicability in real-world scenarios. This work highlights ChatGPT's potential and limitations on molecule property prediction, which we hope can inspire future design and evaluation of Large Language Models within scientific domains.

PatentNetML: A Novel Framework for Predicting Key Compounds in Patents Using Network Science and Machine Learning.

Patents play a crucial role in drug research and development, providing early access to unpublished data and offering unique insights. Identifying key compounds in patents is essential to finding novel lead compounds. This study collected a comprehensive data set comprising 1555 patents, encompassing 1000 key compounds, to explore innovative approaches for predicting these key compounds. Our novel PatentNetML framework integrated network science and machine learning algorithms, combining network measures, ADMET properties, and physicochemical properties, to construct robust classification models to identify key compounds. Through a model interpretation and an analysis of three compelling case studies, we showcase the potential of PatentNetML in unveiling hidden patterns and connections within diverse patents. While our framework is pioneering, we acknowledge its limitations when applied to patents that deviate from the assumed central pattern. This work serves as a promising foundation for future research endeavors aimed at efficiently identifying promising drug candidates and expediting drug discovery in the pharmaceutical industry.