Focal Adhesion Kinase (FAK) is a non-receptor tyrosine kinase that plays a crucial role in cell proliferation, migration, and signal transduction. FAK is overexpressed in metastatic and advanced-stage cancers, where it is considered a key kinase in cancer growth and metastasis. However, recent research has revealed that FAK activity decreases in various diseases. we aimed to identify compounds that could enhance FAK activity using structure-based virtual screening and artificial intelligence models from a vast chemical database. We began with an extensive chemical database containing over 10 million compounds and used our newly developed pipeline to screen candidate molecules. To select compounds structurally similar to ZINC40099027 (ZN27), a known FAK activator, we calculated Tanimoto Similarity scores and chose compounds with a score of at least 0.8. Clustering was performed using K-means based on the molecular properties. Subsequently, we utilized docking simulation, deep learning and SAScorer to evaluate and predict the protein-ligand docking affinity and physicochemical properties of the candidate compounds. The deep learning models were selected as state-of-the-art models: GLAM predicts the blood-brain barrier permeability of FAK, and elEmBERT predicts the potential toxicity of compound. The combined results were used to create an evaluation matrix. We selected 10 promising candidate compounds from the initial dataset of 10 million. To evaluate the stability of these top 10 candidate compounds in interaction with the FAK protein, we conducted Molecular Dynamics (MD) simulations. We performed a molecular dynamics simulation for a total of 50 ns and identified the top three promising candidate compounds.

Despite the increasing global prevalence of neurological disorders, the development of nanoparticle (NP) technologies for brain-targeted therapies confronts considerable challenges. One of the key obstacles in treating brain diseases is the blood-brain barrier (BBB), which restricts the penetration of NP-based therapies into the brain. To address this issue, NPs can be installed with specific ligands or bioengineered to boost their precision and efficacy in targeting brain-diseased cells by navigating across the BBB, ultimately improving patient treatment outcomes. At the outset of this review, we highlighted the critical role of ligand-functionalized or bioengineered NPs in treating brain diseases from a clinical perspective. We then identified the key obstacles and challenges NPs encounter during brain delivery, including immune clearance, capture by the reticuloendothelial system (RES), the BBB, and the complex post-BBB microenvironment. Following this, we overviewed the recent progress in NPs engineering, focusing on ligand-functionalization or bionic designs to enable active BBB transcytosis and targeted delivery to brain-diseased cells. Lastly, we summarized the critical challenges hindering clinical translation, including scalability issues and off-target effects, while outlining future opportunities for designing cutting-edge brain delivery technologies.

In today's world, with an increasing patient population, the need for medications is increasing rapidly. However, the current practice of drug development is time-consuming and requires a lot of investment by the pharmaceutical industries. Currently, it takes around 8-10 years and $3 billion of investment to develop a medication. Pharmaceutical industries and regulatory authorities are continuing to adopt new technologies to improve the efficiency of the drug development process. However, over the decades the pharmaceutical industries were not able to accelerate the drug development process. The pandemic (COVID-19) has taught the pharmaceutical industries and regulatory agencies an expensive lesson showing the need for emergency preparedness by accelerating the drug development process. Over the last few years, the pharmaceutical industries have been collaborating with artificial intelligence (AI) companies to develop algorithms and models that can be implemented at various stages of the drug development process to improve efficiency and reduce the developmental timelines significantly. In recent years, AI-screened drug candidates have entered clinical testing in human subjects which shows the interest of pharmaceutical companies and regulatory agencies. End-end integration of AI within the drug development process will benefit the industries for predicting the pharmacokinetic and pharmacodynamic profiles, toxicity, acceleration of clinical trials, study design, virtual monitoring of subjects, optimization of manufacturing process, analyzing and real-time monitoring of product quality, and regulatory preparedness. This review article discusses in detail the role of AI in various avenues of the pharmaceutical drug development process, its limitations, regulatory and future perspectives.

This study introduces PROFIS, a new generative model capable of the design of structurally novel and target-focused compound libraries. The model relies on a recurrent neural network that was trained to decode embedded molecular fingerprints into SMILES strings. To identify potential novel ligands, a biological activity predictor is first trained on the low-dimensional fingerprint embedding space, enabling the identification of high-activity subspaces for a given drug target. The search for latent representations that are expected to yield active structures upon decoding to SMILES is conducted with a Bayesian optimization algorithm. We present the rationale for using SMILES as the output notation of the recurrent neural network and compare its performance with models trained to decode DeepSMILES and SELFIES strings. The paper demonstrates the application of this protocol to generate candidate ligands of the dopamine D2 receptor. It also emphasizes the effectiveness of our approach in scaffold-hopping, which is valuable for designing ligands outside the already explored chemical space. We present how passing engineered molecular fingerprints through PROFIS network can be utilized to generate diverse libraries of analogs for a drug molecule of choice. It is worth noting that the protocol is versatile and it can be employed for any biological target, given the availability of a dataset containing known ligands. The potential for widespread use of PROFIS is secured by scripts shared by the authors on GitHub.

The development of new approach methodologies (NAMs) and advances with in vitro testing systems have prompted revisions in regulatory guidelines and inspired dedicated in vitro/ex vivo studies for nonclinical safety assessment. This Review by a safety reflection initiative subgroup of the European Federation of Pharmaceutical Industries and Associations (EFPIA)/Preclinical Development Expert Group (PDEG) summarizes the current state and potential application of in vitro studies using human-derived material for safety assessment in drug development. It focuses on case studies from recent projects in which animal models alone proved to be limited or inadequate for safety testing. It further highlights four categories of drug candidates for which alternative in vitro approaches are applicable and discusses progress in using in vitro testing solutions for safety assessment in these categories. Finally, the article highlights new risk assessment strategies, initiatives and consortia promoting the advancement of NAMs. This collective work is meant to encourage the use of NAMs for more human-relevant safety assessment, which should ultimately result in reduced animal testing for drug development.

Machine learning (ML) is increasingly valuable for predicting molecular properties and toxicity in drug discovery. However, toxicity-related end points have always been challenging to evaluate experimentally with respect to in vivo translation due to the required resources for human and animal studies; this has impacted data availability in the field. ML can augment or even potentially replace traditional experimental processes depending on the project phase and specific goals of the prediction. For instance, models can be used to select promising compounds for on-target effects or to deselect those with undesirable characteristics (e.g., off-target or ineffective due to unfavorable pharmacokinetics). However, reliance on ML is not without risks, due to biases stemming from nonrepresentative training data, incompatible choice of algorithm to represent the underlying data, or poor model building and validation approaches. This might lead to inaccurate predictions, misinterpretation of the confidence in ML predictions, and ultimately suboptimal decision-making. Hence, understanding the predictive validity of ML models is of utmost importance to enable faster drug development timelines while improving the quality of decisions. This perspective emphasizes the need to enhance the understanding and application of machine learning models in drug discovery, focusing on well-defined data sets for toxicity prediction based on small molecule structures. We focus on five crucial pillars for success with ML-driven molecular property and toxicity prediction: (1) data set selection, (2) structural representations, (3) model algorithm, (4) model validation, and (5) translation of predictions to decision-making. Understanding these key pillars will foster collaboration and coordination between ML researchers and toxicologists, which will help to advance drug discovery and development.

Cancer remains a significant global health challenge, with the Cell Division Cycle 7 (CDC7) protein emerging as a potential therapeutic target due to its critical role in tumor proliferation, survival, and resistance. However, a comprehensive analysis of CDC7 across multiple cancers is lacking, and existing therapeutic options have come with limited clinical success. The aim of this is to integrate a comprehensive pan-cancer analysis of CDC7 with the identification of novel marine-derived inhibitors, bridging the understanding of CDC7's role as a prognostic biomarker and therapeutic target across diverse cancer types. In this study, we conducted a pan-cancer analysis of CDC7 across 33 tumor types using publicly available datasets to evaluate its expression, genetic alterations, immune interactions, survival, and prognostic significance. Additionally, a marine-derived compound library of 31,492 molecules was screened to identify potential CDC7 inhibitors using chemoinformatics and machine learning. The top candidates underwent rigorous evaluations, including molecular docking, pharmacokinetics, toxicity, Density Functional Theory (DFT) calculations, and Molecular Dynamics (MD) simulations. The findings revealed that CDC7 is overexpressed in several cancers and is associated with poor survival outcomes and unfavorable prognosis. Enrichment analysis linked CDC7 to critical DNA replication pathways, while its role in modulating tumor-immune interactions highlighted its potential as a target for immunotherapy. Among all tested compounds, Tetrahydroaltersolanol D (CMNPD21999) exhibited the strongest binding affinity and stability, along with better drug-likeness and zero toxicity. These attributes highlight its potential as a promising drug candidate for CDC7 inhibition and future cancer treatment development. Furthermore, additional in vitro and in vivo studies are required to confirm the effectiveness of this drug candidate against the CDC7 protein.

The deployment of artificial intelligence (AI) is revolutionizing neuropharmacology and drug development, allowing the modulation of neurotransmitter systems at the personal level. This review focuses on the neuropharmacology and regulation of neurotransmitters using predictive modeling, closed-loop neuromodulation, and precision drug design. The fusion of AI with applications such as machine learning, deep-learning, and even computational modeling allows for the real-time tracking and enhancement of biological processes within the body. An exemplary application of AI is the use of DeepMind's AlphaFold to design new GABA reuptake inhibitors for epilepsy and anxiety. Likewise, Benevolent AI and IBM Watson have fast-tracked drug repositioning for neurodegenerative conditions. Furthermore, we identified new serotonin reuptake inhibitors for depression through AI screening. In addition, the application of Deep Brain Stimulation (DBS) settings using AI for patients with Parkinson's disease and for patients with major depressive disorder (MDD) using reinforcement learning-based transcranial magnetic stimulation (TMS) leads to better treatment. This review highlights other challenges including algorithm bias, ethical concerns, and limited clinical validation. Their proposal to incorporate AI with optogenetics, CRISPR, neuroprosthesis, and other advanced technologies fosters further exploration and refinement of precision neurotherapeutic approaches. By bridging computational neuroscience with clinical applications, AI has the potential to revolutionize neuropharmacology and improve patient-specific treatment strategies. We addressed critical challenges, such as algorithmic bias and ethical concerns, by proposing bias auditing, diverse datasets, explainable AI, and regulatory frameworks as practical solutions to ensure equitable and transparent AI applications in neurotransmitter modulation.

AI-driven prediction algorithms have the potential to enhance emergency medicine by enabling rapid and accurate decision-making regarding patient status and potential deterioration. However, the integration of multimodal data, including raw waveform signals, remains underexplored in clinical decision support.

We present a dataset and benchmarking protocol designed to advance multimodal decision support in emergency care. Our models utilize demographics, biometrics, vital signs, laboratory values, and electrocardiogram (ECG) waveforms as inputs to predict both discharge diagnoses and patient deterioration.

The diagnostic model achieves area under the receiver operating curve (AUROC) scores above 0.8 for 609 out of 1,428 conditions, covering both cardiac (e.g., myocardial infarction) and non-cardiac (e.g., renal disease, diabetes) diagnoses. The deterioration model attains AUROC scores above 0.8 for 14 out of 15 targets, accurately predicting critical events such as cardiac arrest, mechanical ventilation, ICU admission, and mortality.

Our study highlights the positive impact of incorporating raw waveform data into decision support models, improving predictive performance. By introducing a unique, publicly available dataset and baseline models, we provide a foundation for measurable progress in AI-driven decision support for emergency care.

The increasing adoption of computational methods and artificial intelligence in scientific research has led to a growing interest in versatile tools like Python. In the fields of medical chemistry, biochemistry, and bioinformatics, Python has emerged as a key language for tackling complex challenges. It is used to solve various tasks, such as drug discovery, high-throughput and virtual screening, protein and genome analysis, and predicting drug efficacy. This review presents a list of tools for these tasks, including scripts, libraries, and ready-made programs, and serves as a starting point for scientists wishing to apply automation or optimization to routine tasks in medical chemistry and bioinformatics.

Predicting drug-target interactions (DTIs) accurately is essential in the field of drug discovery. Recently, artificial intelligence (AI) technologies, especially graph convolutional networks (GCNs), have been developed to tackle this challenge. However, as the number of GCN layers increases, models may lose critical information due to excessive smoothing. Moreover, these methods often lack interpretability and are dependent on specific datasets, which limits their generalizability. Consequently, this study introduces a novel method, KRN-DTI, which employs interpretable GCN technology to predict DTIs based on a drug-target heterogeneous network. The method uses GCN technology to identify potential DTIs by leveraging known interactions and dynamically adjusting the weights, thereby enhancing the model's interpretability. Additionally, residual connection technology is employed to integrate GNN outputs, mitigating the over-smoothing issue. Furthermore, the model's interpretability is enhanced by adaptively adjusting weights using Kolmogorov-Arnold Networks (KAN) and attention mechanisms. Experimental results show that KRN-DTI outperforms several advanced computational methods on the benchmark dataset. Case studies further highlight the effectiveness of KRN-DTI in predicting potential DTIs, showcasing its potential for real-world applications in drug discovery. Our code and data are publicly accessible at: https://github.com/lizhen5000/KRN-DTI.git.

We present a shared industry-academic perspective on the principles and opportunities for Quality by Digital Design (QbDD) as a framework to accelerate medicines development and enable regulatory innovation for new medicines approvals. This approach exploits emerging capabilities in industrial digital technologies to achieve robust control strategies assuring product quality and patient safety whilst reducing development time/costs, improving research and development efficiency, embedding sustainability into new products and processes, and promoting supply chain resilience. Key QbDD drivers include the opportunity for new scientific understanding and advanced simulation and model-driven, automated experimental approaches. QbDD accelerates the identification and exploration of more robust design spaces. Opportunities to optimise multiple objectives emerge in route selection, manufacturability and sustainability whilst assuring product quality. Challenges to QbDD adoption include siloed data and information sources across development stages, gaps in predictive capabilities, and the current extensive reliance on empirical knowledge and judgement. These challenges can be addressed via QbDD workflows; model-driven experimental design to collect and structure findable, accessible, interoperable and reusable (FAIR) data; and chemistry, manufacturing and control ontologies for shareable and reusable knowledge. Additionally, improved product, process, and performance predictive tools must be developed and exploited to provide a holistic end-to-end development approach.

When applying machine learning (ML) approaches for the prediction of bioactivity, it is common to collect data from different assays or sources and combine them into single data sets. However, depending on the data domains and sources from which these data are retrieved, bioactivity data for the same macromolecular target may show a high variance of values (looking at a single compound) and cover very different parts of the chemical space as well as the bioactivity range (looking at the whole data set). The effectiveness and applicability domain of the resulting prediction models may be strongly influenced by the sources from which their training data were retrieved. Therefore, we investigated the chemical space and active/inactive distribution of proprietary pharmaceutical data from Bayer AG and the publicly available ChEMBL database, and their impact when applied as training data for classification models. For this end, we applied two different sets of descriptors in combination with different ML algorithms. The results show substantial differences in chemical space between the two different data sources, leading to suboptimal prediction performance when models are applied to domains other than their training data. MCC values between -0.34 and 0.37 among all targets were retrieved, indicating suboptimal model performance when models trained on Bayer AG data were tested on ChEMBL data and vice versa. The mean Tanimoto similarity of the nearest neighbors between these two data sources indicated similarities for 31 targets equal to or less than 0.3. Interestingly, all applied methods to assess overlap of chemical space of the two data sources to predict the applicability of models beyond their training data sets did not correlate with observed performances. Finally, we applied different strategies for creating mixed training data sets based on both public and proprietary sources, using assay format (cell-based and cell-free) information and Tanimoto similarities.

Although cancer chemopreventive agents have been confirmed to effectively protect high-risk populations from cancer invasion or recurrence, only over ten drugs have been approved by the U.S. Food and Drug Administration. Therefore, screening potent cancer chemopreventive agents is crucial to reduce the constantly increasing incidence and mortality rate of cancer. Considering the lengthy prevention process, an ideal chemopreventive agent should be nontoxic, inexpensive, and oral. Natural compounds have become a natural treasure reservoir for cancer chemoprevention because of their superior ease of availability, cost-effectiveness, and safety. The benefits of natural compounds as chemopreventive agents in cancer prevention have been confirmed in various studies. In light of this, the present review is intended to fully delineate the entire scope of cancer chemoprevention, and primarily focuses on various aspects of cancer chemoprevention based on natural compounds, specifically focusing on the mechanism of action of natural compounds in cancer prevention, and discussing in detail how they exert cancer prevention effects by affecting classical signaling pathways, immune checkpoints, and gut microbiome. We also introduce novel cancer chemoprevention strategies and summarize the role of natural compounds in improving chemotherapy regimens. Furthermore, we describe strategies for discovering anticancer compounds with low abundance and high activity, revealing the broad prospects of natural compounds in drug discovery for cancer chemoprevention. Moreover, we associate cancer chemoprevention with precision medicine, and discuss the challenges encountered in cancer chemoprevention. Finally, we emphasize the transformative potential of natural compounds in advancing the field of cancer chemoprevention and their ability to introduce more effective and less toxic preventive options for oncology.

Poly (ADP-ribose) polymerase-1 (PARP-1) is a key enzyme in the base excision repair pathway, crucial for maintaining genomic stability by repairing DNA breaks. In cancers with mutations in DNA repair genes, such as BRCA1 and BRCA2, PARP-1 activity becomes essential for tumor cell survival, making it a promising target for therapeutic intervention. This study employs QSAR modeling, virtual screening, and molecular dynamics (MD) simulations to identify potential PARP-1 inhibitors. A dataset of inhibitors was analyzed using 12 molecular fingerprint descriptors to develop robust QSAR models, with the optimal model based on the CDK descriptor achieving R2 = 0.96, Q2_CV = 0.78, and Q2_Ext = 0.80. The model was applied to virtually screen three chemical libraries-ZINC, FDA, and NPA-identifying promising candidates for PARP-1 inhibition. Molecular docking revealed that compounds ZINC13132446, Z2037280227, and NPC193377 have strong binding affinity for the PARP-1 active site. MD simulations and MM-PBSA confirmed the stability of these complexes, with Z2037280227 and NPC193377 exhibiting the most stable interactions. These results underscore the potential of targeting PARP-1 as a therapeutic strategy for cancers with homologous recombination deficiencies, including prostate, breast, and ovarian cancer, particularly in patients with DNA repair deficiencies.

Prostate cancer (PC) is one of the most common types of malignancies in men, with a noteworthy increase in newly diagnosed cases in recent years. PARP1 is a ubiquitous nuclear enzyme involved in DNA repair, nuclear transport, ribosome synthesis, and epigenetic bookmarking. In this study, a library of 9000 phytochemicals was screened, with a focus on those with high drug efficacy and potential PARP1 inhibition. Different machine learning models were generated and assessed using various statistical measures. The RF model outperformed all other models in terms of accuracy (0.9489), specificity (0.9171), and area under the curve (AUC = 0.9846). Following this, a library of 9510 phytochemicals was screened, yielding 181 compounds predicted to be active. These compounds were subsequently assessed using Lipinski's Rule of Five, yielding 40 interesting candidates. Molecular docking experiments demonstrated that compound ZINC2356684563, ZINC2356558598, and ZINC14584870, had strong affinity for the PARP1 active site. Further molecular dynamics simulations and MM-PBSA validated the stability of the ligand-protein complexes, with ZINC14584870 and ZINC43120769 demonstrating the most stable interaction, as seen by low RMSD and RMSF levels. Our findings emphasize the potential of these phytochemical inhibitors as novel therapeutic agents against PARP1 in prostate cancer treatment, paving the path for further experimental validation and clinical investigations. These results open new possibilities for developing treatments to benefit prostate cancer patients.

Accurate prediction of new compounds' pharmacokinetic (PK) profile in humans is crucial for drug discovery. Traditional methods, including allometric scaling and mechanistic modeling, rely on parameters from in vitro or in vivo testing, which are labor-intensive and involve ethical concerns. This study leverages machine learning (ML) to overcome these limitations by developing data-driven models. We compiled a large data set of small molecules' physicochemical and PK properties from public sources and digitized human plasma concentration-time profiles for approximately 800 compounds from the literature. We introduced a hybrid modeling framework that combines ML with physiologically based pharmacokinetic modeling and a hierarchical ML framework that employs two steps of learning to directly estimate PK profiles. Tested on 106 drugs, these frameworks demonstrated prediction accuracies within a 2-fold and 5-fold error for 40-60% and 80%-90% of compounds, respectively, in both AUC and Cmax. Proposed approaches could enhance early molecular screening and design, advancing drug discovery capabilities.

Despite progress, small-molecule drug discovery remains slow and costly. A paradigm shift is underway by leveraging artificial intelligence (AI) and machine learning (ML); however, these technological advances are necessary but not sufficient. Performance indicators from our partnered portfolio include timelines for data turnaround (5-day) and candidate delivery (2.9 versus 4.0 years for industry). Together with optimised processes and effective decision-making, improved translational predictivity is required. Progressing more compounds through downstream in vitro and in vivo models will rapidly reveal translational thresholds or crucial blockers for compound progression, with humans and machines actively learning from such data. We advocate for more experience-led risk-taking and a mindset shift toward an Every Compound a Candidate strategy, which aims to deliver drug candidates in <2 years.

Cell-penetrating peptides (CPP) have gained rapid attention over the last 25 years; this is attributed to their versatility, customisation, and 'Trojan horse' delivery that evades the immune system. However, the current CPP rational design process is limited, as it requires several rounds of peptide synthesis, prediction and wet-lab validation, which is expensive, time-consuming and requires extensive knowledge in peptide chemistry. Artificial intelligence (AI) has emerged as a promising alternative which can augment the design process, for example by determining physiochemical characteristics, secondary structure, solvent accessibility, disorder and flexibility, as well as predicting in vivo behaviour such as toxicity and peptidase degradation. Other more recent tools utilise supervised machine learning (ML) to predict the penetrative ability of an amino acid sequence. The use of AI in the CPP design process has the potential to reduce development costs and increase the chances of success with respect to delivery. This review provides a survey of in silico tools and AI platforms which can be utilised in the design process, and the key features that should be taken into consideration when designing next generation CPPs.

Prostate cancer is one of the major health challenges in the world and needs novel therapeutic approaches to overcome the limitations of conventional treatment. This review delineates the transformative potential of artificial intelligence (AL) in enhancing nanocarrier-based drug delivery systems for prostate cancer therapy. With its ability to optimize nanocarrier design and predict drug delivery kinetics, AI has revolutionized personalized treatment planning in oncology. We discuss how AI can be integrated with nanotechnology to address challenges related to tumor heterogeneity, drug resistance, and systemic toxicity. Emphasis is placed on strong AI-driven advancements in the design of nanocarriers, structural optimization, targeting of ligands, and pharmacokinetics. We also give an overview of how AI can better predict toxicity, reduce costs, and enable personalized medicine. While challenges persist in the way of data accessibility, regulatory hurdles, and interactions with the immune system, future directions based on explainable AI (XAI) models, integration of multimodal data, and green nanocarrier designs promise to move the field forward. Convergence between AI and nanotechnology has been one key step toward safer, more effective, and patient-tailored cancer therapy.

Antibodies play a crucial role in defending the human body against diseases, including life-threatening conditions like cancer. They mediate immune responses against foreign antigens and, in some cases, self-antigens. Over time, antibody-based technologies have evolved from monoclonal antibodies (mAbs) to chimeric antigen receptor T cells (CAR-T cells), significantly impacting biotechnology, diagnostics, and therapeutics. Although these advancements have enhanced therapeutic interventions, the integration of artificial intelligence (AI) is revolutionizing antibody design and optimization. This review explores recent AI advancements, including large language models (LLMs), diffusion models, and generative AI-based applications, which have transformed antibody discovery by accelerating de novo generation, enhancing immune response precision, and optimizing therapeutic efficacy. Through advanced data analysis, AI enables the prediction and design of antibody sequences, 3D structures, complementarity-determining regions (CDRs), paratopes, epitopes, and antigen-antibody interactions. These AI-powered innovations address longstanding challenges in antibody development, significantly improving speed, specificity, and accuracy in therapeutic design. By integrating computational advancements with biomedical applications, AI is driving next-generation cancer therapies, transforming precision medicine, and enhancing patient outcomes.

Fervent attention was paid to what is coined dual-use research (DUR), or research that can both benefit and harm humanity, and dual-use research of concern (DURC), a particular subset of DUR that is reasonably anticipated to be a safety and security concern if misapplied. The aim of this paper is not to reiterate the challenges of DURC governance but to look at a new turn in DURC, namely the challenges posed by the use of artificial intelligence (AI) in pharmaceutical development. This is important, as AI is increasingly being used for pharmaceutical development in the industry. There is growing recognition that AI is DURC, and there is a dearth of industry and governmental guidance.

This study investigates the risks of exposing confidential chemical structures when machine learning models trained on these structures are made publicly available. We use membership inference attacks, a common method to assess privacy that is largely unexplored in the context of drug discovery, to examine neural networks for molecular property prediction in a black-box setting. Our results reveal significant privacy risks across all evaluated datasets and neural network architectures. Combining multiple attacks increases these risks. Molecules from minority classes, often the most valuable in drug discovery, are particularly vulnerable. We also found that representing molecules as graphs and using message-passing neural networks may mitigate these risks. We provide a framework to assess privacy risks of classification models and molecular representations, available at https://github.com/FabianKruger/molprivacy . Our findings highlight the need for careful consideration when sharing neural networks trained on proprietary chemical structures, informing organisations and researchers about the trade-offs between data confidentiality and model openness.

This work presents the assembly of 48 papers, representing 74 different compounds and blends, into a machine-readable database of nonaqueous proton-conducting materials. SMILES was used to encode the chemical structures of the molecules, and we tabulated the reported proton conductivity, proton diffusion coefficient, and material composition for a total of 3152 data points. The data spans a broad range of temperatures ranging from -70 to 260 °C. To explore this landscape of nonaqueous proton conductors, DFT was used to calculate the proton affinity of 18 unique proton carriers. The results were then compared to the activation energy derived from fitting experimental data to the Arrhenius equation. It was found that while the widely recognized positive correlation between the activation energy and proton affinity may hold among closely related molecules, this correlation does not necessarily apply across a broader range of molecules. This work serves as an example of the potential analyses that can be conducted using literature data combined with emerging research tools in computation and data science to address specific materials design problems.

Automation has been a transformative force for many industries, including manufacturing and chemistry. While the term traditionally referred to mechanical operations to produce physical objects, the definition has since expanded: 1) it can now mean both physical and/or information automation; and 2) it can now produce physical and/or conceptual outputs. While automation has yet to fully revolutionize life science research, much of which still relies on manual processes, we show that biology automation is the ultimate mixture of the concepts listed above - it involves automation of physical and data processing, and production of physical samples as well as conceptual data outputs. Here, we explore the history of automation and what it can - and cannot - teach us about the future of automated life science experimentation. We examine the current state of automated biology, its major successes, and the remaining barriers to wider adoption. Unlike in other fields, however, automation is reaching broader integration in life science at a time when both biology and AI are reaching their adolescence. At The Align Foundation, we are anticipating this change and hoping to leverage this inflection as a way to accelerate and democratize research. We anticipate that this novel combination of automation, AI, and life science learning will impact the trajectory of biological research, including the design and execution of high-throughput experiments and the analysis of resulting large-scale data.

Machine learning (ML) has become an important tool for predicting the pharmaceutical properties of small molecules. Recent advancements in ML algorithms enable the rapid and accurate evaluation of solubility, activity, toxicity, pharmacokinetics, and other molecular properties through ML-based models. By conducting virtual screening of drug targets and elucidating drug-target protein interactions, researchers can conduct preliminary evaluations of the activity and safety of compounds from the ultra-large drug compound libraries, thereby accelerating the screening process for lead compounds. Moreover, ML leverages existing experimental data to train and generate new datasets, addressing the challenge of limited compounds and protein target data. This review provided a concise overview of ML applications in predicting small molecule properties, focusing on model construction principles, molecular feature selection, and other essential aspects. It also discussed the potential applications of ML in the screening of pharmaceutical small molecules.

Insecticidal molecules with high activity are crucial for global pesticide reduction and food security. However, their usage is limited by their concomitant high toxicity to bees. Balancing insecticidal activity and bee toxicity remains a critical challenge in the exploitation of new insecticidal molecules. In this study, we propose a novel strategy for exploiting molecules that are both highly effective against pests and minimally harmful to bees. A series of molecules were synthesized and tested to train a machine learning (ML) model for predicting insecticidal activity against pests. Meanwhile, another ML model was trained by using publicly available data to predict bee toxicity. The models demonstrated good performance, with mean AUC values of 0.88 ± 0.05 for insecticidal activity and 0.91 ± 0.01 for bee toxicity. By integrating these two models, we successfully predicted and experimentally validated a molecule that exhibited a high insecticidal activity and low bee toxicity. This dual-ML-model approach offers a promising pathway for the development of insecticidal molecules that are both effective and environmentally safe, thereby contributing to sustainable agricultures.

The drug development process is a critical challenge in the pharmaceutical industry due to its time-consuming nature and the need to discover new drug potentials to address various ailments. The initial step in drug development, drug target identification, often consumes considerable time. While valid, traditional methods such as in vivo and in vitro approaches are limited in their ability to analyze vast amounts of data efficiently, leading to wasteful outcomes. To expedite and streamline drug development, an increasing reliance on computer-aided drug design (CADD) approaches has merged. These sophisticated in silico methods offer a promising avenue for efficiently identifying viable drug candidates, thus providing pharmaceutical firms with significant opportunities to uncover new prospective drug targets. The main goal of this work is to review in silico methods used in the drug development process with a focus on identifying therapeutic targets linked to specific diseases at the genetic or protein level. This article thoroughly discusses A-to-Z in silico techniques, which are essential for identifying the targets of bioactive compounds and their potential therapeutic effects. This review intends to improve drug discovery processes by illuminating the state of these cutting-edge approaches, thereby maximizing the effectiveness and duration of clinical trials for novel drug target investigation.

The rediscovery of known drug classes represents a major challenge in natural products drug discovery. Compound rediscovery inhibits the ability of researchers to explore novel natural products and wastes significant amounts of time and resources. This study introduces a novel machine learning framework that can effectively characterize the bioactivity of natural products by leveraging liquid chromatography tandem mass spectrometry and untargeted metabolomics analysis. This accelerates natural product drug discovery by addressing the challenge of dereplicating previously discovered bioactive compounds. Utilizing the SIRIUS 5 metabolomics software suite and in-silico-generated fragmentation spectra, we have trained a ML model capable of predicting a compound's drug class. This approach enables the rapid identification of bioactive scaffolds from LC-MS/MS data, even without reference experimental spectra. The model was trained on a diverse set of molecular fingerprints generated by SIRIUS 5 to effectively classify compounds based on their core pharmacophores. Our model robustly classified 21 diverse bioactive drug classes, achieving accuracies greater than 93% on experimental spectra. This study underscores the potential of ML combined with MFPs to dereplicate bioactive natural products based on pharmacophore, streamlining the discovery process and expediting improved methods of isolating novel antibacterial and antifungal agents.

Anthrax, caused by the bacterium Bacillus anthracis, stands as a formidable threat with both natural and bioterrorism-related implications. Its ability to afflict a wide range of hosts, including humans and animals, coupled with its potential use as a bioweapon, underscores the critical importance of understanding and advancing our capabilities to combat this infectious disease. In this context, exploring futuristic approaches becomes imperative, as they hold the promise of not only addressing current challenges but also ushering in a new era in anthrax management. This review delves into strategies to mitigate the impact of anthrax on global health and security, envisioning a future where our arsenal against anthrax is characterized by precision and adaptability.

This article highlights the significant potential of anthrax as a bioweapon, while also highlighting current knowledge and strategies developed against this deadly pathogen. We have performed an extensive research and literature review in concordance with the criteria outlined by the Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. A search strategy was conducted by using numerous keywords on various academic databases, yielding an initial set of 546 records along with 80 supplementary articles. The search included research papers, review papers, perspectives, clinical guidelines, and scientific blogs. The primary and secondary screening of the articles were conducted by 2 independent reviewers along with a third reviewer mitigating any discrepancies and biases encountered during the process. A set of inclusion and exclusion criteria were formulated, and a PICO framework was adapted based on which multiple records were analyzed and considered for the review.

In total, 53 articles were selected after completing a comprehensive systematic literature review. This review proposes novel approaches and scientific analysis of the complexities surrounding anthrax in the context of bioterrorism, highlighting the emerging technologies and strategies employed for bioterrorism mitigation.

The upcoming advancements in anthrax research will be based on cutting-edge technologies and innovative approaches that demonstrate great potential for prevention, detection, and treatment. These advancements may include the incorporation of synthetic biology techniques such as precise manipulation of biological components, nanoscale diagnostics, and Clustered regularly interspaced short palindromic repeats-based technologies, which could revolutionize our ability to combat anthrax on a molecular level. As these progressive methodologies continue to evolve, the integration of these technologies has the potential to redefine our strategies against anthrax, providing more accurate, personalized, and adaptable approaches to address the challenges posed by this infectious threat.

Machine learning is quickly becoming integral to drug discovery pipelines, particularly quantitative structure-activity relationship (QSAR) and absorption, distribution, metabolism, and excretion (ADME) tasks. Graph Convolutional Network (GCN) models have proven especially promising due to their inherent ability to model molecular structures using graph-based representations. However, maximizing the potential of such models in practice is challenging, as companies prioritize data privacy and security over collaboration initiatives to improve model performance and robustness. kMoL is an open-source machine learning library with integrated federated learning capabilities developed to address such challenges. Its key features include state-of-the-art model architectures, Bayesian optimization, explainability, and federated learning mechanisms. It demonstrates extensive customization possibilities, advanced security features, straightforward implementation of user-specific models, and high adaptability to custom datasets without additional programming requirements. kMoL is evaluated through locally trained benchmark settings and distributed federated learning experiments using various datasets to assess the features and flexibility of the library, as well as the ability to facilitate fast and practical experimentation. Additionally, results of these experiments provide further insights into the performance trade-offs associated with federated learning strategies, presenting valuable guidance for deploying machine learning models in a privacy-preserving manner within drug discovery pipelines. kMoL is available on GitHub at https://github.com/elix-tech/kmol .Scientific contribution The primary scientific contribution of this research project is the introduction and evaluation of kMoL, an open-source machine learning library with integrated federated learning capabilities. By demonstrating advanced customization and security capabilities without additional programming requirements, kMoL represents an accessible yet secure open-source platform for collaborative drug discovery projects. Additionally, the experiment results provide further insights into the performance trade-offs associated with federated learning strategies, presenting valuable guidance for deploying machine learning models in a privacy-preserving manner within drug discovery pipelines.

Artificial Intelligence (AI) has revolutionized drug discovery by enhancing data collection, integration, and predictive modeling across various critical stages. It aggregates vast biological and chemical data, including genomic information, protein structures, and chemical interactions with biological targets. Machine learning techniques and QSAR models are applied by AI to predict compound behaviors and predict potential drug candidates. Docking simulations predict drug-protein interactions, while virtual screening eliminates large chemical databases through efficient sifting. Similarly, AI supports de novo drug design by generating novel molecules, optimized against a particular biological target, using generative models such as generative adversarial network (GAN), always finding lead compounds with the most desirable pharmacological properties. AI used in clinical trials improves efficiency by pinpointing responsive patient cohorts leveraging genetic profiles and biomarkers and maintaining propriety such as dataset diversity and compliance with regulations. This chapter aimed to summarize and analyze the mechanism of AI to accelerate drug discovery by streamlining different processes that enable informed decisions and bring potential life-saving therapies to market faster, amounting to a breakthrough in pharmaceutical research and development.

Therapeutic strategies for Alzheimer's disease (AD) often involve inhibiting acetylcholinesterase (AChE), underscoring the need for novel inhibitors with high selectivity and minimal side effects. A detailed analysis of the protein-ligand pharmacophore dynamics can facilitate this. In this study, we developed and employed dyphAI, an innovative approach integrating machine learning models, ligand-based pharmacophore models, and complex-based pharmacophore models into a pharmacophore model ensemble. This ensemble captures key protein-ligand interactions, including π-cation interactions with Trp-86 and several π-π interactions with residues Tyr-341, Tyr-337, Tyr-124, and Tyr-72. The protocol identified 18 novel molecules from the ZINC database with binding energy values ranging from -62 to -115 kJ/mol, suggesting their strong potential as AChE inhibitors. To further validate the predictions, nine molecules were acquired and tested for their inhibitory activity against human AChE. Experimental results revealed that molecules, 4 (P-1894047), with its complex multi-ring structure and numerous hydrogen bond acceptors, and 7 (P-2652815), characterized by a flexible, polar framework with ten hydrogen bond donors and acceptors, exhibited IC₅₀ values lower than or equal to that of the control (galantamine), indicating potent inhibitory activity. Similarly, molecules 5 (P-1205609), 6 (P-1206762), 8 (P-2026435), and 9 (P-533735) also demonstrated strong inhibition. In contrast, molecule 3 (P-617769798) showed a higher IC50 value, and molecules 1 (P-14421887) and 2 (P-25746649) yielded inconsistent results, likely due to solubility issues in the experimental setup. These findings underscore the value of integrating computational predictions with experimental validation, enhancing the reliability of virtual screening in the discovery of potent enzyme inhibitors.

Transdermal drug delivery systems (TDDS) offer an alternative to conventional oral and injectable drug administration by bypassing the gastrointestinal tract and liver metabolism, improving bioavailability, and minimizing systemic side effects. However, widespread adoption of TDDS is limited by challenges such as the skin's permeability barrier, particularly the stratum corneum, and the need for optimized formulations. Factors like skin type, hydration levels, and age further complicate the development of universally effective solutions. Advances in artificial intelligence (AI) address these challenges through predictive modeling and personalized medicine approaches. Machine learning models trained on extensive molecular datasets predict skin permeability and accelerate the selection of suitable drug candidates. AI-driven algorithms optimize formulations, including penetration enhancers and advanced delivery technologies like microneedles and liposomes, while ensuring safety and efficacy. Personalized TDDS design tailors drug delivery to individual patient profiles, enhancing therapeutic precision. Innovative systems, such as sensor-integrated patches, dynamically adjust drug release based on real-time feedback, ensuring optimal outcomes. AI also streamlines the pharmaceutical process, from disease diagnosis to the prediction of drug distribution in skin layers, enabling efficient formulation development. This review highlights AI's transformative role in TDDS, including applications of models such as Deep Neural Networks (DNN), Artificial Neural Networks (ANN), BioSIM, COMSOL, K-Nearest Neighbors (KNN), and Set Covering Machine (SVM). These technologies revolutionize TDDS for both skin and non-skin diseases, demonstrating AI's potential to overcome existing barriers and improve patient care through innovative drug delivery solutions.

The medical community has grappled with the challenge of analysis and early detection of severe and unknown adverse drug reactions (ADRs) from Spontaneous Reporting Systems (SRSs) like the FDA Adverse Event Reporting System (FAERS), which often lack professional verification and have inherent uncertainties. These limitations have exacerbated the difficulty of training a robust machine-learning model for detecting ADR signals from SRSs. A solution is to use some authoritative knowledge bases of ADRs, such as SIDER and BioSNAP, which contain limited confirmed ADR relationships (positive), resulting in a relatively small training set compared to the substantial amount of unknown data (unlabeled). This paper proposes a novel ADR signal detection method, ADR-DQPU, to alleviate the issues above by integrating deep reinforcement Q-learning and positive-unlabeled learning. Upon validation using FAERS data, our model outperformed six traditional methods, exhibiting an overall accuracy improvement of 26.45%, an average accuracy improvement of 52.15%, a precision enhancement of 1.89%, a recall improvement of 18.57%, and an F1 score improvement of 10.95%. In comparison to two state-of-the-art machine learning methods, our approach demonstrated an overall accuracy improvement of 64.1%, an average accuracy improvement of 28.23%, a slight decrease of 1.91% in precision, a recall improvement of 55.56%, and an F1 score improvement of 45.53%.

Parkinson's disease (PD) is one of the most incapacitating neurodegenerative diseases (NDDs). PD is the second most common NDD worldwide which affects approximately 1-2 percent of people over 65 years. It is an attractive pursuit for artificial intelligence (AI) to contribute to and evolve PD treatments through drug repositioning by repurposing existing drugs, shelved drugs, or even candidates that do not meet the criteria for clinical trials. A search was conducted in three databases Web of Science, Scopus, and PubMed. We reviewed the data related to the last years (1975-present) to identify those drugs currently being proposed for repositioning in PD. Moreover, we reviewed the present status of the computational approach, including AI/Machine Learning (AI/ML)-powered pharmaceutical discovery efforts and their implementation in PD treatment. It was found that the number of drug repositioning studies for PD has increased recently. Repositioning of drugs in PD is taking off, and scientific communities are increasingly interested in communicating its results and finding effective treatment alternatives for PD. A better chance of success in PD drug discovery has been made possible due to AI/ML algorithm advancements. In addition to the experimentation stage of drug discovery, it is also important to leverage AI in the planning stage of clinical trials to make them more effective. New AI-based models or solutions that increase the success rate of drug development are greatly needed.

Cyclotides are a class of plant-derived cyclic peptides having a distinctive structure with a cyclic cystine knot (CCK) motif. They are stable molecules that naturally play a role in plant defense. Till date, more than 750 cyclotides have been reported among diverse plant taxa belonging to Cucurbitaceae, Violaceae, Rubiaceae, Solanaceae, and Fabaceae. These native cyclotides exhibit several bioactivities, such as anti-bacterial, anti-HIV, anti-fungal, pesticidal, cytotoxic, and hemolytic activities which have immense significance in agriculture and therapeutics. The general mode of action of cyclotides is related to their structure, where their hydrophobic face penetrates the cell membrane and disrupts it to exhibit anti-microbial, cytotoxic, or hemolytic activities. Thus, the structure-activity relationship is of significance in cyclotides. Further, owing to their, small size, stability, and potential to interact and cross the membrane barrier of cells, they make promising choices for developing peptide-based biologics. However, challenges, such as production complexity, pharmacokinetic limitations, and off-target effects hinder their development. Advancements in cyclotide engineering, such as peptide grafting, ligand conjugation, and nanocarrier integration, heterologous production along with computational design optimization, can help overcome these challenges. Given the potential of these cyclic peptides, the present review focuses on the diversity, bioactivities, and structure-activity relationships of cyclotides, and advancements in cyclotides engineering emphasizing their unique attributes for diverse medical and biotechnological applications.

Alzheimer's disease (AD) is one of the most prevalent neurodegenerative diseases. Given the multifactorial pathophysiology of AD, monotargeted agents can only alleviate symptoms but not cure AD. Acetylcholinesterase (AChE) and Monoamine oxidase B (MAO-B) are two key targets in the treatment of AD, molecules that inhibiting both targets are considered promising avenue to develop more effective AD therapies. In the present work, a dual inhibition dataset containing 449 molecules was established, based on which five machine learning algorithms (KNN, SVM, RF, GBDT, and LGBM) four fingerprints (MACCS, ECFP4, RDKitFP, PubChemFP) and DRAGON descriptors were combined to develop 25 classification models in which GBDT paired with ECFP4 and RF paired with PubchemFP achieved the same best performance across multiple metrics (Accuracy = 0.92, F1 Score = 0.94, MCC = 0.81). Moreover, based on the curated bioactivity datasets of AChE and MAO-B, regression models were developed to predict pIC50 values. For the AChE inhibition task, GBDT demonstrated the best performance (RMSE = 0.683, MAE = 0.500, R2 = 0.721). The SVM algorithm emerged as the most effective for MAO-B inhibition (RMSE = 0.668, MAE = 0.507, R2 = 0.675). The SHAP algorithm was used to interpret the optimal models, identifying and analyzing the key substructures and properties for both dual-target and single-target inhibitors. Moreover, molecules docking process provided potential mechanism and Structure-Activity Relationships (SAR) of dual-target inhibition further.

Translational research serves as the bridge between basic research and practical applications in clinical settings. The journey from "bench to bedside" is fraught with challenges and complexities such as the often-observed disparity between how compounds behave in a laboratory setting versus in the complex systems of living organisms. The challenge is further compounded by the limited ability of in vitro models to mimic the specific biochemical environment of human tissues. This article explores and details the recent advancements and innovative approaches that are increasingly successful in bridging the gap between laboratory research and patient care. These advancements include, but are not limited to, sophisticated in vitro models such as organ-on-a-chip and computational models that utilize artificial intelligence to predict drug efficacy and safety. The article aims to showcase how these technologies improve the predictability of drug performance in human bodies and significantly speed up the drug development process. Furthermore, it discusses the role of biomarker discovery in preparation of more targeted and personalized therapy approaches and covers the impact of regulatory changes designed to facilitate drug approvals. Additionally, by providing detailed case studies of successful applications, we illustrate the practical impacts of these innovations on drug discovery and patient care.

Machine learning has been pervasively touching many fields of science. Chemistry and materials science are no exception. While machine learning has been making a great impact, it is still not reaching its full potential or maturity. In this perspective, we first outline current applications across a diversity of problems in chemistry. Then, we discuss how machine learning researchers view and approach problems in the field. Finally, we provide our considerations for maximizing impact when researching machine learning for chemistry.

Explainable Artificial Intelligence (XAI) is an emerging field in AI that aims to address the opaque nature of machine learning models. Furthermore, it has been shown that XAI can be used to extract input-output relationships, making them a useful tool in chemistry to understand structure-property relationships. However, one of the main limitations of XAI methods is that they are developed for technically oriented users. We propose the XpertAI framework that integrates XAI methods with large language models (LLMs) accessing scientific literature to generate accessible natural language explanations of raw chemical data automatically. We conducted 5 case studies to evaluate the performance of XpertAI. Our results show that XpertAI combines the strengths of LLMs and XAI tools in generating specific, scientific, and interpretable explanations.

Machine learning (ML) models now play a crucial role in predicting properties essential to drug development, such as a drug's logscale acid-dissociation constant (pKa). Despite recent architectural advances, these models often generalize poorly to novel compounds due to a scarcity of ground-truth data. Further, these models lack interpretability. To this end, with deliberate molecular embeddings, atomic-resolution information is accessible in chemical structures by observing the model response to atomic perturbations of an input molecule. Here, we present BCL-XpKa, a deep neural network (DNN)-based multitask classifier for pKa prediction that encodes local atomic environments through Mol2D descriptors. BCL-XpKa outputs a discrete distribution for each molecule, which stores the pKa prediction and the model's uncertainty for that molecule. BCL-XpKa generalizes well to novel small molecules. BCL-XpKa performs competitively with modern ML pKa predictors, outperforms several models in generalization tasks, and accurately models the effects of common molecular modifications on a molecule's ionizability. We then leverage BCL-XpKa's granular descriptor set and distribution-centered output through atomic sensitivity analysis (ASA), which decomposes a molecule's predicted pKa value into its respective atomic contributions without model retraining. ASA reveals that BCL-XpKa has implicitly learned high-resolution information about molecular substructures. We further demonstrate ASA's utility in structure preparation for protein-ligand docking by identifying ionization sites in 93.2% and 87.8% of complex small molecule acids and bases. We then applied ASA with BCL-XpKa to identify and optimize the physicochemical liabilities of a recently published KRAS-degrading PROTAC.

True three-dimensional (3D) data are prevalent in domains such as molecular science or computer vision. In these data, machine learning models are often asked to identify objects subject to intrinsic flexibility. Our study introduces two datasets from molecular science to assess the classification robustness of common model/feature combinations. Molecules are flexible, and shapes alone offer intra-class heterogeneities that yield a high risk for confusions. By blocking training and test sets to reduce overlap, we establish a baseline requiring the trained models to abstract from shape. As training data coverage grows, all tested architectures perform better on unseen data with reduced overfitting. Empirically, 2D embeddings of voxelized data produced the best-performing models. Evidently, both featurization and task-appropriate model design are of continued importance, the latter point reinforced by comparisons to recent, more specialized models. Finally, we show that the shape abstraction learned from database samples extends to samples that are evolving explicitly in time.

One way to treat diabetes mellitus type II is by using α-glucosidase inhibitor, that will slow down the postprandial glucose intake. Metabolomics analysis of Artabotrys sumatranus leaf extract was used in this research to predict the active compounds as α-glucosidase inhibitors from this extract. Both multivariate statistical analysis and machine learning approaches were used to improve the confidence of the predictions. After performance comparisons with other machine learning methods, random forest was chosen to make predictive model for the activity of the extract samples. Feature importance analysis (using random feature permutation and Shapley score calculation) was used to identify the predicted active compound as the important features that influenced the activity prediction of the extract samples. The combined analysis of multivariate statistical analysis and machine learning predicted 9 active compounds, where 6 of them were identified as mangiferin, neomangiferin, norisocorydine, apigenin-7-O-galactopyranoside, lirioferine, and 15,16-dihydrotanshinone I. The activities of norisocorydine, apigenin-7-O-galactopyranoside, and lirioferine as α-glucosidase inhibitors have not yet reported before. Molecular docking simulation, both to 3A4A (α-glucosidase enzyme from Saccharomyces cerevisiae, usually used in bioassay test) and 3TOP (a part of α-glucosidase enzyme in human gut) showed strong to very strong binding of the identified predicted active compounds to both receptors, with exception of neomangiferin which only showed strong binding to 3TOP receptor. Isolation based on bioassay guided fractionation further verified the metabolomics prediction by succeeding to isolate mangiferin from the extract, which showed strong α-glucosidase activity when subjected to bioassay test. The correlation analysis also showed a possibility of 3 groups in the predicted active compounds, which might be related to the biosynthesis pathway (need further research for verification). Another result from correlation analysis was that in general the α-glucosidase inhibition activity in the extract had strong correlation to antioxidant activity, which was also reflected in the predicted active compounds. Only one predicted compound had very low positive correlation to antioxidant activity.