Discovery Process Research Articles

Drugst.One-a plug-and-play solution for online systems medicine and network-based drug repurposing.

In recent decades, the development of new drugs has become increasingly expensive and inefficient, and the molecular mechanisms of most pharmaceuticals remain poorly understood. In response, computational systems and network medicine tools have emerged to identify potential drug repurposing candidates. However, these tools often require complex installation and lack intuitive visual network mining capabilities. To tackle these challenges, we introduce Drugst.One, a platform that assists specialized computational medicine tools in becoming user-friendly, web-based utilities for drug repurposing. With just three lines of code, Drugst.One turns any systems biology software into an interactive web tool for modeling and analyzing complex protein-drug-disease networks. Demonstrating its broad adaptability, Drugst.One has been successfully integrated with 21 computational systems medicine tools. Available at https://drugst.one, Drugst.One has significant potential for streamlining the drug discovery process, allowing researchers to focus on essential aspects of pharmaceutical treatment research.

Phytochemical constituents analysis in laminaria digitata for Alzheimer’s disease: molecular docking and in-silico toxicity approach

ABSTRACT Alzheimer’s disease (AD) is a common brain disease associated with cognitive impairment and dementia. donepezil, an acetylcholinesterase (AChE) inhibitor drug as a commercial AD drug represents a non-cost-effective treatment with the toxic effects reported. As the prevalence of AD increases, the development of effective therapeutic treatments is urgently required. Laminaria digitata is a brown seaweed claimed to be able to prevent and treat neurodegenerative diseases. Therefore, this study measured and compared the binding affinity and toxicity of seven common phytoconstituents in Laminaria digitata against acetylcholinesterase (AChE) with those of donepezil using a molecular docking approach. The binding free energy values of donepezil, dieckol, eckol, fucodiphlorethol G, 7-Phloroecol, laminaran, alginic acid, and fucoidan with acetylcholinesterase (AChE) were −12.3, −13.5, −10.5, −8,7, −9.7, −8.0, −10.3, and −7.4 kcal/mol. All ligands constantly interacted with the AChE amino acid residues, namely Tyr124. Dieckol, with the strongest and most stable interaction, is classified as class IV toxicity, with an LD50 value of 866 mg/kg. It has aryl hydrocarbon receptor (AhR) and mitochondrial membrane potential (MMP) toxicity at certain doses. Theoretically, based on Lipinski’s rule, dieckol is likely to have poor absorption and permeation properties; therefore, several considerations during the drug discovery process are needed.

Insights into the computer-aided drug design and discovery based on anthraquinone scaffold for cancer treatment: A systematic review.

In the search for better anticancer drugs, computer-aided drug design (CADD) techniques play an indispensable role in facilitating the lengthy and costly drug discovery process especially when natural products are involved. Anthraquinone is one of the most widely-recognized natural products with anticancer properties. This review aimed to systematically assess and synthesize evidence on the utilization of CADD techniques centered on the anthraquinone scaffold for cancer treatment. The conduct and reporting of this review were done in accordance to the Preferred Reporting Items for Systematic Reviews and Meta-analysis (PRISMA) 2020 guideline. The protocol was registered in the "International prospective register of systematic reviews" database (PROSPERO: CRD42023432904) and also published recently. The search strategy was designed based on the combination of concept 1 "CADD or virtual screening", concept 2 "anthraquinone" and concept 3 "cancer". The search was executed in PubMed, Scopus, Web of Science and MedRxiv on 30 June 2023. Databases searching retrieved a total of 317 records. After deduplication and applying the eligibility criteria, the final review ended up with 32 articles in which 3 articles were found by citation searching. The CADD methods used in the studies were either structure-based alone (69%) or combined with ligand-based methods via parallel (9%) or sequential (22%) approaches. Molecular docking was performed in all studies, with Glide and AutoDock being the most popular commercial and public software used respectively. Protein data bank was used in most studies to retrieve the crystal structure of the targets of interest while the main ligand databases were PubChem and Zinc. The utilization of in-silico techniques has enabled a deeper dive into the structural, biological and pharmacological properties of anthraquinone derivatives, revealing their remarkable anticancer properties in an all-rounded fashion. By harnessing the power of computational tools and leveraging the natural diversity of anthraquinone compounds, researchers can expedite the development of better drugs to address the unmet medical needs in cancer treatment by improving the treatment outcome for cancer patients.

We create the Universe: artists and scientists take on the Big Bang

Between October 2021 and January 2022 an ambitious combined art and science exhibition presented a unique object-rich cosmological story at the University Library of Leuven, Belgium, as part of the Kunst Leuven KNAL! City Festival 2021 (English: BANG! Big Bang City Festival). To the Edge of Time was a transdisciplinary[1] introduction for general audiences to one of the most famous and complex developments in science, the Big Bang theory. The exhibition presented artworks and science objects as equal partners that through curatorial placement and interpretation could fluidly convey key theoretical moments, materials, philosophical perspectives and ideas. The scientific story focused on how the groundbreaking work of the Belgian priest-astronomer Georges Lemaître bridged the insights of two of the twentieth century’s other leading European scientists, German physicist Albert Einstein and the British cosmologist Stephen Hawking. Objects from their lives and archives revealed their specific ideas and processes of thinking and discovery. Artworks from leading international artists brought new material, critical and conceptual dimensions and multisensory encounters. The exhibition was the result of a curatorial collaboration between the author, British contemporary art and transdisciplinary curator Hannah Redler-Hawes, and Belgian cosmologist and former collaborator of Stephen Hawking, Professor Thomas Hertog, of KU Leuven. As guest curators, they worked with Annelies Vogels, Exhibition Coordinator of the university and Wouter Daenen of KU Leuven Libraries, and others to form a closely collaborating curatorial team. To the Edge of Time was not only the first exhibition worldwide to explore Lemaître’s work through a transdisciplinary narrative, but also to place Stephen Hawking’s work in a broader historical context. In the trans- and interdisciplinary exhibition field, where new commissions and collaborations between living artists and scientists have been increasing, it was somewhat unusual for a cosmology exhibition in its reliance on material culture, concentration on historical art and science objects and its combining of these with presentations of recent contemporary art and advanced theoretical physics concepts. These combinations helped to convey parallel movements of thought where neither the art nor the science were presented as derivative to each other, a key curatorial ambition. This practice-based paper, offering Redler-Hawes’s personal reflections, discusses how the narrative evolved to define a shared language between the contributors. It considers, through a narrated walk-through of key object-artwork ‘constellations’, how the presentation generated new insights into different methods of enquiry, knowledge acquisition and making sense of our place in the cosmos, by bringing major themes in twentieth century science into dialogue with international artists working independently and in collaboration with science during the twentieth and early twenty-first centuries.[2] Note: Where images belong to the Science Museum Group this Journal shares them under a fully open access CC-BY licence (see our Open Access statement here https://journal.sciencemuseum.ac.uk/about-the-journal/). Where the image or work belong to a third party, this is indicated in the credit in the caption and full rights belong to the indicated party.

MASMDDI: multi-layer adaptive soft-mask graph neural network for drug-drug interaction prediction.

Accurately predicting Drug-Drug Interaction (DDI) is a critical and challenging aspect of the drug discovery process, particularly in preventing adverse reactions in patients undergoing combination therapy. However, current DDI prediction methods often overlook the interaction information between chemical substructures of drugs, focusing solely on the interaction information between drugs and failing to capture sufficient chemical substructure details. To address this limitation, we introduce a novel DDI prediction method: Multi-layer Adaptive Soft Mask Graph Neural Network (MASMDDI). Specifically, we first design a multi-layer adaptive soft mask graph neural network to extract substructures from molecular graphs. Second, we employ an attention mechanism to mine substructure feature information and update latent features. In this process, to optimize the final feature representation, we decompose drug-drug interactions into pairwise interaction correlations between the core substructures of each drug. Third, we use these features to predict the interaction probabilities of DDI tuples and evaluate the model using real-world datasets. Experimental results demonstrate that the proposed model outperforms state-of-the-art methods in DDI prediction. Furthermore, MASMDDI exhibits excellent performance in predicting DDIs of unknown drugs in two tasks that are more aligned with real-world scenarios. In particular, in the transductive scenario using the DrugBank dataset, the ACC and AUROC and AUPRC scores of MASMDDI are 0.9596, 0.9903, and 0.9894, which are 2% higher than the best performing baseline.

Pilot-Study to Explore Metabolic Signature of Type 2 Diabetes: A Pipeline of Tree-Based Machine Learning and Bioinformatics Techniques for Biomarkers Discovery.

This study aims to identify unique metabolomics biomarkers associated with Type 2 Diabetes (T2D) and develop an accurate diagnostics model using tree-based machine learning (ML) algorithms integrated with bioinformatics techniques. Univariate and multivariate analyses such as fold change, a receiver operating characteristic curve (ROC), and Partial Least-Squares Discriminant Analysis (PLS-DA) were used to identify biomarker metabolites that showed significant concentration in T2D patients. Three tree-based algorithms [eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Adaptive Boosting (AdaBoost)] that demonstrated robustness in high-dimensional data analysis were used to create a diagnostic model for T2D. As a result of the biomarker discovery process validated with three different approaches, Pyruvate, D-Rhamnose, AMP, pipecolate, Tetradecenoic acid, Tetradecanoic acid, Dodecanediothioic acid, Prostaglandin E3/D3 (isobars), ADP and Hexadecenoic acid were determined as potential biomarkers for T2D. Our results showed that the XGBoost model [accuracy = 0.831, F1-score = 0.845, sensitivity = 0.882, specificity = 0.774, positive predictive value (PPV) = 0.811, negative-PV (NPV) = 0.857 and Area under the ROC curve (AUC) = 0.887] had the slight highest performance measures. ML integrated with bioinformatics techniques offers accurate and positive T2D candidate biomarker discovery. The XGBoost model can successfully distinguish T2D based on metabolites.

Hybrid Environmentally Friendly Method for RCA Concrete Quality Improvement

AbstractResearch on concrete recycling has led to the discovery of many processes for recycled concrete aggregate (RCA) treatment, each with its pros and cons on quality improvement, resource requirements, or scalability. This study aimed to propose a technique that combines two methods (mechanical grinding and acidic soaking) for mortar removal and improves the quality of RCA so as to realize a zero-waste, highly efficient, few-hours-long single-step process which we call acid milling. A quantitative comparison of aggregate and final concrete quality has been performed between each separate method. The proposed method shows about 57% relative improvement of aggregate quality for water absorption and density, while the concrete experiment shows up to 10% relative improvement for the compressive and flexural strengths compared with the untreated RCA concrete. This study paves the way for an efficient and sustainable concrete recycling process to be applied on a large scale.

Using a customer discovery process to enhance the potential dissemination and scalability of a family healthy weight program for rural communities and small towns

AimCustomer discovery, an entrepreneurial and iterative process to understand the context and needs of potential adoption agencies, may be an innovative strategy to improve broader dissemination of evidence-based interventions. This paper describes the customer discovery process for the Building Healthy Families (BHF) Online Training Resources and Program Package (BHF Resource Package) to support rural community adoption of an evidence-based, family healthy weight program.MethodsThe customer discovery process was completed as part of a SPeeding Research-tested INTerventions (SPRINT) training supported by the U.S. Centers for Disease Control and Prevention. Customer discovery interviews (n=47) were conducted with people that could be potential resource users, economic buyers, and BHF adoption influencers to capture multiple contextual and needs-based factors related to adopting new evidence-based interventions. Qualitative analyses were completed in an iterative fashion as each interview was completed.ResultsThe BHF Resource Package was designed to be accessible to a variety of implementation organizations. However, due to different resources being available in different rural communities, customer discovery interviews suggested that focusing on rural health departments may be a consistent setting for intervention adoption. We found that local health departments prioritize childhood obesity but lacked the training and resources necessary to implement effective programming. Several intervention funding approaches were also identified including (1) program grants from local and national foundations, (2) healthcare community benefit initiatives, and (3) regional employer groups. Payment plans recommended in the customer discovery interviews included a mix of licensing and technical support fees for BHF delivery organizations, potential insurance reimbursement, and family fees based on ability to pay. Marketing a range of BHF non-weight related outcomes was also recommended during the customer discovery process to increase the likelihood of BHF scale-up and sustainability.ConclusionsEngaging in customer discovery provided practical directions for the potential adoption, implementation, and sustainability of the BHF Resource Package. However, the inconsistent finding that health departments are both the ideal implementation organization, but also see childhood obesity treatment as a clinical service, is concerning.

Direct sub-atmospheric pressure ionization mass spectrometry: Evaporation/sublimation-driven ionization is amazing, fundamentally, and practically.

This paper covers direct sub-atmospheric pressure ionization mass spectrometry (MS). The discovery, applications, and mechanistic aspects of novel ionization processes for use in MS that are not based on the high-energy input from voltage, laser, and/or high temperature but on sublimation/evaporation within a region linking a higher to lower pressure and modulated by heat and collisions, are discussed, including how this new reality has guided a series of discoveries, instrument developments, and commercialization. A research focus, inter alia, is on how best to understand, improve, and use these novel ionization processes, which convert volatile and nonvolatile compounds from solids (sublimation) or liquids (evaporation) into gas-phase ions for analysis by MS providing reproducible, accurate, sensitive, and prompt results. Our perception on how these unprecedented versus traditional ionization processes/methods relate to each other, how they can be made to coexist on the same mass spectrometer, and an outlook on new and expanded applications (e.g., clinical, portable, fast, safe, and autonomous) is presented, and is based on ST's Opening lecture presentation at the Nordic Mass spectrometry Conference, Geilo, Norway, January 2023. Focus will be on matrix-assisted ionization (MAI) and solvent-assisted ionization (SAI) MS covering the period from 2010 to 2023; a potential paradigm shift in the making.

Book Recommendation System

In the digital age, the vast availability of books poses a significant challenge for readers to discover titles that match their interests and preferences. This report explores the use of machine learning for a Book Recommendation System (BRS) to help readers discover books suited to their interests in the digital age. It will utilize advanced algorithms and techniques, including collaborative filtering, content-based filtering, and hybrid models, to offer personalized recommendations based on users' reading history and behavior. The project aims to tackle challenges like data sparsity and the cold-start problem while ensuring scalability. Evaluation will be based on standard metrics like precision, recall, accuracy, and novelty, with a focus on ethical considerations such as fairness and user privacy. Ultimately, the goal is to develop a robust and user-centric system that enhances the book discovery process across digital platforms. A Graphical User Interface is also developed to discover information and display the recommended books. Keywords—Machine Learning, Book Recommendation System, K-Nearest Neighbor Algorithm

Emerging opportunities of using large language models for translation between drug molecules and indications

A drug molecule is a substance that changes an organism’s mental or physical state. Every approved drug has an indication, which refers to the therapeutic use of that drug for treating a particular medical condition. While the Large Language Model (LLM), a generative Artificial Intelligence (AI) technique, has recently demonstrated effectiveness in translating between molecules and their textual descriptions, there remains a gap in research regarding their application in facilitating the translation between drug molecules and indications (which describes the disease, condition or symptoms for which the drug is used), or vice versa. Addressing this challenge could greatly benefit the drug discovery process. The capability of generating a drug from a given indication would allow for the discovery of drugs targeting specific diseases or targets and ultimately provide patients with better treatments. In this paper, we first propose a new task, the translation between drug molecules and corresponding indications, and then test existing LLMs on this new task. Specifically, we consider nine variations of the T5 LLM and evaluate them on two public datasets obtained from ChEMBL and DrugBank. Our experiments show the early results of using LLMs for this task and provide a perspective on the state-of-the-art. We also emphasize the current limitations and discuss future work that has the potential to improve the performance on this task. The creation of molecules from indications, or vice versa, will allow for more efficient targeting of diseases and significantly reduce the cost of drug discovery, with the potential to revolutionize the field of drug discovery in the era of generative AI.

The dark side of drug repurposing. From clinical trial challenges to antimicrobial resistance: analysis based on three major fields

Drug repurposing is a strategic endeavor that entails the identification of novel therapeutic applications for pharmaceuticals that are already available in the market. Despite the advantageous nature of implementing this particular strategy owing to its cost-effectiveness and efficiency in reducing the time required for the drug discovery process, it is essential to bear in mind that there are various factors that must be meticulously considered and taken into account. Up to this point, there has been a noticeable absence of comprehensive analyses that shed light on the limitations of repurposing drugs. The primary aim of this review is to conduct a thorough illustration of the various challenges that arise when contemplating drug repurposing from a clinical perspective in three major fields—cardiovascular, cancer, and diabetes—and to further underscore the potential risks associated with the emergence of antimicrobial resistance (AMR) when employing repurposed antibiotics for the treatment of noninfectious and infectious diseases. The process of developing repurposed medications necessitates the application of creativity and innovation in designing the development program, as the body of evidence may differ for each specific case. In order to effectively repurpose drugs, it is crucial to consider the clinical implications and potential drawbacks that may arise during this process. By comprehensively analyzing these challenges, we can attain a deeper comprehension of the intricacies involved in drug repurposing, which will ultimately lead to the development of more efficacious and safe therapeutic approaches.

DCGAN-DTA: Predicting drug-target binding affinity with deep convolutional generative adversarial networks

BackgroundIn recent years, there has been a growing interest in utilizing computational approaches to predict drug-target binding affinity, aiming to expedite the early drug discovery process. To address the limitations of experimental methods, such as cost and time, several machine learning-based techniques have been developed. However, these methods encounter certain challenges, including the limited availability of training data, reliance on human intervention for feature selection and engineering, and a lack of validation approaches for robust evaluation in real-life applications.ResultsTo mitigate these limitations, in this study, we propose a method for drug-target binding affinity prediction based on deep convolutional generative adversarial networks. Additionally, we conducted a series of validation experiments and implemented adversarial control experiments using straw models. These experiments serve to demonstrate the robustness and efficacy of our predictive models. We conducted a comprehensive evaluation of our method by comparing it to baselines and state-of-the-art methods. Two recently updated datasets, namely the BindingDB and PDBBind, were used for this purpose. Our findings indicate that our method outperforms the alternative methods in terms of three performance measures when using warm-start data splitting settings. Moreover, when considering physiochemical-based cold-start data splitting settings, our method demonstrates superior predictive performance, particularly in terms of the concordance index.ConclusionThe results of our study affirm the practical value of our method and its superiority over alternative approaches in predicting drug-target binding affinity across multiple validation sets. This highlights the potential of our approach in accelerating drug repurposing efforts, facilitating novel drug discovery, and ultimately enhancing disease treatment. The data and source code for this study were deposited in the GitHub repository, https://github.com/mojtabaze7/DCGAN-DTA. Furthermore, the web server for our method is accessible at https://dcgan.shinyapps.io/bindingaffinity/.

Dynamic knowledge graph applications for augmented built environments through “The World Avatar”

The proliferation of digital building models in recent years has led to a corresponding rise in specialised, non-interoperable models. These models impede sustainable developments by forming data silos that hinder cross-application data exchange and knowledge discovery processes. Although Semantic Web solutions hold promise in addressing these silos, current approaches primarily focus on developing novel ontologies, yielding similar outcomes. But it is unclear how these methodologies could support broader knowledge discovery processes and application requirements. This paper addresses these research challenges by introducing a dynamic knowledge graph as implemented within The World Avatar for interoperable building models. We demonstrate its value through two distinct applications in urban energy management and laboratory automation. The dynamic knowledge graph revolves around a comprehensive structured knowledge model constructed from ontologies and agents. Ontologies semantically annotate data and represent domain knowledge and their relationships with standardised definitions. When augmented with an agent architecture, the resulting knowledge model can align stakeholder perspectives and accommodate the dynamic and scalable nature of urban data. Moreover, the dynamic knowledge graph fosters innovative human-machine interactions through visualisation interfaces to augment knowledge discovery processes in the built environment for greater efficiencies and innovation. As the knowledge model expands, users gain access to a broader spectrum of private and public data sources and technologies, while reducing integration barriers. This is especially pertinent for smaller and less influential entities like municipal and local governments with limited resources, who can realise substantial benefits at reduced costs.

Importance of Characteristic Features and Their Form for Data Exploration.

The nature of the input features is one of the key factors indicating what kind of tools, methods, or approaches can be used in a knowledge discovery process. Depending on the characteristics of the available attributes, some techniques could lead to unsatisfactory performance or even may not proceed at all without additional preprocessing steps. The types of variables and their domains affect performance. Any changes to their form can influence it as well, or even enable some learners. On the other hand, the relevance of features for a task constitutes another element with a noticeable impact on data exploration. The importance of attributes can be estimated through the application of mechanisms belonging to the feature selection and reduction area, such as rankings. In the described research framework, the data form was conditioned on relevance by the proposed procedure of gradual discretisation controlled by a ranking of attributes. Supervised and unsupervised discretisation methods were employed to the datasets from the stylometric domain and the task of binary authorship attribution. For the selected classifiers, extensive tests were performed and they indicated many cases of enhanced prediction for partially discretised datasets.

Revealing the Improved Binding Interaction of Plant Alkaloid Harmaline with Human Hemoglobin in Molecular Crowding Condition.

Harmaline and harmine are two structurally similar β-carboline alkaloids with several therapeutic activities, such as anti-inflammatory, antioxidant, neuroprotective, nephroprotective, antidiabetic, and antitumor activities. It has been previously reported that the interaction between harmaline and hemoglobin (Hb) is weak in buffer media compared to harmine. Crowding agents induce a molecular crowding environment in the ex vivo condition, which is almost similar to the intracellular environment. In this present study, we have investigated the nature of the interactions of harmaline and harmine with Hb by increasing the percentage of the crowding agent in buffer solution. The results of the UV-vis and fluorescence spectroscopy analysis have showed that with an increasing proportion of crowding agents, the interaction between harmaline and Hb is steadily improving in comparison to harmine. It has been found that the binding constant of Hb-harmaline reaches 6.82 × 105 M-1 in the 40% polyethylene glycol 200-mediated crowding condition, indicating high affinity compared to very low interaction in buffer media. Steady-state fluorescence anisotropy along with fluorescence lifetime measurements further revealed that the rotational movement of harmaline is maximally restricted by Hb in high crowding environments. Stoichiometry results represent that Hb and harmaline interacts in a 1:1 ratio in different percentages of the crowding agent. The circular dichroism spectroscopic results predict stronger interaction of harmaline with Hb (secondary structure alterations) in a higher crowding environment. From the melting study, it was found that the reactions between Hb and harmaline in crowding environments are endothermic (ΔH > 0) and disordering (ΔS > 0) in nature, indicating that hydrogen bonding and van der Waals interactions are the main interacting forces between Hb and harmaline. Harmaline molecules are more reactive in molecular crowding conditions than in normal buffer condition. This study represents that the interaction between harmaline and Hb is stronger compared to the structurally similar harmine in a molecular crowding environment, which may enlighten the drug discovery process in cell-mimicking conditions.

EnTdecker - A Machine Learning-Based Platform for Guiding Substrate Discovery in Energy Transfer Catalysis.

Due to the magnitude of chemical space, the discovery of novel substrates in energy transfer (EnT) catalysis remains a daunting task. Experimental and computational strategies to identify compounds that successfully undergo EnT-mediated reactions are limited by their time and cost efficiency. To accelerate the discovery process in EnT catalysis, we herein present the EnTdecker platform, which facilitates the large-scale virtual screening of potential substrates using machine-learning (ML) based predictions of their excited state properties. To achieve this, a data set is created containing more than 34,000 molecules aiming to cover a vast fraction of synthetically relevant compound space for EnT catalysis. Using this data predictive models are trained, and their aptitude for an in-lab application is demonstrated by rediscovering successful substrates from literature as well as experimental validation through luminescence-based screening. By reducing the computational effort needed to obtain excited state properties, the EnTdecker platform represents a tool to efficiently guide substrate selection and increase the experimental success rate for EnT catalysis. Moreover, through an easy-to-use web application, EnTdecker is made publicly accessible under entdecker.uni-muenster.de.

Molecular property prediction based on graph structure learning.

Molecular property prediction (MPP) is a fundamental but challenging task in the computer-aided drug discovery process. More and more recent works employ different graph-based models for MPP, which have achieved considerable progress in improving prediction performance. However, current models often ignore relationships between molecules, which could be also helpful for MPP. For this sake, in this article we propose a graph structure learning (GSL) based MPP approach, called GSL-MPP. Specifically, we first apply graph neural network (GNN) over molecular graphs to extract molecular representations. Then, with molecular fingerprints, we construct a molecule similarity graph (MSG). Following that, we conduct GSL on the MSG, i.e. molecule-level GSL, to get the final molecular embeddings, which are the results of fuzing both GNN encoded molecular representations and the relationships among molecules. That is, combining both intra-molecule and inter-molecule information. Finally, we use these molecular embeddings to perform MPP. Extensive experiments on 10 various benchmark datasets show that our method could achieve state-of-the-art performance in most cases, especially on classification tasks. Further visualization studies also demonstrate the good molecular representations of our method. Source code is available at https://github.com/zby961104/GSL-MPP.

Streamlining Computational Fragment-Based Drug Discovery through Evolutionary Optimization Informed by Ligand-Based Virtual Prescreening.

Recent advances in computational methods provide the promise of dramatically accelerating drug discovery. While mathematical modeling and machine learning have become vital in predicting drug-target interactions and properties, there is untapped potential in computational drug discovery due to the vast and complex chemical space. This paper builds on our recently published computational fragment-based drug discovery (FBDD) method called fragment databases from screened ligand drug discovery (FDSL-DD). FDSL-DD uses in silico screening to identify ligands from a vast library, fragmenting them while attaching specific attributes based on predicted binding affinity and interaction with the target subdomain. In this paper, we further propose a two-stage optimization method that utilizes the information from prescreening to optimize computational ligand synthesis. We hypothesize that using prescreening information for optimization shrinks the search space and focuses on promising regions, thereby improving the optimization for candidate ligands. The first optimization stage assembles these fragments into larger compounds using genetic algorithms, followed by a second stage of iterative refinement to produce compounds with enhanced bioactivity. To demonstrate broad applicability, the methodology is demonstrated on three diverse protein targets found in human solid cancers, bacterial antimicrobial resistance, and the SARS-CoV-2 virus. Combined, the proposed FDSL-DD and a two-stage optimization approach yield high-affinity ligand candidates more efficiently than other state-of-the-art computational FBDD methods. We further show that a multiobjective optimization method accounting for drug-likeness can still produce potential candidate ligands with a high binding affinity. Overall, the results demonstrate that integrating detailed chemical information with a constrained search framework can markedly optimize the initial drug discovery process, offering a more precise and efficient route to developing new therapeutics.

Exploring Scoring Function Space: Developing Computational Models for Drug Discovery.

The idea of scoring function space established a systems-level approach to address the development of models to predict the affinity of drug molecules by those interested in drug discovery. Our goal here is to review the concept of scoring function space and how to explore it to develop machine learning models to address protein-ligand binding affinity. We searched the articles available in PubMed related to the scoring function space. We also utilized crystallographic structures found in the protein data bank (PDB) to represent the protein space. The application of systems-level approaches to address receptor-drug interactions allows us to have a holistic view of the process of drug discovery. The scoring function space adds flexibility to the process since it makes it possible to see drug discovery as a relationship involving mathematical spaces. The application of the concept of scoring function space has provided us with an integrated view of drug discovery methods. This concept is useful during drug discovery, where we see the process as a computational search of the scoring function space to find an adequate model to predict receptor-drug binding affinity.