Science Analysis Research Articles

ESPressoscope: A small and powerful approach for in situ microscopy.

Microscopy is essential for detecting, identifying, analyzing, and measuring small objects. Access to modern microscopy equipment is crucial for scientific research, especially in the biomedical and analytical sciences. However, the high cost of equipment, limited availability of parts, and challenges associated with transporting equipment often limit the accessibility and operational capabilities of these tools, particularly in field sites and other remote or resource-limited settings. Thus, there is a need for affordable and accessible alternatives to traditional microscopy systems. We address this challenge by investigating the feasibility of using a simple microcontroller board not only as a portable and field-ready digital microscope, but furthermore as a versatile platform which can easily be adapted to a variety of imaging applications. By adding a few external components, we demonstrate that a low-cost ESP32 camera board can be used to build an autonomous in situ platform for digital time-lapse imaging of cells. Our prototype of this approach, which we call ESPressoscope, can be adapted to applications ranging from monitoring incubator cell cultures in the lab to observing ecological phenomena in the sea, and it can be adapted for other techniques such as microfluidics or spectrophotometry. Our prototype of the ESPressoscope concept achieves a low power consumption and small size, which makes it ideal for field research in environments and applications where microscopy was previously infeasible. Its Wi-Fi connectivity enables integration with external image processing and storage systems, including on cloud platforms when internet access is available. Finally, we present several web browser-based tools to help users operate and manage our prototype's software. Our findings demonstrate the potential for low-cost, portable microscopy solutions to enable new and more accessible experiments for biological and analytical applications.

Hydrogel Grating Sensors with Boron Affinity and Molecular Imprinting Effects for Rapid and Sensitive Detection of Tumor Marker Sialic Acid.

Rapid and sensitive detection of the concentration of sialic acid (SA) in serum is crucial for early tumor screening and prognostic assessment; however, it still remains challenging. Here, we propose a novel kind of hydrogel grating sensor with boron affinity and molecular imprinting effects (B-MIP) for the rapid and sensitive detection of SA concentration in serum. The hydrogel gratings feature uniform surface relief microstructures and incorporate highly specific recognition binding sites into SA molecules provided by boron affinity and molecular imprinting. The periodic nanoridges of hydrogel gratings increase the specific surface area contacting the environmental solution; therefore, fast detection can be achieved within 2 min. Upon recognition of SA molecules, the height of hydrogel gratings changes at the nanoscale, causing a change in the diffraction efficiency of the hydrogel gratings. The B-MIP hydrogel grating sensors have highly specific binding sites to SA molecules distributed throughout the whole hydrogel and can preferentially and selectively recognize and respond to the SA molecules even in the presence of interference substances glucose and fructose with high concentrations. The B-MIP hydrogel grating sensors are effectively applicable for the rapid and sensitive detection of SA concentrations in real serum samples with satisfactory accuracy and precision. Our approach provides an excellent strategy to address the current challenges in SA detection and provides new insights into the detection of tumor markers in serum, thereby opening up new ways to accurately detect complex biological samples in analytical science.

Fabrication of Surface-Enhanced Raman Scattering (SERS) Substrates in Analytical Science by Natural-inspired Materials: A Review

Surface-Enhanced Raman Scattering (SERS) spectroscopy, as a novel rapid detection technology, offers molecular fingerprinting capabilities that achieve trace-level detection. The key to optimizing SERS sensitivity and reliability lies in the precise control of the nanostructures of SERS substrates. Nature, through billions of years of evolution, has served as a masterful creator, developing organisms with remarkable abilities based on micro/nanostructures, such as the superhydrophobicity of lotus leaves and the strong adhesive forces of gecko feet. This review categorizes the recent developments in SERS substrates inspired by natural materials into three main types: plant-based, animal-based, and virus-based. Each category is explored in detail, describing how their unique nanoarchitectures inspire the development of highly sensitive SERS substrates, along with their fabrication methods and applications in analytical science. Additionally, the review identifies current challenges, such as the uniformity and scalability of naturally inspired SERS substrates and suggests future directions, including the integration of hybrid biomimetic structures and advanced manufacturing techniques. By fostering a deeper understanding of these nature-inspired materials, we aim to enhance the practical application of SERS in analytical science in the future.

Ultrafast metaproteomics for quantitative assessment of strain isolates and microbiomes

BackgroundMicrobial communities are essential in human health and environmental regulation, but present a challenge for the analytical science due to their diversity and dynamic range. Tandem mass spectrometry provides functional insights on microbial life cycle, but is time-consuming. MALDI TOF excels in rapid species identification, but not functional assessment. To address critical challenges in human health and environmental sustainability, microbiology needs advanced mass spectrometry methods and bioinformatic tools enabling both rapid identification and accurate assessment of functional activity of microbial communities. ResultsWe show for the first time that both identity and functional activity of microorganisms and their communities can be accurately determined in experiments as short as 7 min per sample, using the basic Orbitrap MS configuration without peptide fragmentation. The approach was validated using strain isolates, mock microbiomes composed of bacteria spiked at known concentrations and human fecal microbiomes. Our new bioinformatic algorithm identifies the bacterial species with an accuracy of 95 %, when no prior information on the sample is available. Microbiome composition was resolved at the genus level with the mean difference between the actual and identified components of 12 %. For mock microbiomes, Pearson coefficient of up to 0.97 was achieved in estimates of strain biomass change. By the example of Rhodococcus biodegradation of n-alkanes, phenols and its derivatives, we showed the accurate assessment of functional activity of strain isolates, compared with the standard label-free and label-based approaches. SignificanceOur approach makes microbial proteomics fast, functional and insightful using the Orbitrap instruments even without employing peptide fragmentation technology. The approach can be applied to any microorganisms and can take a niche in routine functional assessment of microbial pathogens and consortiums in clinical diagnostics together with MALDI TOF MS and 16S rRNA gene sequencing.

Development of deep learning software to improve HPLC and GC predictions using a new crown-ether based mesogenic stationary phase and beyond

The application of AI to analytical and separative sciences is a recent challenge that offers new perspectives in terms of data prediction. In this work, we report an AI-based software, named Chrompredict 1.0, which based on chromatographic data of a novel mesogenic crown ether stationary phase (CESP). Its molecular design represents a significant advancement due to the unique combination of properties and binding capabilities, including the formation of a cavity, mesogenic behavior via mobile chains, and a range of polar and non-polar interactions (aromatic rings, N=N and O=O double bonds, alkyl chains, π–π interactions, and hydrogen bonding). The mesogenic phase is effective in both normal and reversed-phase chromatography, enhancing the software's adaptability across diverse datasets.Here we introduce for the first time an unprecedented scientific approach, integrating deep learning techniques with the novel CESP, which demonstrates exceptional thermal and analytical performance in both liquid chromatography modes, especially in the separation of complex hydrocarbon isomers. This ability enables the results obtained with CESP to extend across various types of stationary phases.Leveraging these insights, a comprehensive chromatographic dataset on a series of aromatic and polyaromatic molecules interacting with our CESP was used to train a Deep Learning Model (DLM). This model is embedded within a user-friendly software, Chrompredict 1.0, designed for predicting chromatographic parameters (MAE = 0.042, R² = 0.95) by selecting chemical descriptors directly from SMILES notation. It offers a deeper understanding of molecular structure and interactions through exploratory data analysis, identifying key factors affecting model accuracy and chromatographic behavior.Users can configure hyperparameters, choose from six machine learning models, and compare their performance with DLM. Chrompredict 1.0 excels in retention behavior prediction for compounds with known structures, and it accurately predicts chromatographic retention and thermal characteristics for different temperatures in HPLC and GC. The model has been successfully tested with METLIN database of 1,023 small molecules of diverse structures and polarities (R² > 0.75, error range ±7.8 s). Overall, the CESP, combined with Chrompredict 1.0, offers a robust tool for intelligent chromatographic analysis, encompassing chemo-informatics, statistical analysis, and graphical capabilities across a broad range of compounds and stationary phases.

2025 IUPAC Awards in Analytical Chemistry—Call for nominations

Abstract The Analytical Chemistry Division of IUPAC is inviting nominations for two awards, including: · The IUPAC Emerging Innovator Award in Analytical Chemistry—an award to recognize outstanding work undertaken by an emerging analytical scientist that corresponds to the aims of the Analytical Chemistry Division. · The IUPAC Analytical Chemistry Medal—an award to recognize significant lifetime contribution to the aims of the Analytical Chemistry Division.

Stochastic dynamics mass spectrometric and Fourier transform infrared spectroscopic structural analyses of composite biodegradable plastics

<p>The (partial) replacement of synthetic polymers with bioplastics is due to increased production of conventional packaging plastics causing for severe environmental pollution with plastics waste. The bioplastics, however, represent complex mixtures of known and unknown (bio)polymers, fillers, plasticizers, stabilizers, flame retardant, pigments, antioxidants, hydrophobic polymers such as poly(lactic acid), polyethylene, polyesters, glycol, or poly(butylene succinate), and little is known of their chemical safety for both the environment and the human health. Polymerization reactions of bioplastics can produce no intentionally added chemicals to the bulk material, which could be toxic, as well. When polymers are used to food packing, then the latter chemicals could also migrate from the polymer to food. This fact compromises the safety for consumers, as well. The scarce data on chemical safety of bioplastics makes a gap in knowledge of their toxicity to humans and environment. Thus, development of exact analytical protocols for determining chemicals of bioplastics in environmental and food samples as well as packing polymers can only provide warrant for reliable conclusive evidence of their safety for both the human health and the environment. The task is compulsory according to legislation Directives valid to environmental protection, food control, and assessment of the risk to human health. The quantitative and structural determination of analytes is primary research task of analysis of polymers. The methods of mass spectrometry are fruitfully used for these purposes. Methodological development of exact analytical mass spectrometric tools for reliable structural analysis of bioplastics only guarantees their safety, efficacy, and quality to both humans and environment. This study, first, highlights innovative stochastic dynamics equations processing exactly mass spectrometric measurands and, thus, producing exact analyte quantification and 3D molecular and electronic structural analyses. There are determined synthetic polymers such as poly(ethylenglycol), poly(propylene glycol), and polyisoprene as well as biopolymers in bags for foodstuffs made from renewable cellulose and starch, and containing, in total within the 20,416–17,495 chemicals per sample of the composite biopolymers. Advantages of complementary employment in mass spectrometric methods and Fourier transform infrared spectroscopy is highlighted. The study utilizes ultra-high resolution electrospray ionization mass spectrometric and Fourier transform infrared spectroscopic data on biodegradable plastics bags for foodstuffs; high accuracy quantum chemical static methods, molecular dynamics; and chemometrics. There is achieved method performance |<em>r</em>| = 0.99981 determining poly(propylene glycol) in bag for foodstuff containing 20,416 species and using stochastic dynamics mass spectrometric formulas. The results highlight their great capability and applicability to the analytical science as well as relevance to both the fundamental research and to the industry.</p>

Highlights of the 15th Japan Bioanalysis Forum Symposium.

The 15th Japan Bioanalysis Forum (JBF) Symposium was held in Kyoto, Japan, between 5 and 7 February 2024. The conference theme, 'Toward the new world - Science as a universal endeavor' indicated that universal discussion based on science is making a basis of regulatory and analytical sciences, now internationally harmonized. The symposium discussed a wide range of topics, including ICH M10, quantitative PCR, immunogenicity, peptide LC-MS, e-notebooks, artificial intelligence, reliability standards, carrier development, inviting domestic and overseas experts. Approximately 360 attendees from various fields, including pharmaceutical companies, contract research organizations, academia and regulators, gathered in person or online.

Nursing Informatics Competency among Nurses at a Teaching Hospital in Malaysia

Nursing informatics merges nursing science with information and analytical sciences to identify, describe, manage, and disseminate nursing data, information, knowledge, and wisdom. Identifying nurses’ informatics competency will help improve information technology utilisation in clinical practice. The aim of this study was to assess basic competency in nursing informatics and related factors influencing nurses working in a university teaching hospital. Thus, a cross-sectional study was conducted. A stratified random sampling of the total population of 1,136 nurses with sample size of 316 nurses participated in this study. The data was collected using a self-reported questionnaire utilising the Nursing Informatics Competency Assessment Tool (NICAT) reaching targeted sample by convenient approach. The results of this study showed that 85% (n = 269) nurses were competent in nursing informatics competency. There was a significant relationship between basic nursing informatics competency and sociodemographic of age (t = 4.194, p = 0.000), gender (t = –2.558, p = 0.011), educational level (F [2,313] = 5.094, p = 0.007) and working discipline (F [6,309] = 8.309, p = 0.000). There was also a significant relationship between basic nursing informatics competency and working experience (ρ = –0.231, n = 316, p = 0.000). However, the study is based on self-reporting and does not measure the actual performance of nursing informatics competency. Overall, the findings indicated the need for improvement in nursing informatics by exposure or awareness for potential age group and particular clinical setting for training and educational of nursing informatics.

Stochastic dynamics mass spectrometric and Fourier transform infrared spectroscopic structural analyses of composite biodegradable plastics

<p>The (partial) replacement of synthetic polymers with bioplastics is due to increased production of conventional packaging plastics causing for severe environmental pollution with plastics waste. The bioplastics, however, represent complex mixtures of known and unknown (bio)polymers, fillers, plasticizers, stabilizers, flame retardant, pigments, antioxidants, hydrophobic polymers such as poly(lactic acid), polyethylene, polyesters, glycol, or poly(butylene succinate), and little is known of their chemical safety for both the environment and the human health. Polymerization reactions of bioplastics can produce no intentionally added chemicals to the bulk material, which could be toxic, as well. When polymers are used to food packing, then the latter chemicals could also migrate from the polymer to food. This fact compromises the safety for consumers, as well. The scarce data on chemical safety of bioplastics makes a gap in knowledge of their toxicity to humans and environment. Thus, development of exact analytical protocols for determining chemicals of bioplastics in environmental and food samples as well as packing polymers can only provide warrant for reliable conclusive evidence of their safety for both the human health and the environment. The task is compulsory according to legislation Directives valid to environmental protection, food control, and assessment of the risk to human health. The quantitative and structural determination of analytes is primary research task of analysis of polymers. The methods of mass spectrometry are fruitfully used for these purposes. Methodological development of exact analytical mass spectrometric tools for reliable structural analysis of bioplastics only guarantees their safety, efficacy, and quality to both humans and environment. This study, first, highlights innovative stochastic dynamics equations processing exactly mass spectrometric measurands and, thus, producing exact analyte quantification and 3D molecular and electronic structural analyses. There are determined synthetic polymers such as poly(ethylenglycol), poly(propylene glycol), and polyisoprene as well as biopolymers in bags for foodstuffs made from renewable cellulose and starch, and containing, in total within the 20,416–17,495 chemicals per sample of the composite biopolymers. Advantages of complementary employment in mass spectrometric methods and Fourier transform infrared spectroscopy is highlighted. The study utilizes ultra-high resolution electrospray ionization mass spectrometric and Fourier transform infrared spectroscopic data on biodegradable plastics bags for foodstuffs; high accuracy quantum chemical static methods, molecular dynamics; and chemometrics. There is achieved method performance |<em>r</em>| = 0.99981 determining poly(propylene glycol) in bag for foodstuff containing 20,416 species and using stochastic dynamics mass spectrometric formulas. The results highlight their great capability and applicability to the analytical science as well as relevance to both the fundamental research and to the industry.</p>

The Fourier transform in analytical science

The Fourier transform in analytical science

The Fourier transform in analytical science

The Fourier transform in analytical science

Machine Learning-Driven SERS Nanoendoscopy and Optophysiology.

A frontier of analytical sciences is centered on the continuous measurement of molecules in or near cells, tissues, or organs, within the biological context in situ, where the molecular-level information is indicative of health status, therapeutic efficacy, and fundamental biochemical function of the host. Following the completion of the Human Genome Project, current research aims to link genes to functions of an organism and investigate how the environment modulates functional properties of organisms. New analytical methods have been developed to detect chemical changes with high spatial and temporal resolution, including minimally invasive surface-enhanced Raman scattering (SERS) nanofibers using the principles of endoscopy (SERS nanoendoscopy) or optical physiology (SERS optophysiology). Given the large spectral data sets generated from these experiments, SERS nanoendoscopy and optophysiology benefit from advances in data science and machine learning to extract chemical information from complex vibrational spectra measured by SERS. This review highlights new opportunities for intracellular, extracellular, and in vivo chemical measurements arising from the combination of SERS nanosensing and machine learning.

Study for Photo-Induced Enhanced Raman Spectroscopy with Laser-Induced Periodic Surface Structures on Lithium Niobate on Insulator.

Femtosecond laser irradiation (FLI) of laser-induced periodic surface structures (LIPSSs) has proven to be an efficient and robust strategy for surface modification in nanoscale. Lithium niobate on insulator (LNOI) retains the excellent optoelectric properties of bulk lithium niobate and features intrinsic roughness and defects, exhibiting promising potential in the applications of surface-enhanced Raman spectroscopy (SERS) and photo-induced enhancement Raman spectroscopy (PIERS). Herein, we proposed a novel LNOI-LIPSSs-AgNPs substrate that exhibited an increased SERS enhancement by a factor of 3.7 relative to that without LIPSSs. More remarkably, with UV pre-irradiation, a PIERS amplification up to 8.1 times in comparison to SERS was achieved. Detailed and comprehensive analyses of the enhancement mechanisms prove the synergy between the electromagnetic mechanism and chemical mechanism. Additionally, the PIERS substrate exhibits advantages of high-fabrication efficiency, long-term stability, excellent detection universality, and multicyclic self-cleaning ability, which may trigger new applications in various branches of analytical science.

Carbon-based Flame Retardants for Polymers: A Bottom-up Review.

This state-of-the-art review is geared toward elucidating the molecular understanding of the carbon-based flame-retardant mechanisms for polymers via holistic characterization combining detailed analytical assessments and computational material science. The use of carbon-based flame retardants, which include graphite, graphene, carbon nanotubes (CNTs), carbon dots (CDs), and fullerenes, in their pure and functionalized forms are initially reviewed to evaluate their flame retardancy performance and to determine their elevation of the flammability resistance on various types of polymers. The early transition metal carbides such as MXenes, regarded as next-generation carbon-based flame retardants, are discussed with respect to their superior flame retardancy and multifunctional applications. At the core of this review is the utilization of cutting-edge molecular dynamics (MD) simulations which sets a precedence of an alternative bottom-up approach to fill the knowledge gap through insights into the thermal resisting process of the carbon-based flame retardants, such as the formation of carbonaceous char and intermediate chemical reactions offered by the unique carbon bonding arrangements and microscopic in-situ architectures. Combining MD simulations with detailed experimental assessments and characterization, a more targeted development as well as a systematic material synthesis framework can be realized for the future development of advanced flame-retardant polymers.

Combined ultra‐microelectrode: Exploring new potentials for in vivo/in situ ascorbic acid electroanalysis

AbstractMiniaturized and portable analytical tools show promise for sophisticated analysis, particularly in biological systems such as fruits, and they are suitable for advanced agriculture and related food industries. In this study, we developed combined ultra‐microelectrodes (UME) by modifying a microscale carbon fiber electrode (33 μm) coated with an Au nano‐film in a micropipette‐tip system. The proposed UME@Au exhibited a linear response to AC concentrations ranging from 30 to 1400 μM, with a 16 μM limit of detection. It demonstrated the ability to perform in vivo‐in vitro AC analysis in micro‐zones and volumes, such as different points of fruit tissue (Such as lemon) and within the body of a living plant (Such as Cactus arms and trunk), serving as a tiny implanted probe.In the first part of our study, we analyzed AC levels in lemon tissue directly. Our measurements revealed that AC levels are distributed heterogeneously in a single fruit. Additionally, stored AC levels depend on the color of the lemon (yellow ones have higher levels than the green ones). Furthermore, the UME was applied to control AC levels in different storage conditions, including opened containers, airtight containers, with and without exposing daylight, etc.In the second part, the UME@Au was utilized as an implanted sensor for in vivo analysis of AC in different parts of the cactus, recognized as a source of AC. No sample preparation is needed with minimum damage. The implanted microsensor could perform electroanalysis inside the live plant and stored parenchyma cells, etc. Notably, our results showed that AC levels are higher in the younger arms compared to the older ones, and so on.Based on our findings, the miniaturized, small, cheap, user‐friendly electrode demonstrated many capabilities, such as being implantable, having satisfactory stability, and not requiring sample preparations for analysis. It can open up a new window for micro‐electroanalysis in food and analytical plant sciences. We predict that this microscale platform can be modified and used for bioanalysis of other (bio)targets, such as vitamins, ions, and even the detection of plant pathogens in plants and crops directly. This involvement in the smart and modern farming industry is anticipated in the near future.

Quantitative description of the quality of size exclusion chromatography separations

Size exclusion chromatography (SEC) is unique among chromatographic methods as it allows separation of non-retained analytes. However, such mechanism often put an analytical scientist in front of relatively poorly resolved set of peaks that may have strikingly different abundance. The description of such chromatograms needs a particular approach to accurately capture the overall quality of separation. Consequently, use of a single parameter description may not be accurate enough and therefore we introduce a dimensionless separation quality factor, which is based on five SEC specific measures (peak-to-valley, elution window width, peak widths, peak-positioning and recovery). Combining several factors allowed detailed differentiation of various simulated separations, clearly correlating column characteristics with specific contributions to separation quality whether they concern a single peak pair or entire peak landscape. The method could be further elaborated by the addition of normalized priority weighting allowing for flexible quality quantification of a relevant portion of real-life nucleic acid separation on different columns. With growing complexity of biotherapeutics to be separated, such a term is predicted to be a useful response function for purposes of factorial method optimization.

The Potential of Generative AI in Analytical Science

The Potential of Generative AI in Analytical Science

SYNTHESIS AND STRUCTURE OF NEW COMPLEXES BASED ON SILVER NANOPARTICLES, BISACETYLACETONETHYLENEDIIMINE REAGENT AND CETYLTRIMETHYLAMMONIUM BROMIDE

This article provides a comprehensive review of the relationship between azo reagents and silver nanoparticles (AgNP), highlighting significant advances in analytical chemistry and materials science. The integration of silver nanoparticles with azo compounds has shown remarkable improvements in sensitivity, selectivity, and catalytic activity, leading to new applications in various fields. The article highlights the principles of ultraviolet spectroscopy (UV), discusses experimental methodologies, and elucidates the insights gained into the nature of the complexes formed between silver nanoparticles and azo compounds. Today, the synthesis of silver nanoparticles is widespread due to their many applications in various fields. In the presented article, silver nanoparticles were obtained by the green synthesis method. At the same time, the bisacetylacetonethylenediimine (R) reagent was synthesized and new complexes of nanoparticles were synthesized based on the cetylacetonethylenediimine (CTAB) reagent and acetyl trimethylammonium bromide. The complexes were investigated by UV spectroscopy and the optimal formation conditions were determined. It was determined that the optimal formation of the complex is observed at concentrations of 0.01 M of silver nanoparticles, 10-³ M of the reactant, and 0.5% of the surfactant. UV analysis of the synthesized complexes was conducted, and it was determined that the R reagent gives a maximum peak at the wavelength of 223 nm, 270 nm, 299 nm. During the UV study of the synthesized complexes, it was determined that the binary complex is 227 nm, 272 nm, 308 nm, and the maximum wavelength of the peaks of the ternary complex formed by adding CTAB as a stabilizer is 214 nm, 243 nm, 285 nm. Keywords: silver, nanoparticle, CTAB, complex, reagent.

Chemometric-based drug discovery approaches from natural origins using hyphenated chromatographic techniques.

Isolation and characterization of bioactive components from complex matrices of marine or terrestrial biological origins are the most challenging issues for natural product chemists. Biochemometric is a new potential scope in natural product analytical science, and it is a methodology to find the compound's correlation to their bioactivity with the help of hyphenated chromatographic techniques and chemometric tools. The present review aims to evaluate the application of chemometric tools coupled to chromatographic techniques for drug discovery from natural resources. The searching keywords "biochemometric," "chemometric," "chromatography," "natural products bioassay," and "bioassay" were selected to search the published articles between 2010-2023 using different search engines including "Pubmed", "Web of Science," "ScienceDirect," and "Google scholar." An initial stage in natural product analysis is applying the chromatographic hyphenated techniques in conjunction with biochemometric approaches. Among the applied chromatographic techniques, liquid chromatography (LC) techniques, have taken up more than half (53%) and also, mass spectroscopy (MS)-based chromatographic techniques such as LC-MS are the most widely used techniques applied in combination with chemometric methods for natural products bioassay. Considering the complexity of dataset achieved from chromatographic hyphenated techniques, chemometric tools have been increasingly employed for phytochemical studies in the context of determining botanicals geographical origin, quality control, and detection of bioactive compounds. Biochemometric application is expected to be further improved with advancing in data acquisition methods, new efficient preprocessing, model validation and variable selection methods which would guarantee that the applied model to have good prediction ability in compound relation to its bioactivity.