Application scenario-oriented molecule generation platform developed for drug discovery.

Design of molecules for candidate compound selection is one of the central challenges in drug discovery due to the complexity of chemical space and requirement of multi-parameter optimization. Here we present an application scenario-oriented platform (ID4Idea) for molecule generation in different scenarios of drug discovery. This platform utilizes both library or rule based and generative based algorithms (VAE, RNN, GAN, etc.), in combination with various AI learning types (pre-training, transfer learning, reinforcement learning, active learning, etc.) and input representations (1D SMILES, 2D graph, 3D shape, binding site, pharmacophore, etc.), to enable customized solutions for a given molecular design scenario. Besides the usual generation followed screening protocol, goal-directed molecule generation can also be conducted towards predefined goals, enhancing the efficiency of hit identification, lead finding, and lead optimization. We demonstrate the effectiveness of ID4Idea platform through case studies, showcasing customized solutions for different design tasks using various input information, such as binding pockets, pharmacophores, and compound representations. In addition, remaining challenges are discussed to unlock the full potential of AI models in drug discovery and pave the way for the development of novel therapeutics.

A Combination of Machine Learning and PBPK Modeling Approach for Pharmacokinetics Prediction of Small Molecules in Humans.

PURPOSE: Recently, there has been rapid development in model-informed drug development, which has the potential to reduce animal experiments and accelerate drug discovery. Physiologically based pharmacokinetic (PBPK) and machine learning (ML) models are commonly used in early drug discovery to predict drug properties. However, basic PBPK models require a large number of molecule-specific inputs from in vitro experiments, which hinders the efficiency and accuracy of these models. To address this issue, this paper introduces a new computational platform that combines ML and PBPK models. The platform predicts molecule PK profiles with high accuracy and without the need for experimental data. METHODS: This study developed a whole-body PBPK model and ML models of plasma protein fraction unbound ( f up ), Caco-2 cell permeability, and total plasma clearance to predict the PK of small molecules after intravenous administration. Pharmacokinetic profiles were simulated using a "bottom-up" PBPK modeling approach with ML inputs. Additionally, 40 compounds were used to evaluate the platform's accuracy. RESULTS: Results showed that the ML-PBPK model predicted the area under the concentration-time curve (AUC) with 65.0 % accuracy within a 2-fold range, which was higher than using in vitro inputs with 47.5 % accuracy. CONCLUSION: The ML-PBPK model platform provides high accuracy in prediction and reduces the number of experiments and time required compared to traditional PBPK approaches. The platform successfully predicts human PK parameters without in vitro and in vivo experiments and can potentially guide early drug discovery and development.

Application of IRI Visualization to Terahertz Vibrational Spectroscopy of Hydroxybenzoic Acid Isomers.

The characteristic absorption spectra of three positional isomers of hydroxybenzoic acid are measured using a terahertz time-domain spectroscopy system (THz-TDS) in the 0.6-2.0 THz region at room temperature. Significant differences in their terahertz spectra are discovered, which indicates that THz-TDS is an effective means to identify positional isomers. In order to simulate their spectra, the seven molecular clusters of 2-, 3-, and 4-hydroxybenzoic acid (2-, 3-, and 4-HA) are calculated using the DFT-D3 method. Additionally, the potential energy distribution (PED) method is used to analyze their vibration modes. The analysis indicates that the vibration modes of 2-HA are mainly out-of-plane angle bending and bond angle bend in plane. The vibration modes of 3-HA are mainly bond length stretch and dihedral angle torsion. The vibration modes of 4-HA are mainly bond angle bend in plane and dihedral angle torsion. Interaction region indicator (IRI) analysis is used to visualize the location and type of intermolecular interactions in 2-, 3-, and 4-HA crystals. The results show that the weak interaction type of 2-, 3-, and 4-HA is dominated by van der Waals (vdW) interaction. Therefore, we can confirm that terahertz spectroscopy detection technology can be used as an effective means to identify structural isomers and detect the intermolecular interactions in these crystals. In addition, it can explain the absorption mechanism of terahertz waves interacting with matter.

Vacancy tuned coupling in terahertz metamaterial arrays.

Metamaterials have shown great potential for modulation on the amplitude, phase and polarization of the terahertz wave. Here vacancies were introduced into the metamaterial arrays to tune the mutual interaction between the constituent resonators, which could heavily affect the electromagnetic response of the whole metamaterial arrays. We show that the introduced vacancies in the metamaterial arrays can effectively affect the resonance mode of the metamaterial arrays. Based upon the vacancy mediated coupling, a silicon-metal hybrid metamaterial arrays were designed to achieve active modulation of propagating terahertz waves.

Classification, identification, and growth stage estimation of microalgae based on transmission hyperspectral microscopic imaging and machine learning.

A transmission hyperspectral microscopic imager (THMI) that utilizes machine learning algorithms for hyperspectral detection of microalgae is presented. The THMI system has excellent performance with spatial and spectral resolutions of 4 µm and 3 nm, respectively. We performed hyperspectral imaging (HSI) of three species of microalgae to verify their absorption characteristics. Transmission spectra were analyzed using principal component analysis (PCA) and peak ratio algorithms for dimensionality reduction and feature extraction, and a support vector machine (SVM) model was used for classification. The average accuracy, sensitivity and specificity to distinguish one species from the other two species were found to be 94.4%, 94.4% and 97.2%, respectively. A species identification experiment for a group of mixed microalgae in solution demonstrates the usability of the classification method. Using a random forest (RF) model, the growth stage in a phaeocystis growth cycle cultivated under laboratory conditions was predicted with an accuracy of 98.1%, indicating the feasibility to evaluate the growth state of microalgae through their transmission spectra. Experimental results show that the THMI system has the capability for classification, identification and growth stage estimation of microalgae, with strong potential for in-situ marine environmental monitoring and early warning detection applications.

Superstructure microfiber grating characterized by temperature, strain, and refractive index sensing.

Microfiber gratings with diameters in the subwavelength scale have recently attracted much attention for developments of sensitive sensors; however, a specific structure is usually chosen for sensing one parameter according to the optical response. In this work, a superstructure microfiber grating combined with microfiber Bragg grating and long-period microfiber grating is reported for the first time. The proposed superstructure is formed by ultraviolet laser inscription and femtosecond laser scratching techniques, which simultaneously endows the unique properties of the two individual gratings. The reflection and transmission spectral characteristics differing to conventional counterparts are demonstrated. The responsivities of the two gratings to temperature, strain and refractive index are investigated, providing a possibility for simultaneous multi-parameter sensing.

Bamboo-like microfiber structures fabricated by one-step-tapering a fiber preform.

The microfiber-based optical structures have been attracting increasing research interests in communications and sensing fields. However, the fabrication of forming structures on fragile microfibers requires delicate operations, which limits the developments of their practical applications. In this work, a one-step-tapering technique is proposed to manufacture structures on microfibers. As a demonstration, the fiber preform, consisting of sawtooth shaped solid-air interfaces with designed dimensions, is obtained using a femtosecond laser milling technique. By one-step tapering the preform, periodic bumps are formed, resulting in a bamboo-like microfiber device. The fabricated structure shows spectral characteristics of a long-period grating, of which extinction ratio is up to 18.2 dB around 1553.3 nm. The response to refractive index is measured to be ∼875.02 nm/RIU and the temperature coefficient is ∼5.78 pm/°C. The theoretical analysis shows good agreement with the experimental results. The microfiber-based structure fabricated using the one-step-tapering-preform technique is featured with flexibility of design, reproducibility, and structural stability.

Semiconductor terahertz modulator arrays: the size and edge effect.

A terahertz spatial modulator is the critical component for active terahertz imaging using compressive sensing. Here small silicon pieces were put in arrays on flexible polymer substrate to fabricate semiconductor terahertz spatial modulators. By doing this, the inter-diffusion of photo-generated charge carriers is prevented for better resolution, and flexibility is achieved. Since the size of silicon is comparable to the wavelength of the terahertz wave, and the dielectric properties of the gap are very different from silicon, the optical modulation of each element is very different from the large silicon. In this Letter, the terahertz wave interaction and optical modulation of the small silicon are systematically studied by time domain spectroscopy. Notably, a strong resonance-like absorption peak was observed in a transmittance spectrum for the small silicon due to the size and edge effect. The spatial modulation of the terahertz wave was also compared between the silicon array and the large silicon samples.

[Quantitative Analysis of Deep-Frying Oil Adulterated Virgin Olive Oil Using Vis-NIR Spectroscopy with iPLS].

To explore a rapid and reliable method for quantitative analysis of deep-frying oil adulterated virgin olive oil, visible and near infrared(Vis-NIR) spectroscopy and three improved partial least squares methods, including interval Partial Least Squares (iPLS), synergy interval partial least squares (SiPLS) and backward interval partial least squares (BiPLS) were employed to establish predicting models of doping content based on virgin olive oil adulterating different levels and different types of deep-frying oil. And the models were compared in order to choose the best one. The Vis-NIR spectroscopy ranged from 400 to 2 500 nm was obtained directly from the adulterated samples, and the spectroscopic data was preprocessed with Savitzky-Golay (SG). Then, the samples were divided into calibration set and test set by Sample Set Partitioning based on Joint X-Y Distance (SPXY) after rejecting the odd samples. At last, the predicting models of doping content were built by using different interval partial least squares methods. The results showed that the optimal model for predicting the doping content of deep-frying soybean oil in virgin olive oil was obtained with SiPLS method that separated the whole spectra into 20 intervals and combined the fourth and the sixteenth intervals. The SiPLS model had correlation coefficient (r) of 0.998 9 and root mean standard error of prediction (RMSEP) of 0.019 2. In addition, for deep-frying peanut oil adulterated virgin olive oil, the SiPLS and BiPLS models with interval 2 and interval 16 which the whole spectra was separated into 20 intervals, had same results. The RMSEP was 0.012 0, lower than iPLS model. Moreover, compared to SiPLS method, BiPLS method saved computation and was more efficient. Overall, through selecting the effective wavelength range, SiPLS method and BiPLS method could accurately predict the doping content of deep-frying oil in virgin olive oil based on its' Vis-NIR spectroscopy. In addition, this fast and nondestructive experiment doesn't need sample pretreatment with advantages of no environment pollution, easy operation.

[Rapid Identification of Cistanche via Fluorescence Spectrum Imaging Technology Combined with Principal Components Analysis and Fisher Distinction].

In order to explore rapid reliable Hebra cistanche detection methods, identification of 3 different sources of Hebra cistanche: cistanche deserticola, cistanche tubulosa, sand rossia is studied via fluorescent spectral imaging technology combined with pattern recognition. It is found in experiment that cistanche samples have obvious fluorescence properties. Forty fluorescence spectral images of 3 different sources of Hebra cistanche samples are collected through fluorescent spectral imaging system. After carrying on denoising and binarization processing to these images, the spectral curves of each sample was drawn according to the spectral cube. The obtained spectra data in the 450 - 680 nm wavelength range is regarded as the study object of discriminant analysis. Then, principal component analysis (PCA) is applied to reduce the dimension of spectroscopic data of the three kinds of cistanche and fisher distinction is used in combination to classify them; During the experiment were compared the effects of three methods of data preprocessing on the model: multiplicative scatter correction (MSC), standard normal variable correction (SNV) and first-order differential (FD) and then according to the cumulative contribution rate of the principal component and the effect of number of factors on the discriminant model to optimize the number of principal components factor. The results showed that. identification of the best after the first derivative pretreatment then the first four principal components is extracted to carry on fisher discriminant, discriminant model of 3 different sources of Hebra cistanche is set up through PCA combined with fisher discriminant the precision of original discrimination is 100%, recognition rate of the cross validation is 95%. It was thus shown that the fluorescent spectral imaging technology combined with principal components analysis and fisher distinction can be used for the identification study of 3 different sources of Hebra cistanche and has the advantages of easy operation, speediness, reliability.

Gaining insights into the responses of individual yeast cells to ethanol fermentation using Raman tweezers and chemometrics.

Saccharomyces cerevisiae is the most common microbe used for the industrial production of bioethanol, and it encounters various stresses that inhibit cell growth and metabolism during fermentation. However, little is currently known about the physiological changes that occur in individual yeast cells during ethanol fermentation. Therefore, in this work, Raman spectroscopy and chemometric techniques were employed to monitor the metabolic changes of individual yeast cells at distinct stages during high gravity ethanol fermentation. Raman tweezers was used to acquire the Raman spectra of individual yeast cells. Multivariate curve resolution-alternating least squares (MCR-ALS) and principal component analysis were employed to analyze the Raman spectra dataset. MCR-ALS extracted the spectra of proteins, phospholipids, and triacylglycerols and their relative contents in individual cells. Changes in intracellular biomolecules showed that yeast cells undergo three distinct physiological stages during fermentation. In addition, heterogeneity among yeast cells significantly increased in the late fermentation period, and different yeast cells may respond to ethanol stress via different mechanisms. Our findings suggest that the combination of Raman tweezers and chemometrics approaches allows for characterizing the dynamics of molecular components within individual cells. This approach can serve as a valuable tool in investigating the resistance mechanism and metabolic heterogeneity of yeast cells during ethanol fermentation.

Insights into enhanced immobilization of uranyl carbonate from seawater by Fe-doped MXene.

Extracting uranium from seawater not only reduces radioactive contamination in seawater but also provides a source of uranium energy. However, due to the low concentration of uranium in seawater and the high salinity of seawater, extraction of uranium from seawater is challenging. In this work, we demonstrated a simple strategy to synthesize Fe-doped MXene (Fe@Ti3C2Tx) via a hydrothermal method and applied for uranium enrichment in seawater. The Fe@Ti3C2Tx exhibited excellent adsorption performance in high salinity environments. The removal capacity of Fe@Ti3C2Tx was determined to be 526.6 mg/g for UO2(CO3)22- at 328 K with quick reaction equilibrium (∼ 30 min). Kinetic and thermodynamic analyses of UO2(CO3)22- elimination process on Fe@Ti3C2Tx surface revealed it to be a spontaneous and endothermic single-phase elimination process. FT-IR and XPS analyses further indicated that the removal mechanism of UO2(CO3)22- by Fe@Ti3C2Tx was surface complexation. Our study suggests that Fe@Ti3C2Tx can provide a feasible solution for uranium enrichment in seawater.

Differential diagnosis of Crohn's disease and intestinal tuberculosis based on ATR-FTIR spectroscopy combined with machine learning.

BACKGROUND: Crohn's disease (CD) is often misdiagnosed as intestinal tuberculosis (ITB). However, the treatment and prognosis of these two diseases are dramatically different. Therefore, it is important to develop a method to identify CD and ITB with high accuracy, specificity, and speed. AIM: To develop a method to identify CD and ITB with high accuracy, specificity, and speed. METHODS: A total of 72 paraffin wax-embedded tissue sections were pathologically and clinically diagnosed as CD or ITB. Paraffin wax-embedded tissue sections were attached to a metal coating and measured using attenuated total reflectance fourier transform infrared spectroscopy at mid-infrared wavelengths combined with XGBoost for differential diagnosis. RESULTS: The results showed that the paraffin wax-embedded specimens of CD and ITB were significantly different in their spectral signals at 1074 cm-1 and 1234 cm-1 bands, and the differential diagnosis model based on spectral characteristics combined with machine learning showed accuracy, specificity, and sensitivity of 91.84%, 92.59%, and 90.90%, respectively, for the differential diagnosis of CD and ITB. CONCLUSION: Information on the mid-infrared region can reveal the different histological components of CD and ITB at the molecular level, and spectral analysis combined with machine learning to establish a diagnostic model is expected to become a new method for the differential diagnosis of CD and ITB.

Rapid detection of hepatitis B virus DNA level based on interval-point data fusion of infrared spectra.

Hepatitis B is an infectious disease cause by the hepatitis B virus (HBV). In recent years, HBV-DNA level clinically gets more attention for its detailed information than other serological markers. Unfortunately, common clinical method for HBV-DNA level detection is limited for its hours consuming. This study combined infrared spectroscopy with machine learning to investigate the feasibility of near-infrared (NIR) and mid-infrared (MIR) spectra for rapid detection of HBV-DNA level. Based on partial least squares-discriminant analysis (PLS-DA) modeling method, the optimal NIR and MIR models and traditional data fusion models were constructed, respectively. Considering inequal weight between interval and point data in machine learning, interval-point data fusion method was used to compare with other traditional date fusion methods. The results of the study illustrate that interval-point data fusion of NIR and MIR spectra combined with PLS-DA modeling can provide a rapid method for HBV-DNA level detection.

Identification of mercury species in coal combustion by-products from power plants using thermal desorption-atomic fluorescence spectrometry on-line coupling system.

Along with the environmental protection policies becoming strict in China, the air pollution control devices (especially selective catalytic reduction (SCR)) are widely equipped in coal-fired power plants. The installation and run of these devices will inevitably affect mercury (Hg) species distribution in coal fired by-products such like fly ash (FA) and gypsum. In this work, a new on-line coupling system based on atomic fluorescence spectrometry (AFS) with a home-made chromatographic workstation was successfully developed to identify Hg species through thermal programmed desorption (TPD). The influences of matrix, furnace temperature, and carrier gas flow on analytical performance were investigated and the parameters were optimized. The FA and gypsum samples from coal-fired power plants equipped with SCR were collected and the mercury species were analyzed by the developed coupling system. HgCl2 and HgO were the main species in FA, while Hg2Cl2 and HgO were the main species in gypsum. All of Hg species in the studied FA and gypsum samples were released below 400 °C. A sequential extraction procedure was applied to further verify the operational Hg species including mobile and non-mobile fractions in FA and gypsum samples. This study demonstrated that AFS coupled with TPD procedure was an effective method to analyze Hg species in coal combustion by-products from power plants.

Early osteoarthritis diagnosis based on near-infrared spectroscopy combined with aquaphotomics.

Osteoarthritis (OA) is the most common joint disease and the leading cause of disability in elderly individuals. Despite rapid advances in imaging techniques, early OA diagnosis remains a clinical challenge. In the present study, the feasibility of early OA diagnosis was explored via near-infrared spectroscopy (NIRS) combined with aquaphotomics. Synovial fluid samples from 65 cases of OA categorized as mild, moderate, and severe according to theKellgrenandLawrence classification criteria were analyzed via NIRS. The 1st overtone of water (1300-1600 nm) was considered as the research object for an aquaphotomics model, and aquagrams of the mild, moderate, and severe OA cases were generated using 12 water absorption patterns for early OA diagnosis.The aquaphotomics results exhibited clear differences in the region of 1300-1500 nm, and the number of hydrogen bonds of different water species (1412,1424, 1482, and 1496 nm) evidently correlated with OA occurrence and development. With OA progression, the absorption intensity of water molecules without hydrogen bonds (1412 nm/1424 nm) became stronger, while the absorption intensity of water molecules with four hydrogen bonds (1482 nm/1496 nm) decreased.These results together reveal that the established accurate and rapid early OA diagnosis model based on NIRS combined with aquaphotomics is effective and feasible, and that the number of hydrogen bonds can be used as a biomarker for early OA diagnosis.

Rapid identification of flaxseed oil based on portable fiber optic Raman spectroscopy combined with an oil microscopy method.

To explore a fast, simple, and accurate method to identify adulteration in flaxseed oil, the Raman spectral data of 130 samples containing flaxseed, canola, cottonseed, and adulterated oils were obtained using a portable fiber optic Raman spectrometer. The Raman spectral results showed that the Raman spectra of the flaxseed and canola oils had noticeable peak shifts, whereas the peak positions of the flaxseed and cottonseed oils were relatively similar. Clear peak intensity differences were observed in the flaxseed, cottonseed, and canola oils, mainly at 868 cm-1 , 1022 cm-1 , 1265 cm-1 , and 1655 cm-1 , with Raman shift intensities in the following order: Iflaxseed oil  > Icottonseed oil  > Icanola oil . Similarly, the peak intensity of the flaxseed and adulterated oils also exhibited certain differences (at 868 cm-1 , 1022 cm-1 , 1265 cm-1 , and 1655 cm-1 ), and the Raman shift intensity tended to decrease gradually with the increasing content of canola and cottonseed oils in the flaxseed oil. Additionally, the results of Raman spectroscopy combined with the "oil microscopy" method exhibited large variations in the radar patterns of the flaxseed, canola, and cottonseed oils, whereas the radar patterns of the flaxseed and adulterated oils closely resembled each other. The results indicated that Raman spectroscopy in combination with oil microscopy more effectively revealed the subtle differences in the Raman shift intensity, serving as a more visual and comprehensive approach for differentiating the quality variations between pure flaxseed oil and other oil species and adulterated oil. PRACTICAL APPLICATION: This study analyzed the Raman spectra of flaxseed, canola, cottonseed, and adulterated oils using fiber optic Raman spectroscopy. Combined with the oil microscopy method for comprehensive evaluation and analysis, it is feasible to effectively identify the quality differences among flaxseed, canola, cottonseed, and adulterated oils.

A new technology for rapid determination of isomers of hydroxybenzoic acid by terahertz spectroscopy.

This study investigated the feasibility of using terahertz (THz) technology for the rapid identification of isomers. The time-domain spectra of 2-hydroxybenzoic acid (2-HA), 3-hydroxybenzoic acid (3-HA), and 4-hydroxybenzoic acid (4-HA) were measured by a THz time-domain spectroscopy system (THz-TDS) in the range of 0.3-1.8 THz. Aiming at the isomer classification problem, a THz spectral data classification model based on a variational mode decomposition-particle swarm optimization-support vector machine (VMD-PSO-SVM) method was proposed. Empirical mode decomposition (EMD) and variational mode decomposition (VMD) were used to extract the first eight intrinsic mode functions (IMFs) of the time-domain signal. Principal component analysis (PCA) was used to extract the first 80 principal components of each modal component as the classification feature vector. The particle swarm optimization (PSO) and support vector machine (SVM) algorithms were used to construct 2-, 3-, and 4-HA classification models. We found that the prediction accuracy of the VMD-PSO-SVM model was significantly higher than that of EMD-PSO-SVM model regardless of the modal components. For both EMD and VMD, with the increase in the IMF number, the corresponding classification recognition accuracy tended to decrease. The results showed that the rapid identification model of hydroxybenzoic acid isomers based on THz spectroscopy and SVM was effective and feasible, providing an accurate and rapid method for the chemical synthesis and quality monitoring of biomedicine.

Microbial Fertilization Improves Soil Health When Compared to Chemical Fumigation in Sweet Lily.

Lanzhou Lily(Lilium davidii) var. unicolor, which is also known as sweet lily in China, is used as a type of food. This lily is distributed in narrow regions, propagates asexually, cultivates perennially, and cultivates commonly in serious consecutive replant problems (CRPs). Soil fumigation is commonly used to control soil-borne disease to alleviate crops' consecutive replant problems (CRPs). However, due to the improper fumigation application, it is common to cause chemical hazard to crops. In this study, we designed a two-factor experiment to explore the bacterial and fungal community structure and some specific microbial groups in the lily rhizosphere soil after chemical versus bacterial fertilizer treatments, by using a metagenomic analysis of the treated soils. The results showed that metham-sodium soil fumigation (SMF treatment) significantly decreased plant growth, as well as it significantly decreased both soil fungal diversity and abundance at the OTUs levels, while Special 8™ microbial fertilizer supplement (MF treatment) significantly improved plant growth and increased fungal diversity and abundance. Under FM treatment, Chao1 richness and Shannon's diversity increased by 6.70% and 35.09% compared to CK (no treatment). However, the bacterial diversity and abundance were not significantly changed among these treatments. The fungal and bacterial community structure were different in all treatments. In SMF treatment, the pathogenic fungal species Fusarium oxysporum increased compared to CK, but it significantly decreased in MF treatment; in MF and MMF treatments, some beneficial bacteria groups such as the bacterial phylum Proteobacteria and its member genus Sphingomonas, as well as the fungal genus Mortierella, increased compared to CK and SFM treatments, but the harmful bacterial genera Gemmatimona was decreased, as well as the harmful fungal genus Cryptococcus. Thus, we concluded that under chemical fumigation conditions, both fungal diversity loss and overall microorganism reduction, which impair multiple ecosystem function, in conjunction with the increase of harmful fungal species such as Fusarium oxysporum, are causes for soil degradation. On the other hand, under microbial fertilizer supplement, it was the fungal diversity increase, as well as these beneficial microorganisms groups' accumulation, together with those harmful groups' depletion, played important roles in restoring and improving soil health that suffered from the chemical fumigant hazard. In addition, the bacterial phylum Proteobacteria and its member genus Sphingomonas are involved in soil health recovery and promotion. The results also emphasized that whether soil is chemically fumigated or not, beneficial microorganism supplementary is effective in ensuring soil productivity.

A three-layer competition-based giant magnetoresistive assay for direct quantification of endoglin from human urine.

This study presents a three-layer competition-based assay for ultrasensitive detection and quantification of endoglin from unprocessed human urine samples using a giant magnetoresistive (GMR) sensor and high-moment magnetic nanoparticle-based biosensing technology. This biosensing platform detects as few as 1000 copies of endoglin at concentrations as low as 83 fM with high detection specificity and has a three-order dynamic range. The results reveal that endoglin levels in urine have the potential to predict for the presence of prostate cancer and to distinguish between prostate cancers of different grades.