Holographic phase enables quantitative observation of the morphology of bioprinted structures and holds strong potential in bio-fabrication. However, achieving accurate and rapid holographic phase reconstruction for real-time monitoring during 3D bioprinting remains a challenge. In this paper, we propose a novel Global Attention Phase Network (GAP-Net) that focuses on real-time and accurate phase reconstruction for holographic phase monitoring in bioprinting. The GAP-Net leverages lightweight feature extraction module and global attention for semantic segmentation of wrapped phases, enhancing reconstruction precision. In addition, by predicting the first six Zernike coefficients to capture the dominant background aberrations, the method effectively mitigates phase distortions and further improves reconstruction accuracy. The approach achieves real-time phase reconstruction at 22.8 FPS with a 1.11-fold accuracy improvement over existing deep learning methods. The proposed method also enables successful real-time visualization of the curing dynamics of biological samples during bioprinting, further demonstrating its practical effectiveness. This work not only provides real-time observational data for bioprinting but also shows promising potential for broader applications in fields such as optics and biomedical imaging.

BACKGROUND: Interactions between microRNAs and RNA-binding proteins are crucial for microRNA-mediated gene regulation and sorting. Despite their significance, the molecular mechanisms governing these interactions remain underexplored, apart from sequence motifs identified on microRNAs. To date, only a limited number of microRNA-binding proteins have been confirmed, typically through labor-intensive experimental procedures. Advanced bioinformatics tools are urgently needed to facilitate this research. METHODS: We present DeepMiRBP, a novel hybrid deep learning model specifically designed to predict microRNA-binding proteins by modeling molecular interactions. This innovation approach is the first to target the direct interactions between small RNAs and proteins. DeepMiRBP consists of two main components. The first component employs bidirectional long short-term memory (Bi-LSTM) neural networks to capture sequential dependencies and context within RNA sequences, attention mechanisms to enhance the model's focus on the most relevant features and transfer learning to apply knowledge gained from a large dataset of RNA-protein binding sites to the specific task of predicting microRNA-protein interactions. Cosine similarity is applied to assess RNA similarities. The second component utilizes Convolutional Neural Networks (CNNs) to process the spatial data inherent in protein structures based on Position-Specific Scoring Matrices (PSSM) and contact maps to generate detailed and accurate representations of potential microRNA-binding sites and assess protein similarities. RESULTS: DeepMiRBP achieved a prediction accuracy of 87.4% during training and 85.4% using testing, with an F score of 0.860. Additionally, we validated our method using three case studies, focusing on microRNAs such as miR-451, -19b, -23a, -21, -223, and -let-7d. DeepMiRBP successfully predicted known miRNA interactions with recently discovered RNA-binding proteins, including AGO, YBX1, and FXR2, identified in various exosomes. CONCLUSIONS: Our proposed DeepMiRBP strategy represents the first of its kind designed for microRNA-protein interaction prediction. Its promising performance underscores the model's potential to uncover novel interactions critical for small RNA sorting and packaging, as well as to infer new RNA transporter proteins. The methodologies and insights from DeepMiRBP offer a scalable template for future small RNA research, from mechanistic discovery to modeling disease-related cell-to-cell communication, emphasizing its adaptability and potential for developing novel small RNA-centric therapeutic interventions and personalized medicine.

Microrobotic contact manipulation enables automated and precise cell capture, positioning and screening and has potential in biomedical engineering and disease detection. However, when using an optical microscope for visual positioning of targets, the poor clarity, limited cell-background contrast and lack of global 3D information of the cells in the field of view hinder global strategy making and automation, thereby affecting the accuracy and efficiency of manipulation. Here, we propose the 3D locating of multiple biological targets based on digital holography. Global–local combined visual feedback is developed for overall spatial locating and partial locating in a liquid-phase bright-field environment. By applying a filtering-based planar locating algorithm and maximum-area-based depth detection algorithm, the 3D global distribution of micro-targets in the field of view is periodically updated with a high detection rate. By applying a planar locating algorithm based on a convolutional neural network and a depth detection algorithm based on a gradient descent, the 3D fast locating of targets is performed precisely. Experiments show that the detection rate of the global positioning is 95.1%, the mean average precision of the local planar positioning is 90.53%, and the deviation of the local depth positioning is$1.22~\mu \text{m}$. When capturing cells, this method reaches an average speed of 7.4 cells/min and a collection rate of 90.5%. We anticipate that our method will support the research in cell-based bioengineering including cell screening and early disease diagnosis. Note to Practitioners—Automated cell manipulation is one of the most significant techniques in cell-based biomedical applications. This paper introduces a three-dimensional multi-target visual positioning method for automated cell manipulation. Combining with holographic imaging technique, the global information for the cells in the limited field of view is provided with improved imaging clarity and extended depth of field. The visual recognition algorithm can screen and extract the rare cells in the cell population, which will support the research in the field of early disease diagnosis and biomedicine. The research outcome provides an effective and precise solution to achieve biological targets positioning, capture, and screening within 3D liquid-phase bright-field environment.

Manipulating heterogeneous microtargets based on optoelectronic tweezers (OETs) to construct micropatterns with specific distribution and ordered arrangement enables recapitulating the spatial architecture of cells in native tissues, and has significant potential in tissue regeneration, medical diagnostics, and cell behavior research. However, the uncertain disturbances in liquid environment, collision risk, and electrokinetic interference in OETs system can cause microtargets to deviate from the safe and controlled state, especially for manipulation tasks with heterogeneous microtargets. Here, we propose an improved hierarchical value iteration network (IHVIN)-GAT-based path planning method for parallel manipulation of heterogeneous microtargets with independent control, integrating goal assignment, feature extraction, and decentralized decision-making. The Kuhn-Munkres-based goal assignment model periodically modifies the matching relationship between microtargets and goal positions to reduce the task complexity. High-order features involving path planning are extracted by an IHVIN model, and then selectively aggregated and convolved through GAT to yield real-time locomotion strategies for all microtargets. For the issues of constraint variability and system heterogeneity, discrete locomotion constraints are developed through analysis of escape mechanism, then embedded into modeling procedures and converted to heterogeneous edge weights in graph domain. The simulation and experimental results demonstrate the desired performance of the IHVIN-GAT model in high timeliness, high strategy quality, and compatibility for microtarget number, where up to 20 microtargets from three categories are parallel manipulated within 16 s to form arbitrary micropatterns recapitulating microscale architecture of cells in native tissues. We anticipate that our method will contribute to construct more biomimetic microstructures with heterogeneous cells for biomedical applications in the future.

Food monitoring has become an indispensable practice for personal health management in increasingly growing populations. To facilitate this process, advanced image processing and AI technologies have been applied to empower automated recognition of food item and nutrient using food images taken by smart mobile devices. However, existing tools suffered from unsatisfactory precision and compromised convenience, which has hindered broad application of food logging tools. In this study we explore new solutions to image-based food recognition for improved performance, with a particular focus on domestic cooking applications. Particularly, we leverage advanced machine learning and nature language processing techniques, in conjunction with comprehensive food nutrient profiles in the knowledge base and the contextual ingredient information parsed from publicly available recipes, in developing a new food recognition system. Our optimized models were proved to be effective in ingredient recognition based on food images and is under the integration into an Android app named FoodInsight, available at https://github.con zhuxinyishcn/FoodInSight.

Based on the fast-accumulating genomics data, gene regulation network modeling has been the primary computational means to infer interactions between genes and their regulators, such as such Transcription factors (TFs) and microRNAs, to study (post-)transcriptional regulation in biological systems. However, learning dynamic behaviors from data in complex diseases constitutes a challenge task due to the chaotic interplay between regulatory mechanisms and the fact that those interactions vary over time. It is therefore crucial to build scalable learning models that can consider different types of regulations by leveraging heterogeneous data that captures each behavior while meaningfully treating each specie in its uniqueness. This work explores integrative approaches to gene network learning in human cancer, with a particular focus on microRNA-mediated regulation. Specifically, we introduce a learning framework that integrates expression and interactome information of RNA and fuses distinct graphical models to transform the prediction of static interactions into the identification of semi-conditional ones. Through analyzing data on human pancreatic cancer, we have identified distinct gene regulatory networks associated with four progressive stages, from which a list of 15 microRNA-gene interactions are found conditional to stages. The subsequent functional analysis reveals significant microRNA-mediated dysregulations in major cancer hallmarks, particularly in adaptive immune response and lymphocyte proliferation, which shed light on the pathological processes and regulatory roles that microRNAs play in the process of pancreatic cancer progression. We believe this integrative model can be a robust and effective discovery tool to facilitate the discovery of key regulatory characteristics in other complex biological systems.

MOTIVATION: Empowered by advanced genomics discovery tools, recent biomedical research has produced a massive amount of genomic data on (post-)transcriptional regulations related to transcription factors, microRNAs, long non-coding RNAs, epigenetic modifications and genetic variations. Computational modeling, as an essential research method, has generated promising testable quantitative models that represent complex interplay among different gene regulatory mechanisms based on these data in many biological systems. However, given the dynamic changes of interactome in chaotic systems such as cancers, and the dramatic growth of heterogeneous data on this topic, such promise has encountered unprecedented challenges in terms of model complexity and scalability. In this study, we introduce a new integrative machine learning approach that can infer multifaceted gene regulations in cancers with a particular focus on microRNA regulation. In addition to new strategies for data integration and graphical model fusion, a supervised deep learning model was integrated to identify conditional microRNA-mRNA interactions across different cancer stages. RESULTS: In a case study of human breast cancer, we have identified distinct gene regulatory networks associated with four progressive stages. The subsequent functional analysis focusing on microRNA-mediated dysregulation across stages has revealed significant changes in major cancer hallmarks, as well as novel pathological signaling and metabolic processes, which shed light on microRNAs' regulatory roles in breast cancer progression. We believe this integrative model can be a robust and effective discovery tool to understand key regulatory characteristics in complex biological systems. AVAILABILITY: http://sbbi-panda.unl.edu/pin/.

Empowered by the advancement of high-throughput bio technologies, recent research on body-fluid proteomes has led to the discoveries of numerous novel disease biomarkers and therapeutic drugs. In the meantime, a tremendous progress in disclosing the body-fluid proteomes was made, resulting in a collection of over 15 000 different proteins detected in major human body fluids. However, common challenges remain with current proteomics technologies about how to effectively handle the large variety of protein modifications in those fluids. To this end, computational effort utilizing statistical and machine-learning approaches has shown early successes in identifying biomarker proteins in specific human diseases. In this article, we first summarized the experimental progresses using a combination of conventional and high-throughput technologies, along with the major discoveries, and focused on current research status of 16 types of body-fluid proteins. Next, the emerging computational work on protein prediction based on support vector machine, ranking algorithm, and protein-protein interaction network were also surveyed, followed by algorithm and application discussion. At last, we discuss additional critical concerns about these topics and close the review by providing future perspectives especially toward the realization of clinical disease biomarker discovery.

MOTIVATION: Human proteins that are secreted into different body fluids from various cells and tissues can be promising disease indicators. Modern proteomics research empowered by both qualitative and quantitative profiling techniques has made great progress in protein discovery in various human fluids. However, due to the large number of proteins and diverse modifications present in the fluids, as well as the existing technical limits of major proteomics platforms (e.g. mass spectrometry), large discrepancies are often generated from different experimental studies. As a result, a comprehensive proteomics landscape across major human fluids are not well determined. RESULTS: To bridge this gap, we have developed a deep learning framework, named DeepSec, to identify secreted proteins in 12 types of human body fluids. DeepSec adopts an end-to-end sequence-based approach, where a Convolutional Neural Network is built to learn the abstract sequence features followed by a Bidirectional Gated Recurrent Unit with fully connected layer for protein classification. DeepSec has demonstrated promising performances with average area under the ROC curves of 0.85-0.94 on testing datasets in each type of fluids, which outperforms existing state-of-the-art methods available mostly on blood proteins. As an illustration of how to apply DeepSec in biomarker discovery research, we conducted a case study on kidney cancer by using genomics data from the cancer genome atlas and have identified 104 possible marker proteins. AVAILABILITY: DeepSec is available at https://bmbl.bmi.osumc.edu/deepsec/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Rapid advances in genomics discovery tools and a growing realization of microRNA's implication in intercellular communication have led to a proliferation of studies of circulating microRNA sorting and regulation across cells and different species. Although sometimes, reaching controversial scientific discoveries and conclusions, these studies have yielded new insights in the functional roles of circulating microRNA and a plethora of analytical methods and tools. Here, we consider this body of work in light of key computational principles underpinning discovery of circulating microRNAs in terms of their sorting and targeting, with the goal of providing practical guidance for applications that is focused on the design and analysis of circulating microRNAs and their context-dependent regulation. We survey a broad range of informatics methods and tools that are available to the researcher, discuss their key features, applications and various unsolved problems and close this review with prospects and broader implication of this field.

Computational modeling of complex gene regulation among different mechanisms involving transcript factors, microRNAs, lncRNAs, epigenetic modification, in a chaotic disease system such as cancer, has posed unprecedented challenges. In this study, we introduce a new integrative framework that handles genomics data integration and network model fusion with focus on the inference of context-dependent microRNA-gene interactions. Using breast cancer as a case study, we have identified stage-specific microRNA-gene binding patterns. Functional analysis indicates microRNA regulated signaling during cancer progression.

Advanced measurement techniques such as genomics are capable of acquiring high-throughput data in high dimensions, enabling new scientific discoveries, and offering unique insights in biomedical research. However, biological measurements can be easily affected by systematic variations especially when those measures are obtained from distinct batches involving different platforms and experimental conditions. Such batch effect is usually larger than biological signal of interest and can cause invalid downstream analysis and false discovery if not properly handled. Here we proposed a new learning approach based on multivariate distribution matching in the latent space for batch effect removal while preserving signals of most interest. This new data-driven approach consists of three key components: an autoencoder trained to encode the data into low-dimension neurons that represent data pattern; a similarity measurement procedure to identify batch-effect associated neurons; and a residual network-based matching framework to transform the affected neurons' distribution from one batch to another where the adjusted neurons will be decoded to reconstruct new datasets with batch effect removed. The effectiveness of the proposed approach has been validated in several ways using public genomic data on Alzheimer disease. This new method provides a highly promising tool for complex batch-effect adjustment and outperforms other commonly used methods.

The research on rare cells makes a significant contribution to biology research and medical treatment for the application of diagnostic operation as well as prognoses treatment. Therefore, sorting them from heterogeneous mixtures is crucial and valuable. Traditional cell sorting methods featured with poor purity and recovery rate as well as limited flexibility, which are not ideal approaches for rare type. In this paper, we proposed a cell screening method based on automated microrobotic aspiration-and-placement strategy under fluorescence microscope. An innovative autofocusing visual feedback (AVF) method is proposed for precise three-dimensional (3D) locating of target cells. For depth detection, multiple depth from defocus (MDFD) method is adopted to solve symmetry problem and attain an average accuracy of 97.07%. For planar locating, Markov random field (MRF) based locating method is utilized to separate and locate the overlapped cells. The end actuator locating and real-time tracking are performed relying on normalized cross-correlation (NCC) method. Experiential results show that our system collects rare cells (100 cells ml-1) at a speed of 5 cells min-1with 90% purity and 75% recovery rate, which is valuable for biological and medical application.

Study of cellular behaviors, especially the ultra-rare cell type, can aid in the accuracy of clinic diagnoses as well as the development of bioresearch engineering, thus the importance of isolating them from heterogeneous mixtures. However, current methods may fail in purity, versatility or cause contamination to cell targets, which is fatal drawback to rare cells. To address this issue, we propose a versatile method to automatically select and capture fluorescent stained target cells with high purity and recovery rate, through developing a novel 3D image processing algorithm under dark field. With the automated pick-and-place strategies, the micro-robotic system achieves cell screening even in an environment with ultra-sparse cells. In the proposed visual method, Markov Random Field (MRF) separation is adapted into the fluorescent environment to attain real-time planar location of micropipette and target cells. A reformative method derived from Depth from Defocus (DFD) is brought up to acquire 3D information. The basic system for this method mainly consists of a camera mounted on motorized fluorescent microscope and a micromanipulator for cell capture. The fluorescent label help to screen out most of the undesired cells while also bring extra constraints and requisition to our visual method. Finally, experiments of collecting 3 T3 cells are performed to verify the feasibility and validity of the designed method, achieving average 98% purity and 80% recovery rate within the time limits. This study indicates that proposed visual processing method can not only provides reliable location feedback for micro-manipulation in rare cell sorting, but also can be easily extended to satisfy other automated micro-robotics manipulation.

Small RNA sequencing is the most widely used tool for microRNA (miRNA) discovery, and shows great potential for the efficient study of miRNA cross-species transport, i.e., by detecting the presence of exogenous miRNA sequences in the host species. Because of the increased appreciation of dietary miRNAs and their far-reaching implication in human health, research interests are currently growing with regard to exogenous miRNAs bioavailability, mechanisms of cross-species transport and miRNA function in cellular biological processes. In this article, we present microRNA Discovery (miRDis), a new small RNA sequencing data analysis pipeline for both endogenous and exogenous miRNA detection. Specifically, we developed and deployed a Web service that supports the annotation and expression profiling data of known host miRNAs and the detection of novel miRNAs, other noncoding RNAs, and the exogenous miRNAs from dietary species. As a proof-of-concept, we analyzed a set of human plasma sequencing data from a milk-feeding study where 225 human miRNAs were detected in the plasma samples and 44 show elevated expression after milk intake. By examining the bovine-specific sequences, data indicate that three bovine miRNAs (bta-miR-378, -181* and -150) are present in human plasma possibly because of the dietary uptake. Further evaluation based on different sets of public data demonstrates that miRDis outperforms other state-of-the-art tools in both detection and quantification of miRNA from either animal or plant sources. The miRDis Web server is available at: http://sbbi.unl.edu/miRDis/index.php.

MicroRNAs regulate virtually the whole gene network in human body and have been implicated in most physiological and pathological conditions including cancers. Understanding the precise mechanisms of microRNA-mRNA interaction is fundamentally important to elucidate the important roles of miRNA in regulating various cellular and disease developmental stages. Numerous computational methods have been developed for miRNA target prediction, mostly focusing on static binding prediction and highly dependent on sequence-pairing interactions. However, the interplay between competing and cooperative microRNA-target binding makes it exceptionally complex and challenging for reliable target identification, which has hindered the existing tools from practical use. In this study, we present a new computational method for microRNA target prediction using the Dirichlet Process Gaussian Mixture Model (DPGMM). A comprehensive collection of features related to sequence and structure of microRNAs, mRNAs, and the binding sites have been assessed to optimize the statistical prediction of new binding sites in human transcriptome. Through multiple evaluations on recently-discovered miRNA-mRNA interactions reported in large-scale sequencing analyses and a screening test on the entire human transcripts, the results show that our model outperformed several state-of-the-art tools in terms of reduced false positive prediction and promising predictive power on binding sites specific to transcript isoforms.

In this paper, we present the design and implementation of a stand-alone tool for metabolic simulation and its deployment on the Open Science Grid (OSG). The case study model of glucose-insulin metabolism aims at the development of a real-time monitoring system that can assist patients with diabetes to handle their blood glucose profile and maintain healthy diet habit. This system is able to integrate custom-built SBML models along with users' food intake information and produces the estimation of ATP, Glucose, and Insulin for the given duration using numerical analysis and simulation. The tool has also been generalized to take into consideration of temporal genomic information and be flexible for simulation of any given biochemical models. After implementation on OSG, the results have demonstrated the effectiveness of numerical optimization for model selection and the feasibility of the proposed tool for the given metabolic simulation. The ATP-glucose and glucose-insulin correlations revealed by this tool can be promising for a variety of different application cases.

MicroRNA is a type of short non-coding RNAs, which post-transcriptionally regulate gene expressions. It has been well-documented that human microRNAs contribute in the disease development, such as cancers and obesity. While most microRNA functional studies heavily rely on the regulatory interactions between microRNAs and their target messenger RNAs, the accumulating evidence has shown that the altered availability of microRNAs, their target, and other types of endogenous RNAs competing are able to affect the microRNA-target interactions efficiently, which reflects the dynamic and conditional property of microRNA-mediated gene regulation. Here we present a new computational pipeline, miRDR-OSG, that utilizing the high-throughput computing resource provided by Open Science Grid to study the dynamic regulation of microRNAs in cancer development with the consideration of both competing and cooperative mechanisms. A large-scale genomic dataset from over four thousand patients with 9 major types of cancer was used to demonstrate the usage of miRDR-OSG. As a result, we identified 10,726 microRNA regulatory interactions that only occurred in a specific stage and/or cancer type. This observation demonstrated the dynamic and conditional microRNA regulation during cancer progression. miRDR-OSG is freely available at http://sbbi.unl.edu/miRDR.

Bell-LaPadula model is the most classical multilevel security access control model, however, the existence of the response blind area in Bell-LaPadula model is a great threat for system. In this paper we propose an improved Bell-LaPadula model combining with obligation mechanism. Response mechanism is also introduced in the improved model which can resolve the disadvantage of response blind area. Furthermore, the security of the improved model and covert channel is analyzed in detail.

MicroRNAs are functionally important non-coding RNAs that silence host genes via destabilizing the mRNAs or preventing the translation. Given the far-reaching implication of microRNA regulation in human health, novel bioinformatics tools are desired to facilitate the mechanistic understanding of microRNA mediated gene regulation and its regulatory roles in human disease development. Most state-of-the-art computational methods focus on the functional inference through identifying microRNA targets and none has comprehensively investigated the functional similarity among microRNAs. Here we present a new method to quantitatively measure the functional relevance among microRNAs that is solely based on the Gene Ontology and integrated functional annotation data from public pathways and PFam gene databases. In this study, we further demonstrated the use of the derived microRNA pairwise similarities to investigate the cooperative microRNA modules and construct the genome scale microRNA mediated gene network in human. The complete results and the similarity assessment system can be freely accessed at (http://sbbi.unl.edu/microRNASim).

MicroRNAs, a class of short non-coding RNAs, are able to regulate more than half of human genes and affect many fundamental biological processes. It has been long considered synthesized endogenously until very recent discoveries showing that human can absorb exogenous microRNAs from dietary resources. This finding has raised a challenge scientific question: which exogenous microRNAs can be integrated into human circulation and possibly exert functions in human? Here we present a well-designed ensemble manifold ranking model for identifying human absorbable exogenous miRNAs from 14 common dietary species. Specifically, we have analyzed 4,910 dietary microRNAs with 1,120 features derived based on the microRNA sequence and structure. In total, 70 discriminative features were selected to characterize the circulating microRNAs in human and have been used to infer the possibility of a certain exogenous microRNA getting integrated into human circulation. Finally, 461 dietary microRNAs have been identified as transportable exogenous microRNAs. To assess the performance of our ensemble model, we have validated the top predictions through a milk-feeding study. In addition, 26 microRNAs from two virus species were predicted as transportable and have been validated in two external experiments. The results demonstrate the data-driven computational model is highly promising to study transportable microRNAs while bypassing the complex mechanistic details.

UNLABELLED: A challenge in biodata analysis is to understand the underlying phenomena among many interactions in signaling pathways. Such study is formulated as the pathway enrichment analysis, which identifies relevant pathways functional enriched in high-throughput data. The question faced here is how to analyze different data types in a unified and integrative way by characterizing pathways that these data simultaneously reveal. To this end, we developed integrative Pathway Enrichment Analysis Platform, iPEAP, which handles transcriptomics, proteomics, metabolomics and GWAS data under a unified aggregation schema. iPEAP emphasizes on the ability to aggregate various pathway enrichment results generated in different high-throughput experiments, as well as the quantitative measurements of different ranking results, thus providing the first benchmark platform for integration, comparison and evaluation of multiple types of data and enrichment methods. AVAILABILITY AND IMPLEMENTATION: iPEAP is freely available at http://www.tongji.edu.cn/∼qiliu/ipeap.html.

A new relaying scheme with the combination of incremental decode-and-forward (DF) relaying and selective relaying employed hybrid decode-amplify-forward (HDAF), termed incremental HDAF relaying (IHDAF), is proposed and analyzed in this paper. Closed-form expressions of outage probability for the incremental HDAF relaying scheme is derived. Simulation results and analysis show that the incremental HDAF relaying scheme outperforms the incremental DF relaying scheme especially when the relay locates near the destination.

BACKGROUND: Computational identification of blood-secretory proteins, especially proteins with differentially expressed genes in diseased tissues, can provide highly useful information in linking transcriptomic data to proteomic studies for targeted disease biomarker discovery in serum. RESULTS: A new algorithm for prediction of blood-secretory proteins is presented using an information-retrieval technique, called manifold ranking. On a dataset containing 305 known blood-secretory human proteins and a large number of other proteins that are either not blood-secretory or unknown, the new method performs better than the previous published method, measured in terms of the area under the recall-precision curve (AUC). A key advantage of the presented method is that it does not explicitly require a negative training set, which could often be noisy or difficult to derive for most biological problems, hence making our method more applicable than classification-based data mining methods in general biological studies. CONCLUSION: We believe that our program will prove to be very useful to biomedical researchers who are interested in finding serum markers, especially when they have candidate proteins derived through transcriptomic or proteomic analyses of diseased tissues. A computer program is developed for prediction of blood-secretory proteins based on manifold ranking, which is accessible at our website http://csbl.bmb.uga.edu/publications/materials/qiliu/blood_secretory_protein.html.

We present a novel computational method for predicting which proteins from highly and abnormally expressed genes in diseased human tissues, such as cancers, can be secreted into the bloodstream, suggesting possible marker proteins for follow-up serum proteomic studies. A main challenging issue in tackling this problem is that our understanding about the downstream localization after proteins are secreted outside the cells is very limited and not sufficient to provide useful hints about secretion to the bloodstream. To bypass this difficulty, we have taken a data mining approach by first collecting, through extensive literature searches, human proteins that are known to be secreted into the bloodstream due to various pathological conditions as detected by previous proteomic studies, and then asking the question: 'what do these secreted proteins have in common in terms of their physical and chemical properties, amino acid sequence and structural features that can be used to predict them?' We have identified a list of features, such as signal peptides, transmembrane domains, glycosylation sites, disordered regions, secondary structural content, hydrophobicity and polarity measures that show relevance to protein secretion. Using these features, we have trained a support vector machine-based classifier to predict protein secretion to the bloodstream. On a large test set containing 98 secretory proteins and 6601 non-secretory proteins of human, our classifier achieved approximately 90% prediction sensitivity and approximately 98% prediction specificity. Several additional datasets are used to further assess the performance of our classifier. On a set of 122 proteins that were found to be of abnormally high abundance in human blood due to various cancers, our program predicted 62 as blood-secreted proteins. By applying our program to abnormally highly expressed genes in gastric cancer and lung cancer tissues detected through microarray gene expression studies, we predicted 13 and 31 as blood secreted, respectively, suggesting that they could serve as potential biomarkers for these two cancers, respectively. Our study demonstrated that our method can provide highly useful information to link genomic and proteomic studies for disease biomarker discovery. Our software can be accessed at http://csbl1.bmb.uga.edu/cgi-bin/Secretion/secretion.cgi.