An introduction to artificial neural networks in bioinformatics--application to complex microarray and mass spectrometry datasets in cancer studies

Development of a quantitative prediction algorithm for human cord blood-derived CD34+ hematopoietic stem-progenitor cells using parametric and non-parametric machine learning models

The transplantation of CD34+ hematopoietic stem-progenitor cells (HSPCs) derived from cord blood serves as the standard treatment for selected hematological, oncological, metabolic, and immunodeficiency disorders, of which the dose is pivotal to the clinical outcome. Based on numerous maternal and neonatal parameters, we evaluated the predictive power of mathematical pipelines to the proportion of CD34+ cells in the final cryopreserved cord blood product adopting both parametric and non-parametric algorithms. Twenty-four predictor variables associated with the cord blood processing of 802 processed cord blood units randomly sampled in 2020-2022 were retrieved and analyzed. Prediction models were developed by adopting the parametric (multivariate linear regression) and non-parametric (random forest and back propagation neural network) statistical models to investigate the data patterns for determining the single outcome (i.e., the proportion of CD34+ cells). The multivariate linear regression model produced the lowest root-mean-square deviation (0.0982). However, the model created by the back propagation neural network produced the highest median absolute deviation (0.0689) and predictive power (56.99%) in comparison to the random forest and multivariate linear regression. The predictive model depending on a combination of continuous and discrete maternal with neonatal parameters associated with cord blood processing can predict the CD34+ dose in the final product for clinical utilization. The back propagation neural network algorithm produces a model with the highest predictive power which can be widely applied to assisting cell banks for optimal cord blood unit selection to ensure the highest chance of transplantation success.

Machine learning: an advancement in biochemical engineering

One of the most remarkable techniques recently introduced into the field of bioprocess engineering is machine learning. Bioprocess engineering has drawn much attention due to its vast application in different domains like biopharmaceuticals, fossil fuel alternatives, environmental remediation, and food and beverage industry, etc. However, due to their unpredictable mechanisms, they are very often challenging to optimize. Furthermore, biological systems are extremely complicated; hence, machine learning algorithms could potentially be utilized to improve and build new biotechnological processes. Gaining insight into the fundamental mathematical understanding of commonly used machine learning algorithms, including Support Vector Machine, Principal Component Analysis, Partial Least Squares and Reinforcement Learning, the present study aims to discuss various case studies related to the application of machine learning in bioprocess engineering. Recent advancements as well as challenges posed in this area along with their potential solutions are also presented.

Deep learning for predicting 16S rRNA gene copy number

Culture-independent 16S rRNA gene metabarcoding is a commonly used method for microbiome profiling. To achieve more quantitative cell fraction estimates, it is important to account for the 16S rRNA gene copy number (hereafter 16S GCN) of different community members. Currently, there are several bioinformatic tools available to estimate the 16S GCN values, either based on taxonomy assignment or phylogeny. Here we present a novel approach ANNA16, Artificial Neural Network Approximator for 16S rRNA gene copy number, a deep learning-based method that estimates the 16S GCN values directly from the 16S gene sequence strings. Based on 27,579 16S rRNA gene sequences and gene copy number data from the rrnDB database, we show that ANNA16 outperforms the commonly used 16S GCN prediction algorithms. Interestingly, Shapley Additive exPlanations (SHAP) shows that ANNA16 can identify unexpected informative positions in 16S rRNA gene sequences without any prior phylogenetic knowledge, which suggests potential applications beyond 16S GCN prediction.

A machine learning-based quantitative model (LogBB_Pred) to predict the blood-brain barrier permeability (logBB value) of drug compounds

MOTIVATION

Efficient assessment of the blood-brain barrier (BBB) penetration ability of a drug compound is one of the major hurdles in central nervous system drug discovery since experimental methods are costly and time-consuming. To advance and elevate the success rate of neurotherapeutic drug discovery, it is essential to develop an accurate computational quantitative model to determine the absolute logBB value (a logarithmic ratio of the concentration of a drug in the brain to its concentration in the blood) of a drug candidate.

RESULTS

Here, we developed a quantitative model (LogBB_Pred) capable of predicting a logBB value of a query compound. The model achieved an R2 of 0.61 on an independent test dataset and outperformed other publicly available quantitative models. When compared with the available qualitative (classification) models that only classified whether a compound is BBB-permeable or not, our model achieved the same accuracy (0.85) with the best qualitative model and far-outperformed other qualitative models (accuracies between 0.64 and 0.70). For further evaluation, our model, quantitative models, and the qualitative models were evaluated on a real-world central nervous system drug screening library. Our model showed an accuracy of 0.97 while the other models showed an accuracy in the range of 0.29-0.83. Consequently, our model can accurately classify BBB-permeable compounds as well as predict the absolute logBB values of drug candidates.

AVAILABILITY AND IMPLEMENTATION

Web server is freely available on the web at http://ssbio.cau.ac.kr/software/logbb_pred/. The data used in this study are available to download at http://ssbio.cau.ac.kr/software/logbb_pred/dataset.zip.

Current uses of artificial intelligence in the analysis of biofluid markers involved in corneal and ocular surface diseases: a systematic review

Corneal and ocular surface diseases (OSDs) carry significant psychosocial and economic burden worldwide. We set out to review the literature on the application of artificial intelligence (AI) and bioinformatics for analysis of biofluid biomarkers in corneal and OSDs and evaluate their utility in clinical decision making. MEDLINE, EMBASE, Cochrane and Web of Science were systematically queried for articles using AI or bioinformatics methodology in corneal and OSDs and examining biofluids from inception to August 2021. In total, 10,264 articles were screened, and 23 articles consisting of 1058 individuals were included. Using various AI/bioinformatics tools, changes in certain tear film cytokines that are proinflammatory such as increased expression of apolipoprotein, haptoglobin, annexin 1, S100A8, S100A9, Glutathione S-transferase, and decreased expression of supportive tear film components such as lipocalin-1, prolactin inducible protein, lysozyme C, lactotransferrin, cystatin S, and mammaglobin-b, proline rich protein, were found to be correlated with pathogenesis and/or treatment outcomes of dry eye, keratoconus, meibomian gland dysfunction, and Sjögren's. Overall, most AI/bioinformatics tools were used to classify biofluids into diseases subgroups, distinguish between OSD, identify risk factors, or make predictions about treatment response, and/or prognosis. To conclude, AI models such as artificial neural networks, hierarchical clustering, random forest, etc., in conjunction with proteomic or metabolomic profiling using bioinformatics tools such as Gene Ontology or Kyoto Encylopedia of Genes and Genomes pathway analysis, were found to inform biomarker discovery, distinguish between OSDs, help define subgroups with OSDs and make predictions about treatment response in a clinical setting.

Improvement of predictive accuracies of functional outcomes after subacute stroke inpatient rehabilitation by machine learning models

OBJECTIVES

Stepwise linear regression (SLR) is the most common approach to predicting activities of daily living at discharge with the Functional Independence Measure (FIM) in stroke patients, but noisy nonlinear clinical data decrease the predictive accuracies of SLR. Machine learning is gaining attention in the medical field for such nonlinear data. Previous studies reported that machine learning models, regression tree (RT), ensemble learning (EL), artificial neural networks (ANNs), support vector regression (SVR), and Gaussian process regression (GPR), are robust to such data and increase predictive accuracies. This study aimed to compare the predictive accuracies of SLR and these machine learning models for FIM scores in stroke patients.

METHODS

Subacute stroke patients (N = 1,046) who underwent inpatient rehabilitation participated in this study. Only patients' background characteristics and FIM scores at admission were used to build each predictive model of SLR, RT, EL, ANN, SVR, and GPR with 10-fold cross-validation. The coefficient of determination (R2) and root mean square error (RMSE) values were compared between the actual and predicted discharge FIM scores and FIM gain.

RESULTS

Machine learning models (R2 of RT = 0.75, EL = 0.78, ANN = 0.81, SVR = 0.80, GPR = 0.81) outperformed SLR (0.70) to predict discharge FIM motor scores. The predictive accuracies of machine learning methods for FIM total gain (R2 of RT = 0.48, EL = 0.51, ANN = 0.50, SVR = 0.51, GPR = 0.54) were also better than of SLR (0.22).

CONCLUSIONS

This study suggested that the machine learning models outperformed SLR for predicting FIM prognosis. The machine learning models used only patients' background characteristics and FIM scores at admission and more accurately predicted FIM gain than previous studies. ANN, SVR, and GPR outperformed RT and EL. GPR could have the best predictive accuracy for FIM prognosis.

ESRRG, ATP4A, and ATP4B as Diagnostic Biomarkers for Gastric Cancer: A Bioinformatic Analysis Based on Machine Learning

Based on multiple bioinformatics methods and machine learning techniques, this study was designed to explore potential hub genes of gastric cancer with a diagnostic value. The novel biomarkers were detected through multiple databases of gastric cancer–related genes. The NCBI Gene Expression Omnibus (GEO) database was used to obtain gene expression files. Three hub genes (ESRRG, ATP4A, and ATP4B) were detected through a combination of weighted gene co-expression network analysis (WGCNA), gene–gene interaction network analysis, and supervised feature selection method. GEPIA2 was used to verify the differences in the expression levels of the hub genes in normal and cancer tissues in the RNA-seq levels of Genotype-Tissue Expression (GTEx) and The Cancer Genome Atlas (TCGA) databases. The objectivity of potential hub genes was also verified by immunohistochemistry in the Human Protein Atlas (HPA) database and transcription factor–hub gene regulatory network. Machine learning (ML) methods including data pre-processing, model selection and cross-validation, and performance evaluation were examined on the hub-gene expression profiles in five Gene Expression Omnibus datasets and verified on a GEO external validation (EV) dataset. Six supervised learning models (support vector machine, random forest, k-nearest neighbors, neural network, decision tree, and eXtreme Gradient Boosting) and one semi-supervised learning model (label spreading) were established to evaluate the diagnostic value of biomarkers. Among the six supervised models, the support vector machine (SVM) algorithm was the most effective one according to calculated performance metrics, including 0.93 and 0.99 area under the curve (AUC) scores on the test and external validation datasets, respectively. Furthermore, the semi-supervised model could also successfully learn and predict sample types, achieving a 0.986 AUC score on the EV dataset, even when 10% samples in the five GEO datasets were labeled. In conclusion, three hub genes (ATP4A, ATP4B, and ESRRG) closely related to gastric cancer were mined, based on which the ML diagnostic model of gastric cancer was conducted.

Incorporating Radiomics into Machine Learning Models to Predict Outcomes of Neuroblastoma

Neuroblastoma is one of the most common pediatric cancers. This study used machine learning (ML) to predict the mortality and a few other investigated intermediate outcomes of neuroblastoma patients non-invasively from CT images. Performances of multiple ML algorithms over retrospective CT images of 65 neuroblastoma patients are analyzed. An artificial neural network (ANN) is used on tumor radiomic features extracted from 3D CT images. A pre-trained 2D convolutional neural network (CNN) is used on slices of the same images. ML models are trained for various pathologically investigated outcomes of these patients. A subspecialty-trained pediatric radiologist independently reviewed the manually segmented primary tumors. Pyradiomics library is used to extract 105 radiomic features. Six ML algorithms are compared to predict the following outcomes: mortality, presence or absence of metastases, neuroblastoma differentiation, mitosis-karyorrhexis index (MKI), presence or absence of MYCN gene amplification, and presence of image-defined risk factors (IDRF). The prediction ranges over multiple experiments are measured using the area under the receiver operating characteristic (ROC-AUC) for comparison. Our results show that the radiomics-based ANN method slightly outperforms the other algorithms in predicting all outcomes except classification of the grade of neuroblastic differentiation, for which the elastic regression model performed the best. Contributions of the article are twofold: (1) noninvasive models for the prognosis from CT images of neuroblastoma, and (2) comparison of relevant ML models on this medical imaging problem.

Detection of intra-family coronavirus genome sequences through graphical representation and artificial neural network

In this study, chaos game representation (CGR) is introduced for investigating the pattern of genome sequences. It is an image representation of the genome for the overall visualization of the sequence. The CGR representation is a mapping technique that assigns each sequence base into the respective position in the two-dimension plane to portray the DNA sequence. Importantly, CGR provides one to one mapping to nucleotides as well as sequence. A coordinate of the CGR plane can tell the corresponding base and its location in the original genome. Therefore, the whole nucleotide sequence (until the current nucleotide) can be restored from the one point of the CGR. In this study, CGR coupled with artificial neural network (ANN) is introduced as a new way to represent the genome and to classify intra-coronavirus sequences. A hierarchy clustering study is done to validate the approach and found to be more than 90% accurate while comparing the result with the phylogenetic tree of the corresponding genomes. Interestingly, the method makes the genome sequence significantly shorter (more than 99% compressed) saving the data space while preserving the genome features.

A Comprehensive Review of Computation-Based Metal-Binding Prediction Approaches at the Residue Level

Clear evidence has shown that metal ions strongly connect and delicately tune the dynamic homeostasis in living bodies. They have been proved to be associated with protein structure, stability, regulation, and function. Even small changes in the concentration of metal ions can shift their effects from natural beneficial functions to harmful. This leads to degenerative diseases, malignant tumors, and cancers. Accurate characterizations and predictions of metalloproteins at the residue level promise informative clues to the investigation of intrinsic mechanisms of protein-metal ion interactions. Compared to biophysical or biochemical wet-lab technologies, computational methods provide open web interfaces of high-resolution databases and high-throughput predictors for efficient investigation of metal-binding residues. This review surveys and details 18 public databases of metal-protein binding. We collect a comprehensive set of 44 computation-based methods and classify them into four categories, namely, learning-, docking-, template-, and meta-based methods. We analyze the benchmark datasets, assessment criteria, feature construction, and algorithms. We also compare several methods on two benchmark testing datasets and include a discussion about currently publicly available predictive tools. Finally, we summarize the challenges and underlying limitations of the current studies and propose several prospective directions concerning the future development of the related databases and methods.

Aligned Poly-l-lactic Acid Nanofibers Induce Self-Assembly of Primary Cortical Neurons into 3D Cell Clusters

Relative to two-dimensional (2D) culture, three-dimensional (3D) culture of primary neurons has yielded increasingly physiological responses from cells. Electrospun nanofiber scaffolds are frequently used as a 3D biomaterial support for primary neurons in neural tissue engineering, while hydrophobic surfaces typically induce aggregation of cells. Poly-l-lactic acid (PLLA) was electrospun as aligned PLLA nanofiber scaffolds to generate a structure with both qualities. Primary cortical neurons from E18 Sprague-Dawley rats cultured on aligned PLLA nanofibers generated 3D clusters of cells that extended highly aligned, fasciculated neurite bundles within 10 days. These clusters were viable for 28 days and responsive to AMPA and GABA. Relative to the 2D culture, the 3D cultures exhibited a more developed profile; mass spectrometry demonstrated an upregulation of proteins involved in cortical lamination, polarization, and axon fasciculation and a downregulation of immature neuronal markers. The use of artificial neural network inference suggests that the increased formation of synapses may drive the increase in development that is observed for the 3D cell clusters. This research suggests that aligned PLLA nanofibers may be highly useful for generating advanced 3D cell cultures for high-throughput systems.

A roadmap for multi-omics data integration using deep learning

High-throughput next-generation sequencing now makes it possible to generate a vast amount of multi-omics data for various applications. These data have revolutionized biomedical research by providing a more comprehensive understanding of the biological systems and molecular mechanisms of disease development. Recently, deep learning (DL) algorithms have become one of the most promising methods in multi-omics data analysis, due to their predictive performance and capability of capturing nonlinear and hierarchical features. While integrating and translating multi-omics data into useful functional insights remain the biggest bottleneck, there is a clear trend towards incorporating multi-omics analysis in biomedical research to help explain the complex relationships between molecular layers. Multi-omics data have a role to improve prevention, early detection and prediction; monitor progression; interpret patterns and endotyping; and design personalized treatments. In this review, we outline a roadmap of multi-omics integration using DL and offer a practical perspective into the advantages, challenges and barriers to the implementation of DL in multi-omics data.

Predicting the targets of IRF8 and NFATc1 during osteoclast differentiation using the machine learning method framework cTAP

BACKGROUND

Interferon regulatory factor-8 (IRF8) and nuclear factor-activated T cells c1 (NFATc1) are two transcription factors that have an important role in osteoclast differentiation. Thanks to ChIP-seq technology, scientists can now estimate potential genome-wide target genes of IRF8 and NFATc1. However, finding target genes that are consistently up-regulated or down-regulated across different studies is hard because it requires analysis of a large number of high-throughput expression studies from a comparable context.

METHOD

We have developed a machine learning based method, called, Cohort-based TF target prediction system (cTAP) to overcome this problem. This method assumes that the pathway involving the transcription factors of interest is featured with multiple "functional groups" of marker genes pertaining to the concerned biological process. It uses two notions, Gene-Present Sufficiently (GP) and Gene-Absent Insufficiently (GA), in addition to log2 fold changes of differentially expressed genes for the prediction. Target prediction is made by applying multiple machine-learning models, which learn the patterns of GP and GA from log2 fold changes and four types of Z scores from the normalized cohort's gene expression data. The learned patterns are then associated with the putative transcription factor targets to identify genes that consistently exhibit Up/Down gene regulation patterns within the cohort. We applied this method to 11 publicly available GEO data sets related to osteoclastgenesis.

RESULT

Our experiment identified a small number of Up/Down IRF8 and NFATc1 target genes as relevant to osteoclast differentiation. The machine learning models using GP and GA produced NFATc1 and IRF8 target genes different than simply using a log2 fold change alone. Our literature survey revealed that all predicted target genes have known roles in bone remodeling, specifically related to the immune system and osteoclast formation and functions, suggesting confidence and validity in our method.

CONCLUSION

cTAP was motivated by recognizing that biologists tend to use Z score values present in data sets for the analysis. However, using cTAP effectively presupposes assembling a sizable cohort of gene expression data sets within a comparable context. As public gene expression data repositories grow, the need to use cohort-based analysis method like cTAP will become increasingly important.

Enhancing the Discovery of Functional Post-Translational Modification Sites with Machine Learning Models - Development, Validation, and Interpretation

Protein posttranslational modifications (PTMs) are a rapidly expanding feature class of significant importance in cell biology. Due to a high burden of experimental proof, the number of functionals PTMs in the eukaryotic proteome is currently underestimated. Furthermore, not all PTMs are functionally equivalent. Computational approaches that can confidently recommend PTMs of probable function can improve the heuristics of PTM investigation and alleviate these problems. To address this need, we developed SAPH-ire: a multifeature heuristic neural network model that takes community wisdom into account by recommending experimental PTMs similar to those which have previously been established as having regulatory impact. Here, we describe the principle behind the SAPH-ire model, how it is developed, how we evaluate its performance, and important caveats to consider when building and interpreting such models. Finally, we discus current limitations of functional PTM prediction models and highlight potential mechanisms for their improvement.

Newborn Eye Screening as an Application of AI

Artificial intelligence (AI) applications are diverse and serve varied functions in clinical practice. The most successful products today are clinical decision tools used by physicians, but autonomous AI is gaining traction. Widespread use of AI is limited in part because of concerns about bias, fault-tolerance, and specificity. Adoption of AI often depends on removing cost and complexity in clinical workflow integration, providing clear incentives for use, and providing clear demonstration of clinical outcome. Existing wide-angle photographic screening could be integrated into the clinical workflow based on prior implementations for premature babies and linked with AI interpretation with existing technology. Incidence of retinal abnormality, clinical considerations, AI performance, grading variation for AI-augmented human grading, and cost and policy aspects play a significant role. Improved outcomes for newborns and a relatively high estimated incidence of abnormality have been named as benefits to counterweigh costs in the long term. [Ophthalmic Surg Lasers Imaging Retina. 2021;52:S17-S22.].

Artificial intelligence in the embryology laboratory: a review

The goal of an IVF cycle is a healthy live-born baby. Despite the many advances in the field of assisted reproductive technologies, accurately predicting the outcome of an IVF cycle has yet to be achieved. One reason for this is the method of selecting an embryo for transfer. Morphological assessment of embryos is the traditional method of evaluating embryo quality and selecting which embryo to transfer. However, this subjective method of assessing embryos leads to inter- and intra-observer variability, resulting in less than optimal IVF success rates. To overcome this, it is common practice to transfer more than one embryo, potentially resulting in high-risk multiple pregnancies. Although time-lapse incubators and preimplantation genetic testing for aneuploidy have been introduced to help increase the chances of live birth, the outcomes remain less than ideal. Utilization of artificial intelligence (AI) has become increasingly popular in the medical field and is increasingly being leveraged in the embryology laboratory to help improve IVF outcomes. Many studies have been published investigating the use of AI as an unbiased, automated approach to embryo assessment. This review summarizes recent AI advancements in the embryology laboratory.

Bioinformatics Approach for Data Capturing: The Case of Breast Cancer

Background:

With the rapid evolution in advanced computer systems and various statistical algorithms, it is now a days possible to analyze complex biological data. Bioinformatics is an interface between computational and biological assemblies. It is applied in various fields of biological as well as medical sciences.

Aim:

The manuscript aims to summarize the developments in the field of breast cancer research through the applications of bioinformatics.

Methods:

Various search engines like google, science direct, Scopus, PubMed, etc., were used for the literature survey.

Results:

It describes the bioinformatics analysis tools and models, which include mainly artificial neural network models.

Conclusion:

Bioinformatics is the evolutionary approach that is used for the capturing of data from the various case studies related to breast cancer.

Application of an artificial neural network for predicting the potential chemotherapy benefit of patients with gastric cancer after radical surgery

BACKGROUND

Artificial neural network models have a strong self-learning ability and can deal with complex biological information, but there is no artificial neural network model for predicting the benefits of adjuvant chemotherapy in patients with gastric cancer.

METHODS

The clinicopathological data of patients who underwent radical resection of gastric cancer from January 2010 to September 2014 were analyzed retrospectively. Patients who underwent surgery combined with adjuvant chemotherapy were randomly divided into a training cohort (70%) and a validation cohort (30%). An artificial neural network model (potential-CT-benefit-ANN) was established, and its ability to predict the potential benefit of chemotherapy was evaluated by the C-index. The prognostic prediction and stratification ability of potential-CT-benefit-ANN and the eighth American Joint Committee on Cancer staging system were compared by receiver operating characteristic curves and Kaplan-Meier curves.

RESULTS

In both the training and validation cohort, potential-CT-benefit-ANN shows good prediction accuracy for potential adjuvant chemotherapy benefit. The receiver operating characteristic curve showed that the prediction accuracy of potential-CT-benefit-ANN was better than that of the eighth American Joint Committee on Cancer staging system in all groups. The calibration plots showed that the predicted prognosis of potential-CT-benefit-ANN was highly consistent with the actual value. The survival curves showed that potential-CT-benefit-ANN could stratify prognosis well for all groups and performed significantly better than the eighth AJCC staging system.

CONCLUSION

The potential-CT-benefit-ANN model developed in this study can accurately predict the potential benefits of adjuvant chemotherapy in patients with stage II/III gastric cancer. The benefit score based on potential-CT-benefit-ANN can predict the long-term prognosis of patients with adjuvant chemotherapy and has good prognostic stratification ability.

On transformative adaptive activation functions in neural networks for gene expression inference

Gene expression profiling was made more cost-effective by the NIH LINCS program that profiles only ∼1, 000 selected landmark genes and uses them to reconstruct the whole profile. The D-GEX method employs neural networks to infer the entire profile. However, the original D-GEX can be significantly improved. We propose a novel transformative adaptive activation function that improves the gene expression inference even further and which generalizes several existing adaptive activation functions. Our improved neural network achieves an average mean absolute error of 0.1340, which is a significant improvement over our reimplementation of the original D-GEX, which achieves an average mean absolute error of 0.1637. The proposed transformative adaptive function enables a significantly more accurate reconstruction of the full gene expression profiles with only a small increase in the complexity of the model and its training procedure compared to other methods.

On tower and checkerboard neural network architectures for gene expression inference

BACKGROUND

One possible approach how to economically facilitate gene expression profiling is to use the L1000 platform which measures the expression of ∼1,000 landmark genes and uses a computational method to infer the expression of another ∼10,000 genes. One such method for the gene expression inference is a D-GEX which employs neural networks.

RESULTS

We propose two novel D-GEX architectures that significantly improve the quality of the inference by increasing the capacity of a network without any increase in the number of trained parameters. The architectures partition the network into individual towers. Our best proposed architecture - a checkerboard architecture with a skip connection and five towers - together with minor changes in the training protocol improves the average mean absolute error of the inference from 0.134 to 0.128.

CONCLUSIONS

Our proposed approach increases the gene expression inference accuracy without increasing the number of weights of the model and thus without increasing the memory footprint of the model that is limiting its usage.

Patterns of biomarker expression in patients treated with primary endocrine therapy - a unique insight using core needle biopsy tissue microarray

Purpose

Prediction of response to primary endocrine therapy (PET) in older women is based on measurement of oestrogen receptor (ER), progesterone receptor (PgR) and human epidermal growth factor (HER)-2. This study uses a unique method for construction of core needle biopsy (CNB) tissue microarray (TMA), to correlate expression of a panel of 17 biomarkers with clinical outcome, in patients receiving PET.

Methods

Over 37 years (1973–2010), 1758 older (≥ 70 years) women with operable primary breast cancer were managed in a single institution. Of these, 693 had sufficient good-quality CNB to construct TMA, of which 334 had ER-positive tumours treated by PET with a minimum of 6-month follow-up. A panel of biomarkers was measured by immunohistochemistry (ER, PgR, HER2, Ki-67, p53, CK5/6, CK 7/8, EGFR, BCL-2, MUC1, VEGF, LKB1, BRCA1, HER3, HER4, PTEN and AIB1). Expression of each biomarker was dichotomised into ‘low’ or ‘high’ based on breast cancer-specific survival (BCSS).

Results

From the panel of biomarkers, multivariate analysis showed:

High ER (p = 0.003) and PgR (p = 0.002) were associated with clinical benefit of PET at 6 months, as opposed to progressive disease.

High ER (p = 0.0023), PgR (p < 0.001) and BCL-2 (p = 0.043) and low LKB1 (p = 0.022) were associated with longer time to progression.

High PgR (p < 0.001) and low MUC1 (p = 0.021) were associated with better BCSS.

Expression of other biomarkers did not show any significant correlation.

Conclusions

In addition to ER and PgR; MUC1, BCL-2 and LKB1 are important in determining the outcome of PET in this cohort.

Electronic supplementary material

The online version of this article (10.1007/s10549-020-06023-4) contains supplementary material, which is available to authorised users.

Role of a schistosoma haematobium specific microRNA as a predictive and prognostic tool for bilharzial bladder cancer in Egypt

Urinary bladder cancer is a common malignancy in Egypt, thus reliable methodologies are required for screening and early detection. In this study, we analyzed the gene expression of a Schistosoma hematobium specific microRNA "Sha-miR-71a" and mitogen-associated protein kinase-3 (MAPK-3) in the urine samples of 50 bladder cancer patients and 50 patients with benign bilharzial cystitis. Fifty control subjects were also tested. Indirect hemagglutination test (IHA) diagnosed 70% of studied cancer cases as bilharzial associated bladder cancer (BBC), while histopathological examination detected only 18%. Urinary Sha-miR-71a & MAPK-3 revealed enhanced expression in BBC (p-value = 0.001) compared to non-bilharzial bladder cancer (NBBC) cases. Patients with chronic bilharzial cystitis exhibited a significant increase in gene expression compared to those with acute infection (p-value = 0.001). Sha-miR-71a and MAPK-3 showed good sensitivity and specificity in the diagnosis of BBC when analyzed by the receiver operating characteristic (ROC) curve. They were also prognostic regarding malignancy grade. Both biomarkers showed a positive correlation. Our results revealed that IHA is a reliable test in the diagnosis of bilharziasis associated with bladder cancer, and that Sha-miR-71a and MAPK-3 provide non-invasive specific biomarkers to diagnose BBC, as well as a potential role in testing bilharzial patients for risk to develop cancer.

High-dimensionality Data Analysis of Pharmacological Systems Associated with Complex Diseases

It is widely accepted that molecular reductionist views of highly complex human physiologic activity, e.g., the aging process, as well as therapeutic drug efficacy are largely oversimplifications. Currently some of the most effective appreciation of biologic disease and drug response complexity is achieved using high-dimensionality (H-D) data streams from transcriptomic, proteomic, metabolomics, or epigenomic pipelines. Multiple H-D data sets are now common and freely accessible for complex diseases such as metabolic syndrome, cardiovascular disease, and neurodegenerative conditions such as Alzheimer's disease. Over the last decade our ability to interrogate these high-dimensionality data streams has been profoundly enhanced through the development and implementation of highly effective bioinformatic platforms. Employing these computational approaches to understand the complexity of age-related diseases provides a facile mechanism to then synergize this pathologic appreciation with a similar level of understanding of therapeutic-mediated signaling. For informative pathology and drug-based analytics that are able to generate meaningful therapeutic insight across diverse data streams, novel informatics processes such as latent semantic indexing and topological data analyses will likely be important. Elucidation of H-D molecular disease signatures from diverse data streams will likely generate and refine new therapeutic strategies that will be designed with a cognizance of a realistic appreciation of the complexity of human age-related disease and drug effects. We contend that informatic platforms should be synergistic with more advanced chemical/drug and phenotypic cellular/tissue-based analytical predictive models to assist in either de novo drug prioritization or effective repurposing for the intervention of aging-related diseases. SIGNIFICANCE STATEMENT: All diseases, as well as pharmacological mechanisms, are far more complex than previously thought a decade ago. With the advent of commonplace access to technologies that produce large volumes of high-dimensionality data (e.g., transcriptomics, proteomics, metabolomics), it is now imperative that effective tools to appreciate this highly nuanced data are developed. Being able to appreciate the subtleties of high-dimensionality data will allow molecular pharmacologists to develop the most effective multidimensional therapeutics with effectively engineered efficacy profiles.

Risk Assessment Program of Highly Pathogenic Avian Influenza with Deep Learning Algorithm

Objectives

This study presents the development and validation of a risk assessment program of highly pathogenic avian influenza (HPAI). This program was developed by the Korean government (Animal and Plant Quarantine Agency) and a private corporation (Korea Telecom, KT), using a national database (Korean animal health integrated system, KAHIS).

Methods

Our risk assessment program was developed using the multilayer perceptron method using R Language. HPAI outbreaks on 544 poultry farms (307 with H5N6, and 237 with H5N8) that had available visit records of livestock-related vehicles amongst the 812 HPAI outbreaks that were confirmed between January 2014 and June 2017 were involved in this study.

Results

After 140,000 iterations without drop-out, a model with 3 hidden layers and 10 nodes per layer, were selected. The activation function of the model was hyperbolic tangent. Precision and recall of the test gave F1 measures of 0.41, 0.68 and 0.51, respectively, at validation. The predicted risk values were higher for the “outbreak” (average ± SD, 0.20 ± 0.31) than “non-outbreak” (0.18 ± 0.30) farms (p < 0.001).

Conclusion

The risk assessment model developed was employed during the epidemics of 2016/2017 (pilot version) and 2017/2018 (complementary version). This risk assessment model enhanced risk management activities by enabling preemptive control measures to prevent the spread of diseases.

Identification of flux checkpoints in a metabolic pathway through white-box, grey-box and black-box modeling approaches

Metabolic pathway modeling plays an increasing role in drug design by allowing better understanding of the underlying regulation and controlling networks in the metabolism of living organisms. However, despite rapid progress in this area, pathway modeling can become a real nightmare for researchers, notably when few experimental data are available or when the pathway is highly complex. Here, three different approaches were developed to model the second part of glycolysis of E. histolytica as an application example, and have succeeded in predicting the final pathway flux: one including detailed kinetic information (white-box), another with an added adjustment term (grey-box) and the last one using an artificial neural network method (black-box). Afterwards, each model was used for metabolic control analysis and flux control coefficient determination. The first two enzymes of this pathway are identified as the key enzymes playing a role in flux control. This study revealed the significance of the three methods for building suitable models adjusted to the available data in the field of metabolic pathway modeling, and could be useful to biologists and modelers.

Biology of Oestrogen-Receptor Positive Primary Breast Cancer in Older Women with Utilisation of Core Needle Biopsy Samples and Correlation with Clinical Outcome

The majority of biological profiling studies use surgical excision (SE) samples, excluding patients receiving nonsurgical and neoadjuvant therapy. We propose using core needle biopsy (CNB) for biological profiling in older women. Over 37 years (1973–2010), 1 758 older (≥70 years) women with operable primary breast cancer attended a dedicated clinic. Of these, 693 had sufficient quality CNB to construct tissue microarray (TMA). The pattern of biomarkers was analysed in oestrogen receptor (ER)-positive cases, using immunohistochemistry and partitional clustering analysis. The biomarkers measured were: progesterone receptor (PgR), Ki67, Epidermal Growth Factor Receptor (EGFR), Human Epidermal Growth Factor Receptor (HER)-2, HER3, HER4, p53, cytokeratins CK5/6 and CK7/8, Mucin (MUC)1, liver kinase B1 (LKB1), Breast Cancer Associated gene (BRCA) 1, B-Cell Lymphoma (BCL)-2, phosphate and tensin homolog (PTEN), vascular endothelial growth factor (VEGF), and Amplified in breast cancer 1 (AIB1). CNB TMA construction was possible in 536 ER-positive cases. Multivariate analysis showed progesterone receptor (PgR) (p = 0.015), Ki67 (p = 0.001), and mucin (MUC)1 (p = 0.033) as independent predictors for breast-cancer-specific survival (BCSS). Cluster analysis revealed three biological clusters, which were consistent with luminal A, luminal B, and low-ER luminal. The low-ER luminal cluster had lower BCSS compared to luminal A and B. The presence of the low-ER luminal cluster unique to older women, identified in a previous study in SE TMAs in the same cohort, is confirmed. This present study is novel in its use of core needle biopsy tissue microarrays to profile the biology of breast cancer in older women.

Identifying playing talent in professional football using artificial neural networks

The aim of the current study was to objectively identify position-specific key performance indicators in professional football that predict out-field players league status. The sample consisted of 966 out-field players who completed the full 90 minutes in a match during the 2008/09 or 2009/10 season in the Football League Championship. Players were assigned to one of three categories (0, 1 and 2) based on where they completed most of their match time in the following season, and then split based on five playing positions. 340 performance, biographical and esteem variables were analysed using a Stepwise Artificial Neural Network approach. The models correctly predicted between 72.7% and 100% of test cases (Mean prediction of models = 85.9%), the test error ranged from 1.0% to 9.8% (Mean test error of models = 6.3%). Variables related to passing, shooting, regaining possession and international appearances were key factors in the predictive models. This is highly significant as objective position-specific predictors of players league status have not previously been published. The method could be used to aid the identification and comparison of transfer targets as part of the due diligence process in professional football.

Harnessing the potential of artificial neural networks for predicting protein glycosylation

Kinetic models offer incomparable insight on cellular mechanisms controlling protein glycosylation. However, their ability to reproduce site-specific glycoform distributions depends on accurate estimation of a large number of protein-specific kinetic parameters and prior knowledge of enzyme and transport protein levels in the Golgi membrane. Herein we propose an artificial neural network (ANN) for protein glycosylation and apply this to four recombinant glycoproteins produced in Chinese hamster ovary (CHO) cells, two monoclonal antibodies and two fusion proteins. We demonstrate that the ANN model accurately predicts site-specific glycoform distributions of up to eighteen glycan species with an average absolute error of 1.1%, correctly reproducing the effect of metabolic perturbations as part of a hybrid, kinetic/ANN, glycosylation model (HyGlycoM), as well as the impact of manganese supplementation and glycosyltransferase knock out experiments as a stand-alone machine learning algorithm. These results showcase the potential of machine learning and hybrid approaches for rapidly developing performance-driven models of protein glycosylation.

Machine Learning Neuroprotective Strategy Reveals a Unique Set of Parkinson Therapeutic Nicotine Analogs

AIMS

Present a novel machine learning computational strategy to predict the neuroprotection potential of nicotine analogs acting over the behavior of unpaired signaling pathways in Parkinson's disease.

BACKGROUND

Dopaminergic replacement has been used for Parkinson's Disease (PD) treatment with positive effects on motor symptomatology but low progression and prevention effects. Epidemiological studies have shown that nicotine consumption decreases PD prevalence through neuroprotective mechanisms activation associated with the overstimulation of signaling pathways (SP) such as PI3K/AKT through nicotinic acetylcholine receptors (e.g α7 nAChRs) and over-expression of anti-apoptotic genes such as Bcl-2. Nicotine analogs with similar neuroprotective activity but decreased secondary effects remain as a promissory field.

OBJECTIVE

The objective of this study is to develop an interdisciplinary computational strategy predicting the neuroprotective activity of a series of 8 novel nicotine analogs over Parkinson's disease.

METHODS

We present a computational strategy integrating structural bioinformatics, SP manual reconstruction, and deep learning to predict the potential neuroprotective activity of 8 novel nicotine analogs over the behavior of PI3K/AKT. We performed a protein-ligand analysis between nicotine analogs and α7 nAChRs receptor using geometrical conformers, physicochemical characterization of the analogs and developed manually curated neuroprotective datasets to analyze their potential activity. Additionally, we developed a predictive machine-learning model for neuroprotection in PD through the integration of Markov Chain Monte-Carlo transition matrix for the 2 SP with synthetic training datasets of the physicochemical properties and structural dataset.

RESULTS

Our model was able to predict the potential neuroprotective activity of seven new nicotine analogs based on the binomial Bcl-2 response regulated by the activation of PI3K/AKT.

CONCLUSION

Hereby, we present a robust novel strategy to assess the neuroprotective potential of biomolecules based on SP architecture. Our theoretical strategy can be further applied to the study of new treatments related to SP deregulation and may ultimately offer new opportunities for therapeutic interventions in neurodegenerative diseases.

Study of the Binding Pattern of HLA Class I Alleles of Indian Frequency and cTAP Binding Peptide for Chikungunya Vaccine Development

Chikungunya is a mosquito-borne disease, caused by the member of the Togaviridae family belongs to the genus alphavirus, making it a major threat in all developing countries as well as some developed countries. The mosquito acts as a vector for the disease and carries the CHIK-Virus. To date there is no direct treatment available and that demands the development of more effective vaccines. In this study author employed Immune Epitope Database and Analysis Resource, a machine learning-based algorithm principally working on the Artificial Neural Network (ANN) algorithm, also known as (IEDB-ANN) for the prediction and analysis of Epitopes. A total of 173 epitopes were identified on the basis of IC50 values, among them 40 epitopes were found, sharing part with the linear B-cell epitopes and exposed to the cTAP1protein, and out of 40, 6 epitopes were noticed to show interactions with the cTAP with their binding energy ranging from - 3.61 to - 1.22 kcal/mol. The six epitopes identified were exposed to the HLA class I alleles and from this all revealed interaction with the HLA alleles and minimum binding energy that ranges from - 4.12 to - 5.88 kcal/mol. Besides, two T cell epitopes i.e. 145KVFTGVYPE153 and 395STVPVAPPR403 were found most promiscuous candidates. These promiscuous epitopes-HLA complexes were further analyzed by the molecular dynamics simulation to check the stability of the complex. Results obtained from this study suggest that the identified epitopes i.e. and 395 STVPVAPPR 403 , are likely to be capable of passing through the lumen of ER to bind withthe HLA class I allele and provide new insights and potential application in the designing and development of peptide-based vaccine candidate for the treatment of chikungunya.

Application of preoperative artificial neural network based on blood biomarkers and clinicopathological parameters for predicting long-term survival of patients with gastric cancer

BACKGROUND

Because of the powerful abilities of self-learning and handling complex biological information, artificial neural network (ANN) models have been widely applied to disease diagnosis, imaging analysis, and prognosis prediction. However, there has been no trained preoperative ANN (preope-ANN) model to preoperatively predict the prognosis of patients with gastric cancer (GC).

AIM

To establish a neural network model that can predict long-term survival of GC patients before surgery to evaluate the tumor condition before the operation.

METHODS

The clinicopathological data of 1608 GC patients treated from January 2011 to April 2015 at the Department of Gastric Surgery, Fujian Medical University Union Hospital were analyzed retrospectively. The patients were randomly divided into a training set (70%) for establishing a preope-ANN model and a testing set (30%). The prognostic evaluation ability of the preope-ANN model was compared with that of the American Joint Commission on Cancer (8^th edition) clinical TNM (cTNM) and pathological TNM (pTNM) staging through the receiver operating characteristic curve, Akaike information criterion index, Harrell's C index, and likelihood ratio chi-square.

RESULTS

We used the variables that were statistically significant factors for the 3-year overall survival as input-layer variables to develop a preope-ANN in the training set. The survival curves within each score of the preope-ANN had good discrimination (P < 0.05). Comparing the preope-ANN model, cTNM, and pTNM in both the training and testing sets, the preope-ANN model was superior to cTNM in predictive discrimination (C index), predictive homogeneity (likelihood ratio chi-square), and prediction accuracy (area under the curve). The prediction efficiency of the preope-ANN model is similar to that of pTNM.

CONCLUSION

The preope-ANN model can accurately predict the long-term survival of GC patients, and its predictive efficiency is not inferior to that of pTNM stage.

Predicting degradation rate of genipin cross-linked gelatin scaffolds with machine learning

Genipin can improve weak mechanical properties and control high degradation rate of gelatin, as a cross-linker of gelatin which is widely used in tissue engineering. In this study, genipin cross-linked gelatin biodegradable porous scaffolds with different weight percentages of gelatin and genipin were prepared for tissue regeneration and measurement of their various properties including morphological characteristics, mechanical properties, swelling, degree of crosslinking and degradation rate. Results indicated that the sample containing the highest amount of gelatin and genipin had the highest degree of crosslinking and increasing the percentage of genipin from 0.125% to 0.5% enhances ultimate tensile strength (UTS) up to 113% and 92%, for samples with 2.5% and 10% gelatin, respectively. For these samples, increasing the percentage of genipin, reduce their degradation rate significantly with an average value of 124%. Furthermore, experimental data are used to develop a machine learning model, which compares artificial neural networks (ANN) and kernel ridge regression (KRR) to predict degradation rate of genipin-cross-linked gelatin scaffolds as a property of interest. The predicted degradation rate demonstrates that the ANN, with mean squared error (MSE) of 2.68%, outperforms the KRR with MSE = 4.78% in terms of accuracy. These results suggest that machine learning models offer an excellent prediction accuracy to estimate the degradation rate which will significantly help reducing experimental costs needed to carry out scaffold design.

Deep neural networks for single shot structured light profilometry

In 3D optical metrology, single-shot structured light profilometry techniques have inherent advantages over their multi-shot counterparts in terms of measurement speed, optical setup simplicity, and robustness to motion artifacts. In this paper, we present a new approach to extract height information from single deformed fringe patterns, based entirely on deep learning. By training a fully convolutional neural network on a large set of simulated height maps with corresponding deformed fringe patterns, we demonstrate the ability of the network to obtain full-field height information from previously unseen fringe patterns with high accuracy. As an added benefit, intermediate data processing steps such as background masking, noise reduction and phase unwrapping that are otherwise required in classic demodulation strategies, can be learned directly by the network as part of its mapping function.

Architectures and accuracy of artificial neural network for disease classification from omics data

BACKGROUND

Deep learning has made tremendous successes in numerous artificial intelligence applications and is unsurprisingly penetrating into various biomedical domains. High-throughput omics data in the form of molecular profile matrices, such as transcriptomes and metabolomes, have long existed as a valuable resource for facilitating diagnosis of patient statuses/stages. It is timely imperative to compare deep learning neural networks against classical machine learning methods in the setting of matrix-formed omics data in terms of classification accuracy and robustness.

RESULTS

Using 37 high throughput omics datasets, covering transcriptomes and metabolomes, we evaluated the classification power of deep learning compared to traditional machine learning methods. Representative deep learning methods, Multi-Layer Perceptrons (MLP) and Convolutional Neural Networks (CNN), were deployed and explored in seeking optimal architectures for the best classification performance. Together with five classical supervised classification methods (Linear Discriminant Analysis, Multinomial Logistic Regression, Naïve Bayes, Random Forest, Support Vector Machine), MLP and CNN were comparatively tested on the 37 datasets to predict disease stages or to discriminate diseased samples from normal samples. MLPs achieved the highest overall accuracy among all methods tested. More thorough analyses revealed that single hidden layer MLPs with ample hidden units outperformed deeper MLPs. Furthermore, MLP was one of the most robust methods against imbalanced class composition and inaccurate class labels.

CONCLUSION

Our results concluded that shallow MLPs (of one or two hidden layers) with ample hidden neurons are sufficient to achieve superior and robust classification performance in exploiting numerical matrix-formed omics data for diagnosis purpose. Specific observations regarding optimal network width, class imbalance tolerance, and inaccurate labeling tolerance will inform future improvement of neural network applications on functional genomics data.

Prognostic relevance and performance characteristics of serum IGFBP-2 and PAPP-A in women with breast cancer: a long-term Danish cohort study

Measurement of circulating insulin‐like growth factors (IGFs), in particular IGF‐binding protein (IGFBP)‐2, at the time of diagnosis, is independently prognostic in many cancers, but its clinical performance against other routinely determined prognosticators has not been examined. We measured IGF‐I, IGF‐II, pro‐IGF‐II, IGF bioactivity, IGFBP‐2, ‐3, and pregnancy‐associated plasma protein A (PAPP‐A), an IGFBP regulator, in baseline samples of 301 women with breast cancer treated on four protocols (Odense, Denmark: 1993–1998). We evaluated performance characteristics (expressed as area under the curve, AUC) using Cox regression models to derive hazard ratios (HR) with 95% confidence intervals (CIs) for 10‐year recurrence‐free survival (RFS) and overall survival (OS), and compared those against the clinically used Nottingham Prognostic Index (NPI). We measured the same biomarkers in 531 noncancer individuals to assess multidimensional relationships (MDR), and evaluated additional prognostic models using survival artificial neural network (SANN) and survival support vector machines (SSVM), as these enhance capture of MDRs. For RFS, increasing concentrations of circulating IGFBP‐2 and PAPP‐A were independently prognostic [HR_{biomarker doubling}: 1.474 (95% CIs: 1.160, 1.875, P = 0.002) and 1.952 (95% CIs: 1.364, 2.792, P < 0.001), respectively]. The AUC_RFS for NPI was 0.626 (Cox model), improving to 0.694 (P = 0.012) with the addition of IGFBP‐2 plus PAPP‐A. Derived AUC_RFS using SANN and SSVM did not perform superiorly. Similar patterns were observed for OS. These findings illustrate an important principle in biomarker qualification—measured circulating biomarkers may demonstrate independent prognostication, but this does not necessarily translate into substantial improvement in clinical performance.

Analysis of Gene Regulatory Networks of Maize in Response to Nitrogen

Nitrogen (N) fertilizer has a major influence on the yield and quality. Understanding and optimising the response of crop plants to nitrogen fertilizer usage is of central importance in enhancing food security and agricultural sustainability. In this study, the analysis of gene regulatory networks reveals multiple genes and biological processes in response to N. Two microarray studies have been used to infer components of the nitrogen-response network. Since they used different array technologies, a map linking the two probe sets to the maize B73 reference genome has been generated to allow comparison. Putative Arabidopsis homologues of maize genes were used to query the Biological General Repository for Interaction Datasets (BioGRID) network, which yielded the potential involvement of three transcription factors (TFs) (GLK5, MADS64 and bZIP108) and a Calcium-dependent protein kinase. An Artificial Neural Network was used to identify influential genes and retrieved bZIP108 and WRKY36 as significant TFs in both microarray studies, along with genes for Asparagine Synthetase, a dual-specific protein kinase and a protein phosphatase. The output from one study also suggested roles for microRNA (miRNA) 399b and Nin-like Protein 15 (NLP15). Co-expression-network analysis of TFs with closely related profiles to known Nitrate-responsive genes identified GLK5, GLK8 and NLP15 as candidate regulators of genes repressed under low Nitrogen conditions, while bZIP108 might play a role in gene activation.

An Artificial Neural Network Integrated Pipeline for Biomarker Discovery Using Alzheimer's Disease as a Case Study

The field of machine learning has allowed researchers to generate and analyse vast amounts of data using a wide variety of methodologies. Artificial Neural Networks (ANN) are some of the most commonly used statistical models and have been successful in biomarker discovery studies in multiple disease types. This review seeks to explore and evaluate an integrated ANN pipeline for biomarker discovery and validation in Alzheimer's disease, the most common form of dementia worldwide with no proven cause and no available cure. The proposed pipeline consists of analysing public data with a categorical and continuous stepwise algorithm and further examination through network inference to predict gene interactions. This methodology can reliably generate novel markers and further examine known ones and can be used to guide future research in Alzheimer's disease.

Inferring gene and protein interactions using PubMed citations and consensus Bayesian networks

The PubMed database offers an extensive set of publication data that can be useful, yet inherently complex to use without automated computational techniques. Data repositories such as the Genomic Data Commons (GDC) and the Gene Expression Omnibus (GEO) offer experimental data storage and retrieval as well as curated gene expression profiles. Genetic interaction databases, including Reactome and Ingenuity Pathway Analysis, offer pathway and experiment data analysis using data curated from these publications and data repositories. We have created a method to generate and analyze consensus networks, inferring potential gene interactions, using large numbers of Bayesian networks generated by data mining publications in the PubMed database. Through the concept of network resolution, these consensus networks can be tailored to represent possible genetic interactions. We designed a set of experiments to confirm that our method is stable across variation in both sample and topological input sizes. Using gene product interactions from the KEGG pathway database and data mining PubMed publication abstracts, we verify that regardless of the network resolution or the inferred consensus network, our method is capable of inferring meaningful gene interactions through consensus Bayesian network generation with multiple, randomized topological orderings. Our method can not only confirm the existence of currently accepted interactions, but has the potential to hypothesize new ones as well. We show our method confirms the existence of known gene interactions such as JAK-STAT-PI3K-AKT-mTOR, infers novel gene interactions such as RAS- Bcl-2 and RAS-AKT, and found significant pathway-pathway interactions between the JAK-STAT signaling and Cardiac Muscle Contraction KEGG pathways.

ChimeRScope: a novel alignment-free algorithm for fusion transcript prediction using paired-end RNA-Seq data

The RNA-Seq technology has revolutionized transcriptome characterization not only by accurately quantifying gene expression, but also by the identification of novel transcripts like chimeric fusion transcripts. The ‘fusion’ or ‘chimeric’ transcripts have improved the diagnosis and prognosis of several tumors, and have led to the development of novel therapeutic regimen. The fusion transcript detection is currently accomplished by several software packages, primarily relying on sequence alignment algorithms. The alignment of sequencing reads from fusion transcript loci in cancer genomes can be highly challenging due to the incorrect mapping induced by genomic alterations, thereby limiting the performance of alignment-based fusion transcript detection methods. Here, we developed a novel alignment-free method, ChimeRScope that accurately predicts fusion transcripts based on the gene fingerprint (as k-mers) profiles of the RNA-Seq paired-end reads. Results on published datasets and in-house cancer cell line datasets followed by experimental validations demonstrate that ChimeRScope consistently outperforms other popular methods irrespective of the read lengths and sequencing depth. More importantly, results on our in-house datasets show that ChimeRScope is a better tool that is capable of identifying novel fusion transcripts with potential oncogenic functions. ChimeRScope is accessible as a standalone software at (https://github.com/ChimeRScope/ChimeRScope/wiki) or via the Galaxy web-interface at (https://galaxy.unmc.edu/).

Identification of Filamin-A and -B as potential biomarkers for prostate cancer

Aim:

A novel strategy for prostate cancer (PrCa) biomarker discovery is described.

Materials & methods:

In vitro perturbation biology, proteomics and Bayesian causal analysis identified biomarkers that were validated in in vitro models and clinical specimens.

Results:

Filamin-B (FLNB) and Keratin-19 were identified as biomarkers. Filamin-A (FLNA) was found to be causally linked to FLNB. Characterization of the biomarkers in a panel of cells revealed differential mRNA expression and regulation. Moreover, FLNA and FLNB were detected in the conditioned media of cells. Last, in patients without PrCa, FLNA and FLNB blood levels were positively correlated, while in patients with adenocarcinoma the relationship is dysregulated.

Conclusion:

These data support the strategy and the potential use of the biomarkers for PrCa.

The goal of this study was to use a novel strategy that combines biological outputs with Bayesian network learning to identify potential biomarkers for prostate cancer (PrCa). This methodology identified two proteins, filamin B and keratin-19, as potential biomarkers for PrCa. The network map also identified a direct linkage between filamin B and filamin A, which is a protein that has previously been identified as playing a role in PrCa etiology. The identified proteins were then validated by examining their levels in a panel of PrCa cell lines and in human plasma samples.

Artificial neural network classifier predicts neuroblastoma patients' outcome

Background

More than fifty percent of neuroblastoma (NB) patients with adverse prognosis do not benefit from treatment making the identification of new potential targets mandatory. Hypoxia is a condition of low oxygen tension, occurring in poorly vascularized tissues, which activates specific genes and contributes to the acquisition of the tumor aggressive phenotype. We defined a gene expression signature (NB-hypo), which measures the hypoxic status of the neuroblastoma tumor. We aimed at developing a classifier predicting neuroblastoma patients’ outcome based on the assessment of the adverse effects of tumor hypoxia on the progression of the disease.

Methods

Multi-layer perceptron (MLP) was trained on the expression values of the 62 probe sets constituting NB-hypo signature to develop a predictive model for neuroblastoma patients’ outcome. We utilized the expression data of 100 tumors in a leave-one-out analysis to select and construct the classifier and the expression data of the remaining 82 tumors to test the classifier performance in an external dataset. We utilized the Gene set enrichment analysis (GSEA) to evaluate the enrichment of hypoxia related gene sets in patients predicted with “Poor” or “Good” outcome.

Results

We utilized the expression of the 62 probe sets of the NB-Hypo signature in 182 neuroblastoma tumors to develop a MLP classifier predicting patients’ outcome (NB-hypo classifier). We trained and validated the classifier in a leave-one-out cross-validation analysis on 100 tumor gene expression profiles. We externally tested the resulting NB-hypo classifier on an independent 82 tumors’ set. The NB-hypo classifier predicted the patients’ outcome with the remarkable accuracy of 87 %. NB-hypo classifier prediction resulted in 2 % classification error when applied to clinically defined low-intermediate risk neuroblastoma patients. The prediction was 100 % accurate in assessing the death of five low/intermediated risk patients. GSEA of tumor gene expression profile demonstrated the hypoxic status of the tumor in patients with poor prognosis.

Conclusions

We developed a robust classifier predicting neuroblastoma patients’ outcome with a very low error rate and we provided independent evidence that the poor outcome patients had hypoxic tumors, supporting the potential of using hypoxia as target for neuroblastoma treatment.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-016-1194-3) contains supplementary material, which is available to authorized users.