Search

• Data doppelgängers abound in biological data. • Data doppelgängers confound machine learning performance. • Data doppelgängers should be identified before model validation. Machine learning (ML) models have been increasingly adopted in drug development for faster identification of potential targets. Cross-validation techniques are commonly used to evaluate these models. However, the reliability of such validation methods can be affected by the presence of data doppelgängers. Data doppelgängers occur when independently derived data are very similar to each other, causing models to perform well regardless of how they are trained (i.e., the doppelgänger effect). Despite the abundance of data doppelgängers in biomedical data and their inflationary effects, they remain uncharacterized. We show their prevalence in biomedical data, demonstrate how doppelgängers arise, and provide proof of their confounding effects. To mitigate the doppelgänger effect, we recommend identifying data doppelgängers before the training-validation split. [ABSTRACT FROM AUTHOR]

Highlights • Meta-analysis can lead towards better signature inference. • Careful and systematic evaluation can produce robust signatures. • The generalizability test is a tough but rigorous guard against trivial association. Reproducible and generalizable gene signatures are essential for clinical deployment, but are hard to come by. The primary issue is insufficient mitigation of confounders: ensuring that hypotheses are appropriate, test statistics and null distributions are appropriate, and so on. To further improve robustness, additional good analytical practices (GAPs) are needed, namely: leveraging existing data and knowledge; careful and systematic evaluation of gene sets, even if they overlap with known sources of confounding; and rigorous testing of inferred signatures against as many published data sets as possible. Here, using a re-examination of a breast cancer data set and 48 published signatures, we illustrate the value of adopting these GAPs. [ABSTRACT FROM AUTHOR]

Random signature superiority (RSS) occurs when random gene signatures outperform published and/or known signatures. Unlike reproducibility and generalizability issues, RSS is relatively underexplored. Yet, understanding it is imperative for better analytical outcome. In breast cancer, RSS correlates strongly with enrichment for proliferation genes and signature size. Removal of proliferation genes from random signatures reduces the predictive power of random signatures. Almost all genes are correlated to a certain extent with the proliferation signature, making complete elimination of its confounding effects impossible. RSS goes beyond breast cancer, because it also exists in other diseases; it is especially strong in other cancers in a platform-independent manner, and less severe, but present nonetheless, in nonproliferative diseases. [ABSTRACT FROM AUTHOR]

Proteins physically interact with each other and form protein complexes to perform their biological functions. The prediction of protein complexes from protein–protein interaction (PPI) network is usually difficult when the complexes are overlapping with each other in a dense region of the network. To address the problem of predicting overlapping complexes, a previously proposed network–decomposition approach is promising. It decomposes a PPI network by e.g. removing proteins with high degree (hubs) which may participate in different complexes. This motivates us to examine a list of proteins, which bind their different partners at different time or at different location (viz. date hubs), manually collected from literature, for network decomposition. Results show that the CMC complex discovery algorithm after removing date hubs recalls more overlapping complexes that were missed earlier. Further improvement in performance is achieved when we predict date hub proteins based on simple network features and remove them from PPI networks. [ABSTRACT FROM AUTHOR]

The Anna Karenina effect is a manifestation of the theory–practice gap that exists when theoretical statistics are applied on real-world data. In the course of analyzing biological data for differential features such as genes or proteins, it derives from the situation where the null hypothesis is rejected for extraneous reasons (or confounders), rather than because the alternative hypothesis is relevant to the disease phenotype. The mechanics of applying statistical tests therefore must address and resolve confounders. It is inadequate to simply rely on manipulating the P -value. We discuss three mechanistic elements (hypothesis statement construction, null distribution appropriateness, and test-statistic construction) and suggest how they can be designed to foil the Anna Karenina effect to select phenotypically relevant biological features. [ABSTRACT FROM AUTHOR]

A missing protein (MP) is an unconfirmed genetic sequence for which a protein product is not yet detected. Currently, MPs are tiered based on supporting evidence mainly in the form of protein existence (PE) classification. As we discuss here, this definition is overly restrictive because proteins go missing in day-to-day proteomics as a result of low abundance, lack of sequence specificity, splice variants, and so on. Thus, we propose a broader functional classification of MPs that complements PE classification, discuss major causes, and examine three corresponding solution tiers: biological, technical, and informatics. We assert that informatics-driven solutions would have a major role in resolving the MP problem (MPP). [ABSTRACT FROM AUTHOR]

Networks can resolve many analytical problems in proteomics, including incomplete coverage and inconsistency. Despite high expectations, network-related research in proteomics has experienced only modest growth. In practice, most current research examines non-quantitative usages, for example determining physical interactions among proteins or contextualizing a differential protein list, rather than addressing practical quantitative usages, for example predicting missing proteins or making sample-class predictions. Moreover, many applications are irreproducible and are not widely adopted owing to a lack of common standards, particularly evaluation criteria and gold-standard datasets. A concerted drive towards quantitative applications and convergence towards common standards is essential for ‘network-based proteomics’ to realize its development potential and make meaningful contributions to clinical applications. [ABSTRACT FROM AUTHOR]

Integrating biological networks with proteomics is a tantalizing option for system-level analysis; for example it can help remove false-positives from proteomics data and improve coverage by detecting false-negatives, as well as resolving inconsistent inter-sample protein expression due to biological heterogeneity. Yet, designing a robust network-based analysis strategy on proteomics data is nontrivial. The issues include dealing with test set bias caused by, for example, inappropriate normalization procedure, devising appropriate benchmarking criteria and formulating statistically robust feature-selection techniques. Given the increasing importance of proteomics in contemporary clinical studies, more powerful network-based approaches are needed. We provide some design principles and considerations that can help achieve this, while taking into account the idiosyncrasies of proteomics data. [ABSTRACT FROM AUTHOR]

Highlights: [•] Proper combination of proteomics with bioinformatics is highly synergistic. [•] Appropriate experimental design is needed for proper bioinformatics analysis. [•] Enhanced resolution renders proteomics suitable for functional studies. [•] New discovery paradigms can lead to novel drug targets/biomarkers. [Copyright &y& Elsevier]

Proteomics provides direct biological information on proteins but is still a limited platform. Borrowing from genomics, its cancer-specific applications can be broadly categorized as (1) pure diagnostics, (2) biomarkers, (3) identification of root causes and (4) identification of cancer-specific network rewirings. Biological networks capture complex relationships between proteins and provide an appropriate means of contextualization. While playing significantly larger roles, especially in 1 and 3, progress in proteomics-specific network-based methods is lagging as compared to genomics. Rapid hardware advances and improvements in proteomic identification and quantification have given rise to much better quality data alongside advent of new network-based analysis methods. However, a tighter integration between analytics and hardware is still essential for network analysis to play more significant roles in proteomics analysis. [Copyright &y& Elsevier]

Protein interactions are crucial components of all cellular processes. An in-depth knowledge of the full complement of protein interactions in a cell, therefore, provides insight into the structure, properties and functions of the cell and its components. An accurate and comprehensive protein interaction network is, thus, an invaluable framework to study protein regulation in disease. Although the amount of protein–protein interaction data has grown significantly because of advances in high-throughput experimental techniques, these high-throughput methods are highly susceptible to noise. Therefore, computational techniques for assessing the reliability of a protein–protein interaction are highly desirable. We review here computational techniques for assessing and improving the reliability of protein–protein interaction data from these high-throughput experiments. [Copyright &y& Elsevier]

Batch effects (BEs) are technical biases that may confound analysis of high-throughput biotechnological data. BEs are complex and effective mitigation is highly context-dependent. In particular, the advent of high-resolution technologies such as single-cell RNA sequencing presents new challenges. We first cover how BE modeling differs between traditional datasets and the new data landscape. We also discuss new approaches for measuring and mitigating BEs, including whether a BE is significant enough to warrant correction. Even with the advent of machine learning and artificial intelligence, the increased complexity of next-generation biotechnological data means increased complexities in BE management. We forecast that BEs will not only remain relevant in the age of big data but will become even more important. As data expands in size and complexity, batch effect correction will become even more important. Batch effect-correction methods based on machine learning approaches will become commonplace. Better batch effect visualization methods are needed. [ABSTRACT FROM AUTHOR]

• Missing value imputation and batch effect correction are inter-dependent. • Batch-sensitized missing value imputation is useful. • Accounting for missing information improves batch effect correction. In data-processing pipelines, upstream steps can influence downstream processes because of their sequential nature. Among these data-processing steps, batch effect (BE) correction (BEC) and missing value imputation (MVI) are crucial for ensuring data suitability for advanced modeling and reducing the likelihood of false discoveries. Although BEC–MVI interactions are not well studied, they are ultimately interdependent. Batch sensitization can improve the quality of MVI. Conversely, accounting for missingness also improves proper BE estimation in BEC. Here, we discuss how BEC and MVI are interconnected and interdependent. We show how batch sensitization can improve any MVI and bring attention to the idea of BE-associated missing values (BEAMs). Finally, we discuss how batch-class imbalance problems can be mitigated by borrowing ideas from machine learning. [ABSTRACT FROM AUTHOR]

Effective integration and analysis of new high-throughput data, especially gene-expression and proteomic-profiling data, are expected to deliver novel clinical insights and therapeutic options. Unfortunately, technical heterogeneity or batch effects (different experiment times, handlers, reagent lots, etc.) have proven challenging. Although batch effect-correction algorithms (BECAs) exist, we know little about effective batch-effect mitigation: even now, new batch effect-associated problems are emerging. These include false effects due to misapplying BECAs and positive bias during model evaluations. Depending on the choice of algorithm and experimental set-up, biological heterogeneity can be mistaken for batch effects and wrongfully removed. Here, we examine these emerging batch effect-associated problems, propose a series of best practices, and discuss some of the challenges that lie ahead. [ABSTRACT FROM AUTHOR]

Abstract: A sequential rule expresses a relationship between two series of events happening one after another. Sequential rules are potentially useful for analyzing data in sequential format, ranging from purchase histories, network logs and program execution traces. In this work, we investigate and propose a syntactic characterization of a non-redundant set of sequential rules built upon past work on compact set of representative patterns. A rule is redundant if it can be inferred from another rule having the same support and confidence. When using the set of mined rules as a composite filter, replacing a full set of rules with a non-redundant subset of the rules does not impact the accuracy of the filter. We consider several rule sets based on composition of various types of pattern sets—generators, projected-database generators, closed patterns and projected-database closed patterns. We investigate the completeness and tightness of these rule sets. We characterize a tight and complete set of non-redundant rules by defining it based on the composition of two pattern sets. Furthermore, we propose a compressed set of non-redundant rules in a spirit similar to how closed patterns serve as a compressed representation of a full set of patterns. Lastly, we propose an algorithm to mine this compressed set of non-redundant rules. A performance study shows that the proposed algorithm significantly improves both the runtime and compactness of mined rules over mining a full set of sequential rules. [Copyright &y& Elsevier]

DNA microarrays make possible the rapid and comprehensive assessment of the transcriptional activity of a cell, and as such have proven valuable in assessing the molecular contributors to biological processes and in the classification of human cancers. The major challenge in using this technology is the analysis of its massive data output, which requires computational means for interpretation and a heightened need for quality data. The optimal analysis requires an accounting and control of the many sources of variance within the system, an understanding of the limitations of the statistical approaches, and the ability to make sense of the results through intelligent database interrogation. [Copyright &y& Elsevier]

Valproic acid (VPA) is an anti-convulsant drug that is recently shown to have neuroregenerative therapeutic actions. In this study, we investigate the underlying molecular mechanism of VPA and its effects on Bdnf transcription through microRNAs (miRNAs) and their corresponding target proteins. Using in silico algorithms, we predicted from our miRNA microarray and iTRAQ data that miR-124 is likely to target at guanine nucleotide binding protein alpha inhibitor 1 (GNAI1), an adenylate cyclase inhibitor. With the reduction of GNAI1 mediated by VPA, the cAMP is enhanced to increase Bdnf expression. The levels of GNAI1 protein and Bdnf mRNA can be manipulated with either miR-124 mimic or inhibitor. In summary, we have identified a novel molecular mechanism of VPA that induces miR-124 to repress GNAI1. The implication of miR-124→GNAI1→BDNF pathway with valproic acid treatment suggests that we could repurpose an old drug, valproic acid, as a clinical application to elevate neurotrophin levels in treating neurodegenerative diseases. [ABSTRACT FROM AUTHOR]

Treatment of pediatric acute lymphoblastic leukemia (ALL) is based on the concept of tailoring the intensity of therapy to a patient''s risk of relapse. To determine whether gene expression profiling could enhance risk assignment, we used oligonucleotide microarrays to analyze the pattern of genes expressed in leukemic blasts from 360 pediatric ALL patients. Distinct expression profiles identified each of the prognostically important leukemia subtypes, including T-ALL, E2A-PBX1, BCR-ABL, TEL-AML1, MLL rearrangement, and hyperdiploid >50 chromosomes. In addition, another ALL subgroup was identified based on its unique expression profile. Examination of the genes comprising the expression signatures provided important insights into the biology of these leukemia subgroups. Further, within some genetic subgroups, expression profiles identified those patients that would eventually fail therapy. Thus, the single platform of expression profiling should enhance the accurate risk stratification of pediatric ALL patients. [Copyright &y& Elsevier]