Predicting protein phosphorylation from gene expression: top methods from the IMPROVER Species Translation Challenge

The amniotic fluid proteome predicts imminent preterm delivery in asymptomatic women with a short cervix

Preterm birth, the leading cause of perinatal morbidity and mortality, is associated with increased risk of short- and long-term adverse outcomes. For women identified as at risk for preterm birth attributable to a sonographic short cervix, the determination of imminent delivery is crucial for patient management. The current study aimed to identify amniotic fluid (AF) proteins that could predict imminent delivery in asymptomatic patients with a short cervix. This retrospective cohort study included women enrolled between May 2002 and September 2015 who were diagnosed with a sonographic short cervix (< 25 mm) at 16-32 weeks of gestation. Amniocenteses were performed to exclude intra-amniotic infection; none of the women included had clinical signs of infection or labor at the time of amniocentesis. An aptamer-based multiplex platform was used to profile 1310 AF proteins, and the differential protein abundance between women who delivered within two weeks from amniocentesis, and those who did not, was determined. The analysis included adjustment for quantitative cervical length and control of the false-positive rate at 10%. The area under the receiver operating characteristic curve was calculated to determine whether protein abundance in combination with cervical length improved the prediction of imminent preterm delivery as compared to cervical length alone. Of the 1,310 proteins profiled in AF, 17 were differentially abundant in women destined to deliver within two weeks of amniocentesis independently of the cervical length (adjusted p-value < 0.10). The decreased abundance of SNAP25 and the increased abundance of GPI, PTPN11, OLR1, ENO1, GAPDH, CHI3L1, RETN, CSF3, LCN2, CXCL1, CXCL8, PGLYRP1, LDHB, IL6, MMP8, and PRTN3 were associated with an increased risk of imminent delivery (odds ratio > 1.5 for each). The sensitivity at a 10% false-positive rate for the prediction of imminent delivery by a quantitative cervical length alone was 38%, yet it increased to 79% when combined with the abundance of four AF proteins (CXCL8, SNAP25, PTPN11, and MMP8). Neutrophil-mediated immunity, neutrophil activation, granulocyte activation, myeloid leukocyte activation, and myeloid leukocyte-mediated immunity were biological processes impacted by protein dysregulation in women destined to deliver within two weeks of diagnosis. The combination of AF protein abundance and quantitative cervical length improves prediction of the timing of delivery compared to cervical length alone, among women with a sonographic short cervix.

Maternal whole blood mRNA signatures identify women at risk of early preeclampsia: a longitudinal study

PURPOSE

To determine whether previously established mRNA signatures are predictive of early preeclampsia when evaluated by maternal cellular transcriptome analysis in samples collected before clinical manifestation.

MATERIALS AND METHODS

We profiled gene expression at exon-level resolution in whole blood samples collected longitudinally from 49 women with normal pregnancy (controls) and 13 with early preeclampsia (delivery <34 weeks of gestation). After preprocessing and removal of gestational age-related trends in gene expression, data were converted into Z-scores based on the mean and standard deviation among controls for six gestational-age intervals. The average Z-scores of mRNAs in each previously established signature considered herein were compared between cases and controls at 9-11, 11-17, 17-22, 22-28, 28-32, and 32-34 weeks of gestation.Results: (1) Average expression of the 16-gene untargeted cellular mRNA signature was higher in women diagnosed with early preeclampsia at 32-34 weeks of gestation, yet more importantly, also prior to diagnosis at 28-32 weeks and 22-28 weeks of gestation, compared to controls (all, p < .05). (2) A combination of four genes from this signature, including a long non-protein coding RNA [H19 imprinted maternally expressed transcript (H19)], fibronectin 1 (FN1), tubulin beta-6 class V (TUBB6), and formyl peptide receptor 3 (FPR3) had a sensitivity of 0.85 (0.55-0.98) and a specificity of 0.92 (0.8-0.98) for prediction of early preeclampsia at 22-28 weeks of gestation. (3) H19, FN1, and TUBB6 were increased in women with early preeclampsia as early as 11-17 weeks of gestation (all, p < .05). (4) After diagnosis at 32-34 weeks, but also prior to diagnosis at 11-17 weeks, women destined to have early preeclampsia showed a coordinated increase in whole blood expression of several single-cell placental signatures, including the 20-gene signature of extravillous trophoblast (all, p < .05). (5) A combination of three mRNAs from the extravillous trophoblast signature (MMP11, SLC6A2, and IL18BP) predicted early preeclampsia at 11-17 weeks of gestation with a sensitivity of 0.83 (0.52-0.98) and specificity of 0.94 (0.79-0.99).

CONCLUSIONS

Circulating early transcriptomic markers for preeclampsia can be found either by untargeted profiling of the cellular transcriptome or by focusing on placental cell-specific mRNAs. The untargeted cellular mRNA signature was consistently increased in early preeclampsia after 22 weeks of gestation, and individual mRNAs of this signature were significantly increased as early as 11-17 weeks of gestation. Several single-cell placental signatures predicted future development of the disease at 11-17 weeks and were also increased in women already diagnosed at 32-34 weeks of gestation.

A meta-analysis of Watson for Oncology in clinical application

Using the method of meta-analysis to systematically evaluate the consistency of treatment schemes between Watson for Oncology (WFO) and Multidisciplinary Team (MDT), and to provide references for the practical application of artificial intelligence clinical decision-support system in cancer treatment. We systematically searched articles about the clinical applications of Watson for Oncology in the databases and conducted meta-analysis using RevMan 5.3 software. A total of 9 studies were identified, including 2463 patients. When the MDT is consistent with WFO at the ‘Recommended’ or the ‘For consideration’ level, the overall concordance rate is 81.52%. Among them, breast cancer was the highest and gastric cancer was the lowest. The concordance rate in stage I–III cancer is higher than that in stage IV, but the result of lung cancer is opposite (P < 0.05).Similar results were obtained when MDT was only consistent with WFO at the "recommended" level. Moreover, the consistency of estrogen and progesterone receptor negative breast cancer patients, colorectal cancer patients under 70 years old or ECOG 0, and small cell lung cancer patients is higher than that of estrogen and progesterone positive breast cancer patients, colorectal cancer patients over 70 years old or ECOG 1–2, and non-small cell lung cancer patients, with statistical significance (P < 0.05). Treatment recommendations made by WFO and MDT were highly concordant for cancer cases examined, but this system still needs further improvement. Owing to relatively small sample size of the included studies, more well-designed, and large sample size studies are still needed.

Progress of Artificial Intelligence in Gynecological Malignant Tumors

Artificial intelligence (AI) is a sort of new technical science which can simulate, extend and expand human intelligence by developing theories, methods and application systems. In the last five years, the application of AI in medical research has become a hot topic in modern science and technology. Gynecological malignant tumors involves a wide range of knowledge, and AI can play an important part in these aspects, such as medical image recognition, auxiliary diagnosis, drug research and development, treatment scheme formulation and other fields. The purpose of this paper is to describe the progress of AI in gynecological malignant tumors and discuss some problems in its application. It is believed that AI improves the efficiency of diagnosis, reduces the burden of clinicians, and improves the effect of treatment and prognosis. AI will play an irreplaceable role in the field of gynecological malignant oncology and will promote the development of medicine and further promote the transformation from traditional medicine to precision medicine and preventive medicine. However, there are also some problems in the application of AI in gynecologic malignant tumors. For example, AI, inseparable from human participation, still needs to be more “humanized”, and needs to further protect patients’ privacy and health, improve legal and insurance protection, and further improve according to local ethnic conditions and national conditions. However, it is believed that with the continuous development of AI, especially ensemble classifier, and deep learning will have a profound influence on the future of medical technology, which is a powerful driving force for future medical innovation and reform.

SemanticGO: a tool for gene functional similarity analysis in Arabidopsis thaliana and rice

Gene or pathway functional similarities are important information for researchers. However, these similarities are often described sparsely and qualitatively. The latent semantic analysis of Arabidopsis thaliana (Arabidopsis) Gene Ontology (GO) data produced a set of 200-dimension feature vectors for each gene. Pathways were represented by summing the vectors of the pathway member genes. Thus, the similarities between genes and pathways were assessed. Additionally, the gene feature vectors were correlated with external gene data, including gene expression and gene network connectivity, to elucidate the associated functions. The gene feature vectors were decoded, and their applications were demonstrated. A simple online tool, SemanticGO (http://bioinformatics.fafu.edu.cn/semanticGO/), is herein provided to enable researchers to explore the similarities between genes and pathways in both Arabidopsis and rice.

The prediction of early preeclampsia: Results from a longitudinal proteomics study

OBJECTIVES

To identify maternal plasma protein markers for early preeclampsia (delivery <34 weeks of gestation) and to determine whether the prediction performance is affected by disease severity and presence of placental lesions consistent with maternal vascular malperfusion (MVM) among cases.

STUDY DESIGN

This longitudinal case-control study included 90 patients with a normal pregnancy and 33 patients with early preeclampsia. Two to six maternal plasma samples were collected throughout gestation from each woman. The abundance of 1,125 proteins was measured using high-affinity aptamer-based proteomic assays, and data were modeled using linear mixed-effects models. After data transformation into multiples of the mean values for gestational age, parsimonious linear discriminant analysis risk models were fit for each gestational-age interval (8-16, 16.1-22, 22.1-28, 28.1-32 weeks). Proteomic profiles of early preeclampsia cases were also compared to those of a combined set of controls and late preeclampsia cases (n = 76) reported previously. Prediction performance was estimated via bootstrap.

RESULTS

We found that 1) multi-protein models at 16.1-22 weeks of gestation predicted early preeclampsia with a sensitivity of 71% at a false-positive rate (FPR) of 10%. High abundance of matrix metalloproteinase-7 and glycoprotein IIbIIIa complex were the most reliable predictors at this gestational age; 2) at 22.1-28 weeks of gestation, lower abundance of placental growth factor (PlGF) and vascular endothelial growth factor A, isoform 121 (VEGF-121), as well as elevated sialic acid binding immunoglobulin-like lectin 6 (siglec-6) and activin-A, were the best predictors of the subsequent development of early preeclampsia (81% sensitivity, FPR = 10%); 3) at 28.1-32 weeks of gestation, the sensitivity of multi-protein models was 85% (FPR = 10%) with the best predictors being activated leukocyte cell adhesion molecule, siglec-6, and VEGF-121; 4) the increase in siglec-6, activin-A, and VEGF-121 at 22.1-28 weeks of gestation differentiated women who subsequently developed early preeclampsia from those who had a normal pregnancy or developed late preeclampsia (sensitivity 77%, FPR = 10%); 5) the sensitivity of risk models was higher for early preeclampsia with placental MVM lesions than for the entire early preeclampsia group (90% versus 71% at 16.1-22 weeks; 87% versus 81% at 22.1-28 weeks; and 90% versus 85% at 28.1-32 weeks, all FPR = 10%); and 6) the sensitivity of prediction models was higher for severe early preeclampsia than for the entire early preeclampsia group (84% versus 71% at 16.1-22 weeks).

CONCLUSION

We have presented herein a catalogue of proteome changes in maternal plasma proteome that precede the diagnosis of preeclampsia and can distinguish among early and late phenotypes. The sensitivity of maternal plasma protein models for early preeclampsia is higher in women with underlying vascular placental disease and in those with a severe phenotype.

Targeted expression profiling by RNA-Seq improves detection of cellular dynamics during pregnancy and identifies a role for T cells in term parturition

Development of maternal blood transcriptomic markers to monitor placental function and risk of obstetrical complications throughout pregnancy requires accurate quantification of gene expression. Herein, we benchmark three state-of-the-art expression profiling techniques to assess in maternal circulation the expression of cell type-specific gene sets previously discovered by single-cell genomics studies of the placenta. We compared Affymetrix Human Transcriptome Arrays, Illumina RNA-Seq, and sequencing-based targeted expression profiling (DriverMap^TM) to assess transcriptomic changes with gestational age and labor status at term, and tested 86 candidate genes by qRT-PCR. DriverMap identified twice as many significant genes (q < 0.1) than RNA-Seq and five times more than microarrays. The gap in the number of significant genes remained when testing only protein-coding genes detected by all platforms. qRT-PCR validation statistics (PPV and AUC) were high and similar among platforms, yet dynamic ranges were higher for sequencing based platforms than microarrays. DriverMap provided the strongest evidence for the association of B-cell and T-cell gene signatures with gestational age, while the T-cell expression was increased with spontaneous labor at term according to all three platforms. We concluded that sequencing-based techniques are more suitable to quantify whole-blood gene expression compared to microarrays, as they have an expanded dynamic range and identify more true positives. Targeted expression profiling achieved higher coverage of protein-coding genes with fewer total sequenced reads, and it is especially suited to track cell type-specific signatures discovered in the placenta. The T-cell gene expression signature was increased in women who underwent spontaneous labor at term, mimicking immunological processes at the maternal-fetal interface and placenta.

Applying Artificial Intelligence to Address the Knowledge Gaps in Cancer Care

BACKGROUND

Rapid advances in science challenge the timely adoption of evidence-based care in community settings. To bridge the gap between what is possible and what is practiced, we researched approaches to developing an artificial intelligence (AI) application that can provide real-time patient-specific decision support.

MATERIALS AND METHODS

The Oncology Expert Advisor (OEA) was designed to simulate peer-to-peer consultation with three core functions: patient history summarization, treatment options recommendation, and management advisory. Machine-learning algorithms were trained to construct a dynamic summary of patients cancer history and to suggest approved therapy or investigative trial options. All patient data used were retrospectively accrued. Ground truth was established for approximately 1,000 unique patients. The full Medline database of more than 23 million published abstracts was used as the literature corpus.

RESULTS

OEA's accuracies of searching disparate sources within electronic medical records to extract complex clinical concepts from unstructured text documents varied, with F1 scores of 90%-96% for non-time-dependent concepts (e.g., diagnosis) and F1 scores of 63%-65% for time-dependent concepts (e.g., therapy history timeline). Based on constructed patient profiles, OEA suggests approved therapy options linked to supporting evidence (99.9% recall; 88% precision), and screens for eligible clinical trials on ClinicalTrials.gov (97.9% recall; 96.9% precision).

CONCLUSION

Our results demonstrated technical feasibility of an AI-powered application to construct longitudinal patient profiles in context and to suggest evidence-based treatment and trial options. Our experience highlighted the necessity of collaboration across clinical and AI domains, and the requirement of clinical expertise throughout the process, from design to training to testing.

IMPLICATIONS FOR PRACTICE

Artificial intelligence (AI)-powered digital advisors such as the Oncology Expert Advisor have the potential to augment the capacity and update the knowledge base of practicing oncologists. By constructing dynamic patient profiles from disparate data sources and organizing and vetting vast literature for relevance to a specific patient, such AI applications could empower oncologists to consider all therapy options based on the latest scientific evidence for their patients, and help them spend less time on information "hunting and gathering" and more time with the patients. However, realization of this will require not only AI technology maturation but also active participation and leadership by clincial experts.

The prediction of late-onset preeclampsia: Results from a longitudinal proteomics study

BACKGROUND

Late-onset preeclampsia is the most prevalent phenotype of this syndrome; nevertheless, only a few biomarkers for its early diagnosis have been reported. We sought to correct this deficiency using a high through-put proteomic platform.

METHODS

A case-control longitudinal study was conducted, including 90 patients with normal pregnancies and 76 patients with late-onset preeclampsia (diagnosed at ≥34 weeks of gestation). Maternal plasma samples were collected throughout gestation (normal pregnancy: 2-6 samples per patient, median of 2; late-onset preeclampsia: 2-6, median of 5). The abundance of 1,125 proteins was measured using an aptamers-based proteomics technique. Protein abundance in normal pregnancies was modeled using linear mixed-effects models to estimate mean abundance as a function of gestational age. Data was then expressed as multiples of-the-mean (MoM) values in normal pregnancies. Multi-marker prediction models were built using data from one of five gestational age intervals (8-16, 16.1-22, 22.1-28, 28.1-32, 32.1-36 weeks of gestation). The predictive performance of the best combination of proteins was compared to placental growth factor (PIGF) using bootstrap.

RESULTS

1) At 8-16 weeks of gestation, the best prediction model included only one protein, matrix metalloproteinase 7 (MMP-7), that had a sensitivity of 69% at a false positive rate (FPR) of 20% (AUC = 0.76); 2) at 16.1-22 weeks of gestation, MMP-7 was the single best predictor of late-onset preeclampsia with a sensitivity of 70% at a FPR of 20% (AUC = 0.82); 3) after 22 weeks of gestation, PlGF was the best predictor of late-onset preeclampsia, identifying 1/3 to 1/2 of the patients destined to develop this syndrome (FPR = 20%); 4) 36 proteins were associated with late-onset preeclampsia in at least one interval of gestation (after adjustment for covariates); 5) several biological processes, such as positive regulation of vascular endothelial growth factor receptor signaling pathway, were perturbed; and 6) from 22.1 weeks of gestation onward, the set of proteins most predictive of severe preeclampsia was different from the set most predictive of the mild form of this syndrome.

CONCLUSIONS

Elevated MMP-7 early in gestation (8-22 weeks) and low PlGF later in gestation (after 22 weeks) are the strongest predictors for the subsequent development of late-onset preeclampsia, suggesting that the optimal identification of patients at risk may involve a two-step diagnostic process.

Human blood gene signature as a marker for smoking exposure: computational approaches of the top ranked teams in the sbv IMPROVER Systems Toxicology challenge

Crowdsourcing has emerged as a framework to address methodological challenges in omics data analysis and assess the extent to which omics data are predictive of phenotypes of interest. The sbv IMPROVER Systems Toxicology Challenge was designed to leverage crowdsourcing to determine whether human blood gene expression levels are informative of current and past smoking. Participating teams were invited to use a training gene expression dataset to derive parsimonious models (up to 40 genes) that can accurately classify subjects into exposure groups: smokers, former smokers that quit for at least one year, and never-smokers. Teams were ranked based on two classification performance metrics evaluated on a blinded test dataset. The analytical approaches of the first- and third-ranked teams, that are presented in detail in this article, involved feature selection by moderated t-test or LASSO regression and linear discriminant analysis (LDA) and logistic regression classifiers, respectively. While the 12-gene signature of the top team allowed the classification of current smokers with 100% sensitivity at 93% specificity, discriminating former smokers from never-smokers was much more challenging (65% sensitivity at 57% specificity). Gene ontology molecular functions and KEGG pathways associated with current smoking included G protein-coupled receptor activity, signaling receptor activity, calcium ion binding, and the Neuroactive ligand-receptor interaction pathway. Selection of marker genes by either moderated t-test or multivariate LASSO regression followed by LDA or logistic regression, are robust approaches to classification with omics data, confirming in part findings of previous sbv IMPROVER challenges. While current smoking is accurately identified based on blood mRNA levels, smoking cessation for more than one year is accompanied by a "normalization" of the expression of certain mRNAs, making it difficult to distinguish former smokers from never-smokers.

Species translatable blood gene signature as a marker of exposure to smoking: computational approaches of the top ranked teams in the sbv IMPROVER Systems Toxicology challenge

Crowdsourcing has been used to address computational challenges in systems biology and assess translation of findings across species. Sub-challenge 2 of the sbv IMPROVER Systems Toxicology Challenge was designed to determine whether a common set of genes can be used to identify exposure to cigarette smoke in both human and mouse. Participating teams used a training set of human and mouse blood gene expression data to derive parsimonious models (up to 40 genes) that classify subjects into exposure groups: smokers, former smokers, and never-smokers. Teams were ranked based on two classification performance metrics evaluated on a blinded test dataset. Prediction of current exposure to cigarette smoke in human and mouse by a common prediction model was achieved by the top ranked team (Team 219) with 89% balanced accuracy (BAC), while past exposure was predicted with only 57% BAC. The prediction model of the top ranked team was a random forest classifier trained on sets of genes that appeared best for each species separately with no overlap between species. By contrast, Team 264, ranked second (tied with Team 250), selected genes that were simultaneously predictive in both species and achieved 80% and 59% BAC when predicting current and past exposure, respectively. These performance values were lower than the 96.5% and 61% BAC estimates for current and past exposure, respectively, obtained by Team 264 (top ranked in sub-challenge 1) when using only human data. Unlike past exposure, current exposure to cigarette smoke can be accurately assessed in both human and mouse with a common prediction model based on blood mRNAs. However, requiring a common gene signature to be predictive in both species resulted in a substantial decrease in balanced accuracy for prediction of current exposure to cigarette smoke (from 96.5% to 80%), suggesting species-specific responses exist.

Inter-species pathway perturbation prediction via data-driven detection of functional homology

MOTIVATION

Experiments in animal models are often conducted to infer how humans will respond to stimuli by assuming that the same biological pathways will be affected in both organisms. The limitations of this assumption were tested in the IMPROVER Species Translation Challenge, where 52 stimuli were applied to both human and rat cells and perturbed pathways were identified. In the Inter-species Pathway Perturbation Prediction sub-challenge, multiple teams proposed methods to use rat transcription data from 26 stimuli to predict human gene set and pathway activity under the same perturbations. Submissions were evaluated using three performance metrics on data from the remaining 26 stimuli.

RESULTS

We present two approaches, ranked second in this challenge, that do not rely on sequence-based orthology between rat and human genes to translate pathway perturbation state but instead identify transcriptional response orthologs across a set of training conditions. The translation from rat to human accomplished by these so-called direct methods is not dependent on the particular analysis method used to identify perturbed gene sets. In contrast, machine learning-based methods require performing a pathway analysis initially and then mapping the pathway activity between organisms. Unlike most machine learning approaches, direct methods can be used to predict the activation of a human pathway for a new (test) stimuli, even when that pathway was never activated by a training stimuli.

AVAILABILITY

Gene expression data are available from ArrayExpress (accession E-MTAB-2091), while software implementations are available from http://bioinformaticsprb.med.wayne.edu?p=50 and http://goo.gl/hJny3h.

CONTACT

christoph.hafemeister@nyu.edu or atarca@med.wayne.edu.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.