Iterative Cross-Correlation Analysis of Resting State Functional Magnetic Resonance Imaging Data

Seed-based cross-correlation analysis (sCCA) and independent component analysis have been widely employed to extract functional networks from the resting state functional magnetic resonance imaging data. However, the results of sCCA, in terms of both connectivity strength and network topology, can be sensitive to seed selection variations. ICA avoids the potential problems due to seed selection, but choosing which component(s) to represent the network of interest could be subjective and problematic. In this study, we proposed a seed-based iterative cross-correlation analysis (siCCA) method for resting state brain network analysis. The method was applied to extract default mode network (DMN) and stable task control network (STCN) in two independent datasets acquired from normal adults. Compared with the networks obtained by traditional sCCA and ICA, the resting state networks produced by siCCA were found to be highly stable and independent on seed selection. siCCA was used to analyze DMN in first-episode major depressive disorder (MDD) patients. It was found that, in the MDD patients, the volume of DMN negatively correlated with the patients'' social disability screening schedule scores.     

Frontal-Subcortical Volumetric Deficits in Single Episode,Medication-Na?ve Depressed Patients and the Effects of 8 Weeks Fluoxetine Treatment: A VBM-DARTEL Study

Background

Convergent studies suggest that morphological abnormalities of frontal-subcortical circuits which involved with emotional and cognitive processing may contribute to the pathophysiology of major depressive disorder (MDD). Antidepressant treatment which has been reported to reverse the functional abnormalities of frontal-subcortical circuits in MDD may have treating effects to related brain morphological abnormalities. In this study, we used voxel-based morphometry method to investigate whole brain structural abnormalities in single episode, medication-naïve MDD patients. Furthermore, we investigated the effects of an 8 weeks pharmacotherapy with fluoxetine.

Methods

28 single episode, medication-naïve MDD participants and 28 healthy controls (HC) acquired the baseline high-resolution structural magnetic resonance imaging (sMRI) scan. 24 MDD participants acquired a follow-up sMRI scan after 8 weeks antidepressant treatment. Gray matter volumetric (GMV) difference between groups was examined.

Results

Medication-naïve MDD had significantly decreased GMV in the right dorsolateral prefrontal cortex and left middle frontal gyrus as well as increased GMV in the left thalamus and right insula compared to HC (P<0.05, corrected). Moreover, treated MDD had significantly increased GMV in the left middle frontal gyrus and right orbitofrontal cortex compared to HC (P<0.05, corrected). No difference on GMV was detected between medication-naïve MDD group and treated MDD group.

Conclusions

This study of single episode, medication-naïve MDD subjects demonstrated structural abnormalities of frontal-subcortical circuitsin the early stage of MDD and the effects of 8 weeks successful antidepressant treatment, suggesting these abnormalities may play an important role in the neuropathophysiology of MDD at its onset.     

Disrupted Structural and Functional Connectivity in Prefrontal-Hippocampus Circuitry in First-Episode Medication-Na?ve Adolescent Depression

Background

Evidence implicates abnormalities in prefrontal-hippocampus neural circuitry in major depressive disorder (MDD). This study investigates the potential disruptions in prefrontal-hippocampus structural and functional connectivity, as well as their relationship in first-episode medication-naïve adolescents with MDD in order to investigate the early stage of the illness without confounds of illness course and medication exposure.

Methods

Diffusion tensor imaging and resting-state functional magnetic resonance imaging (rs-fMRI) data were acquired from 26 first-episode medication-naïve MDD adolescents and 31 healthy controls (HC). Fractional anisotropy (FA) values of the fornix and the prefrontal-hippocampus functional connectivity was compared between MDD and HC groups. The correlation between the FA value of fornix and the strength of the functional connectivity in the prefrontal cortex (PFC) region showing significant differences between the two groups was identified.

Results

Compared with the HC group, adolescent MDD group had significant lower FA values in the fornix, as well as decreased functional connectivity in four PFC regions. Significant negative correlations were observed between fornix FA values and functional connectivity from hippocampus to PFC within the HC group. There was no significant correlation between the fornix FA and the strength of functional connectivity within the adolescent MDD group.

Conclusions

First-episode medication-naïve adolescent MDD showed decreased structural and functional connectivity as well as deficits of the association between structural and functional connectivity shown in HC in the PFC-hippocampus neural circuitry. These findings suggest that abnormal PFC-hippocampus neural circuitry may present in the early onset of MDD and play an important role in the neuropathophysiology of MDD.     

Increased Cortical-Limbic Anatomical Network Connectivity in Major Depression Revealed by Diffusion Tensor Imaging

Magnetic resonance imaging studies have reported significant functional and structural differences between depressed patients and controls. Little attention has been given, however, to the abnormalities in anatomical connectivity in depressed patients. In the present study, we aim to investigate the alterations in connectivity of whole-brain anatomical networks in those suffering from major depression by using machine learning approaches. Brain anatomical networks were extracted from diffusion magnetic resonance images obtained from both 22 first-episode, treatment-naive adults with major depressive disorder and 26 matched healthy controls. Using machine learning approaches, we differentiated depressed patients from healthy controls based on their whole-brain anatomical connectivity patterns and identified the most discriminating features that represent between-group differences. Classification results showed that 91.7% (patients = 86.4%, controls = 96.2%; permutation test, p<0.0001) of subjects were correctly classified via leave-one-out cross-validation. Moreover, the strengths of all the most discriminating connections were increased in depressed patients relative to the controls, and these connections were primarily located within the cortical-limbic network, especially the frontal-limbic network. These results not only provide initial steps toward the development of neurobiological diagnostic markers for major depressive disorder, but also suggest that abnormal cortical-limbic anatomical networks may contribute to the anatomical basis of emotional dysregulation and cognitive impairments associated with this disease.     

Modeling the Dynamics of Disease States in Depression

Major depressive disorder (MDD) is a common and costly disorder associated with considerable morbidity, disability, and risk for suicide. The disorder is clinically and etiologically heterogeneous. Despite intense research efforts, the response rates of antidepressant treatments are relatively low and the etiology and progression of MDD remain poorly understood. Here we use computational modeling to advance our understanding of MDD. First, we propose a systematic and comprehensive definition of disease states, which is based on a type of mathematical model called a finite-state machine. Second, we propose a dynamical systems model for the progression, or dynamics, of MDD. The model is abstract and combines several major factors (mechanisms) that influence the dynamics of MDD. We study under what conditions the model can account for the occurrence and recurrence of depressive episodes and how we can model the effects of antidepressant treatments and cognitive behavioral therapy within the same dynamical systems model through changing a small subset of parameters. Our computational modeling suggests several predictions about MDD. Patients who suffer from depression can be divided into two sub-populations: a high-risk sub-population that has a high risk of developing chronic depression and a low-risk sub-population, in which patients develop depression stochastically with low probability. The success of antidepressant treatment is stochastic, leading to widely different times-to-remission in otherwise identical patients. While the specific details of our model might be subjected to criticism and revisions, our approach shows the potential power of computationally modeling depression and the need for different type of quantitative data for understanding depression.     

SuccSite: Incorporating Amino Acid Composition and Informative k-spaced Amino Acid Pairs to Identify Protein Succinylation Sites

Protein succinylation is a biochemical reaction in which a succinyl group (-CO-CH2-CH2-CO-) is attached to the lysine residue of a protein molecule. Lysine succinylation plays important regulatory roles in living cells. However, studies in this field are limited by the difficulty in experimentally identifying the substrate site specificity of lysine succinylation. To facilitate this process, several tools have been proposed for the computational identification of succinylated lysine sites. In this study, we developed an approach to investigate the substrate specificity of lysine succinylated sites based on amino acid composition. Using experimentally verified lysine succinylated sites collected from public resources, the significant differences in position-specific amino acid composition between succinylated and non-succinylated sites were represented using the Two Sample Logo program. These findings enabled the adoption of an effective machine learning method, support vector machine, to train a predictive model with not only the amino acid composition, but also the composition of k-spaced amino acid pairs. After the selection of the best model using a ten-fold cross-validation approach, the selected model significantly outperformed existing tools based on an independent dataset manually extracted from published research articles. Finally, the selected model was used to develop a web-based tool, SuccSite, to aid the study of protein succinylation. Two proteins were used as case studies on the website to demonstrate the effective prediction of succinylation sites. We will regularly update SuccSite by integrating more experimental datasets. SuccSite is freely accessible at http://csb.cse.yzu.edu.tw/SuccSite/.     

Neural Processing of Emotional Musical and Nonmusical Stimuli in Depression

BackgroundAnterior cingulate cortex (ACC) and striatum are part of the emotional neural circuitry implicated in major depressive disorder (MDD). Music is often used for emotion regulation, and pleasurable music listening activates the dopaminergic system in the brain, including the ACC. The present study uses functional MRI (fMRI) and an emotional nonmusical and musical stimuli paradigm to examine how neural processing of emotionally provocative auditory stimuli is altered within the ACC and striatum in depression.MethodNineteen MDD and 20 never-depressed (ND) control participants listened to standardized positive and negative emotional musical and nonmusical stimuli during fMRI scanning and gave subjective ratings of valence and arousal following scanning.ResultsND participants exhibited greater activation to positive versus negative stimuli in ventral ACC. When compared with ND participants, MDD participants showed a different pattern of activation in ACC. In the rostral part of the ACC, ND participants showed greater activation for positive information, while MDD participants showed greater activation to negative information. In dorsal ACC, the pattern of activation distinguished between the types of stimuli, with ND participants showing greater activation to music compared to nonmusical stimuli, while MDD participants showed greater activation to nonmusical stimuli, with the greatest response to negative nonmusical stimuli. No group differences were found in striatum.ConclusionsThese results suggest that people with depression may process emotional auditory stimuli differently based on both the type of stimulation and the emotional content of that stimulation. This raises the possibility that music may be useful in retraining ACC function, potentially leading to more effective and targeted treatments.     

Prediction of Depression in Individuals at High Familial Risk of Mood Disorders Using Functional Magnetic Resonance Imaging

Objective

Bipolar disorder is a highly heritable condition. First-degree relatives of affected individuals have a more than a ten-fold increased risk of developing bipolar disorder (BD), and a three-fold risk of developing major depressive disorder (MDD) than the general population. It is unclear however whether differences in brain activation reported in BD and MDD are present before the onset of illness.

Methods

We studied 98 young unaffected individuals at high familial risk of BD and 58 healthy controls using functional Magnetic Resonance Imaging (fMRI) scans and a task involving executive and language processing. Twenty of the high-risk subjects subsequently developed MDD after the baseline fMRI scan.

Results

At baseline the high-risk subjects who later developed MDD demonstrated relatively increased activation in the insula cortex, compared to controls and high risk subjects who remained well. In the healthy controls and high-risk group who remained well, this region demonstrated reduced engagement with increasing task difficulty. The high risk subjects who subsequently developed MDD did not demonstrate this normal disengagement. Activation in this region correlated positively with measures of cyclothymia and neuroticism at baseline, but not with measures of depression.

Conclusions

These results suggest that increased activation of the insula can differentiate individuals at high-risk of bipolar disorder who later develop MDD from healthy controls and those at familial risk who remain well. These findings offer the potential of future risk stratification in individuals at risk of mood disorder for familial reasons.     

Assessing Regional Cerebral Blood Flow in Depression Using 320-Slice Computed Tomography

While there is evidence that the development and course of major depressive disorder (MDD) symptomatology is associated with vascular disease, and that there are changes in energy utilization in the disorder, the extent to which cerebral blood flow is changed in this condition is not clear. This study utilized a novel imaging technique previously used in coronary and stroke patients, 320-slice Computed-Tomography (CT), to assess regional cerebral blood flow (rCBF) in those with MDD and examine the pattern of regional cerebral perfusion. Thirty nine participants with depressive symptoms (Hamilton Depression Rating Scale 24 (HAMD24) score >20, and Self-Rating Depression Scale (SDS) score >53) and 41 healthy volunteers were studied. For all subjects, 3 ml of venous blood was collected to assess hematological parameters. Trancranial Doppler (TCD) ultrasound was utilized to measure parameters of cerebral artery rCBFV and analyse the Pulsatility Index (PI). 16 subjects (8 =  MDD; 8 =  healthy) also had rCBF measured in different cerebral artery regions using 320-slice CT. Differences among groups were analyzed using ANOVA and Pearson''s tests were employed in our statistical analyses. Compared with the control group, whole blood viscosity (including high\middle\low shear rate)and hematocrit (HCT) were significantly increased in the MDD group. PI values in different cerebral artery regions and parameters of rCBFV in the cerebral arteries were decreased in depressive participants, and there was a positive relationship between rCBFV and the corresponding vascular rCBF in both gray and white matter. rCBF of the left gray matter was lower than that of the right in MDD. Major depression is characterized by a wide range of CBF impairments and prominent changes in gray matter blood flow. 320-slice CT appears to be a valid and promising tool for measuring rCBF, and could thus be employed in psychiatric settings for biomarker and treatment response purposes.     

Prevalence of Subthreshold Hypomania and Impact on Internal Validity of RCTs for Major Depressive Disorder: Results from a National Epidemiological Sample

Background

Growing evidence supports the validity of distinguishing major depressive disorder (MDD) plus a lifetime history of subthreshold hypomania (D(m)) from pure MDD in psychiatric classifications. The present study sought to estimate the proportion of individuals with D(m) that would have been included in RCTs for MDD using typical eligibility criteria, and examine the potential impact of including these participants on internal validity.

Methods

Data were derived from the 2001–2002 National Epidemiological Survey on Alcohol and Related Conditions (NESARC), a national representative sample of 43,093 adults of the United States population. We examined the proportion of participants with a current diagnosis of pure MDD and D(m) that would have been eligible in clinical trials for MDD with a traditional set of eligibility criteria, and compared it with that of participants with bipolar 2 disorder if the same set of eligibility criteria was applied. We considered 4 models including different definitions of subthreshold hypomania.

Results

We found that more than 7 out of ten participants with pure MDD and with D(m) would have been excluded by at least one classical eligibility criterion. Prevalence rate of individuals with D(m) in RCTs for MDD with traditional eligibility criteria would have ranged from 7.98% to 22.59%. Overall exclusion rate of individuals with MDD plus at least 4 lifetime concomitant hypomanic probes significantly differ from those with pure MDD, whereas it was not significantly different in those with at least 2 lifetime concomitant hypomanic probes compared to those with bipolar 2 disorder.

Conclusions

The current design of clinical trials for MDD may suffer from impaired external validity and potential impaired internal validity, due to the inclusion of a substantial proportion of individuals with subthreshold hypomania presenting with similar pattern of exclusion rates to those with bipolar 2 disorder, possibly resulting in a selection bias.     

CT-based radiomics model with machine learning for predicting primary treatment failure in diffuse large B-cell Lymphoma

Biomarkers which can identify Diffuse Large B-Cell Lymphoma (DLBCL) likely to be refractory to first-line therapy are essential for selecting this population prior to therapy initiation to offer alternate therapeutic options that can improve prognosis. We tested the ability of a CT-based radiomics approach with machine learning to predict Primary Treatment Failure (PTF)-DLBCL from initial imaging evaluation. Twenty-six refractory patients were matched to 26 non-refractory patients, yielding 180 lymph nodes for analysis. Manual 3D delineation of the total node volume was performed by two independent readers to test the reproducibility. Then, 1218 hand-crafted radiomic features were extracted. The Random Forests machine learning approach was used as a classifier for constructing the prediction models. Seventy percent of the nodes were randomly assigned to a training set and the remaining 30% were assigned to an independent test set. The final model was tested on the dataset from the 2 readers, showing a mean accuracy, sensitivity and specificity of 73%, 62% and 82%, respectively, for distinguishing between refractory and non-refractory patients. The area under the receiver operating characteristic curve (AUC) was 0.83 and 0.79 for the two readers. We conclude that machine learning CT-based radiomics analysis is able to identify a priori PTF-DLBCL with a good accuracy.     

Depression, comorbid anxiety disorders, and heart rate variability in physically healthy, unmedicated patients: implications for cardiovascular risk

Context

There is evidence that heart rate variability (HRV) is reduced in major depressive disorder (MDD), although there is debate about whether this effect is caused by medication or the disorder per se. MDD is associated with a two to fourfold increase in the risk of cardiac mortality, and HRV is a robust predictor of cardiac mortality; determining a direct link between HRV and not only MDD, but common comorbid anxiety disorders, will point to psychiatric indicators for cardiovascular risk reduction.

Objective

To determine in physically healthy, unmedicated patients whether (1) HRV is reduced in MDD relative to controls, and (2) HRV reductions are driven by MDD alone, comorbid generalized anxiety disorder (GAD, characterized by anxious anticipation), or comorbid panic and posttraumatic stress disorders (PD/PTSD, characterized by anxious arousal).

Design, Setting, and Patients

A case-control study in 2006 and 2007 on 73 MDD patients, including 24 without anxiety comorbidity, 24 with GAD, and 14 with PD/PTSD. Seventy-three MDD and 94 healthy age- and sex-matched control participants were recruited from the general community. Participants had no history of drug addiction, alcoholism, brain injury, loss of consciousness, stroke, neurological disorder, or serious medical conditions. There were no significant differences between the four groups in age, gender, BMI, or alcohol use.

Main Outcome Measures

HRV was calculated from electrocardiography under a standardized short-term resting state condition.

Results

HRV was reduced in MDD relative to controls, an effect associated with a medium effect size. MDD participants with comorbid generalized anxiety disorder displayed the greatest reductions in HRV relative to controls, an effect associated with a large effect size.

Conclusions

Unmedicated, physically healthy MDD patients with and without comorbid anxiety had reduced HRV. Those with comorbid GAD showed the greatest reductions. Implications for cardiovascular risk reduction strategies in otherwise healthy patients with psychiatric illness are discussed.     

Prediction of regulation relationship between protein interactions in signaling networks

The discovery of regulation relationship of protein interactions is crucial for the mechanism research in signaling network. Bioinformatics methods can be used to accelerate the discovery of regulation relationship between protein interactions, to distinguish the activation relations from inhibition relations. In this paper, we describe a novel method to predict the regulation relations of protein interactions in the signaling network. We detected 4,417 domain pairs that were significantly enriched in the activation or inhibition dataset. Three machine learning methods, logistic regression, support vector machines(SVMs), and naïve bayes, were explored in the classifier models. The prediction power of three different models was evaluated by 5-fold cross-validation and the independent test dataset. The area under the receiver operating characteristic curve for logistic regression, SVM, and naïve bayes models was 0.946, 0.905 and 0.809, respectively. Finally, the logistic regression classifier was applied to the human proteome-wide interaction dataset, and 2,591 interactions were predicted with their regulation relations, with 2,048 in activation and 543 in inhibition. This model based on domains can be used to identify the regulation relations between protein interactions and furthermore reconstruct signaling pathways.     

Autistic-Like Traits in Adult Patients with Mood Disorders and Schizophrenia

Autism spectrum disorder often co-occurs with other psychiatric disorders. Although a high prevalence of autistic-like traits/symptoms has been identified in the pediatric psychiatric population of normal intelligence, there are no reports from adult psychiatric population. This study examined whether there is a greater prevalence of autistic-like traits/symptoms in patients with adult-onset psychiatric disorders such as major depressive disorder (MDD), bipolar disorder, or schizophrenia, and whether such an association is independent of symptom severity. The subjects were 290 adults of normal intelligence between 25 and 59 years of age (MDD, n=125; bipolar disorder, n=56; schizophrenia, n=44; healthy controls, n=65). Autistic-like traits/symptoms were measured using the Social Responsiveness Scale for Adults. Symptom severity was measured using the Positive and Negative Symptoms Scale, the Hamilton Depression Rating Scale, and/or the Young Mania Rating Scale. Almost half of the clinical subjects, except those with remitted MDD, exhibited autistic-like traits/symptoms at levels typical for sub-threshold or threshold autism spectrum disorder. Furthermore, the proportion of psychiatric patients that demonstrated high autistic-like traits/symptoms was significantly greater than that of healthy controls, and not different between that of remitted or unremitted subjects with bipolar disorder or schizophrenia. On the other hand, remitted subjects with MDD did not differ from healthy controls with regard to the prevalence or degree of high autistic-like traits/symptoms. A substantial proportion of adults with bipolar disorder and schizophrenia showed high autistic-like traits/symptoms independent of symptom severity, suggesting a shared pathophysiology among autism spectrum disorder and these psychiatric disorders. Conversely, autistic-like traits among subjects with MDD were associated with the depressive symptom severity. These findings suggest the importance of evaluating autistic-like traits/symptoms underlying adult-onset psychiatric disorders for the best-suited treatment. Further studies with a prospective design and larger samples are needed.     

Social jetlag and depression status: Results obtained from the Netherlands Study of Depression and Anxiety

Social jetlag, the misalignment between the internal clock and the socially required timing of activities, is highly prevalent, especially in people with an evening chronotype and is hypothesized to be related to the link between the evening chronotype and major depressive disorder. Although social jetlag has been linked to depressive symptoms in non-clinical samples, it has never been studied in patients with major depressive disorder (MDD). This study is aimed to study social jetlag in patients with major depressive disorder and healthy controls, and to further examine the link between social jetlag and depressive symptomatology. Patients with a diagnosis of MDD (n = 1084) and healthy controls (n = 385), assessed in a clinical interview, were selected from the Netherlands Study of Depression and Anxiety. Social jetlag was derived from the Munich Chronotype Questionnaire, by calculating the absolute difference between the midsleep on free days and midsleep on work days. Depression severity was measured with the Inventory of Depressive Symptomatology. It was found that patients with MDD did not show more social jetlag compared to healthy controls, neither in a model without medication use (β = 0.06, 95% CI: ?0.03–0.15, p = 0.17) nor in a model where medication use is accounted for. There was no direct association between the amount of social jetlag and depressive symptoms, neither in the full sample, nor in the patient group or the healthy control group. This first study on social jetlag in a clinical sample showed no differences in social jetlag between patients with MDD and healthy controls.     

An approach to multi-class imbalanced problem in ecology using machine learning

Ecologists collect their data manually by visiting multiple sampling sites. Since there can be multiple species in the multiple sampling sites, manually classifying them can be a daunting task. Much work in literature has focused mostly on statistical methods for classification of single species and very few studies on classification of multiple species. In addition to looking at multiple species, we noted that classification of multiple species result in multi-class imbalanced problem. This study proposes to use machine learning approach to classify multiple species in population ecology. In particular, bagging (random forests (RF) and bagging classification trees (bagCART)) and boosting (boosting classification trees (bootCART), gradient boosting machines (GBM) and adaptive boosting classification trees (AdaBoost)) classifiers were evaluated for their performances on imbalanced multiple fish species dataset. The recall and F1-score performance metrics were used to select the best classifier for the dataset. The bagging classifiers (RF and bagCART) achieved high performances on the imbalanced dataset while the boosting classifiers (bootCART, GBM and AdaBoost) achieved lower performances on the imbalanced dataset. We found that some machine learning classifiers were sensitive to imbalanced dataset hence they require data resampling to improve their performances. After resampling, the bagging classifiers (RF and bagCART) had high performances compared to boosting classifiers (bootCART, GBM and AdaBoost). The strong performances shown by bagging classifiers (RF and bagCART) suggest that they can be used for classifying multiple species in ecological studies.     

Genetic risk score analysis indicates migraine with and without comorbid depression are genetically different disorders

Migraine and major depressive disorder (MDD) are comorbid, moderately heritable and to some extent influenced by the same genes. In a previous paper, we suggested the possibility of causality (one trait causing the other) underlying this comorbidity. We present a new application of polygenic (genetic risk) score analysis to investigate the mechanisms underlying the genetic overlap of migraine and MDD. Genetic risk scores were constructed based on data from two discovery samples in which genome-wide association analyses (GWA) were performed for migraine and MDD, respectively. The Australian Twin Migraine GWA study (N = 6,350) included 2,825 migraine cases and 3,525 controls, 805 of whom met the diagnostic criteria for MDD. The RADIANT GWA study (N = 3,230) included 1,636 MDD cases and 1,594 controls. Genetic risk scores for migraine and for MDD were used to predict pure and comorbid forms of migraine and MDD in an independent Dutch target sample (NTR–NESDA, N = 2,966), which included 1,476 MDD cases and 1,058 migraine cases (723 of these individuals had both disorders concurrently). The observed patterns of prediction suggest that the ‘pure’ forms of migraine and MDD are genetically distinct disorders. The subgroup of individuals with comorbid MDD and migraine were genetically most similar to MDD patients. These results indicate that in at least a subset of migraine patients with MDD, migraine may be a symptom or consequence of MDD.     

Review and comparative analysis of machine learning-based phage virion protein identification methods

Phage virion protein (PVP) identification plays key role in elucidating relationships between phages and hosts. Moreover, PVP identification can facilitate the design of related biochemical entities. Recently, several machine learning approaches have emerged for this purpose and have shown their potential capacities. In this study, the proposed PVP identifiers are systemically reviewed, and the related algorithms and tools are comprehensively analyzed. We summarized the common framework of these PVP identifiers and constructed our own novel identifiers based upon the framework. Furthermore, we focus on a performance comparison of all PVP identifiers by using a training dataset and an independent dataset. Highlighting the pros and cons of these identifiers demonstrates that g-gap DPC (dipeptide composition) features are capable of representing characteristics of PVPs. Moreover, SVM (support vector machine) is proven to be the more effective classifier to distinguish PVPs and non-PVPs.     

Duplication of the SLIT3 locus on 5q35.1 predisposes to major depressive disorder

Major depressive disorder (MDD) is a common psychiatric and behavioral disorder. To discover novel variants conferring risk to MDD, we conducted a whole-genome scan of copy number variation (CNV), including 1,693 MDD cases and 4,506 controls genotyped on the Perlegen 600K platform. The most significant locus was observed on 5q35.1, harboring the SLIT3 gene (P = 2×10⁻³). Extending the controls with 30,000 subjects typed on the Illumina 550 k array, we found the CNV to remain exclusive to MDD cases (P = 3.2×10⁻⁹). Duplication was observed in 5 unrelated MDD cases encompassing 646 kb with highly similar breakpoints. SLIT3 is integral to repulsive axon guidance based on binding to Roundabout receptors. Duplication of 5q35.1 is a highly penetrant variation accounting for 0.7% of the subset of 647 cases harboring large CNVs, using a threshold of a minimum of 10 SNPs and 100 kb. This study leverages a large dataset of MDD cases and controls for the analysis of CNVs with matched platform and ethnicity. SLIT3 duplication is a novel association which explains a definitive proportion of the largely unknown etiology of MDD.