ALL Metrics
-
Views
-
Downloads
Get PDF
Get XML
Cite
Export
Track
Research Article
Revised

Predicting lithium treatment response in bipolar patients using gender-specific gene expression biomarkers and machine learning

[version 2; peer review: 1 approved, 1 approved with reservations]
PUBLISHED 29 May 2018
Author details Author details
OPEN PEER REVIEW
REVIEWER STATUS

This article is included in the Artificial Intelligence and Machine Learning gateway.

Abstract

Background: We sought to test the hypothesis that transcriptiome-level genes signatures are differentially expressed between male and female bipolar patients, prior to lithium treatment, in a patient cohort who later were clinically classified as lithium treatment responders.
Methods: Gene expression study data was obtained from the Lithium Treatment-Moderate dose Use Study data accessed from the National Center for Biotechnology Information’s Gene Expression Omnibus via accession number GSE4548. Differential gene expression analysis was conducted using the Linear Models for Microarray and RNA-Seq (limma) package and the Random Forests machine learning algorithm in R.
Results: In pre-treatment lithium responders, the following genes were found having a greater than 0.5 fold-change, and differentially expressed indicating a male bias: RBPMS2, SIDT2, CDH23, LILRA5, and KIR2DS5; while the female-biased genes were: HLA-H, RPS23, FHL3, RPL10A, NBPF14, PSTPIP2, FAM117B, CHST7, and ABRACL.
Conclusions: Using machine learning, we developed a pre-treatment gender- and gene-expression-based predictive model selective for lithium responders with an ROC AUC of 0.92 for men and an ROC AUC of 1 for women.

Keywords

lithium, treatment response, gene expression, machine learning, microarray, transcriptome, precision medicine, pharmacogenomics

Revised Amendments from Version 1

  • For all differentially expressed results reported throughout tables within the manuscript, I changed the wording from genes up-regulated or down-regulated in males or females to a clearer description statement that of genes-associated with males or females.
  • For the caption in Figure 1, I updated the sample sizes for males and female patients. The updated Figure 1 text reads: Males (n=20; with 40 pre- and post-treatment samples) and Females (n=40; with 80 pre- and post-treatment samples).
  • I also updated the text to explain the variable importance plot shown in Figure 2.
  • Further, I added a more elaborative rationale in the study design found in the methods for the top 250 genes in the analysis.
  • Lastly, I added the American Board of Clinical Pharmacology as opposed to simply the board-certified/eligible pharmacologist in the text.

See the authors' detailed response to the review by Sunil V. Kalmady
See the authors' detailed response to the review by Ming-Fen Ho

Introduction

Lithium is the most well-established mood-stabilizer in the practice of psychiatry (Jermain et al., 1991; Landersdorfer et al., 2017). A recent propensity-score adjusted and matched longitudinal cohort-study evaluating the effectiveness of the newer mood stabilizers: olanzapine (n=1477), quetiapine (n=1376), and valproate (n=1670), in comparison to lithium (n=2148), found that patients treated with lithium experienced reduced rates of both unintentional injury and self-harm (Hayes et al., 2016). However, due to lithium’s narrow window, 0.5–1.2 mEq/mL, of maximal effectiveness and safety (i.e. therapeutic index), Therapeutic Drug Monitoring is the standard-of-care to ensure patient safety in medical practice (Hiemke et al., 2011). Further, divergent clinical response rates have been reported among male and female patients diagnosed with bipolar disorder and treated with lithium (Viguera et al., 2000).

In a 1986, Zetin and colleagues published the results of a study that evaluated four methods for predicting lithium daily dosages, and the final equation resulted in a 147.8mg/day increased dosage-adjustment for male patients (Zetin et al., 1986). Similarly, a later study by Lobeck and colleagues corroborated the 147.8 mg/day male increase dose requirement for the lithium maintenance dose in bipolar patients (Lobeck et al., 1987). However, neither do the current dosing guidelines recommend a gender-based dose adjustment via clinical pharmacometrics, to avoid toxicity, nor are gender-specific gene expression screening panels available to predict lithium efficacy currently available and implemented.

A recent large-scale meta-analysis of human body-tissue gene expression reported that the body organ with the most abundant gender-biased gene expression is the anterior cingulate cortex within the frontal cortex of the brain (Mayne et al., 2016). Thus, these findings suggest that therapeutic drug response may be influenced not only via drug absorption, distribution, metabolism, and elimination, but also within the underlying gene signatures across the human transcriptome and mechanisms of gene-gene interactions that regulate physiology. Beech and colleagues conducted a study to identify gene expression differences from the peripheral blood in patients classified as lithium responders and non-responders (Beech et al., 2014). However, the study reported that no significant gender-biased gene expression differences were found (p-value=0.941) in patients who were randomized to optimal therapy (control), defined as one FDA-approved mood stabilizer, versus patients treated with lithium plus optimal therapy (Beech et al., 2014). Despite these initially reported findings, a recent study by Labonté and colleagues, which used RNA-Seq to evaluate the transcriptome in patients diagnosed with major depressive disorder (MDD), concluded that gender dimorphism exists at the transcriptome-level in MDD patients and that gender-specific treatments should be investigated (Labonté et al., 2017).

Therefore, there is an urgent clinical need to improve behavioral healthcare by understanding gene expression variability that may lead to personalizing medicine in patients with mania. These findings may improve prediction of clinical drug response of lithium prior to initiating pharmacotherapy in patients with bipolar or schizoaffective disorders, who cannot risk drug inefficacy for obvious safety reasons. Therefore, the overall aim for our study is to define gender-specific transcriptional-level regulators of lithium treatment response that may influence treatment of bipolar or schizoaffective disorders. We will test the hypothesis that biologically plausible gene expression differences exist, prior to lithium treatment, in patients diagnosed with bipolar disorder in the following three patient subgroups: (1) male and female patients who were later clinically classified as lithium treatment responders; (2) male-responders versus male-non-responders; (3) female-responders versus female-non-responders.

Methods

Data

DNA microarray data analyzed in this study are originally referenced from the Lithium Treatment-Moderate dose Use Study placed in the National Center for Biotechnology Information (NCBI) Gene Expression Omnibus (GEO) via accession number GSE45484 with the Illumina HumanHT­12 V4.0 expression Beadchip GPL10558 platform file to associate gene names and descriptions. The original multisite clinical study recruited patients from Case Western Reserve University, Massachusetts General Hospital, Stanford University, Yale University, and the Universities of: Pittsburgh, Texas Health Science Center at San Antonio, and Pennsylvania (Beech et al., 2014). From the original 120 peripheral blood samples used to generate probe and gene expression profiles, from patients diagnosed with bipolar disorder, the clinical phenotype of being either a treatment- responder or non-responder was assessed using the Clinical Global Impression Scale for Bipolar Disorder-Severity (CGI-BP-S) (Spearing et al., 1997).

Study design

To assess for gender-specific differential gene signatures, in our first analysis we grouped patients based on gender alone and not on any other variables (i.e. optimal treatment versus lithium, or responder versus non-responder status). Then, we rationalized that from the results of the gender-specific transcriptome signatures from our first analysis, we will set the top two-hundred and fifty genes as controls in an effort to identify pharmacologic treatment-response transcriptome biomarkers that are not directly linked to the X or Y chromosome. Therefore, we excluded the top two-hundred and fifty genes from all results that were reported in subsequent analyses to identify genes with lithium-specific transcriptional differences between genders associated with response treatment. In our second analysis, we only selected patients who were classified as lithium treatment-responders, at baseline, and the results from the gene expression differences are reported excluding the sex-specific control genes identified in the first experiment. In our third and fourth analyses, we compared: male-responders vs. male non-responders, and female-responders vs. female non-responders, respectively.

Gene expression analysis

Differential gene expression analysis of the microarray data was conducted using the Empirical Bayes method implemented within the limma package (version 3.34.5) and utilizes the Biobase package (version 2.38.0) which both run within the R for Statistical Programming environment (version 3.4.3; R Foundation for Statistical Computing, Vienna, Austria) (Ritchie et al., 2015; Team, 2013). Due to multiple testing of the peripheral blood transcriptome, the False-Discovery Rate was adjusted using the Benjamini-Hochberg method. The Decision Tree and Random Forests machine learning algorithms were used to assess gender using transcriptional signatures and for predictive modeling using the discovered microarray genes to select for the gender-specific lithium responders. A p-value of less 0.05 was considered to be statistically significant and a differential gene expression threshold of 0.5 was used and reported during the machine learning process. Further methods detailing the Random Forests decision processes for male- and female-responders are located in Supplementary File 1.

Results

Table 1 provides the patient age and sample sizes used during subgroup analyses. In our first analysis, which aimed to group patients based on gender alone and not based on clinical variables detailed in the original study, data-driven gene analytics identified four female-labeled patient samples with gene expression levels similar to that found in male patients for the following Y-chromosome genes: RPS4Y1, EIF1AY, KDM5D, RPS4Y2; and the XIST gene located on the X-chromosome. Therefore, all subsequent hypothesis-testing were analyzed with the updated male-gender classification for the following NCBI GEO patient samples: GSM1105526 (baseline lithium-non-responder), GSM1105528 (1-month lithium-non-responder), GSM1105546 (baseline lithium-non-responder), and GSM1105548 (1-month lithium-non-responder). Figure 1 illustrates the gene expression findings resulting in re-assignment for the aforementioned patient samples from females to males using a decision-tree approach that evaluated if the RPS4Y1 gene had an expression level of greater than or equal to 9.6 resulting in: yes=male (31%) and no=female (69%). After proceeding with the machine learning analysis of both the ‘training’ and ‘validation’ datasets, the final ‘test’ dataset resulted in the following diagnostic test evaluation parameters: Sensitivity=100% (95% C.I. 66.37%-100.00%), Specificity=100% (95% C.I. 78.20%-100.00%), and an area under the receiver operator characteristic (ROC) curve of 1. Figure 2 illustrates the variable importance plots used in the machine learning process for classifying patients as being a male-lithium-responder or female-lithium-responder relative to the full patient population. The results show, in descending order of predictive power, the genes selective for male lithium-responders versus the full patient population being RBPMS2, CDH23, and SIDT2. Similarly, in descending order of predictive power, for female lithium-responders versus the entire patient population, the FHL3, ABRACL, RPL10A, and RPS23 genes are most selective.

Table 1. Patient age and sample sizes used during subgroup analyses.

Lithium treated patient population
BaselineMean ageS.D.Sample size (n)
Male-responder368.13
Female-responder3111.86
Male-non-responder40107
Female-non-responder449.212
*General mood stabilizers patient population
BaselineMean ageS.D.Sample size (n)
Male-responder51--1
Female-responder4910.53
Male-non-responder4312.59
Female-non-responder3714.519
Total patient population
GenderMean ageS.D.Sample size (n)
Male4110.820
Female3913.140
Study population4012.360

*Note: United States Food and Drug Administration approved Mood Stabilizers.

ac222cef-fb44-4842-95a9-5a6b0591660f_figure1.gif

Figure 1. Gene expression levels for the Ribosomal protein S4, Y-linked 1 (RPS4Y1) gene illustrating 4 patient samples as labeled as female and were re-assigned to the male patient gender group.

Males (n=20; with 40 pre- and post-treatment samples) and Females (n=40; with 80 pre- and post-treatment samples).

ac222cef-fb44-4842-95a9-5a6b0591660f_figure2.gif

Figure 2. Variable importance ratings of genes selective (above) male lithium responders versus the entire population of treated and untreated patient men and women; and (below) female lithium responders versus the entire population of treated and untreated men and women.

Table 2 provides the results for the gender-specific differentially expressed genes from the entire study population using a fold-change (FC) threshold of 0.5. A total of five genes met the a priori FC requirements and were found to be RPS4Y1, EIF1AY, KDM5D, RPS4Y2, and EIF1AY. These five down-regulated male-biased genes were all found on the Y-chromosome. Contrastingly, a total of 10 upregulated female-biased genes were found to be: XIST, S100P, IFIT3, TNFAIP6, IFITM3, IFIT2, CHURC1, ANXA3, ADM, and PROK2. The RPS4Y1 gene in males (FC= -4.9807, p=7.36E-47) and the XIST gene (FC=1.7615, p=2.98E-36), found on the X-chromosome, in females resulted in the greatest expression changes between genders. The male-favored genes resulted in a larger expression change than compared to the females.

Table 2. Differentially expressed genes between genders across all study participants with a log fold-change threshold of 0.5.

Male-associated genes
GeneAdjusted
P-value
P-valueLog fold changeGene descriptionLocation
RPS4Y17.36E-472.81E-51-4.9807Ribosomal Protein S4, Y-linked 1Yp11.3
EIF1AY1.02E-418.61E-46-2.5861Eukaryotic Translation Initiation Factor 1A, Y-linkedYq11.223
KDM5D7.36E-474.67E-51-1.6658Lysine Demethylase 5DYq11
HLA-DRB10.0160.0000362-1.7072Major Histocompatibility Complex, Class II, DR Beta 1
RPS4Y21.35E-401.43E-44-1.5014Ribosomal Protein S4, Y-linked 2Yq11.223
EIF1AY9.38E-311.98E-34-0.9443Eukaryotic Translation Initiation Factor 1A, Y-linkedYq11.223
Female-associated genes
GeneAdjusted
P-value
P-valueLog fold changeGene descriptionLocation
XIST2.98E-365.03E-401.7615X Inactive Specific Transcript (non-protein coding)Xq13.2
S100P1.70E-023.31E-051.028S100 Calcium Binding Protein P4p16
IFIT35.00E-035.82E-060.8765Interferon Induced Protein with Tetratricopeptide
Repeats 3
10q24
TNFAIP63.73E-042.52E-070.7304TNF Alpha Induced Protein 62q23.3
IFITM34.51E-021.69E-040.7284Interferon Induced Transmembrane Protein 311p15.5
IFIT24.91E-021.95E-040.6739Interferon Induced Protein with Tetratricopeptide
Repeats 2
10q23.31
CHURC16.30E-023.18E-040.6678Churchill Domain Containing 114q23.3
ANXA32.33E-032.26E-060.6218Annexin A34q21.21
ADM8.69E-046.80E-070.5986Adrenomedullin11p15.4
PROK22.16E-024.79E-050.5189Prokineticin 23p13

Table 3 provides the results for the differentially expressed genes that were found between male and female responders prior to initiation of lithium and optimal therapy, meeting the FC criteria of at least 0.5. In male lithium responders, we found 5 differentially expressed while the RNA binding protein with multiple splicing 2 (RBPMS2) gene ranked with the greatest FC of -1.351 (unadjusted p=0.00111). Whereas, 9 genes were associated with female lithium responders, with greatest expression change being the major histocompatibility complex class-1-H (HLA-H) at 1.602 (unadjusted p-value=0.00099). The neuroblastoma breakpoint family member-14 (NBPF14) gene met the Benjamani-Hochberg adjusted p-value criteria and resulted with an expression change of 0.586 (adjusted p=0.0462). Figure 3 illustrates the heat-map and dendrogram overview of the two-way unsupervised hierarchical cluster analysis of the reported differentially expressed genes among male and female responders to lithium therapy at baseline that correspond to values reported in Table 3.

Table 3. Differentially expressed genes between male and female responders prior to Lithium pharmacotherapy with a log fold-change threshold of 0.5.

Genes associated with male lithium responders
GeneAdjusted
P-value
P-valueLog fold changeGene descriptionHighest gene tissue
expression
RBPMS210.00111-1.351RNA Binding Protein with Multiple Splicing 2Heart, Urinary
Bladder
SIDT210.00932-0.82SID1 Transmembrane Family Member 2Stomach, Prostate
CDH2310.00388-0.674Cadherin-Related 23Ovary, Fat
LILRA510.00359-0.592Leukocyte Immunoglobulin Like Receptor A5Appendix, Bone
Marrow
KIR2DS510.00431-0.506Killer Cell Immunoglobulin Like Receptor, Two
Ig Domains and Short Cytoplasmic Tail 5
--
Genes associated with female lithium responders
GeneAdjusted
P-value
P-valueLog fold changeGene descriptionHighest gene tissue
expression
HLA-H10.0009961.602Major Histocompatibility Complex, Class I,
H (pseudogene)
Lymph Node, Bone
Marrow
RPS2310.003081.471Ribosomal Protein S23Ovary, Bone Marrow
FHL310.0007510.893Four and a Half LIM Domains 3Esophagus,
Endometrium
RPL10A10.002990.628Ribosomal Protein L10aOvary, Bone Marrow
**NBPF14**0.04620.000007820.586Neuroblastoma Breakpoint Family Member 14Skin, Ovary
PSTPIP210.0004730.569Proline-Serine-Threonine Phosphatase
Interacting Protein 2
Bone Marrow, Spleen
FAM117B10.009490.556Family with Sequence Similarity 117 Member BTestis, Adrenal
CHST710.008120.529Carbohydrate Sulfotransferase 7Spleen, Fat
ABRACL10.003960.505ABRA C-Terminal LikeColon, Lymph Node

Notes: **The NBPF14 gene reached the Benjamani-Hochberg adjusted p-value.

ac222cef-fb44-4842-95a9-5a6b0591660f_figure3.gif

Figure 3. Heat-map and dendrogram overview of the two-way unsupervised hierarchical cluster analysis of differentially expressed genes in male (n=3) and female (n=6) lithium responders after filtering out the top 250 differentially expressed genes found gender biased genes.

Using the baseline blood sample microarray data, the predictive modeling results for identifying lithium-responders from the complete study population of male and female controls and treatment samples, resulted in a validation/test sample cohort for males of: Sensitivity=95.83% (95% C.I. 78.88%-99.89%), Specificity=not calculated due sample size of test dataset, and an ROC curve AUC = 0.92 using the RBPMS2 and LILRA5 genes. Likewise, in the test dataset for females: Sensitivity=91.67% (95% C.I. 61.52%-99.79%), Specificity= not calculated due sample size of test dataset, and an ROC curve AUC = 1 with the ABRACL and NBPF14 genes. Therefore, we developed a 2-gene predictive model for men and likewise for women predicting lithium response in bipolar patients from a general population of bipolar patients using transcriptional signatures at baseline.

Table 4 provides the list of 10 differentially expressed genes found in male lithium responders (5-genes) and male lithium-non-responders (5-genes). The RNA binding protein with multiple splicing 2 (RBPMS2) gene (FC= -1.326, unadjusted p=0.001358) in male lithium responders and the Ribosomal protein S23 (RPS23) gene (FC=1.521, unadjusted p=0.013306) were found to result in the largest expression change differences between subgroups. However, in female responders and female non-responders, the Family with Sequence Similarity 117 Member B (FAM117B) gene (FC=0.5257, unadjusted p=0.0048554) and the Golgin B1 (GOLGB1) gene (FC= -0.6536, unadjusted p=0.0003716) were differentially expressed, respectively and shown in Table 5.

Table 4. Differentially expressed genes between Male Responders and Male Non-Responders at baseline with a log fold-change threshold of 0.3.

Genes associated with male lithium responders
GeneAdjusted
P-value
P-valueLog fold
change
Gene descriptionHighest gene tissue
expression
RBPMS210.001358-1.326RNA Binding Protein with Multiple Splicing 2Heart, Urinary Bladder
SVBP10.01366-0.76Small Vasohibin Binding ProteinTestis, Fat
LILRA510.011739-0.714Leukocyte Immunoglobulin Like Receptor A5Appendix, Bone
Marrow
CPA310.008048-0.592Carboxypeptidase A3Gall Bladder, Lung
SLC45A310.016508-0.455Solute Carrier Family 45 member 3Prostate, Stomach
ZNF23410.003254-0.41Zinc Finger Protein 234Spleen, Thyroid
DIDO1 10.008232-0.385Death Inducer-Obliterator 1Ovary, Spleen
TPP2 10.013053-0.385Tripeptidyl Peptidase 2Testis, Thyroid
KRT73 10.007333-0.373Keratin 73Skin, Lymph Nodes
ZMYM3 10.00363-0.372Zinc Finger MYM-type Containing 3Ovary, Testis
NOTCH2 NL 10.009657-0.348Notch 2 N-terminal LikeTestis, Skin
TIPRL 10.007794-0.34TOR Signaling Pathway RegulatorEndometrium, Brain
CAMK1D 10.005376-0.333Calcium/Calmodulin dependent Protein Kinase IDBrain, Skin
EFNA1 10.00632-0.324Ephrin A1Placenta, Lung
Genes associated with male lithium non-responders
GeneAdjusted
P-value
P-valueLog fold
change
Gene descriptionHighest gene tissue
expression
RPS23 10.0133061.521Ribosomal Protein S23Ovary, Bone Marrow
IRF2BPL 10.0109521.005Interferon Regulatory Factor 2 Binding Protein
Like
--
HLA-C 10.0034610.997Major Histocompatibility Complex, Class I, CLung, Bone Marrow
RGPD1 10.0017450.76RANBP2-like and GRIP Domain Containing 1Testis, Liver
ASGR2 10.0199470.598Asialoglycoprotein Receptor 2Liver, Gall Bladder
LPAR1 10.013740.453Lysophosphatidic Acid Receptor 1Brain, Placenta
RRN3P1 10.0170250.42RRN3 homolog, RNA Polymerase I Transcription
Factor Pseudogene 1
Thyroid, Lymph Node
TOMM34 10.0166550.416Translocase of Outer Mitochondrial Membrane 34Testis, Adrenal
ACAD11 10.0158820.405Acyl-CoA Dehydrogenase Family Member 11Kidney, Liver
CEBPE 10.002690.404CCAAT/enhancer Binding Protein EpsilonBone Marrow, Small
Intestine
CMIP 10.0172030.394C-Maf Inducing ProteinBrain, Small Intestine
IGSF6 10.0117860.38Immunoglobulin Superfamily Member 6Spleen, Appendix
HDHD2 10.017640.361Haloacid Dehalogenase Like Hydrolase Domain
Containing 2
Brain, Thyroid
LMO4 10.0128720.359LIM Domain Only 4Brain, Stomach
BACE2 10.0007110.353Beta-site APP-Cleaving Enzyme 2Stomach, Gall Bladder
TPP1 10.000610.341Tripeptidyl Peptidase 1Spleen, Appendix
GALNS 10.0076130.341Galactosamine (N-acetyl)-6-SulfataseBone Marrow, Testis
SYNM 10.0190420.322SyneminEsophagus, Prostate

Table 5. Differentially expressed genes between Female Responders and Female Non-Responders at baseline with a log fold-change threshold of 0.3.

Genes associated with female lithium responders
GeneAdjusted
P-value
P-valueLog fold changeGene descriptionHighest gene tissue
expression
FAM117B0.9980.00485540.5257Family with Sequence Similarity 117
Member B
Testis, Adrenal
STAMBPL10.9980.00744330.39STAM Binding Protein Like 1Adrenal, Testis
CD2480.9980.00381990.3626CD248 Molecule--
IFIH10.9980.00758220.3453Interferon Induced with Helicase C
domain 1
Spleen, Appendix
GPR1600.9980.00717230.3394G Protein-coupled Receptor 160Small Intestine,
Duodenum
STAP10.9980.00530960.3222Signal Transducing Adaptor Family
Member 1
Lymph Node, Appendix
YEATS40.9980.00890030.3103YEATS Domain Containing 4Testis, Bone Marrow
CD830.9980.00043670.3014CD83 MoleculeBone Marrow, Lymph
Node
TMOD20.9980.00815140.3012Tropomodulin 2Brain, Appendix
Genes associated with female lithium non-responders
GeneAdjusted
P-value
P-valueLog fold changeGene descriptionHighest gene tissue
expression
GOLGB10.9980.0003716-0.6536Golgin B1
RASA4CP0.9980.0030349-0.4554RAS p21 Protein Activator 4C,
Pseudogene
Spleen, Endometrium
NACC20.9980.0061286-0.3803NACC Family Member 2Brain, Fat
EDARADD0.9980.0021425-0.3553EDAR Associated Death DomainUrinary Bladder, Kidney
ZNF5730.9980.0058465-0.3463Zinc Finger Protein 573Thyroid, Spleen
ALDH20.9980.0031872-0.335Aldehyde Dehydrogenase 2 Family
(mitochondrial)
Fat, Liver
TAPBPL0.9980.0032596-0.3206TAP Binding Protein LikeDuodenum, Small
Intestine

Discussion

The purpose of this investigation was to define gender-specific transcriptome-level regulators of lithium treatment response prior to the initiation of lithium treatment. We first established the gender-relevant transcriptional control genes across all study-participant blood samples and specifically to male- and female-responders using a differential gene expression threshold of 0.5. We found this to be adequate and corroborated with similar studies that used a similar threshold for establishing gene transcription signatures (Jansen et al., 2014; Mayne et al., 2016). However, when comparing the male-responders to male non-responders, as well as, the female responders to female non-responders, we set an inclusion fold-change threshold to 0.3. This approach is not unusual, since it is already established that both large and subtle expression changes produce to significant biological and physiological processes (Wurmbach et al., 2002). Our analysis is both hypothesis-generating, and establishes a computational methodology that provides insight to the importance of subgroup analysis in genomic medicine, irrespective of patient sample-sizes. The end-goal of such analyses serves as a testing methodology for establishing gene screening panels to improve personalized medicine in vulnerable and high-risk patient populations. In these patient populations, it is often not feasible to wait for weeks to determine whether a prescribed medication will work and in some cases manic patients are neither able to fully comprehend and be objectively assessed using the CGI-BP-S (Spearing et al., 1997).

When reviewing the heat-map and dendrogram hierarchical cluster analysis patterns, specifically the numerous non-responders clinically-labeled and illustrated in Figure 4, they suggest that the underlying etiology resulting in clinical symptoms (e.g. mania) that led to the diagnosis of bipolar disorder may need re-classification. Further, the subsequent treatments may need to be tailored in data-driven computational psychiatry approaches. In Figure 4, for the females, the samples in the center cluster illustrates that a group of patients are clear non-responders while the patients clustered in the far-right are partial-responders, from a molecular perspective. The natural questions that arise are: (1) How to best convert the non- and partial-responders to treatment-responders? (2) Is a behavioral intervention, in this select group of patients, for whom lithium is not effective, the best answer because the symptoms maybe of a different etiology? If indeed the symptoms are of a different etiology (e.g. inflammatory), from the lithium treatment-responders, then other diagnostic (e.g. electrophysiological neuroimaging) tools may be warranted and corresponding most efficacious treatments sought.

ac222cef-fb44-4842-95a9-5a6b0591660f_figure4.gif

Figure 4. Heat-map and dendrogram overview of the two-way unsupervised hierarchical cluster analysis of differentially expressed genes prior to lithium treatment in (above) male lithium responders (n=3, RESP_Male) and male lithium non-responders (n=7, NR_Male); and (below) female responders (n=6, RESP_Fem) and female non-responders (n=14, NR_Fem).

When differentiating between male and female patients, we found that the Ribosomal Protein S4, Y-linked 1 (RPS4Y1, adjusted p-value=7.36E-47) male-linked gene and the X Inactive Specific Transcript (XIST, adjusted p-value=2.98E-36) female-linked gene were the most differentially expressed among genders, which is consistent with previously published studies (Guillén et al., 2014; Jansen et al., 2014; Mayne et al., 2016). The genes that are specific to male lithium responders, relative to female lithium responders, are RBPMS2, SIDT2, CDH23, LILRA5, and KIR2DS5. Using the same methodology, genes identifying female lithium responders, relative to male lithium responders, are HLA-H, RPS23, FHL3, RPL10A, NBPF14, PSTPIP2, FAM117B, CHST7, and ABRACL. The Neuroblastoma Breakpoint Family Member 14 (NBPF14, adjusted p-value=0.0462, Fold-change=0.586) achieved the Benjamani-Hochberg adjusted p-value of 0.0462, and has been reported to be associated with cortical neurogenesis (Suzuki et al., 2017).

Computational psychiatry, as advocated by the National Institute of Mental Health’s Research Domain Criteria (RDoC), may need data to drive the classification, diagnosis, and treatment response status, especially in patients with developmental delay, language difficulty, and condition of a potentially different etiology than traditionally taught (Clark et al., 2017; Eugene & Masiak, 2016). Ideally, in such cases, alternative FDA-approved mood stabilizers may be initially selected prior to any pharmacological intervention by simply using a blood test. Perhaps, a gene expression screening panel at baseline, prior to the initiation of lithium and/or other FDA-approved mood stabilizer, may be better in high-risk patient populations.

These findings suggest that when implementing genomic medicine, clinical research teams should move beyond the single-gene approach when screening for treatment responders or non-responders. This approach is currently the standard when screening for patient toxicity at standard doses in poor or ultra-rapid metabolizers; however, as more transcriptional factors are discovered that regulate the cytochrome (CYP) P-450 system of genes, multi-gene pharmacokinetic panels are inevitable and may be included in future Clinical Pharmacogenetics Implementation Consortium (CPIC) guidelines. Next, medical management of patients with mania and psychosis either with pharmacotherapy and/or behavioral intervention should be tailored to biological gender due to known neuronal circuitry differences in age-matched patients with psychosis (Eugene et al., 2015). Further, as a result of lithium not being hepatically metabolized, but rather transported and renally excreted, as well as, the known myriad drug-drug interactions, patient dose selection may benefit from clinical pharmacometrics modeling by American Board of Clinical Pharmaology certified physicians in applied clinical pharmacology/clinical pharmacology (Perera et al., 2014; Zetin et al., 1986). This approach may be implemented to ensure drug pharmacokinetic safety.

The limitations of our analysis and in most genetic studies are understandably due to multiple-comparison p-value adjustments and patient sample size (Dudoit et al., 2003). The fundamental aims of our research questions were designed to answer biological questions of gender and clinical response to lithium and not meant to be driven exclusively by multiple comparisons adjusted p-values. This approach has led to various successes in genomic medicine, specifically, in genome-wide association studies; however, understandably, the limitations are thoroughly acknowledged. In reference to patient sample sizes, 9 out of the 28 patients who received lithium and optimal therapy were classified as lithium treatment responders. Further, 30% of men and 33% of women, who were treated with lithium, were found to be responders at the respective gender categories (Beech et al., 2014). However, the strengths of our findings are in the gender-gene screening ability for lithium treatment-responders in the general population of 60 patients at baseline, minus the tested responder group. Opportunities exist for prospective clinical trials and application of the methods outlined in this text for other therapeutic agents across several medical specialties.

Conclusion

We explored the Lithium Treatment-Moderate dose Use Study clinical trial gene expression data with the aim of identifying gender-specific transcriptome-level regulators of lithium treatment response. Using machine learning, we successfully developed a pre-treatment gender- and gene-expression-specific predictive model selective for lithium responders with an ROC AUC of 0.92 for men and an ROC AUC of 1 for women. Further, by using well-established Bayesian statistical methods, to identify differentially expressed genes and then machine learning, we discovered 5-genes selective for men and 9-genes that are selective for women that will inform the physicians and clinical staff of whether the patient will respond to lithium prior to being prescribed the drug. With the small number of patient responders from the clinical trial, our results should be confirmed. Lastly, in an overall context, our results suggest that the methodology used in this analysis may be extended to other therapeutic drug classes and provides insight to the gender-based gene transcriptome differences influencing lithium pharmacodynamics.

Data availability

Data used in this study are available from https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE45484

Comments on this article Comments (0)

Version 3
VERSION 3 PUBLISHED 18 Apr 2018
Comment
Author details Author details
Competing interests
Grant information
Copyright
Download
 
Export To
metrics
Views Downloads
F1000Research - -
PubMed Central
Data from PMC are received and updated monthly.
- -
Citations
CITE
how to cite this article
Eugene AR, Masiak J and Eugene B. Predicting lithium treatment response in bipolar patients using gender-specific gene expression biomarkers and machine learning [version 2; peer review: 1 approved, 1 approved with reservations]. F1000Research 2018, 7:474 (https://doi.org/10.12688/f1000research.14451.2)
NOTE: If applicable, it is important to ensure the information in square brackets after the title is included in all citations of this article.
track
receive updates on this article
Track an article to receive email alerts on any updates to this article.

Open Peer Review

Current Reviewer Status: ?
Key to Reviewer Statuses VIEW
ApprovedThe paper is scientifically sound in its current form and only minor, if any, improvements are suggested
Approved with reservations A number of small changes, sometimes more significant revisions are required to address specific details and improve the papers academic merit.
Not approvedFundamental flaws in the paper seriously undermine the findings and conclusions
Version 2
VERSION 2
PUBLISHED 29 May 2018
Revised
Views
14
Cite
Reviewer Report 12 Nov 2018
Sunil V. Kalmady, Department of Psychiatry, University of Alberta, Alberta, Canada;  Alberta Machine Intelligence Institute, Alberta, Canada 
Approved with Reservations
VIEWS 14
Eugene et al. tackles the hard question on the transcriptome predictors of clinical outcome in lithium treatment of Bipolar disorder. This research question is of clinical relevance and importance, however, there might be some issues with how the data was ... Continue reading
CITE
CITE
HOW TO CITE THIS REPORT
Kalmady SV. Reviewer Report For: Predicting lithium treatment response in bipolar patients using gender-specific gene expression biomarkers and machine learning [version 2; peer review: 1 approved, 1 approved with reservations]. F1000Research 2018, 7:474 (https://doi.org/10.5256/f1000research.16407.r39873)
NOTE: it is important to ensure the information in square brackets after the title is included in all citations of this article.
  • Author Response 07 Dec 2018
    Andy Eugene, Department of Pharmacogenomics, Bernard J. Dunn School of Pharmacy, Inova Center for Personalized Health, Shenandoah University, Fairfax, 22031, USA
    07 Dec 2018
    Author Response
    Please see our responses in bold-face to the comments from Referee #2. We thank you for reviewing this article.

    Eugene et al. tackles the hard question on the transcriptome ... Continue reading
COMMENTS ON THIS REPORT
  • Author Response 07 Dec 2018
    Andy Eugene, Department of Pharmacogenomics, Bernard J. Dunn School of Pharmacy, Inova Center for Personalized Health, Shenandoah University, Fairfax, 22031, USA
    07 Dec 2018
    Author Response
    Please see our responses in bold-face to the comments from Referee #2. We thank you for reviewing this article.

    Eugene et al. tackles the hard question on the transcriptome ... Continue reading
Views
18
Cite
Reviewer Report 27 Jun 2018
Ming-Fen Ho, Division of Clinical Pharmacology, Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic, Rochester, MN, USA 
Approved
VIEWS 18
I confirm that I have read this submission and believe that I have an ... Continue reading
CITE
CITE
HOW TO CITE THIS REPORT
Ho MF. Reviewer Report For: Predicting lithium treatment response in bipolar patients using gender-specific gene expression biomarkers and machine learning [version 2; peer review: 1 approved, 1 approved with reservations]. F1000Research 2018, 7:474 (https://doi.org/10.5256/f1000research.16407.r34437)
NOTE: it is important to ensure the information in square brackets after the title is included in all citations of this article.
Version 1
VERSION 1
PUBLISHED 18 Apr 2018
Views
24
Cite
Reviewer Report 21 May 2018
Ming-Fen Ho, Division of Clinical Pharmacology, Department of Molecular Pharmacology and Experimental Therapeutics, Mayo Clinic, Rochester, MN, USA 
Approved with Reservations
VIEWS 24
The authors demonstrated that sex-differences gene expression might contribute to lithium treatment response using microarray expression data.

Major comments:
  1. A samples size of 60 might be too small to determine the sex effects.
... Continue reading
CITE
CITE
HOW TO CITE THIS REPORT
Ho MF. Reviewer Report For: Predicting lithium treatment response in bipolar patients using gender-specific gene expression biomarkers and machine learning [version 2; peer review: 1 approved, 1 approved with reservations]. F1000Research 2018, 7:474 (https://doi.org/10.5256/f1000research.15730.r33941)
NOTE: it is important to ensure the information in square brackets after the title is included in all citations of this article.
  • Author Response 29 May 2018
    Andy Eugene, Department of Pharmacogenomics, Bernard J. Dunn School of Pharmacy, Inova Center for Personalized Health, Shenandoah University, Fairfax, 22031, USA
    29 May 2018
    Author Response
    Major Comment Responses:
    Response 1: 

    This point is well noted; however, it is important to realize that our gender-effects of gene expression is consistent with other studies noted within the paper and ... Continue reading
  • Author Response 29 May 2018
    Andy Eugene, Department of Pharmacogenomics, Bernard J. Dunn School of Pharmacy, Inova Center for Personalized Health, Shenandoah University, Fairfax, 22031, USA
    29 May 2018
    Author Response
    Specific Comment Responses:
    We thank you for your specific comments and have addressed several of the pertinent points in your review. For all differentially expressed results reported throughout tables within ... Continue reading
COMMENTS ON THIS REPORT
  • Author Response 29 May 2018
    Andy Eugene, Department of Pharmacogenomics, Bernard J. Dunn School of Pharmacy, Inova Center for Personalized Health, Shenandoah University, Fairfax, 22031, USA
    29 May 2018
    Author Response
    Major Comment Responses:
    Response 1: 

    This point is well noted; however, it is important to realize that our gender-effects of gene expression is consistent with other studies noted within the paper and ... Continue reading
  • Author Response 29 May 2018
    Andy Eugene, Department of Pharmacogenomics, Bernard J. Dunn School of Pharmacy, Inova Center for Personalized Health, Shenandoah University, Fairfax, 22031, USA
    29 May 2018
    Author Response
    Specific Comment Responses:
    We thank you for your specific comments and have addressed several of the pertinent points in your review. For all differentially expressed results reported throughout tables within ... Continue reading

Comments on this article Comments (0)

Version 3
VERSION 3 PUBLISHED 18 Apr 2018
Comment
Alongside their report, reviewers assign a status to the article:
Approved - the paper is scientifically sound in its current form and only minor, if any, improvements are suggested
Approved with reservations - A number of small changes, sometimes more significant revisions are required to address specific details and improve the papers academic merit.
Not approved - fundamental flaws in the paper seriously undermine the findings and conclusions
Sign In
If you've forgotten your password, please enter your email address below and we'll send you instructions on how to reset your password.

The email address should be the one you originally registered with F1000.

Email address not valid, please try again

You registered with F1000 via Google, so we cannot reset your password.

To sign in, please click here.

If you still need help with your Google account password, please click here.

You registered with F1000 via Facebook, so we cannot reset your password.

To sign in, please click here.

If you still need help with your Facebook account password, please click here.

Code not correct, please try again
Email us for further assistance.
Server error, please try again.