AI and narrative embeddings detect PTSD following childbirth via birth stories

Free-text analysis using machine learning (ML)-based natural language processing (NLP) shows promise for diagnosing psychiatric conditions. Chat Generative Pre-trained Transformer (ChatGPT) has demonstrated preliminary initial feasibility for this purpose; however, whether it can accurately assess mental illness remains to be determined. This study evaluates the effectiveness of ChatGPT and the text-embedding-ada-002 (ADA) model in detecting post-traumatic stress disorder following childbirth (CB-PTSD), a maternal postpartum mental illness affecting millions of women annually, with no standard screening protocol. Using a sample of 1295 women who gave birth in the last six months and were 18+ years old, recruited through hospital announcements, social media, and professional organizations, we explore ChatGPT's and ADA's potential to screen for CB-PTSD by analyzing maternal childbirth narratives. The PTSD Checklist for DSM-5 (PCL-5; cutoff 31) was used to assess CB-PTSD. By developing an ML model that utilizes numerical vector representation of the ADA model, we identify CB-PTSD via narrative classification. Our model outperformed (F1 score: 0.81) ChatGPT and six previously published large text-embedding models trained on mental health or clinical domains data, suggesting that the ADA model can be harnessed to identify CB-PTSD. Our modeling approach could be generalized to assess other mental health disorders.

Persistence of collective memory of corporate bankruptcy events discussed on X (Twitter) is influenced by pre-bankruptcy public attention

Collective attention and memory involving significant events can be quantitatively studied via social media data. Previous studies analyzed user attention to discrete events that do not change post-event, and assume universal public attention patterns. However, dynamic events with ongoing updates are common, yielding varied individual attention patterns. We explore memory of U.S. companies filing Chapter 11 bankruptcy and being mentioned on X (formerly Twitter). Unlike discrete events, Chapter 11 entails ongoing financial changes as the company typically remains operational, influencing post-event attention dynamics. We collected 248,936 X mentions for 74 companies before and after each bankruptcy. Attention surged after bankruptcy, with distinct Low and High persistence levels compared with pre-bankruptcy attention. The two tweeting patterns were modeled using biexponential models, successfully predicting (F1-score: 0.81) post-bankruptcy attention persistence. Studying bankruptcy events on social media reveals diverse attention patterns, demonstrates how pre-bankruptcy attention affects post-bankruptcy recollection, and provides insights into memory of dynamic events.

Screening for post-traumatic stress disorder following childbirth using the Peritraumatic Distress Inventory

BACKGROUND

Post-traumatic stress disorder (PTSD) following traumatic childbirth may undermine maternal and infant health, but screening for maternal childbirth-related PTSD (CB-PTSD) remains lacking. Acute emotional distress in response to a traumatic experience strongly associates with PTSD. The Peritraumatic Distress Inventory (PDI) assesses acute distress in non-postpartum individuals, but its use to classify women likely to endorse CB-PTSD is unknown.

METHODS

3039 women provided information about their mental health and childbirth experience. They completed the PDI regarding their recent childbirth event, and a PTSD symptom screen to determine CB-PTSD. We employed Exploratory Graph Analysis and bootstrapping to reveal the PDI's factorial structure and optimal cutoff value for CB-PTSD classification.

RESULTS

Factor analysis revealed two strongly correlated stable factors based on a modified version of the PDI: (1) negative emotions and (2) bodily arousal and threat appraisal. A score of 15+ on the modified PDI produced high sensitivity and specificity: 88 % with a positive CB-PTSD screen in the first postpartum months and 93 % with a negative screen.

LIMITATIONS

In this cross-sectional study, the PDI was administered at different timepoints postpartum. Future work should examine the PDI's predictive utility for screening women as closely as possible to the time of childbirth, and establish clinical cutoffs in populations after complicated deliveries.

CONCLUSIONS

Brief self-report screening concerning a woman's emotional reactions to childbirth using our modified PDI tool can detect those likely to endorse CB-PTSD in the early postpartum. This may serve as the initial step of managing symptoms to ultimately prevent chronic manifestations.

OpenAI's Narrative Embeddings Can Be Used for Detecting Post-Traumatic Stress Following Childbirth Via Birth Stories

Free-text analysis using Machine Learning (ML)-based Natural Language Processing (NLP) shows promise for diagnosing psychiatric conditions. Chat Generative Pre-trained Transformer (ChatGPT) has demonstrated preliminary initial feasibility for this purpose; however, whether it can accurately assess mental illness remains to be determined. This study evaluates the effectiveness of ChatGPT and the text-embedding-ada-002 (ADA) model in detecting post-traumatic stress disorder following childbirth (CB-PTSD), a maternal postpartum mental illness affecting millions of women annually, with no standard screening protocol. Using a sample of 1,295 women who gave birth in the last six months and were 18+ years old, recruited through hospital announcements, social media, and professional organizations, we explore ChatGPT's and ADA's potential to screen for CB-PTSD by analyzing maternal childbirth narratives. The PTSD Checklist for DSM-5 (PCL-5; cutoff 31) was used to assess CB-PTSD. By developing an ML model that utilizes numerical vector representation of the ADA model, we identify CB-PTSD via narrative classification. Our model outperformed (F1 score: 0.82) ChatGPT and six previously published large language models (LLMs) trained on mental health or clinical domains data, suggesting that the ADA model can be harnessed to identify CB-PTSD. Our modeling approach could be generalized to assess other mental health disorders.

OpenAI's Narrative Embeddings Can Be Used for Detecting Post-Traumatic Stress Following Childbirth Via Birth Stories

Free-text analysis using Machine Learning (ML)-based Natural Language Processing (NLP) shows promise for diagnosing psychiatric conditions. Chat Generative Pre-trained Transformer (ChatGPT) has demonstrated preliminary initial feasibility for this purpose; however, whether it can accurately assess mental illness remains to be determined. This study evaluates the effectiveness of ChatGPT and the text-embedding-ada-002 (ADA) model in detecting post-traumatic stress disorder following childbirth (CB-PTSD), a maternal postpartum mental illness affecting millions of women annually, with no standard screening protocol. Using a sample of 1,295 women who gave birth in the last six months and were 18+ years old, recruited through hospital announcements, social media, and professional organizations, we explore ChatGPT's and ADA's potential to screen for CB-PTSD by analyzing maternal childbirth narratives. The PTSD Checklist for DSM-5 (PCL-5; cutoff 31) was used to assess CB-PTSD. By developing an ML model that utilizes numerical vector representation of the ADA model, we identify CB-PTSD via narrative classification. Our model outperformed (F1 score: 0.82) ChatGPT and six previously published large language models (LLMs) trained on mental health or clinical domains data, suggesting that the ADA model can be harnessed to identify CB-PTSD. Our modeling approach could be generalized to assess other mental health disorders.

The Psychedelic Future of Post-Traumatic Stress Disorder Treatment

Post-traumatic stress disorder (PTSD) is a mental health condition that can occur following exposure to a traumatic experience. An estimated 12 million U.S. adults are presently affected by this disorder. Current treatments include psychological therapies (e.g., exposure-based interventions) and pharmacological treatments (e.g., selective serotonin reuptake inhibitors (SSRIs)). However, a significant proportion of patients receiving standard-of-care therapies for PTSD remain symptomatic, and new approaches for this and other trauma-related mental health conditions are greatly needed. Psychedelic compounds that alter cognition, perception, and mood are currently being examined for their efficacy in treating PTSD despite their current status as Drug Enforcement Administration (DEA)- scheduled substances. Initial clinical trials have demonstrated the potential value of psychedelicassisted therapy to treat PTSD and other psychiatric disorders. In this comprehensive review, we summarize the state of the science of PTSD clinical care, including current treatments and their shortcomings. We review clinical studies of psychedelic interventions to treat PTSD, trauma-related disorders, and common comorbidities. The classic psychedelics psilocybin, lysergic acid diethylamide (LSD), and N,N-dimethyltryptamine (DMT) and DMT-containing ayahuasca, as well as the entactogen 3,4-methylenedioxymethamphetamine (MDMA) and the dissociative anesthetic ketamine, are reviewed. For each drug, we present the history of use, psychological and somatic effects, pharmacology, and safety profile. The rationale and proposed mechanisms for use in treating PTSD and traumarelated disorders are discussed. This review concludes with an in-depth consideration of future directions for the psychiatric applications of psychedelics to maximize therapeutic benefit and minimize risk in individuals and communities impacted by trauma-related conditions.

Preventing posttraumatic stress disorder following childbirth: a systematic review and meta-analysis

OBJECTIVE

Women can develop posttraumatic stress disorder in response to experienced or perceived traumatic, often medically complicated, childbirth; the prevalence of these events remains high in the United States. Currently, no recommended treatment exists in routine care to prevent or mitigate maternal childbirth-related posttraumatic stress disorder. We conducted a systematic review and meta-analysis of clinical trials that evaluated any therapy to prevent or treat childbirth-related posttraumatic stress disorder.

DATA SOURCES

PsycInfo, PsycArticles, PubMed (MEDLINE), ClinicalTrials.gov, CINAHL, ProQuest, Sociological Abstracts, Google Scholar, Embase, Web of Science, ScienceDirect, Scopus, and the Cochrane Central Register of Controlled Trials were searched for eligible trials published through September 2023.

STUDY ELIGIBILITY CRITERIA

Trials were included if they were interventional, if they evaluated any therapy for childbirth-related posttraumatic stress disorder for the indication of symptoms or before posttraumatic stress disorder onset, and if they were written in English.

METHODS

Independent coders extracted the sample characteristics and intervention information of the eligible studies and evaluated the trials using the Downs and Black's quality checklist and Cochrane's method for risk of bias evaluation.

RESULTS

A total of 41 studies (32 randomized controlled trials, 9 nonrandomized trials) were reviewed. They evaluated brief psychological therapies including debriefing, trauma-focused therapies (including cognitive behavioral therapy and expressive writing), memory consolidation and reconsolidation blockage, mother-infant-focused therapies, and educational interventions. The trials targeted secondary preventions aimed at buffering childbirth-related posttraumatic stress disorder usually after traumatic childbirth (n=24), tertiary preventions among women with probable childbirth-related posttraumatic stress disorder (n=14), and primary prevention during pregnancy (n=3). A meta-analysis of the combined randomized secondary preventions showed moderate effects in reducing childbirth-related posttraumatic stress disorder symptoms when compared with usual treatment (standardized mean difference, -0.67; 95% confidence interval, -0.92 to -0.42). Single-session therapy within 96 hours of birth was helpful (standardized mean difference, -0.55). Brief, structured, trauma-focused therapies and semi-structured, midwife-led, dialogue-based psychological counseling showed the largest effects (standardized mean difference, -0.95 and -0.91, respectively). Other treatment approaches (eg, the Tetris game, mindfulness, mother-infant-focused treatment) warrant more research. Tertiary preventions produced smaller effects than secondary prevention but are potentially clinically meaningful (standardized mean difference, -0.37; -0.60 to -0.14). Antepartum educational approaches may help, but insufficient empirical evidence exists.

CONCLUSION

Brief trauma-focused and non-trauma-focused psychological therapies delivered early in the period following traumatic childbirth offer a critical and feasible opportunity to buffer the symptoms of childbirth-related posttraumatic stress disorder. Future research that integrates diagnostic and biologic measures can inform treatment use and the mechanisms at work.

The role of the hypothalamic-pituitary-adrenal axis in depression across the female reproductive lifecycle: current knowledge and future directions

The aim of this narrative review is to consolidate knowledge on the role of the hypothalamic-pituitary-adrenal (HPA) axis in depression pathophysiology at different reproductive stages across the female lifespan. Despite growing evidence about the impact of gonadal hormones on mood disorders, no previous review has examined the interaction between such hormonal changes and the HPA axis within the context of depressive disorders in women. We will focus on HPA axis function in depressive disorders at different reproductive stages including the menstrual cycle (e.g., premenstrual dysphoric disorder [PMDD]), perinatally (e.g., postpartum depression), and in perimenopausal depression. Each of these reproductive stages is characterized by vast physiological changes and presents major neuroendocrine reorganization. The HPA axis is one of the main targets of such functional alterations, and with its key role in stress response, it is an etiological factor in vulnerable windows for depression across the female lifespan. We begin with an overview of the HPA axis and a brief summary of techniques for measuring HPA axis parameters. We then describe the hormonal milieu of each of these key reproductive stages, and integrate information about HPA axis function in depression across these reproductive stages, describing similarities and differences. The role of a history of stress and trauma exposure as a contributor to female depression in the context of HPA axis involvement across the reproductive stages is also presented. This review advances the pursuit of understanding common biological mechanisms across depressive disorders among women. Our overarching goal is to identify unmet needs in characterizing stress-related markers of depression in women in the context of hormonal changes across the lifespan, and to support future research in women's mental health as it pertains to pathophysiology, early diagnosis, and treatment targets.

D2H2: diabetes data and hypothesis hub

Motivation

There is a rapid growth in the production of omics datasets collected by the diabetes research community. However, such published data are underutilized for knowledge discovery. To make bioinformatics tools and published omics datasets from the diabetes field more accessible to biomedical researchers, we developed the Diabetes Data and Hypothesis Hub (D2H2).

Results

D2H2 contains hundreds of high-quality curated transcriptomics datasets relevant to diabetes, accessible via a user-friendly web-based portal. The collected and processed datasets are curated from the Gene Expression Omnibus (GEO). Each curated study has a dedicated page that provides data visualization, differential gene expression analysis, and single-gene queries. To enable the investigation of these curated datasets and to provide easy access to bioinformatics tools that serve gene and gene set-related knowledge, we developed the D2H2 chatbot. Utilizing GPT, we prompt users to enter free text about their data analysis needs. Parsing the user prompt, together with specifying information about all D2H2 available tools and workflows, we answer user queries by invoking the most relevant tools via the tools' API. D2H2 also has a hypotheses generation module where gene sets are randomly selected from the bulk RNA-seq precomputed signatures. We then find highly overlapping gene sets extracted from publications listed in PubMed Central with abstract dissimilarity. With the help of GPT, we speculate about a possible explanation of the high overlap between the gene sets. Overall, D2H2 is a platform that provides a suite of bioinformatics tools and curated transcriptomics datasets for hypothesis generation.

Availability and implementation

D2H2 is available at: https://d2h2.maayanlab.cloud/ and the source code is available from GitHub at https://github.com/MaayanLab/D2H2-site under the CC BY-NC 4.0 license.

Establishing the validity of a diagnostic questionnaire for childbirth-related posttraumatic stress disorder

BACKGROUND

Labor and delivery can entail complications and severe maternal morbidities that threaten a woman's life or cause her to believe that her life is in danger. Women with these experiences are at risk for developing posttraumatic stress disorder. Postpartum posttraumatic stress disorder, or childbirth-related posttraumatic stress disorder, can become an enduring and debilitating condition. At present, validated tools for a rapid and efficient screen for childbirth-related posttraumatic stress disorder are lacking.

OBJECTIVE

We examined the diagnostic validity of the Posttraumatic Stress Disorder Checklist for Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, for detecting posttraumatic stress disorder among women who have had a traumatic childbirth. This Checklist assesses the 20 Diagnostic and Statistical Manual of Mental Disorders, posttraumatic stress disorder symptoms and is a commonly used patient-administrated screening instrument. Its diagnostic accuracy for detecting childbirth-related posttraumatic stress disorder is unknown.

STUDY DESIGN

The sample included 59 patients who reported a traumatic childbirth experience determined in accordance with the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, posttraumatic stress disorder criterion A for exposure involving a threat or potential threat to the life of the mother or infant, experienced or perceived, or physical injury. The majority (66%) of the participants were less than 1 year postpartum (for full sample: median, 4.67 months; mean, 1.5 years) and were recruited via the Mass General Brigham's online platform, during the postpartum unit hospitalization or after discharge. Patients were instructed to complete the Posttraumatic Stress Disorder Checklist for Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, concerning posttraumatic stress disorder symptoms related to childbirth. Other comorbid conditions (ie, depression and anxiety) were also assessed. They also underwent a clinician interview for posttraumatic stress disorder using the gold-standard Clinician-Administered PTSD Scale for Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition. A second administration of the checklist was performed in a subgroup (n=43), altogether allowing an assessment of internal consistency, test-retest reliability, and convergent and diagnostic validity of the Checklist. The diagnostic accuracy of the Posttraumatic Stress Disorder Checklist for Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, in reference to the Clinician-Administered PTSD Scale for Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, was determined using the area under the receiver operating characteristic curve; an optimal cutoff score was identified using the Youden's J index.

RESULTS

One-third of the sample (35.59%) met the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, criteria for a posttraumatic stress disorder diagnosis stemming from childbirth. The Posttraumatic Stress Disorder Checklist for Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, symptom severity score was strongly correlated with the Clinician-Administered PTSD Scale for Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, total score (ρ=0.82; P<.001). The area under the receiver operating characteristic curve was 0.93 (95% confidence interval, 0.87-0.99), indicating excellent diagnostic performance of the Posttraumatic Stress Disorder Checklist for Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition. A cutoff value of 28 maximized the sensitivity (0.81) and specificity (0.90) and correctly diagnosed 86% of women. A higher value (32) identified individuals with more severe posttraumatic stress disorder symptoms (specificity, 0.95), but with lower sensitivity (0.62). Checklist scores were also stable over time (intraclass correlation coefficient, 0.73), indicating good test-retest reliability. Posttraumatic Stress Disorder Checklist for Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, scores were moderately correlated with the depression and anxiety symptom scores (Edinburgh Postnatal Depression Scale: ρ=0.58; P<.001 and the Brief Symptom Inventory, anxiety subscale: ρ=0.51; P<.001).

CONCLUSION

This study demonstrates the validity of the Posttraumatic Stress Disorder Checklist for Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, as a screening tool for posttraumatic stress disorder among women who had a traumatic childbirth experience. The instrument may facilitate screening for childbirth-related posttraumatic stress disorder on a large scale and help identify women who might benefit from further diagnostics and services. Replication of the findings in larger, postpartum samples is needed.

A Systematic Review of Interventions for Prevention and Treatment of Post-Traumatic Stress Disorder Following Childbirth

Objective

Postpartum women can develop post-traumatic stress disorder (PTSD) in response to complicated, traumatic childbirth; prevalence of these events remains high in the U.S. Currently, there is no recommended treatment approach in routine peripartum care for preventing maternal childbirth-related PTSD (CB-PTSD) and lessening its severity. Here, we provide a systematic review of available clinical trials testing interventions for the prevention and indication of CB-PTSD.

Data Sources

We conducted a systematic review of PsycInfo, PsycArticles, PubMed (MEDLINE), ClinicalTrials.gov, CINAHL, ProQuest, Sociological Abstracts, Google Scholar, Embase, Web of Science, ScienceDirect, and Scopus through December 2022 to identify clinical trials involving CB-PTSD prevention and treatment.

Study Eligibility Criteria

Trials were included if they were interventional, evaluated CB-PTSD preventive strategies or treatments, and reported outcomes assessing CB-PTSD symptoms. Duplicate studies, case reports, protocols, active clinical trials, and studies of CB-PTSD following stillbirth were excluded.

Study Appraisal and Synthesis Methods

Two independent coders evaluated trials using a modified Downs and Black methodological quality assessment checklist. Sample characteristics and related intervention information were extracted via an Excel-based form.

Results

A total of 33 studies, including 25 randomized controlled trials (RCTs) and 8 non-RCTs, were included. Trial quality ranged from Poor to Excellent. Trials tested psychological therapies most often delivered as secondary prevention against CB-PTSD onset (n=21); some examined primary (n=3) and tertiary (n=9) therapies. Positive treatment effects were found for early interventions employing conventional trauma-focused therapies, psychological counseling, and mother-infant dyadic focused strategies. Therapies' utility to aid women with severe acute traumatic stress symptoms or reduce incidence of CB-PTSD diagnosis is unclear, as is whether they are effective as tertiary intervention. Educational birth plan-focused interventions during pregnancy may improve maternal health outcomes, but studies remain scarce.

Conclusions

An array of early psychological therapies delivered in response to traumatic childbirth, rather than universally, in the first postpartum days and weeks, may potentially buffer CB-PTSD development. Rather than one treatment being suitable for all, effective therapy should consider individual-specific factors. As additional RCTs generate critical information and guide recommendations for first-line preventive treatments for CB-PTSD, the psychiatric consequences associated with traumatic childbirth could be lessened.

Screening for Post-Traumatic Stress Disorder following Childbirth using the Peritraumatic Distress Inventory

Background

Maternal psychiatric morbidities include a range of psychopathologies; one condition is post-traumatic stress disorder (PTSD) that develops following a traumatic childbirth experience and may undermine maternal and infant health. Although assessment for maternal mental health problems is integrated in routine perinatal care, screening for maternal childbirth-related PTSD (CB-PTSD) remains lacking. Acute emotional distress in response to a traumatic event strongly associates with PTSD. The brief 13-item Peritraumatic Distress Inventory (PDI) is a common tool to assess acute distress in non-postpartum individuals. How well the PDI specified to childbirth can classify women likely to endorse CB-PTSD is unknown.

Objectives

We sought to determine the utility of the PDI to detect CB-PTSD in the early postpartum period. This involved examining the psychometric properties of the PDI specified to childbirth, pertaining to its factorial structure, and establishing an optimal cutoff point for the classification of women with high vs. low likelihood of endorsing CB-PTSD.

Study Design

A sample of 3,039 eligible women who had recently given birth provided information about their mental health and childbirth experience. They completed the PDI regarding their recent childbirth event, and a PTSD symptom screen to determine CB-PTSD. We employed Exploratory Graph Analysis (EGA) and bootstrapping analysis to reveal the factorial structure of the PDI and the optimal PDI cutoff value for CB-PTSD classification.

Results

Factor analysis of the PDI shows two strongly correlated stable factors based on a modified 12-item version of the PDI consisting of (1) negative emotions and (2) bodily arousal and threat appraisal in regard to recent childbirth. This structure largely accords with prior studies of individuals who experienced acute distress resulting from other forms of trauma. We report that a score of 15 or higher on the modified PDI produces strong sensitivity and specificity. 88% of women with a positive CB-PTSD screen in the first postpartum months and 93% with a negative screen are identified as such using the established cutoff.

Conclusions

Our work reveals that a brief self-report screening concerning a woman's immediate emotional reactions to childbirth that uses our modified PDI tool can detect women likely to endorse CB-PTSD in the early postpartum period. This form of maternal mental health assessment may serve as the initial step of managing symptoms to ultimately prevent chronic symptom manifestation. Future research is needed to examine the utility of employing the PDI as an assessment performed during maternity hospitalization stay in women following complicated deliveries to further guide recommendations to implement maternal mental health screening for women at high risk for developing CB-PTSD.

Identifying women with postdelivery posttraumatic stress disorder using natural language processing of personal childbirth narratives

BACKGROUND

Maternal mental disorders are considered a leading complication of childbirth and a common contributor to maternal death. In addition to undermining maternal welfare, untreated postpartum psychopathology can result in child emotional and physical neglect and associated significant pediatric health costs. Some women may experience traumatic childbirth and develop posttraumatic stress disorder symptoms after delivery (childbirth-related posttraumatic stress disorder). Although women are routinely screened for postpartum depression in the United States, there is no recommended protocol to inform the identification of women who are likely to experience childbirth-related posttraumatic stress disorder. Advancements in computational methods of free text have shown promise in informing the diagnosis of psychiatric conditions. Although the language in narratives of stressful events has been associated with posttrauma outcomes, whether the narratives of childbirth processed via machine learning can be useful for childbirth-related posttraumatic stress disorder screening is unknown.

OBJECTIVE

This study aimed to examine the use of written narrative accounts of personal childbirth experiences for the identification of women with childbirth-related posttraumatic stress disorder. To this end, we developed a model based on natural language processing and machine learning algorithms to identify childbirth-related posttraumatic stress disorder via the classification of birth narratives.

STUDY DESIGN

Overall, 1127 eligible postpartum women who enrolled in a study survey during the COVID-19 pandemic provided short written childbirth narrative accounts in which they were instructed to focus on the most distressing aspects of their childbirth experience. They also completed a posttraumatic stress disorder symptom screen to determine childbirth-related posttraumatic stress disorder. After the exclusion criteria were applied, data from 995 participants were analyzed. A machine learning-based Sentence-Transformers natural language processing model was used to represent narratives as vectors that served as inputs for a neural network machine learning model developed in this study to identify participants with childbirth-related posttraumatic stress disorder.

RESULTS

The machine learning model derived from natural language processing of childbirth narratives achieved good performance (area under the curve, 0.75; F1 score, 0.76; sensitivity, 0.8; specificity, 0.70). Moreover, women with childbirth-related posttraumatic stress disorder generated longer narratives (t test results: t=2.30; p=.02) and used more negative emotional expressions (Wilcoxon test: sadness: p=8.90e-04; W=31,017; anger: p=1.32e-02; W=35,005.50) and death-related words (Wilcoxon test: p=3.48e-05; W=34,538) in describing their childbirth experience than those with no childbirth-related posttraumatic stress disorder.

CONCLUSION

This study provided proof of concept that personal childbirth narrative accounts generated in the early postpartum period and analyzed via advanced computational methods can detect with relatively high accuracy women who are likely to endorse childbirth-related posttraumatic stress disorder and those at low risk. This suggests that birth narratives could be promising for informing low-cost, noninvasive tools for maternal mental health screening, and more research that used machine learning to predict early signs of maternal psychiatric morbidity is warranted.

HetIG-PreDiG: A Heterogeneous Integrated Graph Model for Predicting Human Disease Genes based on gene expression

Graph analytical approaches permit identifying novel genes involved in complex diseases, but are limited by (i) inferring structural network similarity of connected gene nodes, ignoring potentially relevant unconnected nodes; (ii) using homogeneous graphs, missing gene-disease associations' complexity; (iii) relying on disease/gene-phenotype associations' similarities, involving highly incomplete data; (iv) using binary classification, with gene-disease edges as positive training samples, and non-associated gene and disease nodes as negative samples that may include currently unknown disease genes; or (v) reporting predicted novel associations without systematically evaluating their accuracy. Addressing these limitations, we develop the Heterogeneous Integrated Graph for Predicting Disease Genes (HetIG-PreDiG) model that includes gene-gene, gene-disease, and gene-tissue associations. We predict novel disease genes using low-dimensional representation of nodes accounting for network structure, and extending beyond network structure using the developed Gene-Disease Prioritization Score (GDPS) reflecting the degree of gene-disease association via gene co-expression data. For negative training samples, we select non-associated gene and disease nodes with lower GDPS that are less likely to be affiliated. We evaluate the developed model's success in predicting novel disease genes by analyzing the prediction probabilities of gene-disease associations. HetIG-PreDiG successfully predicts (Micro-F1 = 0.95) gene-disease associations, outperforming baseline models, and is validated using published literature, thus advancing our understanding of complex genetic diseases.

Identifying Women with Post-Delivery Posttraumatic Stress Disorder using Natural Language Processing of Personal Childbirth Narratives

Background

Maternal mental disorders are considered a leading complication of childbirth and a common contributor to maternal death. In addition to undermining maternal welfare, untreated postpartum psychopathology can result in child emotional and physical neglect, and associated significant pediatric health costs. Some women may experience a traumatic childbirth and develop posttraumatic stress disorder (PTSD) symptoms following delivery (CB-PTSD). Although women are routinely screened for postpartum depression in the U.S., there is no recommended protocol to inform the identification of women who are likely to experience CB-PTSD. Advancements in computational methods of free text has shown promise in informing diagnosis of psychiatric conditions. Although the language in narratives of stressful events has been associated with post-trauma outcomes, whether the narratives of childbirth processed via machine learning can be useful for CB-PTSD screening is unknown.

Objective

This study examined the utility of written narrative accounts of personal childbirth experience for the identification of women with provisional CB-PTSD. To this end, we developed a model based on natural language processing (NLP) and machine learning (ML) algorithms to identify CB-PTSD via classification of birth narratives.

Study Design

A total of 1,127 eligible postpartum women who enrolled in a study survey during the COVID-19 era provided short written childbirth narrative accounts in which they were instructed to focus on the most distressing aspects of their childbirth experience. They also completed a PTSD symptom screen to determine provisional CB-PTSD. After exclusion criteria were applied, data from 995 participants was analyzed. An ML-based Sentence-Transformer NLP model was used to represent narratives as vectors that served as inputs for a neural network ML model developed in this study to identify participants with provisional CB-PTSD.

Results

The ML model derived from NLP of childbirth narratives achieved good performance: AUC 0.75, F1-score 0.76, sensitivity 0.8, and specificity 0.70. Moreover, women with provisional CB-PTSD generated longer narratives (t-test results: t=2 . 30, p=0 . 02 ) and used more negative emotional expressions (Wilcoxon test: 'sadness': p=8 . 90e- ⁰⁴ , W=31,017 ; 'anger': p=1 . 32e- ⁰² , W=35,005 . 50 ) and death-related words (Wilcoxon test: p=3 . 48e- ⁰⁵ , W=34,538 ) in describing their childbirth experience than those with no CB-PTSD.

Conclusions

This study provides proof of concept that personal childbirth narrative accounts generated in the early postpartum period and analyzed via advanced computational methods can detect with relatively high accuracy women who are likely to endorse CB-PTSD and those at low risk. This suggests that birth narratives could be promising for informing low-cost, non-invasive tools for maternal mental health screening, and more research that utilizes ML to predict early signs of maternal psychiatric morbidity is warranted.

Getting Started with LINCS Datasets and Tools

The Library of Integrated Network-based Cellular Signatures (LINCS) was an NIH Common Fund program that aimed to expand our knowledge about human cellular responses to chemical, genetic, and microenvironment perturbations. Responses to perturbations were measured by transcriptomics, proteomics, cellular imaging, and other high content assays. The second phase of the LINCS program, which lasted 7 years, involved the engagement of six data and signature generation centers (DSGCs) and one data coordination and integration center (DCIC). The DSGCs and the DCIC developed several digital resources, including tools, databases, and workflows that aim to facilitate the use of the LINCS data and integrate this data with other publicly available data. The digital resources developed by the DSGCs and the DCIC can be used to gain new biological and pharmacological insights that can lead to the development of novel therapeutics. This protocol provides step-by-step instructions for processing the LINCS data into signatures, and utilizing the digital resources developed by the LINCS consortia for hypothesis generation and knowledge discovery. © 2022 The Authors. Current Protocols published by Wiley Periodicals LLC. Basic Protocol 1: Navigating L1000 tools and data in CLUE.io Basic Protocol 2: Computing signatures from the L1000 data with the CD method Basic Protocol 3: Analyzing lists of differentially expressed genes and querying them against the L1000 data with BioJupies and the Bulk RNA-seq Appyter Basic Protocol 4: Utilizing the L1000FWD resource for drug discovery Basic Protocol 5: KINOMEscan and the KINOMEscan Appyter Basic Protocol 6: LINCS P100 and GCP Proteomics Assays Basic Protocol 7: The LINCS Joint Project (LJP) Basic Protocol 8: The LINCS Data Portals and SigCom LINCS Basic Protocol 9: Creating and analyzing signatures with iLINCS.

SigCom LINCS: data and metadata search engine for a million gene expression signatures

Millions of transcriptome samples were generated by the Library of Integrated Network-based Cellular Signatures (LINCS) program. When these data are processed into searchable signatures along with signatures extracted from Genotype-Tissue Expression (GTEx) and Gene Expression Omnibus (GEO), connections between drugs, genes, pathways and diseases can be illuminated. SigCom LINCS is a webserver that serves over a million gene expression signatures processed, analyzed, and visualized from LINCS, GTEx, and GEO. SigCom LINCS is built with Signature Commons, a cloud-agnostic skeleton Data Commons with a focus on serving searchable signatures. SigCom LINCS provides a rapid signature similarity search for mimickers and reversers given sets of up and down genes, a gene set, a single gene, or any search term. Additionally, users of SigCom LINCS can perform a metadata search to find and analyze subsets of signatures and find information about genes and drugs. SigCom LINCS is findable, accessible, interoperable, and reusable (FAIR) with metadata linked to standard ontologies and vocabularies. In addition, all the data and signatures within SigCom LINCS are available via a well-documented API. In summary, SigCom LINCS, available at https://maayanlab.cloud/sigcom-lincs, is a rich webserver resource for accelerating drug and target discovery in systems pharmacology.

DrugShot: querying biomedical search terms to retrieve prioritized lists of small molecules

Background

PubMed contains millions of abstracts that co-mention terms that describe drugs with other biomedical terms such as genes or diseases. Unique opportunities exist for leveraging these co-mentions by integrating them with other drug-drug similarity resources such as the Library of Integrated Network-based Cellular Signatures (LINCS) L1000 signatures to develop novel hypotheses.

Results

DrugShot is a web-based server application and an Appyter that enables users to enter any biomedical search term into a simple input form to receive ranked lists of drugs and other small molecules based on their relevance to the search term. To produce ranked lists of small molecules, DrugShot cross-references returned PubMed identifiers (PMIDs) with DrugRIF or AutoRIF, which are curated resources of drug-PMID associations, to produce an associated small molecule list where each small molecule is ranked according to total co-mentions with the search term from shared PubMed IDs. Additionally, using two types of drug-drug similarity matrices, lists of small molecules are predicted to be associated with the search term. Such predictions are based on literature co-mentions and signature similarity from LINCS L1000 drug-induced gene expression profiles.

Conclusions

DrugShot prioritizes drugs and small molecules associated with biomedical search terms. In addition to listing known associations, DrugShot predicts additional drugs and small molecules related to any search term. Hence, DrugShot can be used to prioritize drugs and preclinical compounds for drug repurposing and suggest indications and adverse events for preclinical compounds. DrugShot is freely and openly available at: https://maayanlab.cloud/drugshot and https://appyters.maayanlab.cloud/#/DrugShot.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-022-04590-5.

Gene Set Knowledge Discovery with Enrichr

Profiling samples from patients, tissues, and cells with genomics, transcriptomics, epigenomics, proteomics, and metabolomics ultimately produces lists of genes and proteins that need to be further analyzed and integrated in the context of known biology. Enrichr (Chen et al., 2013; Kuleshov et al., 2016) is a gene set search engine that enables the querying of hundreds of thousands of annotated gene sets. Enrichr uniquely integrates knowledge from many high-profile projects to provide synthesized information about mammalian genes and gene sets. The platform provides various methods to compute gene set enrichment, and the results are visualized in several interactive ways. This protocol provides a summary of the key features of Enrichr, which include using Enrichr programmatically and embedding an Enrichr button on any website. © 2021 Wiley Periodicals LLC. Basic Protocol 1: Analyzing lists of differentially expressed genes from transcriptomics, proteomics and phosphoproteomics, GWAS studies, or other experimental studies Basic Protocol 2: Searching Enrichr by a single gene or key search term Basic Protocol 3: Preparing raw or processed RNA-seq data through BioJupies in preparation for Enrichr analysis Basic Protocol 4: Analyzing gene sets for model organisms using modEnrichr Basic Protocol 5: Using Enrichr in Geneshot Basic Protocol 6: Using Enrichr in ARCHS4 Basic Protocol 7: Using the enrichment analysis visualization Appyter to visualize Enrichr results Basic Protocol 8: Using the Enrichr API Basic Protocol 9: Adding an Enrichr button to a website.

Drugmonizome and Drugmonizome-ML: integration and abstraction of small molecule attributes for drug enrichment analysis and machine learning

Understanding the underlying molecular and structural similarities between seemingly heterogeneous sets of drugs can aid in identifying drug repurposing opportunities and assist in the discovery of novel properties of preclinical small molecules. A wealth of information about drug and small molecule structure, targets, indications and side effects; induced gene expression signatures; and other attributes are publicly available through web-based tools, databases and repositories. By processing, abstracting and aggregating information from these resources into drug set libraries, knowledge about novel properties of drugs and small molecules can be systematically imputed with machine learning. In addition, drug set libraries can be used as the underlying database for drug set enrichment analysis. Here, we present Drugmonizome, a database with a search engine for querying annotated sets of drugs and small molecules for performing drug set enrichment analysis. Utilizing the data within Drugmonizome, we also developed Drugmonizome-ML. Drugmonizome-ML enables users to construct customized machine learning pipelines using the drug set libraries from Drugmonizome. To demonstrate the utility of Drugmonizome, drug sets from 12 independent SARS-CoV-2 in vitro screens were subjected to consensus enrichment analysis. Despite the low overlap among these 12 independent in vitro screens, we identified common biological processes critical for blocking viral replication. To demonstrate Drugmonizome-ML, we constructed a machine learning pipeline to predict whether approved and preclinical drugs may induce peripheral neuropathy as a potential side effect. Overall, the Drugmonizome and Drugmonizome-ML resources provide rich and diverse knowledge about drugs and small molecules for direct systems pharmacology applications. Database URL: https://maayanlab.cloud/drugmonizome/.

Appyters: Turning Jupyter Notebooks into data-driven web apps

Jupyter Notebooks have transformed the communication of data analysis pipelines by facilitating a modular structure that brings together code, markdown text, and interactive visualizations. Here, we extended Jupyter Notebooks to broaden their accessibility with Appyters. Appyters turn Jupyter Notebooks into fully functional standalone web-based bioinformatics applications. Appyters present to users an entry form enabling them to upload their data and set various parameters for a multitude of data analysis workflows. Once the form is filled, the Appyter executes the corresponding notebook in the cloud, producing the output without requiring the user to interact directly with the code. Appyters were used to create many bioinformatics web-based reusable workflows, including applications to build customized machine learning pipelines, analyze omics data, and produce publishable figures. These Appyters are served in the Appyters Catalog at https://appyters.maayanlab.cloud. In summary, Appyters enable the rapid development of interactive web-based bioinformatics applications.

Prioritizing Pain-Associated Targets with Machine Learning

While hundreds of genes have been associated with pain, much of the molecular mechanisms of pain remain unknown. As a result, current analgesics are limited to few clinically validated targets. Here, we trained a machine learning (ML) ensemble model to predict new targets for 17 categories of pain. The model utilizes features from transcriptomics, proteomics, and gene ontology to prioritize targets for modulating pain. We focused on identifying novel G-protein-coupled receptors (GPCRs), ion channels, and protein kinases because these proteins represent the most successful drug target families. The performance of the model to predict novel pain targets is 0.839 on average based on AUROC, while the predictions for arthritis had the highest accuracy (AUROC = 0.929). The model predicts hundreds of novel targets for pain; for example, GPR132 and GPR109B are highly ranked GPCRs for rheumatoid arthritis. Overall, gene-pain association predictions cluster into three groups that are enriched for cytokine, calcium, and GABA-related cell signaling pathways. These predictions can serve as a foundation for future experimental exploration to advance the development of safer and more effective analgesics.

EnrichrBot: Twitter bot tracking tweets about human genes

MOTIVATION

Micro-blogging with Twitter to communicate new results, discuss ideas and share techniques is becoming central. While most Twitter users are real people, the Twitter API provides the opportunity to develop Twitter bots and to analyze global trends in tweets.

RESULTS

EnrichrBot is a bot that tracks and tweets information about human genes implementing six principal functions: (i) tweeting information about under-studied genes including non-coding lncRNAs, (ii) replying to requests for information about genes, (iii) responding to GWASbot, another bot that tweets Manhattan plots from genome-wide association study analysis of the UK Biobank, (iv) tweeting randomly selected gene sets from the Enrichr database for analysis with Enrichr, (v) responding to mentions of human genes in tweets with additional information about these genes and (vi) tweeting a weekly report about the most trending genes on Twitter.

AVAILABILITY AND IMPLEMENTATION

https://twitter.com/botenrichr; source code: https://github.com/MaayanLab/EnrichrBot.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

The COVID-19 Drug and Gene Set Library

In a short period, many research publications that report sets of experimentally validated drugs as potential COVID-19 therapies have emerged. To organize this accumulating knowledge, we developed the COVID-19 Drug and Gene Set Library (https://amp.pharm.mssm.edu/covid19/), a collection of drug and gene sets related to COVID-19 research from multiple sources. The platform enables users to view, download, analyze, visualize, and contribute drug and gene sets related to COVID-19 research. To evaluate the content of the library, we compared the results from six in vitro drug screens for COVID-19 repurposing candidates. Surprisingly, we observe low overlap across screens while highlighting overlapping candidates that should receive more attention as potential therapeutics for COVID-19. Overall, the COVID-19 Drug and Gene Set Library can be used to identify community consensus, make researchers and clinicians aware of new potential therapies, enable machine-learning applications, and facilitate the research community to work together toward a cure.

The COVID-19 Gene and Drug Set Library

The coronavirus (CoV) severe acute respiratory syndrome (SARS)-CoV-2 (COVID-19) pandemic has received rapid response by the research community to offer suggestions for repurposing of approved drugs as well as to improve our understanding of the COVID-19 viral life cycle molecular mechanisms. In a short period, tens of thousands of research preprints and other publications have emerged including those that report lists of experimentally validated drugs and compounds as potential COVID-19 therapies. In addition, gene sets from interacting COVID-19 virus-host proteins and differentially expressed genes when comparing infected to uninfected cells are being published at a fast rate. To organize this rapidly accumulating knowledge, we developed the COVID-19 Gene and Drug Set Library (https://amp.pharm.mssm.edu/covid19/), a collection of gene and drug sets related to COVID-19 research from multiple sources. The COVID-19 Gene and Drug Set Library is delivered as a web-based interface that enables users to view, download, analyze, visualize, and contribute gene and drug sets related to COVID-19 research. To evaluate the content of the library, we performed several analyses including comparing the results from 6 in-vitro drug screens for COVID-19 repurposing candidates. Surprisingly, we observe little overlap across these initial screens. The most common and unique hit across these screen is mefloquine, a malaria drug that should receive more attention as a potential therapeutic for COVID-19. Overall, the library of gene and drug sets can be used to identify community consensus, make researchers and clinicians aware of the development of new potential therapies, as well as allow the research community to work together towards a cure for COVID-19.

Drug Gene Budger (DGB): an application for ranking drugs to modulate a specific gene based on transcriptomic signatures

SUMMARY

Mechanistic molecular studies in biomedical research often discover important genes that are aberrantly over- or under-expressed in disease. However, manipulating these genes in an attempt to improve the disease state is challenging. Herein, we reveal Drug Gene Budger (DGB), a web-based and mobile application developed to assist investigators in order to prioritize small molecules that are predicted to maximally influence the expression of their target gene of interest. With DGB, users can enter a gene symbol along with the wish to up-regulate or down-regulate its expression. The output of the application is a ranked list of small molecules that have been experimentally determined to produce the desired expression effect. The table includes log-transformed fold change, P-value and q-value for each small molecule, reporting the significance of differential expression as determined by the limma method. Relevant links are provided to further explore knowledge about the target gene, the small molecule and the source of evidence from which the relationship between the small molecule and the target gene was derived. The experimental data contained within DGB is compiled from signatures extracted from the LINCS L1000 dataset, the original Connectivity Map (CMap) dataset and the Gene Expression Omnibus (GEO). DGB also presents a specificity measure for a drug-gene connection based on the number of genes a drug modulates. DGB provides a useful preliminary technique for identifying small molecules that can target the expression of a single gene in human cells and tissues.

AVAILABILITY AND IMPLEMENTATION

The application is freely available on the web at http://DGB.cloud and as a mobile phone application on iTunes https://itunes.apple.com/us/app/drug-gene-budger/id1243580241? mt=8 and Google Play https://play.google.com/store/apps/details? id=com.drgenebudger.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Data Portal for the Library of Integrated Network-based Cellular Signatures (LINCS) program: integrated access to diverse large-scale cellular perturbation response data

The Library of Integrated Network-based Cellular Signatures (LINCS) program is a national consortium funded by the NIH to generate a diverse and extensive reference library of cell-based perturbation-response signatures, along with novel data analytics tools to improve our understanding of human diseases at the systems level. In contrast to other large-scale data generation efforts, LINCS Data and Signature Generation Centers (DSGCs) employ a wide range of assay technologies cataloging diverse cellular responses. Integration of, and unified access to LINCS data has therefore been particularly challenging. The Big Data to Knowledge (BD2K) LINCS Data Coordination and Integration Center (DCIC) has developed data standards specifications, data processing pipelines, and a suite of end-user software tools to integrate and annotate LINCS-generated data, to make LINCS signatures searchable and usable for different types of users. Here, we describe the LINCS Data Portal (LDP) (http://lincsportal.ccs.miami.edu/), a unified web interface to access datasets generated by the LINCS DSGCs, and its underlying database, LINCS Data Registry (LDR). LINCS data served on the LDP contains extensive metadata and curated annotations. We highlight the features of the LDP user interface that is designed to enable search, browsing, exploration, download and analysis of LINCS data and related curated content.

Connectivity Mapping: Methods and Applications

Connectivity mapping resources consist of signatures representing changes in cellular state following systematic small-molecule, disease, gene, or other form of perturbations. Such resources enable the characterization of signatures from novel perturbations based on similarity; provide a global view of the space of many themed perturbations; and allow the ability to predict cellular, tissue, and organismal phenotypes for perturbagens. A signature search engine enables hypothesis generation by finding connections between query signatures and the database of signatures. This framework has been used to identify connections between small molecules and their targets, to discover cell-specific responses to perturbations and ways to reverse disease expression states with small molecules, and to predict small-molecule mimickers for existing drugs. This review provides a historical perspective and the current state of connectivity mapping resources with a focus on both methodology and community implementations.

ChEA3: transcription factor enrichment analysis by orthogonal omics integration

Identifying the transcription factors (TFs) responsible for observed changes in gene expression is an important step in understanding gene regulatory networks. ChIP-X Enrichment Analysis 3 (ChEA3) is a transcription factor enrichment analysis tool that ranks TFs associated with user-submitted gene sets. The ChEA3 background database contains a collection of gene set libraries generated from multiple sources including TF-gene co-expression from RNA-seq studies, TF-target associations from ChIP-seq experiments, and TF-gene co-occurrence computed from crowd-submitted gene lists. Enrichment results from these distinct sources are integrated to generate a composite rank that improves the prediction of the correct upstream TF compared to ranks produced by individual libraries. We compare ChEA3 with existing TF prediction tools and show that ChEA3 performs better. By integrating the ChEA3 libraries, we illuminate general transcription factor properties such as whether the TF behaves as an activator or a repressor. The ChEA3 web-server is available from https://amp.pharm.mssm.edu/ChEA3.

Massive mining of publicly available RNA-seq data from human and mouse

RNA sequencing (RNA-seq) is the leading technology for genome-wide transcript quantification. However, publicly available RNA-seq data is currently provided mostly in raw form, a significant barrier for global and integrative retrospective analyses. ARCHS4 is a web resource that makes the majority of published RNA-seq data from human and mouse available at the gene and transcript levels. For developing ARCHS4, available FASTQ files from RNA-seq experiments from the Gene Expression Omnibus (GEO) were aligned using a cloud-based infrastructure. In total 187,946 samples are accessible through ARCHS4 with 103,083 mouse and 84,863 human. Additionally, the ARCHS4 web interface provides intuitive exploration of the processed data through querying tools, interactive visualization, and gene pages that provide average expression across cell lines and tissues, top co-expressed genes for each gene, and predicted biological functions and protein-protein interactions for each gene based on prior knowledge combined with co-expression.

Datasets2Tools, repository and search engine for bioinformatics datasets, tools and canned analyses

Biomedical data repositories such as the Gene Expression Omnibus (GEO) enable the search and discovery of relevant biomedical digital data objects. Similarly, resources such as OMICtools, index bioinformatics tools that can extract knowledge from these digital data objects. However, systematic access to pre-generated 'canned' analyses applied by bioinformatics tools to biomedical digital data objects is currently not available. Datasets2Tools is a repository indexing 31,473 canned bioinformatics analyses applied to 6,431 datasets. The Datasets2Tools repository also contains the indexing of 4,901 published bioinformatics software tools, and all the analyzed datasets. Datasets2Tools enables users to rapidly find datasets, tools, and canned analyses through an intuitive web interface, a Google Chrome extension, and an API. Furthermore, Datasets2Tools provides a platform for contributing canned analyses, datasets, and tools, as well as evaluating these digital objects according to their compliance with the findable, accessible, interoperable, and reusable (FAIR) principles. By incorporating community engagement, Datasets2Tools promotes sharing of digital resources to stimulate the extraction of knowledge from biomedical research data. Datasets2Tools is freely available from: http://amp.pharm.mssm.edu/datasets2tools.

The Library of Integrated Network-Based Cellular Signatures NIH Program: System-Level Cataloging of Human Cells Response to Perturbations

The Library of Integrated Network-Based Cellular Signatures (LINCS) is an NIH Common Fund program that catalogs how human cells globally respond to chemical, genetic, and disease perturbations. Resources generated by LINCS include experimental and computational methods, visualization tools, molecular and imaging data, and signatures. By assembling an integrated picture of the range of responses of human cells exposed to many perturbations, the LINCS program aims to better understand human disease and to advance the development of new therapies. Perturbations under study include drugs, genetic perturbations, tissue micro-environments, antibodies, and disease-causing mutations. Responses to perturbations are measured by transcript profiling, mass spectrometry, cell imaging, and biochemical methods, among other assays. The LINCS program focuses on cellular physiology shared among tissues and cell types relevant to an array of diseases, including cancer, heart disease, and neurodegenerative disorders. This Perspective describes LINCS technologies, datasets, tools, and approaches to data accessibility and reusability.

Developing a framework for digital objects in the Big Data to Knowledge (BD2K) commons: Report from the Commons Framework Pilots workshop

The volume and diversity of data in biomedical research have been rapidly increasing in recent years. While such data hold significant promise for accelerating discovery, their use entails many challenges including: the need for adequate computational infrastructure, secure processes for data sharing and access, tools that allow researchers to find and integrate diverse datasets, and standardized methods of analysis. These are just some elements of a complex ecosystem that needs to be built to support the rapid accumulation of these data. The NIH Big Data to Knowledge (BD2K) initiative aims to facilitate digitally enabled biomedical research. Within the BD2K framework, the Commons initiative is intended to establish a virtual environment that will facilitate the use, interoperability, and discoverability of shared digital objects used for research. The BD2K Commons Framework Pilots Working Group (CFPWG) was established to clarify goals and work on pilot projects that address existing gaps toward realizing the vision of the BD2K Commons. This report reviews highlights from a two-day meeting involving the BD2K CFPWG to provide insights on trends and considerations in advancing Big Data science for biomedical research in the United States.

Training an Actor-Critic Reinforcement Learning Controller for Arm Movement Using Human-Generated Rewards

Functional Electrical Stimulation (FES) employs neuroprostheses to apply electrical current to the nerves and muscles of individuals paralyzed by spinal cord injury to restore voluntary movement. Neuroprosthesis controllers calculate stimulation patterns to produce desired actions. To date, no existing controller is able to efficiently adapt its control strategy to the wide range of possible physiological arm characteristics, reaching movements, and user preferences that vary over time. Reinforcement learning (RL) is a control strategy that can incorporate human reward signals as inputs to allow human users to shape controller behavior. In this paper, ten neurologically intact human participants assigned subjective numerical rewards to train RL controllers, evaluating animations of goal-oriented reaching tasks performed using a planar musculoskeletal human arm simulation. The RL controller learning achieved using human trainers was compared with learning accomplished using human-like rewards generated by an algorithm; metrics included success at reaching the specified target; time required to reach the target; and target overshoot. Both sets of controllers learned efficiently and with minimal differences, significantly outperforming standard controllers. Reward positivity and consistency were found to be unrelated to learning success. These results suggest that human rewards can be used effectively to train RL-based FES controllers.

GEN3VA: aggregation and analysis of gene expression signatures from related studies

BACKGROUND

Genome-wide gene expression profiling of mammalian cells is becoming a staple of many published biomedical and biological research studies. Such data is deposited into data repositories such as the Gene Expression Omnibus (GEO) for potential reuse. However, these repositories currently do not provide simple interfaces to systematically analyze collections of related studies.

RESULTS

Here we present GENE Expression and Enrichment Vector Analyzer (GEN3VA), a web-based system that enables the integrative analysis of aggregated collections of tagged gene expression signatures identified and extracted from GEO. Each tagged collection of signatures is presented in a report that consists of heatmaps of the differentially expressed genes; principal component analysis of all signatures; enrichment analysis with several gene set libraries across all signatures, which we term enrichment vector analysis; and global mapping of small molecules that are predicted to reverse or mimic each signature in the aggregate. We demonstrate how GEN3VA can be used to identify common molecular mechanisms of aging by analyzing tagged signatures from 244 studies that compared young vs. old tissues in mammalian systems. In a second case study, we collected 86 signatures from treatment of human cells with dexamethasone, a glucocorticoid receptor (GR) agonist. Our analysis confirms consensus GR target genes and predicts potential drug mimickers.

CONCLUSIONS

GEN3VA can be used to identify, aggregate, and analyze themed collections of gene expression signatures from diverse but related studies. Such integrative analyses can be used to address concerns about data reproducibility, confirm results across labs, and discover new collective knowledge by data reuse. GEN3VA is an open-source web-based system that is freely available at: http://amp.pharm.mssm.edu/gen3va .

Extraction and analysis of signatures from the Gene Expression Omnibus by the crowd

Gene expression data are accumulating exponentially in public repositories. Reanalysis and integration of themed collections from these studies may provide new insights, but requires further human curation. Here we report a crowdsourcing project to annotate and reanalyse a large number of gene expression profiles from Gene Expression Omnibus (GEO). Through a massive open online course on Coursera, over 70 participants from over 25 countries identify and annotate 2,460 single-gene perturbation signatures, 839 disease versus normal signatures, and 906 drug perturbation signatures. All these signatures are unique and are manually validated for quality. Global analysis of these signatures confirms known associations and identifies novel associations between genes, diseases and drugs. The manually curated signatures are used as a training set to develop classifiers for extracting similar signatures from the entire GEO repository. We develop a web portal to serve these signatures for query, download and visualization.

Enrichr: a comprehensive gene set enrichment analysis web server 2016 update

Enrichment analysis is a popular method for analyzing gene sets generated by genome-wide experiments. Here we present a significant update to one of the tools in this domain called Enrichr. Enrichr currently contains a large collection of diverse gene set libraries available for analysis and download. In total, Enrichr currently contains 180 184 annotated gene sets from 102 gene set libraries. New features have been added to Enrichr including the ability to submit fuzzy sets, upload BED files, improved application programming interface and visualization of the results as clustergrams. Overall, Enrichr is a comprehensive resource for curated gene sets and a search engine that accumulates biological knowledge for further biological discoveries. Enrichr is freely available at: http://amp.pharm.mssm.edu/Enrichr.

Enrichr: a comprehensive gene set enrichment analysis web server 2016 update

Enrichment analysis is a popular method for analyzing gene sets generated by genome-wide experiments. Here we present a significant update to one of the tools in this domain called Enrichr. Enrichr currently contains a large collection of diverse gene set libraries available for analysis and download. In total, Enrichr currently contains 180 184 annotated gene sets from 102 gene set libraries. New features have been added to Enrichr including the ability to submit fuzzy sets, upload BED files, improved application programming interface and visualization of the results as clustergrams. Overall, Enrichr is a comprehensive resource for curated gene sets and a search engine that accumulates biological knowledge for further biological discoveries. Enrichr is freely available at: http://amp.pharm.mssm.edu/Enrichr.

Enrichr: a comprehensive gene set enrichment analysis web server 2016 update

Enrichment analysis is a popular method for analyzing gene sets generated by genome-wide experiments. Here we present a significant update to one of the tools in this domain called Enrichr. Enrichr currently contains a large collection of diverse gene set libraries available for analysis and download. In total, Enrichr currently contains 180 184 annotated gene sets from 102 gene set libraries. New features have been added to Enrichr including the ability to submit fuzzy sets, upload BED files, improved application programming interface and visualization of the results as clustergrams. Overall, Enrichr is a comprehensive resource for curated gene sets and a search engine that accumulates biological knowledge for further biological discoveries. Enrichr is freely available at: http://amp.pharm.mssm.edu/Enrichr.

An optimized proportional-derivative controller for the human upper extremity with gravity

When Functional Electrical Stimulation (FES) is used to restore movement in subjects with spinal cord injury (SCI), muscle stimulation patterns should be selected to generate accurate and efficient movements. Ideally, the controller for such a neuroprosthesis will have the simplest architecture possible, to facilitate translation into a clinical setting. In this study, we used the simulated annealing algorithm to optimize two proportional-derivative (PD) feedback controller gain sets for a 3-dimensional arm model that includes musculoskeletal dynamics and has 5 degrees of freedom and 22 muscles, performing goal-oriented reaching movements. Controller gains were optimized by minimizing a weighted sum of position errors, orientation errors, and muscle activations. After optimization, gain performance was evaluated on the basis of accuracy and efficiency of reaching movements, along with three other benchmark gain sets not optimized for our system, on a large set of dynamic reaching movements for which the controllers had not been optimized, to test ability to generalize. Robustness in the presence of weakened muscles was also tested. The two optimized gain sets were found to have very similar performance to each other on all metrics, and to exhibit significantly better accuracy, compared with the three standard gain sets. All gain sets investigated used physiologically acceptable amounts of muscular activation. It was concluded that optimization can yield significant improvements in controller performance while still maintaining muscular efficiency, and that optimization should be considered as a strategy for future neuroprosthesis controller design.