Discovering NDM-1 inhibitors using molecular substructure embeddings representations

NDM-1 (New-Delhi-Metallo-β-lactamase-1) is an enzyme developed by bacteria that is implicated in bacteria resistance to almost all known antibiotics. In this study, we deliver a new, curated NDM-1 bioactivities database, along with a set of unifying rules for managing different activity properties and inconsistencies. We define the activity classification problem in terms of Multiple Instance Learning, employing embeddings corresponding to molecular substructures and present an ensemble ranking and classification framework, relaying on a k-fold Cross Validation method employing a per fold hyper-parameter optimization procedure, showing promising generalization ability. The MIL paradigm displayed an improvement up to 45.7 %, in terms of Balanced Accuracy, in comparison to the classical Machine Learning paradigm. Moreover, we investigate different compact molecular representations, based on atomic or bi-atomic substructures. Finally, we scanned the Drugbank for strongly active compounds and we present the top-15 ranked compounds.

Learning to Classify Medical Discharge Summaries According to ICD-9

CONTEXT

We present a post-hoc approach to improve the recall of ICD classification.

METHOD

The proposed method can use any classifier as a backbone and aims to calibrate the number of codes returned per document. We test our approach on a new stratified split of the MIMIC-III dataset.

RESULTS

When returning 18 codes on average per document we obtain a recall that is 20% better than a classic classification approach.

Patient Electronic Health Record as Temporal Graphs for Health Monitoring

Machine learning methods are becoming increasingly popular to anticipate critical risks in patients under surveillance reducing the burden on caregivers. In this paper, we propose an original modeling that benefits of recent developments in Graph Convolutional Networks: a patient's journey is seen as a graph, where each node is an event and temporal proximities are represented by weighted directed edges. We evaluated this model to predict death at 24 hours on a real dataset and successfully compared our results with the state of the art.

Acceptability and satisfaction with emma, a smartphone application dedicated to suicide ecological assessment and prevention

BACKGROUND

As mHealth may contribute to suicide prevention, we developed emma, an application using Ecological Momentary Assessment and Intervention (EMA/EMI).

OBJECTIVE

This study evaluated emma usage rate and acceptability during the first month and satisfaction after 1 and 6 months of use.

METHODS

Ninety-nine patients at high risk of suicide used emma for 6 months. The acceptability and usage rate of the EMA and EMI modules were monitored during the first month. Satisfaction was assessed by questions in the monthly EMA (Likert scale from 0 to 10) and the Mobile App Rating Scale (MARS; score: 0-5) completed at month 6. After inclusion, three follow-up visits (months 1, 3, and 6) took place.

RESULTS

Seventy-five patients completed at least one of the proposed EMAs. Completion rates were lower for the daily than weekly EMAs (60 and 82%, respectively). The daily completion rates varied according to the question position in the questionnaire (lower for the last questions, LRT = 604.26, df = 1, p-value < 0.0001). Completion rates for the daily EMA were higher in patients with suicidal ideation and/or depression than in those without. The most used EMI was the emergency call module (n = 12). Many users said that they would recommend this application (mean satisfaction score of 6.92 ± 2.78) and the MARS score at month 6 was relatively high (overall rating: 3.3 ± 0.87).

CONCLUSION

Emma can target and involve patients at high risk of suicide. Given the promising users' satisfaction level, emma could rapidly evolve into a complementary tool for suicide prevention.

A Digital Companion, the Emma App, for Ecological Momentary Assessment and Prevention of Suicide: Quantitative Case Series Study

BACKGROUND

Many suicide risk factors have been identified, but traditional clinical methods do not allow for the accurate prediction of suicide behaviors. To face this challenge, emma, an app for ecological momentary assessment (EMA), ecological momentary intervention (EMI), and prediction of suicide risk in high-risk patients, was developed.

OBJECTIVE

The aim of this case report study was to describe how subjects at high risk of suicide use the emma app in real-world conditions.

METHODS

The Ecological Mental Momentary Assessment (EMMA) study is an ongoing, longitudinal, interventional, multicenter trial in which patients at high risk for suicide are recruited to test emma, an app designed to be used as a self-help tool for suicidal crisis management. Participants undergo clinical assessment at months 0, 1, 3, and 6 after inclusion, mainly to assess and characterize the presence of mental disorders and suicidal thoughts and behaviors. Patient recruitment is still ongoing. Some data from the first 14 participants who already completed the 6-month follow-up were selected for this case report study, which evaluated the following: (1) data collected by emma (ie, responses to EMAs), (2) metadata on emma use, (3) clinical data, and (4) qualitative assessment of the participants' experiences.

RESULTS

EMA completion rates were extremely heterogeneous with a sharp decrease over time. The completion rates of the weekly EMAs (25%-87%) were higher than those of the daily EMAs (0%-53%). Most patients (10/14, 71%) answered the EMA questionnaires spontaneously. Similarly, the use of the Safety Plan Modules was very heterogeneous (2-75 times). Specifically, 11 patients out of 14 (79%) used the Call Module (1-29 times), which was designed by our team to help them get in touch with health care professionals and/or relatives during a crisis. The diversity of patient profiles and use of the EMA and EMI modules proposed by emma were highlighted by three case reports.

CONCLUSIONS

These preliminary results indicate that patients have different clinical and digital profiles and needs that require a highly scalable, interactive, and customizable app. They also suggest that it is possible and acceptable to collect longitudinal, fine-grained, contextualized data (ie, EMA) and to offer personalized intervention (ie, EMI) in real time to people at high risk of suicide. To become a complementary tool for suicide prevention, emma should be integrated into existing emergency procedures.

TRIAL REGISTRATION

ClinicalTrials.gov NCT03410381; https://clinicaltrials.gov/ct2/show/NCT03410381.

Distress, Suicidality, and Affective Disorders at the Time of Social Networks

PURPOSE OF REVIEW

We reviewed how scholars recently addressed the complex relationship that binds distress, affective disorders, and suicidal behaviors on the one hand and social networking on the other. We considered the latest machine learning performances in detecting affective-related outcomes from social media data, and reviewed understandings of how, why, and with what consequences distressed individuals use social network sites. Finally, we examined how these insights may concretely instantiate on the individual level with a qualitative case series.

RECENT FINDINGS

Machine learning classifiers are progressively stabilizing with moderate to high performances in detecting affective-related diagnosis, symptoms, and risks from social media linguistic markers. Qualitatively, such markers appear to translate ambivalent and socially constrained motivations such as self-disclosure, passive support seeking, and connectedness reinforcement. Binding data science and psychosocial research appears as the unique condition to ground a translational web-clinic for treating and preventing affective-related issues on social media.

Expertise in French health forums

More and more health websites hire medical experts (physicians, medical students, experienced volunteers, etc.) and indicate explicitly their medical role in order to notify that they provide high-quality answers. However, medical experts may participate in forum discussions even when their role is not officially indicated. Detecting posts written by medical experts facilitates the quick access to posts that have more chances of being correct and informative. The main objective of this work is to learn classification models that can be used to detect posts written by medical experts in any health forum discussions. Two French health forums have been used to discover the best features and methods for this text categorization task. The obtained results confirm that models learned on appropriate websites may be used efficiently on other websites (more than 98% of F1-measure has been obtained using a Random Forest classifier). A study of misclassified posts highlights the participation of medical experts in forum discussions even if their role is not explicitly indicated.

Mining social networks to improve suicide prevention: A scoping review

Attention about the risks of online social networks (SNs) has been called upon reports describing their use to express emotional distress and suicidal ideation or plans. On the Internet, cyberbullying, suicide pacts, Internet addiction, and "extreme" communities seem to increase suicidal behavior (SB). In this study, the scientific literature about SBs and SNs was narratively reviewed. Some authors focus on detecting at-risk populations through data mining, identification of risks factors, and web activity patterns. Others describe prevention practices on the Internet, such as websites, screening, and applications. Targeted interventions through SNs are also contemplated when suicidal ideation is present. Multiple predictive models should be defined, implemented, tested, and combined in order to deal with the risk of SB through an effective decision support system. This endeavor might require a reorganization of care for SNs users presenting suicidal ideation.

PaFloChar: An Innovating Approach to Characterise Patient Flows in Myocardial Infarction

A better knowledge of patient flows would improve decision making in health planning. In this article, we propose a method to characterise patients flows and also to highlight profiles of care pathways considering times and costs. From medico-administrative data, we extracted spatio-temporal patterns. Then, we clustered time between hospitalisations and cost trajectories in order to identify profiles of change over time. This approach may support renewed management strategies.

Patient healthcare trajectory. An essential monitoring tool: a systematic review

BACKGROUND

Patient healthcare trajectory is a recent emergent topic in the literature, encompassing broad concepts. However, the rationale for studying patients' trajectories, and how this trajectory concept is defined remains a public health challenge. Our research was focused on patients' trajectories based on disease management and care, while also considering medico-economic aspects of the associated management. We illustrated this concept with an example: a myocardial infarction (MI) occurring in a patient's hospital trajectory of care. The patient follow-up was traced via the prospective payment system. We applied a semi-automatic text mining process to conduct a comprehensive review of patient healthcare trajectory studies. This review investigated how the concept of trajectory is defined, studied and what it achieves.

METHODS

We performed a PubMed search to identify reports that had been published in peer-reviewed journals between January 1, 2000 and October 31, 2015. Fourteen search questions were formulated to guide our review. A semi-automatic text mining process based on a semantic approach was performed to conduct a comprehensive review of patient healthcare trajectory studies. Text mining techniques were used to explore the corpus in a semantic perspective in order to answer non-a priori questions. Complementary review methods on a selected subset were used to answer a priori questions.

RESULTS

Among the 33,514 publications initially selected for analysis, only 70 relevant articles were semi-automatically extracted and thoroughly analysed. Oncology is particularly prevalent due to its already well-established processes of care. For the trajectory thema, 80% of articles were distributed in 11 clusters. These clusters contain distinct semantic information, for example health outcomes (29%), care process (26%) and administrative and financial aspects (16%).

CONCLUSION

This literature review highlights the recent interest in the trajectory concept. The approach is also gradually being used to monitor trajectories of care for chronic diseases such as diabetes, organ failure or coronary artery and MI trajectory of care, to improve care and reduce costs. Patient trajectory is undoubtedly an essential approach to be further explored in order to improve healthcare monitoring.

Raising Awareness About Cervical Cancer Using Twitter: Content Analysis of the 2015 #SmearForSmear Campaign

Background

Cervical cancer is the second most common cancer among women under 45 years of age. To deal with the decrease of smear test coverage in the United Kingdom, a Twitter campaign called #SmearForSmear has been launched in 2015 for the European Cervical Cancer Prevention Week. Its aim was to encourage women to take a selfie showing their lipstick going over the edge and post it on Twitter with a raising awareness message promoting cervical cancer screening. The estimated audience was 500 million people. Other public health campaigns have been launched on social media such as Movember to encourage participation and self-engagement. Their result was unsatisfactory as their aim had been diluted to become mainly a social buzz.

Objective

The objectives of this study were to identify the tweets delivering a raising awareness message promoting cervical cancer screening (sensitizing tweets) and to understand the characteristics of Twitter users posting about this campaign.

Methods

We conducted a 3-step content analysis of the English tweets tagged #SmearForSmear posted on Twitter for the 2015 European Cervical Cancer Prevention Week. Data were collected using the Twitter application programming interface. Their extraction was based on an analysis grid generated by 2 independent researchers using a thematic analysis, validated by a strong Cohen kappa coefficient. A total of 7 themes were coded for sensitizing tweets and 14 for Twitter users’ status. Verbatims were thematically and then statistically analyzed.

Results

A total of 3019 tweets were collected and 1881 were analyzed. Moreover, 69.96% of tweets had been posted by people living in the United Kingdom. A total of 57.36% of users were women, and sex was unknown in 35.99% of cases. In addition, 54.44% of the users had posted at least one selfie with smeared lipstick. Furthermore, 32.32% of tweets were sensitizing. Independent factors associated with posting sensitizing tweets were women who experienced an abnormal smear test (OR [odds ratio] 13.456, 95% CI 3.101-58.378, P<.001), female gender (OR 3.752, 95% CI 2.133-6.598, P<.001), and people who live in the United Kingdom (OR 2.097, 95% CI 1.447-3.038, P<.001). Nonsensitizing tweets were statistically more posted by a nonhealth or nonmedia company (OR 0.558, 95% CI 0.383-0.814, P<.001).

Conclusions

This study demonstrates that the success of a public health campaign using a social media platform depends on its ability to get its targets involved. It also suggests the need to use social marketing to help its dissemination. The clinical impact of this Twitter campaign to increase cervical cancer screening is yet to be evaluated.

Genomics and Machine Learning for Taxonomy Consensus: The Mycobacterium tuberculosis Complex Paradigm

Infra-species taxonomy is a prerequisite to compare features such as virulence in different pathogen lineages. Mycobacterium tuberculosis complex taxonomy has rapidly evolved in the last 20 years through intensive clinical isolation, advances in sequencing and in the description of fast-evolving loci (CRISPR and MIRU-VNTR). On-line tools to describe new isolates have been set up based on known diversity either on CRISPRs (also known as spoligotypes) or on MIRU-VNTR profiles. The underlying taxonomies are largely concordant but use different names and offer different depths. The objectives of this study were 1) to explicit the consensus that exists between the alternative taxonomies, and 2) to provide an on-line tool to ease classification of new isolates. Genotyping (24-VNTR, 43-spacers spoligotypes, IS6110-RFLP) was undertaken for 3,454 clinical isolates from the Netherlands (2004-2008). The resulting database was enlarged with African isolates to include most human tuberculosis diversity. Assignations were obtained using TB-Lineage, MIRU-VNTRPlus, SITVITWEB and an algorithm from Borile et al. By identifying the recurrent concordances between the alternative taxonomies, we proposed a consensus including 22 sublineages. Original and consensus assignations of the all isolates from the database were subsequently implemented into an ensemble learning approach based on Machine Learning tool Weka to derive a classification scheme. All assignations were reproduced with very good sensibilities and specificities. When applied to independent datasets, it was able to suggest new sublineages such as pseudo-Beijing. This Lineage Prediction tool, efficient on 15-MIRU, 24-VNTR and spoligotype data is available on the web interface “TBminer.” Another section of this website helps summarizing key molecular epidemiological data, easing tuberculosis surveillance. Altogether, we successfully used Machine Learning on a large dataset to set up and make available the first consensual taxonomy for human Mycobacterium tuberculosis complex. Additional developments using SNPs will help stabilizing it.

Unraveling the molecular architecture of a G protein-coupled receptor/β-arrestin/Erk module complex

β-arrestins serve as signaling scaffolds downstream of G protein-coupled receptors, and thus play a crucial role in a plethora of cellular processes. Although it is largely accepted that the ability of β-arrestins to interact simultaneously with many protein partners is key in G protein-independent signaling of GPCRs, only the precise knowledge of these multimeric arrangements will allow a full understanding of the dynamics of these interactions and their functional consequences. However, current experimental procedures for the determination of the three-dimensional structures of protein-protein complexes are not well adapted to analyze these short-lived, multi-component assemblies. We propose a model of the receptor/β-arrestin/Erk1 signaling module, which is consistent with most of the available experimental data. Moreover, for the β-arrestin/Raf1 and the β-arrestin/ERK interactions, we have used the model to design interfering peptides and shown that they compete with both partners, hereby demonstrating the validity of the predicted interaction regions.

Assisting e-patients in an Ask the Doctor Service

Ask the doctor services are personalized forums allowing patients to ask questions directly to doctors. Usually, patients must choose the most appropriate category for their question among lots of categories to be redirected to the most relevant physician. However, manual selection is tedious and error prone activity. In this work we propose to assist the patients in this task by recommending a short list of most appropriate categories.

E-Patient Reputation in Health Forums

Online health forums are increasingly used by patients to get information and help related to their health. However, information reliability in these forums is unfortunately not always guaranteed. Obviously, consequences of self-diagnosis may be severe on the patient's health if measures are taken without consulting a doctor. Many works on trust issues related to social media have been proposed, but most of them mainly focus only on the structure part of the social network (number of posts, number of likes, etc.). In the case of online health forums, a lot of trust and distrust is expressed inside the posted messages and cannot be inferred by only considering the structure. In this study, we rather suggest inferring the user's trustworthiness from the replies he receives in the forum. The proposed method is divided into three main steps: First, the recipient(s) of each post must be identified. Next, the trust or distrust expressed in these posts is evaluated. Finally, the user's reputation is computed by aggregating all the posts he received. Conducted experiments using a manually annotated corpus are encouraging.

Protein-RNA complexes and efficient automatic docking: expanding RosettaDock possibilities

Protein-RNA complexes provide a wide range of essential functions in the cell. Their atomic experimental structure solving, despite essential to the understanding of these functions, is often difficult and expensive. Docking approaches that have been developed for proteins are often challenging to adapt for RNA because of its inherent flexibility and the structural data available being relatively scarce. In this study we adapted the RosettaDock protocol for protein-RNA complexes both at the nucleotide and atomic levels. Using a genetic algorithm-based strategy, and a non-redundant protein-RNA dataset, we derived a RosettaDock scoring scheme able not only to discriminate but also score efficiently docking decoys. The approach proved to be both efficient and robust for generating and identifying suitable structures when applied to two protein-RNA docking benchmarks in both bound and unbound settings. It also compares well to existing strategies. This is the first approach that currently offers a multi-level optimized scoring approach integrated in a full docking suite, leading the way to adaptive fully flexible strategies.

Community-wide assessment of protein-interface modeling suggests improvements to design methodology

The CAPRI (Critical Assessment of Predicted Interactions) and CASP (Critical Assessment of protein Structure Prediction) experiments have demonstrated the power of community-wide tests of methodology in assessing the current state of the art and spurring progress in the very challenging areas of protein docking and structure prediction. We sought to bring the power of community-wide experiments to bear on a very challenging protein design problem that provides a complementary but equally fundamental test of current understanding of protein-binding thermodynamics. We have generated a number of designed protein-protein interfaces with very favorable computed binding energies but which do not appear to be formed in experiments, suggesting that there may be important physical chemistry missing in the energy calculations. A total of 28 research groups took up the challenge of determining what is missing: we provided structures of 87 designed complexes and 120 naturally occurring complexes and asked participants to identify energetic contributions and/or structural features that distinguish between the two sets. The community found that electrostatics and solvation terms partially distinguish the designs from the natural complexes, largely due to the nonpolar character of the designed interactions. Beyond this polarity difference, the community found that the designed binding surfaces were, on average, structurally less embedded in the designed monomers, suggesting that backbone conformational rigidity at the designed surface is important for realization of the designed function. These results can be used to improve computational design strategies, but there is still much to be learned; for example, one designed complex, which does form in experiments, was classified by all metrics as a nonbinder.

Towards a semi-automatic functional annotation tool based on decision-tree techniques

Background

Due to the continuous improvements of high throughput technologies and experimental procedures, the number of sequenced genomes is increasing exponentially. Ultimately, the task of annotating these data relies on the expertise of biologists. The necessity for annotation to be supervised by human experts is the rate limiting step of the data analysis. To face the deluge of new genomic data, the need for automating, as much as possible, the annotation process becomes critical.

Results

We consider annotation of a protein with terms of the functional hierarchy that has been used to annotate Bacillus subtilis and propose a set of rules that predict classes in terms of elements of the functional hierarchy, i.e., a class is a node or a leaf of the hierarchy tree. The rules are obtained through two decision-trees techniques: first-order decision-trees and multilabel attribute-value decision-trees, by using as training data the proteins from two lactic bacteria: Lactobacillus sakei and Lactobacillus bulgaricus. We tested the two methods, first independently, then in a combined approach, and evaluated the obtained results using hierarchical evaluation measures. Results obtained for the two approaches on both genomes are comparable and show a good precision together with a high prediction rate. Using combined approaches increases the recall and the prediction rate.

Conclusion

The combination of the two approaches is very encouraging and we will further refine these combinations in order to get rules even more useful for the annotators. This first study is a crucial step towards designing a semi-automatic functional annotation tool.

A new protein-protein docking scoring function based on interface residue properties

MOTIVATION

Protein-protein complexes are known to play key roles in many cellular processes. However, they are often not accessible to experimental study because of their low stability and difficulty to produce the proteins and assemble them in native conformation. Thus, docking algorithms have been developed to provide an in silico approach of the problem. A protein-protein docking procedure traditionally consists of two successive tasks: a search algorithm generates a large number of candidate solutions, and then a scoring function is used to rank them.

RESULTS

To address the second step, we developed a scoring function based on a Voronoï tessellation of the protein three-dimensional structure. We showed that the Voronoï representation may be used to describe in a simplified but useful manner, the geometric and physico-chemical complementarities of two molecular surfaces. We measured a set of parameters on native protein-protein complexes and on decoys, and used them as attributes in several statistical learning procedures: a logistic function, Support Vector Machines (SVM), and a genetic algorithm. For the later, we used ROGER, a genetic algorithm designed to optimize the area under the receiver operating characteristics curve. To further test the scores derived with ROGER, we ranked models generated by two different docking algorithms on targets of a blind prediction experiment, improving in almost all cases the rank of native-like solutions.

AVAILABILITY

http://genomics.eu.org/spip/-Bioinformatics-tools-

A docking analysis of the statistical physics of protein–protein recognition

We describe protein-protein recognition within the frame of the random energy model of statistical physics. We simulate, by docking the component proteins, the process of association of two proteins that form a complex. We obtain the energy spectrum of a set of protein-protein complexes of known three-dimensional structure by performing docking in random orientations and scoring the models thus generated. We use a coarse protein representation where each amino acid residue is replaced by its Voronoï cell, and derive a scoring function by applying the evolutionary learning program ROGER to a set of parameters measured on that representation. Taking the scores of the docking models to be interaction energies, we obtain energy spectra for the complexes and fit them to a Gaussian distribution, from which we derive physical parameters such as a glass transition temperature and a specificity transition temperature.