Prediction of Protein Ion-Ligand Binding Sites with ELECTRA.

Interactions between proteins and ions are essential for various biological functions like structural stability, metabolism, and signal transport. Given that more than half of all proteins bind to ions, it is becoming crucial to identify ion-binding sites. The accurate identification of protein-ion binding sites helps us to understand proteins' biological functions and plays a significant role in drug discovery. While several computational approaches have been proposed, this remains a challenging problem due to the small size and high versatility of metals and acid radicals. In this study, we propose IonPred, a sequence-based approach that employs ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately) to predict ion-binding sites using only raw protein sequences. We successfully fine-tuned our pretrained model to predict the binding sites for nine metal ions (Zn2+, Cu2+, Fe2+, Fe3+, Ca2+, Mg2+, Mn2+, Na+, and K+) and four acid radical ion ligands (CO32-, SO42-, PO43-, NO2-). IonPred surpassed six current state-of-the-art tools by over 44.65% and 28.46%, respectively, in the F1 score and MCC when compared on an independent test dataset. Our method is more computationally efficient than existing tools, producing prediction results for a hundred sequences for a specific ion in under ten minutes.

Risk stratification of patients undergoing transvenous lead extraction with the ELECTRa Registry Outcome Score (EROS): an ESC EHRA EORP European lead extraction ConTRolled ELECTRa registry analysis.

AIMS: Transvenous lead extraction is associated with a significant risk of complications and identifying patients at highest risk pre-procedurally will enable interventions to be planned accordingly. We developed the ELECTRa Registry Outcome Score (EROS) and applied it to the ELECTRa registry to determine if it could appropriately risk-stratify patients. METHODS AND RESULTS: EROS was devised to risk-stratify patients into low risk (EROS 1), intermediate risk (EROS 2), and high risk (EROS 3). This was applied to the ESC EORP European Lead Extraction ConTRolled ELECTRa registry; 57.5% EROS 1, 31.8% EROS 2, and 10.7% EROS 3. Patients with EROS 3 or 2 were significantly more likely to require powered sheaths and a femoral approach to complete procedures. Patients with EROS 3 were more likely to suffer procedure-related major complications including deaths (5.1 vs. 1.3%; P < 0.0001), both intra-procedural (3.5 vs. 0.8%; P = 0.0001) and post-procedural (1.6 vs. 0.5%; P = 0.0192). They were more likely to suffer post-procedural deaths (0.8 vs. 0.2%; P 0.0449), cardiac avulsion or tear (3.8 vs. 0.5%; P < 0.0001), and cardiovascular lesions requiring pericardiocentesis, chest tube, or surgical repair (4.6 vs. 1.0%; P < 0.0001). EROS 3 was associated with procedure-related major complications including deaths [odds ratio (OR) 3.333, 95% confidence interval (CI) 1.879-5.914; P < 0.0001] and all-cause in-hospital major complications including deaths (OR 2.339, 95% CI 1.439-3.803; P = 0.0006). CONCLUSION: EROS successfully identified patients who were at increased risk of significant procedural complications that require urgent surgical intervention.

The effect of centre volume and procedure location on major complications and mortality from transvenous lead extraction: an ESC EHRA EORP European Lead Extraction ConTRolled ELECTRa registry subanalysis.

AIMS: Transvenous lead extraction (TLE) should ideally be undertaken by experienced operators in a setting that allows urgent surgical intervention. In this analysis of the ELECTRa registry, we sought to determine whether there was a significant difference in procedure complications and mortality depending on centre volume and extraction location. METHODS AND RESULTS: Analysis of the ESC EORP European Lead Extraction ConTRolled ELECTRa registry was conducted. Low-volume (LoV) centres were defined as <30 procedures/year, and high-volume (HiV) centres as ≥30 procedures/year. Three thousand, two hundred, and forty-nine patients underwent TLE by a primary operator cardiologist; 17.1% in LoV centres and 82.9% in HiV centres. Procedures performed by primary operator cardiologists in LoV centres were less likely to be successful (93.5% vs. 97.1%; P < 0.0001) and more likely to be complicated by procedure-related deaths (1.1% vs. 0.4%; P = 0.0417). Transvenous lead extraction undertaken by primary operator cardiologists in LoV centres were associated with increased procedure-related major complications including death (odds ratio 1.858, 95% confidence interval 1.007-3.427; P = 0.0475). Transvenous lead extraction locations varied; 52.0% operating room, 9.5% hybrid theatre and 38.5% catheterization laboratory. Rates of procedure-related major complications, including death occurring in a high-risk environment (combining operating room and hybrid theatre), were similar to those undertaken in the catheterization laboratory (1.7% vs. 1.6%; P = 0.9297). CONCLUSION: Primary operator cardiologists in LoV centres are more likely to have extractions complicated by procedure-related deaths. There was no significant difference in procedure complications between different extraction settings. These findings support the need for TLE to be performed in experienced centres with appropriate personnel present.

Clinical impact of antithrombotic therapy in transvenous lead extraction complications: a sub-analysis from the ESC-EORP EHRA ELECTRa (European Lead Extraction ConTRolled) Registry.

AIMS: A sub-analysis of the ESC-EHRA European Lead Extraction ConTRolled (ELECTRa) Registry to evaluate the clinical impact of antithrombotic (AT) on transvenous lead extraction (TLE) safety and efficacy. METHODS AND RESULTS: ELECTRa outcomes were compared between patients without AT therapy (No AT Group) and with different pre-operative AT regimens, including antiplatelets (AP), anticoagulants (AC), or both (AP + AC). Out of 3510 pts, 2398 (68%) were under AT pre-operatively. AT patients were older with more comorbidities (P < 0.0001). AT subgroups, defined as AP, AC, or AP + AC, were 1096 (31.2%), 985 (28%), and 317 (9%), respectively. Regarding AP patients, 1413 (40%) were under AP, 1292 (91%) with a single AP, interrupted in 26% about 3.8 ± 3.7 days before TLE. In total, 1302 (37%) patients were under AC, 881 vitamin K antagonist (68%), 221 (17%) direct oral anticoagulants, 155 (12%) low weight molecular heparin, and 45 (3.5%) unfractionated heparin. AC was 'interrupted without bridging' in 696 (54%) and 'interrupted with bridging' in 504 (39%) about 3.3 ± 2.3 days before TLE, and 'continued' in 87 (7%). TLE success rate was high in all subgroups. Only overall in-hospital death (1.4%), but not the procedure-related one, was higher in the AT subgroups (P = 0.0500). Age >65 years and New York Heart Association Class III/IV, but not AT regimens, were independent predictors of death for any cause. Haematomas were more frequent in AT subgroups, especially in AC 'continued' (P = 0.025), whereas pulmonary embolism in the No-AT (P < 0.01). CONCLUSIONS: AT minimization is safe in patients undergoing TLE. AT does not seem to predict death but identifies a subset of fragile patients with a worse in-hospital TLE outcome.

Detection of Adverse Event Signals with Severity Grade Classification from Cancer Patient Narrative.

Adverse event (AE) management is crucial to improve anti-cancer treatment outcomes, but it is reported that some AE signals can be missed in clinical visits. Thus, monitoring AE signals seamlessly, including events outside hospitals, would be helpful for early intervention. Here we investigated how to detect AE signals from texts written by cancer patients themselves by developing deep-learning (DL) models to classify posts mentioning AEs according to severity grade, in order to focus on those that might need immediate treatment interventions. Using patient blogs written in Japanese by cancer patients as a data source, we built DL models based on three approaches, BERT, ELECTRA, and T5. Among these models, T5 showed the best F1 scores for both Grade ≥ 1 and ≥ 2 article classification tasks (0.85 and 0.53, respectively). This model might benefit patients by enabling earlier AE signal detection, thereby improving quality of life.

Twitter-based gender recognition using transformers.

Social media contains useful information about people and society that could help advance research in many different areas of health (e.g. by applying opinion mining, emotion/sentiment analysis and statistical analysis) such as mental health, health surveillance, socio-economic inequality and gender vulnerability. User demographics provide rich information that could help study the subject further. However, user demographics such as gender are considered private and are not freely available. In this study, we propose a model based on transformers to predict the user's gender from their images and tweets. The image-based classification model is trained in two different methods: using the profile image of the user and using various image contents posted by the user on Twitter. For the first method a Twitter gender recognition dataset, publicly available on Kaggle and for the second method the PAN-18 dataset is used. Several transformer models, i.e. vision transformers (ViT), LeViT and Swin Transformer are fine-tuned for both of the image datasets and then compared. Next, different transformer models, namely, bidirectional encoders representations from transformers (BERT), RoBERTa and ELECTRA are fine-tuned to recognize the user's gender by their tweets. This is highly beneficial, because not all users provide an image that indicates their gender. The gender of such users could be detected from their tweets. The significance of the image and text classification models were evaluated using the Mann-Whitney U test. Finally, the combination model improved the accuracy of image and text classification models by 11.73 and 5.26% for the Kaggle dataset and by 8.55 and 9.8% for the PAN-18 dataset, respectively. This shows that the image and text classification models are capable of complementing each other by providing additional information to one another. Our overall multimodal method has an accuracy of 88.11% for the Kaggle and 89.24% for the PAN-18 dataset and outperforms state-of-the-art models. Our work benefits research that critically require user demographic information such as gender to further analyze and study social media content for health-related issues.

ELECTRA-DTA: a new compound-protein binding affinity prediction model based on the contextualized sequence encoding.

MOTIVATION: Drug-target binding affinity (DTA) reflects the strength of the drug-target interaction; therefore, predicting the DTA can considerably benefit drug discovery by narrowing the search space and pruning drug-target (DT) pairs with low binding affinity scores. Representation learning using deep neural networks has achieved promising performance compared with traditional machine learning methods; hence, extensive research efforts have been made in learning the feature representation of proteins and compounds. However, such feature representation learning relies on a large-scale labelled dataset, which is not always available. RESULTS: We present an end-to-end deep learning framework, ELECTRA-DTA, to predict the binding affinity of drug-target pairs. This framework incorporates an unsupervised learning mechanism to train two ELECTRA-based contextual embedding models, one for protein amino acids and the other for compound SMILES string encoding. In addition, ELECTRA-DTA leverages a squeeze-and-excitation (SE) convolutional neural network block stacked over three fully connected layers to further capture the sequential and spatial features of the protein sequence and SMILES for the DTA regression task. Experimental evaluations show that ELECTRA-DTA outperforms various state-of-the-art DTA prediction models, especially with the challenging, interaction-sparse BindingDB dataset. In target selection and drug repurposing for COVID-19, ELECTRA-DTA also offers competitive performance, suggesting its potential in speeding drug discovery and generalizability for other compound- or protein-related computational tasks.

A Pretrained ELECTRA Model for Kinase-Specific Phosphorylation Site Prediction.

Phosphorylation plays a vital role in signal transduction and cell cycle. Identifying and understanding phosphorylation through machine-learning methods has a long history. However, existing methods only learn representations of a protein sequence segment from a labeled dataset itself, which could result in biased or incomplete features, especially for kinase-specific phosphorylation site prediction in which training data are typically sparse. To learn a comprehensive contextual representation of a protein sequence segment for kinase-specific phosphorylation site prediction, we pretrained our model from over 24 million unlabeled sequence fragments using ELECTRA (Efficiently Learning an Encoder that Classifies Token Replacements Accurately). The pretrained model was applied to kinase-specific site prediction of kinases CDK, PKA, CK2, MAPK, and PKC. The pretrained ELECTRA model achieves 9.02% improvement over BERT and 11.10% improvement over MusiteDeep in the area under the precision-recall curve on the benchmark data.

Machine learning-derived major adverse event prediction of patients undergoing transvenous lead extraction: Using the ESC EHRA EORP European lead extraction ConTRolled ELECTRa registry.

BACKGROUND: Transvenous lead extraction (TLE) remains a high-risk procedure. OBJECTIVE: The purpose of this study was to develop a machine learning (ML)-based risk stratification system to predict the risk of major adverse events (MAEs) after TLE. A MAE was defined as procedure-related major complication and procedure-related death. METHODS: We designed and evaluated an ML-based risk stratification system trained using the European Lead Extraction ConTRolled (ELECTRa) registry to predict the risk of MAEs in 3555 patients undergoing TLE and tested this on an independent registry of 1171 patients. ML models were developed, including a self-normalizing neural network (SNN), stepwise logistic regression model ("stepwise model"), support vector machines, and random forest model. These were compared with the ELECTRa Registry Outcome Score (EROS) for MAEs. RESULTS: There were 53 MAEs (1.7%) in the training cohort and 24 (2.4%) in the test cohort. Thirty-two clinically important features were used to train the models. ML techniques were similar to EROS by balanced accuracy (stepwise model: 0.74 vs EROS: 0.70) and superior by area under the curve (support vector machines: 0.764 vs EROS: 0.677). The SNN provided a finite risk for MAE and accurately identified MAE in 14 of 169 "high (>80%) risk" patients (8.3%) and no MAEs in all 198 "low (<20%) risk" patients (100%). CONCLUSION: ML models incrementally improved risk prediction for identifying those at risk of MAEs. The SNN has the additional advantage of providing a personalized finite risk assessment for patients. This may aid patient decision making and allow better preoperative risk assessment and resource allocation.

A new approach to ticagrelor-based de-escalation of antiplatelet therapy after acute coronary syndrome. A rationale for a randomized, double-blind, placebo-controlled, investigator-initiated, multicenter clinical study.

The risk of ischemic events gradually decreases after acute coronary syndrome (ACS), reaching a stable level after 1 month, while the risk of bleeding remains steady during the whole period of dual antiplatelet treatment (DAPT). Several de-escalation strategies of antiplatelet treatment aiming to enhance safety of DAPT without depriving it of its efficacy have been evaluated so far. We hypothesized that reduction of the ticagrelor maintenance dose 1 month after ACS and its continuation until 12 months after ACS may improve adherence to antiplatelet treatment due to better tolerability compared with the standard dose of ticagrelor. Moreover, improved safety of treatment and preserved anti-ischemic benefit may also be expected with additional acetylsalicylic acid (ASA) withdrawal. To evaluate these hypotheses, we designed the Evaluating Safety and Efficacy of Two Ticagrelor-based De-escalation Antiplatelet Strategies in Acute Coronary Syndrome - a randomized clinical trial (ELECTRA-SIRIO 2), to assess the influence of ticagrelor dose reduction with or without continuation of ASA versus DAPT with standard dose ticagrelor in reducing clinically relevant bleeding and maintaining anti-ischemic efficacy in ACS patients. The study was designed as a phase III, randomized, multicenter, double-blind, investigator-initiated clinical study with a 12-month follow-up (ClinicalTrials.gov Identifier: NCT04718025; EudraCT number: 2020-005130-15).

[ELECTRA: electricity-driven low energy and chemical input technology for accelerated bioremediation].

The international cooperation project "electricity-driven low energy and chemical input technology for accelerated bioremediation" (abridged as "ELECTRA") is jointly supported by National Nature Science Foundation of China (NSFC) and European Commission (EC). The ELECTRA consortium consists of 5 research institutions and universities from China and 17 European research institutions and universities, as well as high-tech companies of EC countries. ELECTRA focuses on researches of biodegradation of emerging organic compounds (EOCs) and novel environmental biotechnologies of low-energy and low-chemical inputs. The project has been successfully operated for 2 years, and has made important progresses in obtaining EOCs-degrading microbes, developing weak-electricity-accelerated bioremediation, and 3D-printing techniques for microbial consortium. The ELECTRA has promoted collaborations among the Chinese and European scientists. In the future, ELECTRA will overcome the negative impact of the COVID-19 pandemic and fulfill the scientific objectives through strengthening the international collaboration.

ELECTRA: electricity-driven low energy and chemical input technology for accelerated bioremediation / 生物工程学报

The international cooperation project "electricity-driven low energy and chemical input technology for accelerated bioremediation" (abridged as "ELECTRA") is jointly supported by National Nature Science Foundation of China (NSFC) and European Commission (EC). The ELECTRA consortium consists of 5 research institutions and universities from China and 17 European research institutions and universities, as well as high-tech companies of EC countries. ELECTRA focuses on researches of biodegradation of emerging organic compounds (EOCs) and novel environmental biotechnologies of low-energy and low-chemical inputs. The project has been successfully operated for 2 years, and has made important progresses in obtaining EOCs-degrading microbes, developing weak-electricity-accelerated bioremediation, and 3D-printing techniques for microbial consortium. The ELECTRA has promoted collaborations among the Chinese and European scientists. In the future, ELECTRA will overcome the negative impact of the COVID-19 pandemic and fulfill the scientific objectives through strengthening the international collaboration.

MEDISAN: orgullo de los profesionales de la salud santiagueros / MEDISAN: pride of Santiago health professionals

Se analizan la progresión histórica y producción científica de la revista electrónica Medisan; se comparan sus logros con los de otras publicaciones nacionales, se ofrecen datos estadísticos correspondientes al 2010 y se describen las principales estrategias incorporadas desde el 2008 para el incremento constante de su calidad y rigor científico(AU)

The historical progress and scientific production of the electronic journal MEDISAN are analyzed; Its achievements are compared with those of other national publications, statistical data of 2010 are provided and the main strategies built from 2008 for the steadily increasing quality and scientific rigor are described(AU)