RSS 2.0
Critical Assessment of Information Extraction in Biology - data sets are available from Resources/Corpora and require registration.

BioCreative VII

BioCreative VII Workshop Information [2021-08-23]

Welcome to the BioCreative VII challenge evaluation workshop, November 8-10, 2021. This event is virtual and free.

We are using Zoom webinars. PLease register to get the link. If you are registered and need the link please contact us at biocreativechallenge_AT_gmail.com

Scientific Program


The scientific program includes the talks related to the individual tracks, a panel about mining adverse drug reactions, a keynote talk and a flash talks for selected posters. Detailed agenda is shown below

Monday, November 8, 2021

UTC (Universal)ESTSession
2:30-2:40 pm9:30-9:40 amOpening remarks
2:40-3:55 pm9:40-10:55 am NLM-Chem Track: Full text Chemical Identification and Indexing in PubMed articles (Track 2)
Chair: Zhiyong Lu
  • Overview of the NLM-CHEM track - Full-text Chemical Identification and Indexing in PubMed articles (Rezarta Islamaj, Robert Leaman)
  • Chemical detection and indexing in PubMed full text articles using deep learning and rule-based methods (João Figueira Silva)
  • Improving Tagging Consistency and Entity Coverage for Chemical Identification in Full-text Articles (Hyunjae Kim)
  • A BERT-Based Hybrid System for Chemical Identification and Indexing in Full-Text Articles (Arslan Erdengasileng)
  • Chemical Identification and Indexing in PubMed Articles via BERT and Text-to-Text Based Approaches (Virginia Adams)
3:55-4:15 pm10:55-11:15 amBreak
4:15-5:00 pm11:15 am-12:00 pmKeynote: All of Us Research Program: Improving Health Through Technology, Huge Cohorts and Precision Medicine. Joshua Denny M.D., M.S., Chief Executive Officer of the All of Us Research Program, NIH
5:00-6:15 pm12:00-1:15 pm Automatic extraction of medication names in tweets (Track 3)
Chair: Davy Weissenbacher
  • BioCreative VII – Track 3: Automatic Extraction of Medication Names in Tweets (Davy Weissenbacher)
  • NCU-IISR/AS-GIS: Detecting Medication Names in Imbalanced Twitter Data with Pretrained Extractive QA Model and Data-Centric Approach (Yu Zhang)
  • BCH-NLP at BioCreative VII Track 3 - medications detection in tweets using transformer networks and multi-task learning (Dongfang Xu)

Tuesday, November 9, 2021

UTC (Universal)ESTSession
2:00-2:10 pm9:00-9:10 amOpening remarks
2:10-3:55 pm9:10-10:55 am DrugProt:Text mining drug/chemical-protein interactions (Track 1)
Chair: Antonio Miranda-Escalada
  • Overview of DrugProt BioCreative VII track: quality evaluation and large scale text mining of drug-gene/protein relations (Martin Krallinger, Antonio Miranda-Escalada)
  • Using Knowledge Base to Refine Data Augmentation for Biomedical Relation Extraction (WonJin Yoon)
  • Extracting Drug-Protein Interaction using an Ensemble of Biomedical Pre-trained Language Models through Sequence Labeling and Text Classification Techniques (Ling Luo)
  • Text Mining Drug-Protein Interactions using an Ensemble of BERT, Sentence BERT and T5 models (Xin Sui)
  • Humboldt @ DrugProt: Chemical-Protein Relation Extraction with Pretrained Transformers and Entity Descriptions (Leon Weber)
  • Does constituency analysis enhance domain-specific pre-trained BERT models for relation extraction? (Anfu Tang)
  • Text Mining Drug/Chemical-Protein Interactions using an Ensemble of BERT and T5 Based Models (Virginia Adams)
  • CU-UD: text-mining drug and chemical-protein interactions with ensembles of BERT-based models(Mehmet Efruz Karabulut)
  • TTI-COIN at BioCreative VII Track 1 (Naoki Iinuma/Masaki Asada)
  • A Multi-Task Transfer Learning-based method for Extracting Drug-Protein Interactions (Ed-drissiya El-allaly)
  • UTHealth@BioCreativeVII: Domain-specific Transformer Models for Drug-Protein Relation Extraction (Liang-Chin (Leon) Huang)
  • lasigeBioTM at BioCreative VII Track 1: Text mining drug and chemical-protein interactions using biomedical ontologies (Diana Sousa)
  • Identifying Drug/chemical-protein Interactions in Biomedical Literature using the BERT-based Ensemble Learning Approach for the BioCreative 2021 DrugProt Track (Tzu-Yi Li)
  • Catalytic DS at BioCreative VII: DrugProt Track (Dennis Mehay)
3:55-4:15 pm10:55-11:15 amBreak
4:15-5:00 pm11:15 am-12:00 pm Selected poster flash talks
Chair: Rezarta Islamaj
  • Claim Detection in Biomedical Twitter Posts as a Prerequisite for Fact-Checking (Amelie Wührl)
  • Visual Exploration of Randomized Clinical Trials for COVID-19 (Abel Correa Dias)
  • COVID-SEE: The Scientific Evidence Explorer for COVID-19 Related Research (Karin Verspoor)
  • Long Covid: A Comprehensive Collection of Articles on Post-COVID Conditions (Robert Leaman)
  • Automated topic prediction of LitCovid using BioBERT (Vangala G Saipradeep)
  • A Survey of Relation Extraction Techniques Using Hybrid Classical and State of the Art Methods (Onur Kara)
  • Automatic Extraction of Medication Names in Tweets as Named Entity Recognition (Carole Anderson)
  • PubMedBERT-based Classifier with Data Augmentation Strategy for Detecting Medication Mentions in Tweets (Qing Hang)
  • Extraction of Medication Names from Twitter Using Augmentation and an Ensemble of Language Models (Igor Kulev)
  • Recognizing Chemical Entity in Biomedical Literature using a BERT-based Ensemble Learning Methods for the BioCreative 2021 NLM-Chem Track (Yu Wen Chiu)
  • Fine-tuning transformers for automatic chemical entity identification in PubMed articles (Robert Bevan)
  • PolyU CBS-NLP at BioCreative-VII LitCovid Task: Ensemble Learning for COVID-19 Multilabel Classification (Jinghang Gu)
  • Multi-label topic classification for COVID-19 literature annotation using an ensemble model based on PubMedBERT (Shubo Tian)
  • RobertNLP at the BioCreative VII - LitCovid track: Neural Document Classification Using SciBERT (Friedrich Annemarie)
  • TTI-COIN at BioCreative VII Track 2 (Tomoki Tsujimura)
  • Chemical–protein relation extraction in PubMed abstracts using BERT and neural networks (Rui Antunes)
  • R-BERT-CNN: Drug-target interactions extraction from biomedical literature (Jehad Aldahdooh)
5:00-6:15 pm12:00-1:15 pm Panel: Challenges in mining adverse drug reactions

The BioCreative organizers have convened this panel to explore the possibility of a future BioCreative evaluation on mining adverse drug reactions (ADRs). The panel will explore challenges of mining ADRs, focusing on applications (e.g., post-market surveillance, early warning from tracking social media, predictive models of toxic endpoints for chemicals and drugs, pre-clinical and clinical research) and data sources (including their limitations and accessibility).

Chairs: Martin Krallinger, Lynette Hirschman

Panelists:
  • Dr. Martin Krallinger (Chair)
  • CDR Monica Muñoz, FDA CDER
  • Prof. Özlem Uzuner, George Mason University
  • Dr. Raul Rodriguez-Esteban, Roche Pharmaceutics
  • Prof. Graciela Gonzalez-Hernandez, U Pennsylvania Medical School

Wednesday, November 10, 2021

UTC (Universal)ESTSession
2:30-2:40 pm9:30-9:40 amOpening remarks
2:40-3:55 pm9:40-10:55 am LitCovid track Multi-label topic classification for COVID-19 literature annotation (Track 5)
Chair: Rezarta Islamaj
  • BioCreative VII LitCovid Track: multi-label topic classification for COVID-19 literature annotation (Qingyu Chen)
  • Multic-label topic classification for COVID-19 literature with Bioformer (Fang Li)
  • Multi-label topic classification for COVID-19 literature annotation: A BioBERT-based feature enhancement approach (Wentai Tang)
  • BERT-based bagging-stacking for multi-topic classification (Loïc Rakotoson)
  • Multi-label Topic Classification for COVID-19 Literature Annotation using the BERT-based Ensemble Learning Approach for the BioCreative 2021 LitCovid Track (Sheng-Jie Lin)
3:55-4:15 pm10:55-11:15 amBreak
4:15-5:30 pm11:15 am-12:30 pm COVID-19 text mining tool interactive demo (Track 4)
Chair: Lynette Hirschman
  • Introduction to the COVID-19 Text Mining Tool Interactive Demo Track (Andrew Chatr-Aryamontri)
  • Semantic Search Engine preVIEW COVID-19 - Evaluation in the BioCreative VII IAT Track (Johannes Darms)
  • TopEx: Topic Exploration of COVID-19 Corpora - Results from the Biocreative VII Challenge Track 4 (Amy Olex)
  • Interpretable Visualization of Scientific Hypotheses in Literature-based Discovery (Ilya Tyagin)
  • A self-updating causal model of COVID-19 mechanisms built from the scientific literature (Benjamin Gyori)
  • BioKDE: a Deep Learning Powered Search Engine and Biomedical Knowledge Discovery Platform (Jinfeng Zhang)
  • The COVID-19 Therapeutic Information Browser (Tonia Korves)
  • Overview of the COVID-19 Text Mining Tool Interactive Demo Track (Andrew Chatr-Aryamontri)
5:30-6:10 pm12:30-1:10 pmGeneral discussion
6:10-6:15 pm1:10-1:15 pmClosing remarks

Back to top


Poster session

There are a number of exciting posters presentations. Note that a number of these will be played during flash talk session on November 9.

Back to top


Proceedings


ISBN: 978-0-578-32368-8

Proceedings are available here

Back to top


Registration

Registration is open to participants of the tracks and to anyone interested in learning/discussing about development of state-of-the-art text mining methods for real life applications. There is no fee. Register here. The link to attend the meeting is provided in registration form