William Hayes
Director, Library & Literature Informatics at Biogen Idec
Cambridge, MA United StatesWhat I Do:
Expertise:
Experience:
Biogen Idec
Director, Library & Literature Informatics
Develop enhanced Knowledge Discovery and Delivery capabilities for Biogen Idec.
Manage the Library and Literature Informatics Group. Develop and deploy information management, collaborative technologies. Develop and deploy text analytics. Automate library operations and improve services.
AstraZeneca
Head of Cross-Discovery Strategic Informatics
Managed projects and strategy in Research Informatics broader than the disciplines of Cheminformatics, Bioinformatics, etc. Focused efforts on text, data and image mining. Cross-functional database development.
GlaxoSmithKline
Bioinformatics Research Scientist
Human Genome analysis projects focusing on internal Gene Catalog and genome-wide promoter analyses. Developed expertise in desktop grid computing for additional compute cycles for genome-wide analyses.
Education:
Georgia Institute of Technology
PhD, Molecular Biology
Thesis: "Pattern recognition and signal detection in gene finding". Doctoral work: Bioinformatics, bacterial gene prediction, molecular biology
Georgia Institute of Technology
Bachelor's, Aerospace Engineering
Publications:
Information needs and the role of text mining in drug development.
PSB 2008 2008Advances in text analytics for drug discovery
European Pharmaceutical Contractors 2003Advances in text analytics for drug discovery
European Pharmaceutical Contractors 2003Advances in text analytics for drug discovery
European Pharmaceutical Contractors 2003
Suregene, a scalable system for automated term disambiguation of gene and protein names.
Advances in text analytics for drug discovery.
AZuRE, a scalable system for automated term disambiguation of gene and protein names.
How to interpret an anonymous bacterial genome: machine learning approach to gene identification.
Bacterial start site prediction.
Applications of GeneMark in multispecies environments.
GeneLynx: a gene-centric portal to the human genome.
Metabolism and evolution of Haemophilus influenzae deduced from a whole-genome comparison with Escherichia coli.
Computer survey for likely genes in the one megabase contiguous genomic sequence data of Synechocystis sp. strain PCC6803.
Deriving ribosomal binding site (RBS) statistical models from unannotated DNA sequences and the use of the RBS model for N-terminal prediction.
Gene identification and classification in the Synechocystis genomic sequence by recursive gene mark analysis.
See All 15 Publications
Books:
in silico Technology in Drug Target Identification and Validation; Chapter ?
in silico Technology in Drug Target Identification and Validation; Chapter ?
Semantic Web: Revolutionizing Knowledge Discovery in the Life Sciences; Chapter 3
in silico Technology in Drug Target Identification and Validation; Chapter X
Speaking Engagements:
Enterprise 2.0 Conference
AIM for bioPharma
Alert Information Management (AIM) is about delivering dynamic information where and when it is needed. With a variety of ever changing information feeds (email alerts, updated web pages, RSS feeds, internal company news, intranet portal, etc), we need to manage these feeds to optimize their value and not get overloaded. RSS/Atom was selected as the common protocol for these information streams. Discussed will be the overall strategy, specific use cases and resulting advantages of using the Newsgator Enterprise Server with auxiliary synchronized news readers/output news channels. Also presented will be the required corporate environmental changes and attendant applications that need to be put in place to take better advantage of this approach to managing continuous information streams.
Enterprise 2.0 Conference
AIM for bioPharma
Alert Information Management (AIM) is about delivering dynamic information where and when it is needed. With a variety of ever changing information feeds (email alerts, updated web pages, RSS feeds, internal company news, intranet portal, etc), we need to manage these feeds to optimize their value and not get overloaded. RSS/Atom was selected as the common protocol for these information streams. Discussed will be the overall strategy, specific use cases and resulting advantages of using the Newsgator Enterprise Server with auxiliary synchronized news readers/output news channels. Also presented will be the required corporate environmental changes and attendant applications that need to be put in place to take better advantage of this approach to managing continuous information streams.
Enterprise 2.0 Conference
AIM for bioPharma
Alert Information Management (AIM) is about delivering dynamic information where and when it is needed. With a variety of ever changing information feeds (email alerts, updated web pages, RSS feeds, internal company news, intranet portal, etc), we need to manage these feeds to optimize their value and not get overloaded. RSS/Atom was selected as the common protocol for these information streams. Discussed will be the overall strategy, specific use cases and resulting advantages of using the Newsgator Enterprise Server with auxiliary synchronized news readers/output news channels. Also presented will be the required corporate environmental changes and attendant applications that need to be put in place to take better advantage of this approach to managing continuous information streams.
C-SHALS
Competitive Intelligence Mashups using Semantic Web Technology
There are many drug pipeline and clinical trial databases available none of which are complete or provide a comprehensive set of meta-data. In order to make effective decisions on product development and positioning, we need to be able to understand what competitors have in the pipeline and continually compare it with Biogen Idec's pipeline. The pilot project we initiated to provide a highly customized view of the Rheumatology drug pipeline was made possible and easy to replicate for other therapeutic areas only after bringing the Simile Exhibit and Timeline technology into the project. Competitive intelligence projects are almost always highly targeted requiring a great deal of customization. These projects require significant data integration and excellent visualization capabilities. Utilizing semantic web technology makes the presentation and re-distribution of highly-targeted drug pipeline data tractable.
C-SHALS
Competitive Intelligence Mashups using Semantic Web Technology
There are many drug pipeline and clinical trial databases available none of which are complete or provide a comprehensive set of meta-data. In order to make effective decisions on product development and positioning, we need to be able to understand what competitors have in the pipeline and continually compare it with Biogen Idec's pipeline. The pilot project we initiated to provide a highly customized view of the Rheumatology drug pipeline was made possible and easy to replicate for other therapeutic areas only after bringing the Simile Exhibit and Timeline technology into the project. Competitive intelligence projects are almost always highly targeted requiring a great deal of customization. These projects require significant data integration and excellent visualization capabilities. Utilizing semantic web technology makes the presentation and re-distribution of highly-targeted drug pipeline data tractable.
C-SHALS
Competitive Intelligence Mashups using Semantic Web Technology
There are many drug pipeline and clinical trial databases available none of which are complete or provide a comprehensive set of meta-data. In order to make effective decisions on product development and positioning, we need to be able to understand what competitors have in the pipeline and continually compare it with Biogen Idec's pipeline. The pilot project we initiated to provide a highly customized view of the Rheumatology drug pipeline was made possible and easy to replicate for other therapeutic areas only after bringing the Simile Exhibit and Timeline technology into the project. Competitive intelligence projects are almost always highly targeted requiring a great deal of customization. These projects require significant data integration and excellent visualization capabilities. Utilizing semantic web technology makes the presentation and re-distribution of highly-targeted drug pipeline data tractable.
Scottish Bioinformatics Forum - Biomedical Text Mining
Text Mining and Information Needs of bioPharma
Information needs and production capabilities of text analytics and infrastructure drive the utility of text analytics technologies in bioPharma as in every industry. It takes a great deal of basic infrastructure to deal with large document collections that continue to grow, continuously evolving ontologies, and continous information streams (news articles, etc). Beyond basic management of the raw material, one needs text analytics technologies that fit into a framework to allow for integration. Further, the results of text mining are non-trivial to manage as regards information delivery that is collaborative, re-usable and integratable. This presentation will discuss the challenges and some of the successes found in bioPharma as one example of a customer of text mining in the biomedical community.
Elsevier Corporate Event - London, UK
A view from the bleeding edge of text mining
An overview of the latest capabilities either in production or ready to go into production for large-scale information discovery and delivery for corporate needs.
Elsevier Corporate Event - London, UK
A view from the bleeding edge of text mining
An overview of the latest capabilities either in production or ready to go into production for large-scale information discovery and delivery for corporate needs.
BioIT World
Literature Informatics: Leveraging External Knowledge for Drug Discovery
This presentation will demonstrate how to provide comprehensive analyses of the literature and related databases for biomarker development, toxicology and protein target validation. Literature informatics not only provides more comprehensive extraction of information and facts from the literature than is available manually, it also permits quantitative and qualitative assessments of the resulting information. Visualizing data extracted from the literature in graphs or diagrams can highlight valuable information that is not necessarily obvious from a tabular view of the raw data. Social and technological changes are needed to deploy literature informatics and commitments are required from several departments during deployment (Informatics, IT and most importantly the Research Library).
BioIT World
Literature Informatics: Leveraging External Knowledge for Drug Discovery
This presentation will demonstrate how to provide comprehensive analyses of the literature and related databases for biomarker development, toxicology and protein target validation. Literature informatics not only provides more comprehensive extraction of information and facts from the literature than is available manually, it also permits quantitative and qualitative assessments of the resulting information. Visualizing data extracted from the literature in graphs or diagrams can highlight valuable information that is not necessarily obvious from a tabular view of the raw data. Social and technological changes are needed to deploy literature informatics and commitments are required from several departments during deployment (Informatics, IT and most importantly the Research Library).
BioIT World
Literature Informatics: Leveraging External Knowledge for Drug Discovery
This presentation will demonstrate how to provide comprehensive analyses of the literature and related databases for biomarker development, toxicology and protein target validation. Literature informatics not only provides more comprehensive extraction of information and facts from the literature than is available manually, it also permits quantitative and qualitative assessments of the resulting information. Visualizing data extracted from the literature in graphs or diagrams can highlight valuable information that is not necessarily obvious from a tabular view of the raw data. Social and technological changes are needed to deploy literature informatics and commitments are required from several departments during deployment (Informatics, IT and most importantly the Research Library).
SLA Pharma
Drug Discovery Process and the Information Professionals Role
Review of how advanced technologies can be used to more effectively deliver information to Library customers in bioPharma.
SLA Pharma
Drug Discovery Process and the Information Professionals Role
Review of how advanced technologies can be used to more effectively deliver information to Library customers in bioPharma.
EIM Conference
Semantic Search And Its Role In Finding Information
The potential of the Semantic Web to transform knowledge management is enormous but still on the horizon. Semantic Search technologies, however, are already being deployed into corporations as production capabilities. This presentation will review the advantages gained by semantic search technologies based upon real world experience in delivering information using Agile NLP (as an example of Semantic Search technology). The presentation will also provide a review of the variety of solutions and suggestions on uses.
EIM Conference
Semantic Search And Its Role In Finding Information
The potential of the Semantic Web to transform knowledge management is enormous but still on the horizon. Semantic Search technologies, however, are already being deployed into corporations as production capabilities. This presentation will review the advantages gained by semantic search technologies based upon real world experience in delivering information using Agile NLP (as an example of Semantic Search technology). The presentation will also provide a review of the variety of solutions and suggestions on uses.
EIM Conference
Semantic Search And Its Role In Finding Information
The potential of the Semantic Web to transform knowledge management is enormous but still on the horizon. Semantic Search technologies, however, are already being deployed into corporations as production capabilities. This presentation will review the advantages gained by semantic search technologies based upon real world experience in delivering information using Agile NLP (as an example of Semantic Search technology). The presentation will also provide a review of the variety of solutions and suggestions on uses.
KM World
Improving Information Flows
Automating the assembly and distribution of important company, product, industry, and competitive information throughout the enterprise is revolutionized with RSS. Hear how Biogen Idec, a Fortune 1000 company with market-leading drugs for treating a number of illnesses, has used RSS to get high-value business information into the hands of employees.
Linguamatics User Conference
Overview of workflow technology and how it can be used with I2E.


