CANCELLED - Applying AI/ML in High-Dimensional Data Analysis for Drug Disco...

Event Information

Share this event

Date and Time

Location

Location

Pfizer

1 Portland Street, Kendall Square

Cambridge

Massachusetts, MA 01239

View Map

Event description

Description


Organising Committee

Justin Boyd (Pfizer), Dominic Clark (Pistoia Alliance), Holger Hoefling (Novartis), Sukru Kaymakcalan (AbbVie), Brian Martin (AbbVie), Zahid Tharia (Pistoia Alliance)

Background and Motivation

Continuous improvement in methods of drug discovery is a key driver for the pharmaceutical industry. Machine Learning has already had some success and promises further developments as the quality and breath of data sets are increased (Vamathevan et al. (2019) NRDD, DOI: 10.1038/s41573-019-0024-5).

Draft Program

Better models of diseases and assay methods present an opportunity for generating more comprehensive data sets with higher dimensionality through deep phenotyping. The challenge is then to make sense of this higher dimensional data through AI/ML so that it can most effectively be leveraged in drug discovery programmes.

The focus of this symposium will be on applying AI/ML in high-dimensional data analysis for Drug Discovery and design of personal medicine stratified clinical trials.

The new methods and approaches will be exemplified through presentations from key opinion leaders, industry case studies and new innovative approaches.

Organising Committee

Justin Boyd (Pfizer), Dominic Clark (Pistoia Alliance), Holger Hoefling (Novartis), Sukru Kaymakcalan (AbbVie), Brian Martin (AbbVie), Zahid Tharia (Pistoia Alliance),

Background and Motivation

Continuous improvement in methods of drug discovery is a key driver for the pharmaceutical industry. Machine Learning has already had some success and promises further developments as the quality and breath of data sets are increased (Vamathevan et al. (2019) NRDD, DOI: 10.1038/s41573-019-0024-5).

Better models of diseases and assay methods present an opportunity for generating more comprehensive data sets with higher dimensionality through deep phenotyping. The challenge is then to make sense of this higher dimensional data through AI/ML so that it can most effectively be leveraged in drug discovery programmes.

The focus of this symposium will be on applying AI/ML in high-dimensional data analysis for Drug Discovery and design of personal medicine stratified clinical trials.

The new methods and approaches will be exemplified through presentations from key opinion leaders, industry case studies and new innovative approaches.

Relation to other Pistoia Alliance activities

The symposium will have links to the Pistoia Alliance community of interest in Cell Painting and the Pistoia Alliance Centre of Excellence for AI/ML in Life Sciences.

Scope and coverage

The key topic areas to be covered at the symposium is approaches of ML in Drug Discovery: biomarker, new targets and new drugs with a focus on high dimensional data analysis.

Anticipated outcomes

The Symposium will showcase best practice and promote knowledge exchange between speakers and delegates through case studies, discussion and panel sessions. The Symposium will facilitate enhanced discussion around Pistoia Alliance Cell Painting CoI and AI/ML CoE.

The symposium will have links to the Pistoia Alliance community of interest in Cell Painting and the Pistoia Alliance Centre of Excellence for AI/ML in Life Sciences.

Scope and coverage

The key topic areas to be covered at the symposium is approaches of ML in Drug Discovery: biomarker, new targets and new drugs with a focus on high dimensional data analysis.

Anticipated outcomes

The Symposium will showcase best practice and promote knowledge exchange between speakers and delegates through case studies, discussion and panel sessions. The Symposium will facilitate enhanced discussion around Pistoia Alliance Cell Painting CoI and AI/ML CoE.

Date and Time

Location

Pfizer

1 Portland Street, Kendall Square

Cambridge

Massachusetts, MA 01239

View Map

Save This Event

Event Saved