The Rensselaer Exploratory Center for Cheminformatics Research
The Rensselaer Exploratory Center for Cheminformatics Research is dedicated to advancing the field of Cheminformatics and increasing the availability of new methods within the Cheminformatics user community. Toward this goal RECCR members are developing new multi-objective machine learning methods, high information-content descriptors, data fusion techniques and infrastructure for extending the reliability and applicability of informatics-based prediction techniques.
Advances in the generation, mining and analysis of chemical information is crucial to the development of new drug therapies, and to modern methods of bioinformatics and molecular medicine. RECCR brings together and stimulates collaborative pilot projects among a constantly-evolving nucleus of experts in Cheminformatics-related fields ranging from methods of encoding and capturing molecular information, to machine learning and data mining techniques, to predictive model development, validation, interpretation and utilization. In addition, we will bring together a set of domain specialists and application scientists to serve as both data generators and end-users of the knowledge provided by the molecular property models and modeling methods developed by RECCR. This group will also test the new cheminformatics software developed at RECCR. The many diverse project areas pursued at RECCR can be grouped into one or more overlapping categories:
- Data Generation – using theoretical or experimental methods for creating or extracting knowledge;
- Machine Learning and Datamining – model validation, feature selection, pattern recognition, generation of potentials of mean force and knowledge-based potentials;
- Property-Prediction – chemically-aware model building, molecular property descriptor generation, Quantitative Structure-Property Relationship modeling, validation, and interpretation;
- Applications – utilizing the information made available using the new tools and methods that are developed as part of RECCR.
RECCR emphasizes the central role of Cheminformatics in modern biotechnology efforts, molecular design projects and bioinformatics programs.
RECCR will seed new interdisciplinary projects and train graduate students in these areas. The overall goal of RECCR is to continually advance the field of Cheminformatics research and develop descriptors, machine learning methods and infrastructure for extending the reliability and applicability of informatics-based prediction techniques. ADME/Tox predictions, ligand/protein scoring, drug discovery, molecular fingerprint analysis and bioinformatics methodologies would all benefit from advances in Cheminformatics.
Funding provided by NIH Molecular Libraries Roadmap Initiative Grant # 1P20HG003899-01.