Jaap Heringa, Ph.D.
Director & Professor of Bioinformatics, IBIVU VU University Amsterdam, The Netherlands
Modeling strategy based on Petri-nets
In my talk I will introduce a formal modeling strategy based on Petri-nets, which are a convenient means of modeling biological processes. I will illustrate the capabilities of Petri-nets as reasoning vehicles using two examples: Haematopoietic stem cell differentiation in mice, and vulval development in C. elegance. The first system was modeled using a Boolean implementation, and the second using a coarse-grained multi-cellular Petri-net model. Concepts such as the model state space, attractor states, and reasoning to adapt the model to the biological reality will be discussed.
Lalitha Subramanian, Ph.D.
Chief Scientific Officer & VP, Services at Scienomics, USA
Nanoscale Simulations – Tackling Form and Formulation Challenges in Drug Development and Drug Delivery
Lalitha Subramanian, Dora Spyriouni, Andreas Bick, Sabine Schweizer, and Xenophon Krokidis Scienomics
The discovery of a compound which is potent in activity against a target is a major milestone in Pharmaceutical and Biotech industry. However, a potent compound is only effective as a therapeutic agent when it can be administered such that the optimal quantity is transported to the site of action at an optimal rate. The active pharmaceutical ingredient (API) has to be tested for its physicochemical properties before the appropriate dosage form and formulation can be designed. Some of the commonly evaluated parameters are crystal forms and polymorphs, solubility, dissolution behavior, stability, partition coefficient, water sorption behavior, surface properties, particle size and shape, etc. Pharmaceutical development teams face the challenge of quickly and efficiently determining a number of properties with small quantities of the expensive candidate compounds. Recently the trend has been to screen these properties as early as possible and often the candidate compounds are not available in sufficient quantities. Increasingly, these teams are leveraging nanoscale simulations similar to those employed by drug discovery teams for several decades. Nanoscale simulations are used to predict the behavior using very little experimental data and only if this is promising further experiments are done. Another aspect where nanoscale simulations are being used in drug development and drug delivery is to get insights into the behavior of the system so that process failures can be remediated and formulation performance can be improved. Thus, the predictive screening and the in-depth understanding leads to experimental efficiency resulting in far-reaching business impacts.
With specific examples, this talk will focus on the different types of nanoscale simulations used to predict properties of the API in excipients and also provide insight into system behavior as a function of shelf life, temperature, mechanical stress, etc.
Srisairam Achuthan, Ph.D.
Senior Scientific Programmer, Research Informatics Division, Department of Information Sciences, City of Hope, CA, USA
Applying Machine learning for Automated Identification of Patient Cohorts
Srisairam Achuthan, Mike Chang, Ajay Shah, Joyce Niland
Patient cohorts for a clinical study are typically identified based on specific selection criteria. In most cases considerable time and effort are spent in finding the most relevant criteria that could potentially lead to a successful study. For complex diseases, this process can be more difficult and error prone since relevant features may not be easily identifiable. Additionally, the information captured in clinical notes is in non-coded text format. Our goal is to discover patterns within the coded and non-coded fields and thereby reveal complex relationships between clinical characteristics across different patients that would be difficult to accomplish manually. Towards this, we have applied machine learning techniques such as artificial neural networks and decision trees to determine patients sharing similar characteristics from available medical records. For this proof of concept study, we used coded and non-coded (i.e., clinical notes) patient data from a clinical database. Coded clinical information such as diagnoses, labs, medications and demographics recorded within the database were pooled together with non-coded information from clinical notes including, smoking status, life style (active / inactive) status derived from clinical notes. The non-coded textual information was identified and interpreted using a Natural Language Processing (NLP) tool I2E from Linguamatics.