\n
\nWho is this event intended for? Statisticians and data scientists working on pre-clinical experiments in the pharmaceutical industry.
\nWhat is the benefit of attending? \ ;Learning about experimenting with maximum efficiency i.e. the least numbe r of experiments.
\n
Registration
\nThis event is free to a ttend for both Members of PSI and Non-Members. To register your place\, pl ease \; click here.
\nOverview
\nAdvances in AI
\, lab automation and closed-loop optimisation promise big productivity ga
ins for pharma R&\;D. But experimenting with maximum efficiency - that
is\, the least number of runs - will always be important. This is especial
ly true where there is an ethical imperative\, such as in pre-clinical ani
mal experiments.
\n
\nRecent advances in statistical Design Of E
xperiments (DOE) including Definitive Screening Designs (DSDs) and the bro
ader class of Orthogonal Minimally Aliasing Response Surface (OMARS) desig
ns have given us new options for understanding complex systems with small
experiments. Self-Validated Ensemble Modelling (SVEM) is an innovative ana
lysis approach that applies ideas from Machine Learning to small data from
designed experiments. In this presentation we will show how SVEM works an
d how it can overcome common challenges when you are building useful model
s of complex systems from small experiments.
\n
\nWe will illust
rate this with a case study example on testing the toxicity of an oncology
formulation in a preclinical setting. This (simulated) study examines the
impact of various formulation factors and their interactions on the toxic
ity and efficacy of a new oncology drug cocktail using a rat model. Key fa
ctors include the concentrations of Erlotinib\, Cisplatin\, and Dexamethas
one\, with responses measured such as tumor inhibition rate\, overall surv
ival rate\, and toxicity indicators. Additionally\, the pH of the formulat
ion and particle size were evaluated. Responses measured include efficacy\
, represented by tumor inhibition rate\, and various toxicity parameters\,
such as overall survival rate\, hepatic toxicity\, renal toxicity\, cardi
ac toxicity\, and hematological toxicity.
Speaker details
\n< table border="1" cellspacing="0" cellpadding="0">\n\n| \n Speak er \n | \n \n Biography \n | \n
| \n
| \n \n Phil leads a global team with a mission to sp read the use and impact of data analytics amongst scientists and engineers at some of the world&rsquo\;s largest chemical\, pharmaceutical\, semicon ductor and consumer product companies. Earlier in his career he gained a p assion for statistical design and analysis of experiments while working as a development chemist at FujiFilm. Phil has a master&rsquo\;s degree in a pplied statistics and a master&rsquo\;s and PhD in chemistry. He is a char tered chemist and chair of the RSC process chemistry and technology intere st group. \n | \n
| \n
| \n \n
Chandra (Chandramouli Ramnarayanan)\, PhD\, is a member of the Glo bal Technical Enablement team at JMP Statistical Discovery LLC\, a SAS Ins titute subsidiary. He provides technical support to leading health and lif e sciences clients and contributes to product development. Previously\, Ch andra held senior roles in quality assurance within the pharmaceutical sec tor and served as a professor of pharmaceutical quality assurance. With a PhD in Pharmaceutical Sciences\, over 30 publications\, and certifications in SAS®\; Programming\, PRINCE2 Agile®\;\, and ITIL 4. \n | \n
\;
END:VEVENT END:VCALENDAR