Date: Tuesday 18th November 2025 Time: 14:00 - 15:00 GMT | 9:00 - 10:00 EST (US) Location: Online via Zoom Speakers: Davit Sargsyan
Who is this event intended for?: Statisticians and Scientists involved or interested in randomization techniques in pre-clinical and early clinical studies.
What is the benefit of attending?: Hearing about modern randomization methods.
Cost
This webinar is free to both Members of PSI and Non-Members.
In both, clinical and preclinical studies randomizing subjects to treatment groups is a key part of the study design. This step minimizes the risk of confounding. For large studies, complete randomization is often enough to ensure that treatment groups are similar. However, for small clinical trials and especially for in vivo studies this approach is riskier. More elaborate randomization techniques can be applied for those studies such as randomized block design. However, the best results are achieved when algorithmic approach to subject allocation is taken. One such approach is based on genetic algorithm that is rooted in Theory of Evolution. The methodology minimizes the fitness function criteria for partitions of a dataset into balanced subgroups. The performance of the algorithm was compared to random allocation and the exhaustive search using synthetic and real-world data. The results showed that experimental groups created by this algorithm were more homogeneous compared those created by exhaustive search. Additionally, this algorithm is significantly less expensive computationally compared to the exhaustive search, and the efficiency gains increase rapidly as the number of subjects and design factors increase. We will discuss the theory behind this approach as well as the extensions and variations of the algorithm such as simulated annealing.
Speaker details
Speaker
Biography
Abstract
Davit Sargsyan, Johnson & Johnson
Davit Sargsyan is an associate director in a nonclinical statistics group at J&J Innovative Medicine, mainly supporting Immunology Discover R&D. He received an MS in statistics and completed his PhD in pharmaceutical sciences at Rutgers University. To date, Davit has co-published over 70 scientific articles in peer-reviewed journals on topics ranging from clinical outcomes of cardiovascular patients using a state-wide hospital admission data registry to natural compounds testing in in vivo and in vitro models. Davit’s research at Rutgers School of Pharmacy concentrated on computational methods and visualization of omics data studying the effect of dietary phytochemicals on epigenome, transcriptome and microbiome.
Modern Algorithms for Animal Randomization in Preclinical Studies In both, clinical and preclinical studies randomizing subjects to treatment groups is a key part of the study design. This step minimizes the risk of confounding. For large studies, complete randomization is often enough to ensure that treatment groups are similar. However, for small clinical trials and especially for in vivo studies this approach is riskier. More elaborate randomization techniques can be applied for those studies such as randomized block design. However, the best results are achieved when algorithmic approach to subject allocation is taken. One such approach is based on genetic algorithm that is rooted in Theory of Evolution. The methodology minimizes the fitness function criteria for partitions of a dataset into balanced subgroups. The performance of the algorithm was compared to random allocation and the exhaustive search using synthetic and real-world data. The results showed that experimental groups created by this algorithm were more homogeneous compared those created by exhaustive search. Additionally, this algorithm is significantly less expensive computationally compared to the exhaustive search, and the efficiency gains increase rapidly as the number of subjects and design factors increase. We will discuss the theory behind this approach as well as the extensions and variations of the algorithm such as simulated annealing.
Scientific Meetings
Pre-Clinical SIG Webinar: Modern Algorithms for Animal Randomization in Preclinical Studies
Date: Tuesday 18th November 2025 Time: 14:00 - 15:00 GMT | 9:00 - 10:00 EST (US) Location: Online via Zoom Speakers: Davit Sargsyan
Who is this event intended for?: Statisticians and Scientists involved or interested in randomization techniques in pre-clinical and early clinical studies.
What is the benefit of attending?: Hearing about modern randomization methods.
Cost
This webinar is free to both Members of PSI and Non-Members.
In both, clinical and preclinical studies randomizing subjects to treatment groups is a key part of the study design. This step minimizes the risk of confounding. For large studies, complete randomization is often enough to ensure that treatment groups are similar. However, for small clinical trials and especially for in vivo studies this approach is riskier. More elaborate randomization techniques can be applied for those studies such as randomized block design. However, the best results are achieved when algorithmic approach to subject allocation is taken. One such approach is based on genetic algorithm that is rooted in Theory of Evolution. The methodology minimizes the fitness function criteria for partitions of a dataset into balanced subgroups. The performance of the algorithm was compared to random allocation and the exhaustive search using synthetic and real-world data. The results showed that experimental groups created by this algorithm were more homogeneous compared those created by exhaustive search. Additionally, this algorithm is significantly less expensive computationally compared to the exhaustive search, and the efficiency gains increase rapidly as the number of subjects and design factors increase. We will discuss the theory behind this approach as well as the extensions and variations of the algorithm such as simulated annealing.
Speaker details
Speaker
Biography
Abstract
Davit Sargsyan, Johnson & Johnson
Davit Sargsyan is an associate director in a nonclinical statistics group at J&J Innovative Medicine, mainly supporting Immunology Discover R&D. He received an MS in statistics and completed his PhD in pharmaceutical sciences at Rutgers University. To date, Davit has co-published over 70 scientific articles in peer-reviewed journals on topics ranging from clinical outcomes of cardiovascular patients using a state-wide hospital admission data registry to natural compounds testing in in vivo and in vitro models. Davit’s research at Rutgers School of Pharmacy concentrated on computational methods and visualization of omics data studying the effect of dietary phytochemicals on epigenome, transcriptome and microbiome.
Modern Algorithms for Animal Randomization in Preclinical Studies In both, clinical and preclinical studies randomizing subjects to treatment groups is a key part of the study design. This step minimizes the risk of confounding. For large studies, complete randomization is often enough to ensure that treatment groups are similar. However, for small clinical trials and especially for in vivo studies this approach is riskier. More elaborate randomization techniques can be applied for those studies such as randomized block design. However, the best results are achieved when algorithmic approach to subject allocation is taken. One such approach is based on genetic algorithm that is rooted in Theory of Evolution. The methodology minimizes the fitness function criteria for partitions of a dataset into balanced subgroups. The performance of the algorithm was compared to random allocation and the exhaustive search using synthetic and real-world data. The results showed that experimental groups created by this algorithm were more homogeneous compared those created by exhaustive search. Additionally, this algorithm is significantly less expensive computationally compared to the exhaustive search, and the efficiency gains increase rapidly as the number of subjects and design factors increase. We will discuss the theory behind this approach as well as the extensions and variations of the algorithm such as simulated annealing.
Training Courses
Pre-Clinical SIG Webinar: Modern Algorithms for Animal Randomization in Preclinical Studies
Date: Tuesday 18th November 2025 Time: 14:00 - 15:00 GMT | 9:00 - 10:00 EST (US) Location: Online via Zoom Speakers: Davit Sargsyan
Who is this event intended for?: Statisticians and Scientists involved or interested in randomization techniques in pre-clinical and early clinical studies.
What is the benefit of attending?: Hearing about modern randomization methods.
Cost
This webinar is free to both Members of PSI and Non-Members.
In both, clinical and preclinical studies randomizing subjects to treatment groups is a key part of the study design. This step minimizes the risk of confounding. For large studies, complete randomization is often enough to ensure that treatment groups are similar. However, for small clinical trials and especially for in vivo studies this approach is riskier. More elaborate randomization techniques can be applied for those studies such as randomized block design. However, the best results are achieved when algorithmic approach to subject allocation is taken. One such approach is based on genetic algorithm that is rooted in Theory of Evolution. The methodology minimizes the fitness function criteria for partitions of a dataset into balanced subgroups. The performance of the algorithm was compared to random allocation and the exhaustive search using synthetic and real-world data. The results showed that experimental groups created by this algorithm were more homogeneous compared those created by exhaustive search. Additionally, this algorithm is significantly less expensive computationally compared to the exhaustive search, and the efficiency gains increase rapidly as the number of subjects and design factors increase. We will discuss the theory behind this approach as well as the extensions and variations of the algorithm such as simulated annealing.
Speaker details
Speaker
Biography
Abstract
Davit Sargsyan, Johnson & Johnson
Davit Sargsyan is an associate director in a nonclinical statistics group at J&J Innovative Medicine, mainly supporting Immunology Discover R&D. He received an MS in statistics and completed his PhD in pharmaceutical sciences at Rutgers University. To date, Davit has co-published over 70 scientific articles in peer-reviewed journals on topics ranging from clinical outcomes of cardiovascular patients using a state-wide hospital admission data registry to natural compounds testing in in vivo and in vitro models. Davit’s research at Rutgers School of Pharmacy concentrated on computational methods and visualization of omics data studying the effect of dietary phytochemicals on epigenome, transcriptome and microbiome.
Modern Algorithms for Animal Randomization in Preclinical Studies In both, clinical and preclinical studies randomizing subjects to treatment groups is a key part of the study design. This step minimizes the risk of confounding. For large studies, complete randomization is often enough to ensure that treatment groups are similar. However, for small clinical trials and especially for in vivo studies this approach is riskier. More elaborate randomization techniques can be applied for those studies such as randomized block design. However, the best results are achieved when algorithmic approach to subject allocation is taken. One such approach is based on genetic algorithm that is rooted in Theory of Evolution. The methodology minimizes the fitness function criteria for partitions of a dataset into balanced subgroups. The performance of the algorithm was compared to random allocation and the exhaustive search using synthetic and real-world data. The results showed that experimental groups created by this algorithm were more homogeneous compared those created by exhaustive search. Additionally, this algorithm is significantly less expensive computationally compared to the exhaustive search, and the efficiency gains increase rapidly as the number of subjects and design factors increase. We will discuss the theory behind this approach as well as the extensions and variations of the algorithm such as simulated annealing.
Journal Club
Pre-Clinical SIG Webinar: Modern Algorithms for Animal Randomization in Preclinical Studies
Date: Tuesday 18th November 2025 Time: 14:00 - 15:00 GMT | 9:00 - 10:00 EST (US) Location: Online via Zoom Speakers: Davit Sargsyan
Who is this event intended for?: Statisticians and Scientists involved or interested in randomization techniques in pre-clinical and early clinical studies.
What is the benefit of attending?: Hearing about modern randomization methods.
Cost
This webinar is free to both Members of PSI and Non-Members.
In both, clinical and preclinical studies randomizing subjects to treatment groups is a key part of the study design. This step minimizes the risk of confounding. For large studies, complete randomization is often enough to ensure that treatment groups are similar. However, for small clinical trials and especially for in vivo studies this approach is riskier. More elaborate randomization techniques can be applied for those studies such as randomized block design. However, the best results are achieved when algorithmic approach to subject allocation is taken. One such approach is based on genetic algorithm that is rooted in Theory of Evolution. The methodology minimizes the fitness function criteria for partitions of a dataset into balanced subgroups. The performance of the algorithm was compared to random allocation and the exhaustive search using synthetic and real-world data. The results showed that experimental groups created by this algorithm were more homogeneous compared those created by exhaustive search. Additionally, this algorithm is significantly less expensive computationally compared to the exhaustive search, and the efficiency gains increase rapidly as the number of subjects and design factors increase. We will discuss the theory behind this approach as well as the extensions and variations of the algorithm such as simulated annealing.
Speaker details
Speaker
Biography
Abstract
Davit Sargsyan, Johnson & Johnson
Davit Sargsyan is an associate director in a nonclinical statistics group at J&J Innovative Medicine, mainly supporting Immunology Discover R&D. He received an MS in statistics and completed his PhD in pharmaceutical sciences at Rutgers University. To date, Davit has co-published over 70 scientific articles in peer-reviewed journals on topics ranging from clinical outcomes of cardiovascular patients using a state-wide hospital admission data registry to natural compounds testing in in vivo and in vitro models. Davit’s research at Rutgers School of Pharmacy concentrated on computational methods and visualization of omics data studying the effect of dietary phytochemicals on epigenome, transcriptome and microbiome.
Modern Algorithms for Animal Randomization in Preclinical Studies In both, clinical and preclinical studies randomizing subjects to treatment groups is a key part of the study design. This step minimizes the risk of confounding. For large studies, complete randomization is often enough to ensure that treatment groups are similar. However, for small clinical trials and especially for in vivo studies this approach is riskier. More elaborate randomization techniques can be applied for those studies such as randomized block design. However, the best results are achieved when algorithmic approach to subject allocation is taken. One such approach is based on genetic algorithm that is rooted in Theory of Evolution. The methodology minimizes the fitness function criteria for partitions of a dataset into balanced subgroups. The performance of the algorithm was compared to random allocation and the exhaustive search using synthetic and real-world data. The results showed that experimental groups created by this algorithm were more homogeneous compared those created by exhaustive search. Additionally, this algorithm is significantly less expensive computationally compared to the exhaustive search, and the efficiency gains increase rapidly as the number of subjects and design factors increase. We will discuss the theory behind this approach as well as the extensions and variations of the algorithm such as simulated annealing.
Webinars
Pre-Clinical SIG Webinar: Modern Algorithms for Animal Randomization in Preclinical Studies
Date: Tuesday 18th November 2025 Time: 14:00 - 15:00 GMT | 9:00 - 10:00 EST (US) Location: Online via Zoom Speakers: Davit Sargsyan
Who is this event intended for?: Statisticians and Scientists involved or interested in randomization techniques in pre-clinical and early clinical studies.
What is the benefit of attending?: Hearing about modern randomization methods.
Cost
This webinar is free to both Members of PSI and Non-Members.
In both, clinical and preclinical studies randomizing subjects to treatment groups is a key part of the study design. This step minimizes the risk of confounding. For large studies, complete randomization is often enough to ensure that treatment groups are similar. However, for small clinical trials and especially for in vivo studies this approach is riskier. More elaborate randomization techniques can be applied for those studies such as randomized block design. However, the best results are achieved when algorithmic approach to subject allocation is taken. One such approach is based on genetic algorithm that is rooted in Theory of Evolution. The methodology minimizes the fitness function criteria for partitions of a dataset into balanced subgroups. The performance of the algorithm was compared to random allocation and the exhaustive search using synthetic and real-world data. The results showed that experimental groups created by this algorithm were more homogeneous compared those created by exhaustive search. Additionally, this algorithm is significantly less expensive computationally compared to the exhaustive search, and the efficiency gains increase rapidly as the number of subjects and design factors increase. We will discuss the theory behind this approach as well as the extensions and variations of the algorithm such as simulated annealing.
Speaker details
Speaker
Biography
Abstract
Davit Sargsyan, Johnson & Johnson
Davit Sargsyan is an associate director in a nonclinical statistics group at J&J Innovative Medicine, mainly supporting Immunology Discover R&D. He received an MS in statistics and completed his PhD in pharmaceutical sciences at Rutgers University. To date, Davit has co-published over 70 scientific articles in peer-reviewed journals on topics ranging from clinical outcomes of cardiovascular patients using a state-wide hospital admission data registry to natural compounds testing in in vivo and in vitro models. Davit’s research at Rutgers School of Pharmacy concentrated on computational methods and visualization of omics data studying the effect of dietary phytochemicals on epigenome, transcriptome and microbiome.
Modern Algorithms for Animal Randomization in Preclinical Studies In both, clinical and preclinical studies randomizing subjects to treatment groups is a key part of the study design. This step minimizes the risk of confounding. For large studies, complete randomization is often enough to ensure that treatment groups are similar. However, for small clinical trials and especially for in vivo studies this approach is riskier. More elaborate randomization techniques can be applied for those studies such as randomized block design. However, the best results are achieved when algorithmic approach to subject allocation is taken. One such approach is based on genetic algorithm that is rooted in Theory of Evolution. The methodology minimizes the fitness function criteria for partitions of a dataset into balanced subgroups. The performance of the algorithm was compared to random allocation and the exhaustive search using synthetic and real-world data. The results showed that experimental groups created by this algorithm were more homogeneous compared those created by exhaustive search. Additionally, this algorithm is significantly less expensive computationally compared to the exhaustive search, and the efficiency gains increase rapidly as the number of subjects and design factors increase. We will discuss the theory behind this approach as well as the extensions and variations of the algorithm such as simulated annealing.
Careers Meetings
Pre-Clinical SIG Webinar: Modern Algorithms for Animal Randomization in Preclinical Studies
Date: Tuesday 18th November 2025 Time: 14:00 - 15:00 GMT | 9:00 - 10:00 EST (US) Location: Online via Zoom Speakers: Davit Sargsyan
Who is this event intended for?: Statisticians and Scientists involved or interested in randomization techniques in pre-clinical and early clinical studies.
What is the benefit of attending?: Hearing about modern randomization methods.
Cost
This webinar is free to both Members of PSI and Non-Members.
In both, clinical and preclinical studies randomizing subjects to treatment groups is a key part of the study design. This step minimizes the risk of confounding. For large studies, complete randomization is often enough to ensure that treatment groups are similar. However, for small clinical trials and especially for in vivo studies this approach is riskier. More elaborate randomization techniques can be applied for those studies such as randomized block design. However, the best results are achieved when algorithmic approach to subject allocation is taken. One such approach is based on genetic algorithm that is rooted in Theory of Evolution. The methodology minimizes the fitness function criteria for partitions of a dataset into balanced subgroups. The performance of the algorithm was compared to random allocation and the exhaustive search using synthetic and real-world data. The results showed that experimental groups created by this algorithm were more homogeneous compared those created by exhaustive search. Additionally, this algorithm is significantly less expensive computationally compared to the exhaustive search, and the efficiency gains increase rapidly as the number of subjects and design factors increase. We will discuss the theory behind this approach as well as the extensions and variations of the algorithm such as simulated annealing.
Speaker details
Speaker
Biography
Abstract
Davit Sargsyan, Johnson & Johnson
Davit Sargsyan is an associate director in a nonclinical statistics group at J&J Innovative Medicine, mainly supporting Immunology Discover R&D. He received an MS in statistics and completed his PhD in pharmaceutical sciences at Rutgers University. To date, Davit has co-published over 70 scientific articles in peer-reviewed journals on topics ranging from clinical outcomes of cardiovascular patients using a state-wide hospital admission data registry to natural compounds testing in in vivo and in vitro models. Davit’s research at Rutgers School of Pharmacy concentrated on computational methods and visualization of omics data studying the effect of dietary phytochemicals on epigenome, transcriptome and microbiome.
Modern Algorithms for Animal Randomization in Preclinical Studies In both, clinical and preclinical studies randomizing subjects to treatment groups is a key part of the study design. This step minimizes the risk of confounding. For large studies, complete randomization is often enough to ensure that treatment groups are similar. However, for small clinical trials and especially for in vivo studies this approach is riskier. More elaborate randomization techniques can be applied for those studies such as randomized block design. However, the best results are achieved when algorithmic approach to subject allocation is taken. One such approach is based on genetic algorithm that is rooted in Theory of Evolution. The methodology minimizes the fitness function criteria for partitions of a dataset into balanced subgroups. The performance of the algorithm was compared to random allocation and the exhaustive search using synthetic and real-world data. The results showed that experimental groups created by this algorithm were more homogeneous compared those created by exhaustive search. Additionally, this algorithm is significantly less expensive computationally compared to the exhaustive search, and the efficiency gains increase rapidly as the number of subjects and design factors increase. We will discuss the theory behind this approach as well as the extensions and variations of the algorithm such as simulated annealing.
Upcoming Events
PSI Training Course: Effective Leadership – the keys to growing your leadership capabilities
This course will consist of three online half-day workshops. The first will be aimed at building trust, the backbone of leadership and a key to becoming effective. This is key to building a solid foundation.
The second will be on improving communication as a technical leader. This workshop will focus on communication strategies for different stakeholders and will involve tips on effective communication and how to develop the skills of active listening, coaching and what improv can teach us about good communication.
The final workshop will bring these two components together to help leaders become more influential. This will also focus on how to use Steven Covey’s 7-Habits, in particular Habits 4, 5 and 6, which are called the habits of communication.
The workshops will be interactive, allowing you to practice the concepts discussed. There will be plenty of time for questions and discussion. There will also be reflective time where you can think about what you are learning and how you might experiment with it.
PSI Introduction to Industry Training (ITIT) Course - 2026/2027
An introductory course giving an overview of the pharmaceutical industry and the drug development process as a whole, aimed at those with 1-3 years' experience. It comprises of six 2-day sessions covering a range of topics including Research and Development, Toxicology, Data Management and the Role of a CRO, Clinical Trials, Reimbursement, and Marketing.
This networking event is aimed at statisticians that are new to the pharmaceutical industry who wish to meet colleagues from different companies and backgrounds.
This webinar brings together three bitesize complementary sessions to help PSI contributors create conference presentations and posters that communicate clearly and inclusively. Participants will explore how to refine their message, prepare materials effectively, and adopt practical habits that support confident, accessible delivery. A focused, supportive session designed to elevate every contribution.
Our monthly webinar series allows attendees to gain practical knowledge and skills in open-source coding and tools, with a focus on applications in the pharmaceutical industry. This month’s session, “Graphics Basics,” will introduce the fundamentals of producing graphics using the ggplot2 package.
Joint PSI/EFSPI Visualisation SIG 'Wonderful Wednesday' Webinars
Our monthly webinar explores examples of innovative data visualisations relevant to our day to day work. Each month a new dataset is provided from a clinical trial or other relevant example, and participants are invited to submit a graphic that communicates interesting and relevant characteristics of the data.
Join our Health Technology Assessment (HTA) European Special Interest Group (ESIG) for a webinar on the strategic role of statisticians in the Joint Clinical Assessment (JCA). The introduction of the JCA marks a new era for evidence generation and market access in Europe. As HTA requirements become more harmonized and methodologically demanding, the role of statisticians has evolved far beyond data analysis. Today, statistical expertise is central to shaping clinical development strategies, designing robust comparative evidence, and ensuring that submissions withstand the scrutiny of EU-level assessors. In this webinar, we explore how statisticians contribute strategically to successful JCA outcomes.
Statisticians in the Age of AI: On Route to Strategic Partnership
A 90-minute webinar featuring two case studies from Bayer and Roche demonstrating how statisticians successfully integrated into AI programs, followed by interactive discussion on strategies for elevating statistical expertise in the AI era.
This networking event is aimed at statisticians that are new to the pharmaceutical industry who wish to meet colleagues from different companies and backgrounds.
This networking event is aimed at statisticians that are new to the pharmaceutical industry who wish to meet colleagues from different companies and backgrounds.
This networking event is aimed at statisticians that are new to the pharmaceutical industry who wish to meet colleagues from different companies and backgrounds.
GSK - Statistics Director - Vaccines and Infectious Disease
We are seeking an experienced and visionary Statistics Director to join our Team and lead strategic statistical innovation across GSK’s Vaccines and Infectious Disease portfolio.
As a Senior Biostatistician I at ICON, you will play a pivotal role in designing and analyzing clinical trials, interpreting complex medical data, and contributing to the advancement of innovative treatments and therapies.
As a Statistical Scientist at ICON, you will play a pivotal role in designing and analyzing clinical trials, interpreting complex medical data, and contributing to the advancement of innovative treatments and therapies.
We have an exciting opportunity for an Associate Director, Biostatistics to join a passionate team within Advanced Quantitative Sciences – Full Development.
: We have an exciting opportunity for an Associate Director (AD), Statistical Programming, to join a passionate team within Advanced Quantitative Sciences- Development.
Novartis - Senior Principal Statistical Programmer
We have an exciting opportunity for a Senior Principal Statistical Programmer, to join a passionate team within Advanced Quantitative Sciences – Development.
Pierre Fabre - Clinical Development Safety Statistics Expert M/F
We are seeking a highly skilled and proactive Clinical Development Safety Statistics Expert to join our Biometry Department and the Biometry Leadership Team based in Toulouse (31, Oncopole) or Boulogne (92).
Pierre Fabre - Lead Statistician- Clinical Trials M/F
We are seeking a highly skilled and experienced Lead Statistician in Clinical Trials to join our Biometry Department based in Toulouse (31, Oncopole) or Boulogne (92).
We are looking for Senior Statistical Programmers in the UK to join Veramed, where you'll deliver high-impact programming solutions in an FSP-style capacity, while advancing your career in a supportive, growth-driven environment.
