West Coast Augmented Intelligence in Drug Discovery Xchange
San Francisco
30 September, 2022

Welcome to hubXchange’s West Coast Augmented Intelligence (AI) in Drug Discovery Xchange 2022, bringing together executives from pharma and biotech to address and find solutions to the key issues faced in AI-led drug discovery.
Discussion topics will cover Data Quality, Target Identification, Lead Generation, Lead Optimization and Drug Response Prediction.
Take advantage of this unique highly interactive meeting format designed for maximum engagement, collaboration and networking with your peers.

NOTE: This will be an In-Person event

VENUE DETAILS: DoubleTree by Hilton San Francisco Airport Hotel, 835 Airport Blvd., Burlingame CA 94010-9949

Data Quality

Time

Titles and Bullets

Facilitator

8:00 – 8:30am

Registration

8:30 – 9:00am

Opening Address & Keynote Presentation

Finding a needle in the haystack: Using AI to increase the probability of technical success in drug development

Hindsight is said to be 20/20. What if we could bring future clinical insight into today’s pre-clinical stages? What if patient-drug response data combinations were used to inform development decisions? What if we could more effectively find that needle in a haystack?

The anticipated variation of patient heterogeneity plays a significant role in the complexity and efficacy of the drug development process. This presentation provides a vision for how to leverage AI to bring valuable and relevant patient-centric information into the pre-clinical drug development process stages to increase the probability of success.

Pamela Bush

SVP, Predictive Oncology

Pamela A. Bush, Ph.D., has over 20 years of experience in venture creation, finance and business development in the life sciences industry. Dr. Bush is the Senior Vice President of Strategic Sales and Business Development at Predictive Oncology (POAI) where she leads activities across the portfolio. Prior to joining POAI, Dr. Bush worked at Eli Lilly & Company in various functions including corporate business development, finance and patient services. In addition, she has worked in business consulting and economic development supporting the creation and growth of 80+ life sciences start-ups. Dr. Bush holds a Ph.D. in Molecular Biology and an MBA from the Tepper School of Business at Carnegie Mellon University.

9:05 – 10:05am

The challenges of inefficient data integration – what methods can be used to ensure the integration of more data?

Share examples where data integration challenges are getting in the way or holding us back
Explore both technical and human approaches to solve these challenges
What key challenges have you faced, and solutions you’ve found?
Thoughts on green field vs. evolutionary approaches to achieve data integration – and how to deal with legacy and technical debt

Dana Caulder

Executive Director of Research Informatics & Software Engineering, Genentech

Dana leads the Research Informatics & Software Engineering department within Genentech Research & Early Development (gRED). Her team of engineers, scientists, business analysts and project managers develop, implement and support informatics solutions that enable drug discovery and development processes within Genentech Research and across its interfaces. Dana received her PhD in Chemistry at UC Berkeley and completed a postdoc at Lawrence Berkeley National Lab. Dana joined Genentech in 2008, and every day works with incredibly talented and passionate people to solve hard problems to make a difference in people’s lives.

10:10 – 10:40am

1-2-1 Meetings / Networking Break

10:40 – 11:10am

1-2-1 Meetings / Networking Break

11:10-11:20 am

Morning Refreshments

11:20 am-12:20 pm

Building and maintaining quality data sets for cutting-edge analytics

The central role of ontologies in data harmonization efforts
Semantic enrichment of unstructured data sources
Finding meaningful information and relationships in free-text documents
Data quality requirements and gold set creation for advanced analytics and ML model training

Thomas Woodcock

Technical Consultant, SciBite

Thomas (Tom) Woodcock is a Technical Consultant with SciBite and former Data Science Consultant in Elsevier’s Professional Services group. Tom is an accomplished data scientist offering 20+ years’ experience in biological and pharmaceutical science. He brings specialist scientific domain experience together with comprehensive data science skills to design and implement both large and small scale projects for our customers. His skills include predictive modeling, data mapping, competitive analysis, and data analysis. In this capacity he leverages a variety of SciBite technologies as well as SQL, PHP, Java, Python, KNIME, and data mining. Tom holds a Ph.D. in Pharmaceutical Sciences University of Kentucky, and a Master of Science in Molecular And Cellular Biology University of Bath.

12:20-1:20 pm

Networking Lunch

1:20-1:50 pm

Spotlight Presentation:

Closed-loop drug discovery: Combining wet lab automation and Machine Learning for accelerated program progression from target to hit, lead, and candidate

Drug discovery is powered by the Design-Make-Test-Analyze cycle
Right now, cycle times are long, and only a fraction of drug-like chemical space is being evaluated
Combining wet lab automation with Machine Learning allows us to close the loop, with rapid data generation synergizing with a more efficient exploration of a wider chemical space
This enables an accelerated progression from target to high-quality hit, lead, and candidate

Drug discovery is powered by the Design-Make-Test-Analyze cycle. Right now, cycle times in the industry are long, and only a fraction of drug-like chemical space is being evaluated, with suboptimal chemical design choices driving clinical failure. Computational approaches can help, but availability of and access to high-quality data is the bottleneck. Combining wet lab automation with Machine Learning allows us to close the loop, with rapid data generation powered by robotics synergizing with a more efficient exploration of a wider chemical space. Taken together, we can significantly accelerate the progression from target to high-quality hit, lead, and candidate molecules towards the clinic.

Martin-Immanuel Bittner

CEO, Arctoris

Martin-Immanuel Bittner MD DPhil FRSA is the CEO of Arctoris, a biotech company combining automated wet lab operations and machine learning for accelerated small molecule discovery. Martin graduated as a medical doctor in Germany, followed by his DPhil in Oncology as a Rhodes scholar at the University of Oxford, where he co-founded Arctoris. He has extensive research experience covering both clinical trials and preclinical drug discovery, is an elected member of the Young Academy of the German National Academy of Sciences and of Sigma Xi, and has been named Innovator of the Year in Biotechnology 2020 by SBR.

Presentation title:

Closed-loop drug discovery: Combining wet lab automation and Machine Learning for accelerated program progression from target to hit, lead, and candidate

3:00-3:30 pm

1-2-1 Meetings / Networking Break

3:30-4:00 pm

1-2-1 Meetings / Networking Break

4:00-4:10 pm

Afternoon Refreshments

4:10-4:40 pm

Poster presentation “De-Risking” Predictive ML with Indisputable Data Quality

Predictive models used in drug discovery require a viable level of data quality. A faulty model can lead to completely off-the-mark predictions and sunk project costs.
In sharp contrast, much of the available biomedical data is unstructured and prone to errors due to varying experimental protocols (incomplete metadata information, missing annotations, inconsistent file formats)
To ensure their datasets are ML-Ready, R&D teams must set up a system that continuously assesses and iterates on the data and metadata quality.
This session will demonstrate Elucidata’s data quality assessment approach, which ensures an input dataset is standardized, and has accurate, complete and a breadth of metadata information before it is considered model quality.

Abhishek Jha

CEO & Co-Founder, Elucidata

Dr. Abhishek Jha was an early member of the platform team at Agios Pharmaceuticals and supported multiple drug discovery programs, two of which have been approved by the FDA. As a founder of Elucidata, he is committed to building a transformative biotech company for the future that will provide clean and linked machine learning-ready data at every stage of drug discovery.

5:45-6.45 pm

Closing Address & Canape/Drinks Reception

Target Identification

Time

Titles and Bullets

Facilitator

8:00 – 8:30am

Registration

8:30 – 9:00am

Opening Address & Keynote Presentation

Finding a needle in the haystack: Using AI to increase the probability of technical success in drug development

Pamela Bush

SVP, Predictive Oncology

9:05 – 10:05am

Machine Learning for Accelerating Target Identification: Costs and Benefits

Training Data: The challenge of insufficient true positives.
Feature Selection: What exactly are we trying to learn? What questions are we asking with ML?
The benefits of embedding ML approaches within “full-stack” drug discovery teams, versus ML alone.
Real-world examples of ML for target ID.

Victor Hanson-Smith

PhD Head of Computational Biology Verge Genomics

Victor Hanson-Smith, PhD, leads a world-class team of computational biologists to discover new drugs for neurodegenerative diseases, including ALS and Parkinson’s Disease. His team’s work combines a wide range of methods, including genomics, systems biology, machine learning, and supercomputing. Prior to joining Verge Genomics, Victor completed his PhD in computer science at the University of Oregon, and a post-doctoral fellowship at University of California San Francisco. He has published extensively on topics related to eukaryotic genome function and evolution.

10:10 – 10:40am

1-2-1 Meetings / Networking Break

10:40-11:10 am

1-2-1 Meetings / Networking Break

11:10-11:20 am

Morning Refreshments

11:20am – 12:20pm

Data utilization and challenges for Target ID & Credentialing

Siloed nature of OMICs data
Limited clinical data availability
Approaches for credentialing targets

Chandra Sekhar Pedamallu

Ph.D., FSRB Assoc. Vice President – Bioinformatics, Excelra

Chandra Sekhar Pedamallu comes with extensive experience in Bioinformatics and Computational Biology
specializing in cancer genomics. Before joining Excelra, Chandra was associated with Sanofi Inc., identifying novel
drug targets in Oncology (Molecular and Immuno-oncology). Prior to Sanofi, he was at Dr. Meyerson Lab,
Dana-Farber Cancer Institute, and a visiting scientist at The Broad Institute of MIT and Harvard. During his 6-year
tenure at Harvard, he led microbial analysis, pathogen discovery projects in cancer and other diseases. He has
contributed substantially to over a dozen projects under the auspices of the Cancer Genome Atlas (TCGA).

Chandra holds a Ph.D. in Systems Engineering (area of research : Global Optimization) from School of Mechanical
and Aerospace Engineering, Nanyang Technological University, Singapore. He has co-authored over 80
manuscripts, published in highly reputed journals including Nature, Nature Genetics, Science, Cell, PNAS, etc., and
has been inducted as a Fellow of the Royal Society of Biology (FRSB).

12:20-1:20 pm

Networking Lunch

1:20-1:50 pm

Spotlight Presentation:

Closed-loop drug discovery: Combining wet lab automation and Machine Learning for accelerated program progression from target to hit, lead, and candidate

Drug discovery is powered by the Design-Make-Test-Analyze cycle
Right now, cycle times are long, and only a fraction of drug-like chemical space is being evaluated
Combining wet lab automation with Machine Learning allows us to close the loop, with rapid data generation synergizing with a more efficient exploration of a wider chemical space
This enables an accelerated progression from target to high-quality hit, lead, and candidate

Martin-Immanuel Bittner

CEO, Arctoris

1:55-2:55 pm

Discovering novel drug targets using AI

Define the scope of target discovery and the application of AI?
How accurate are current models for disease pathways- can we confidently predict the outcomes of pathway perturbation?
Discuss how an understanding of disease biology will serve as the main component to AI- allowing the model to highlight drug targets for R&D focus
Explore the communications gaps between domain experts and data scientists to ensure that data collection and AI model selection are fit-for-purpose
Discuss the current landscape of knowledge graph application in pathway modelling

Ali Zarrin

Senior Director, Immunology Discovery
Trex Bio

Ali Zarrin obtained his Ph.D. from University of Toronto in Immunology and then did his postdoctoral study with Fred Alt at Harvard University. He joined Genentech in August 2007 where he led several initiatives to screen and advance multiple therapeutic programs covering diverse pathways in inflammatory and autoimmune indications. Since August 2019, he is currently the senior director of discovery in TRex Bio responsible for target discovery and preclinical therapeutic development in cancer, inflammatory and autoimmune diseases.

3:00-3:30 pm

1-2-1 Meetings / Networking Break

3:30-4:00 pm

1-2-1 Meetings / Networking Break

4:00-4:10 pm

Afternoon refreshments

4:45-5:45 pm

Mining of literature using NLP techniques

Using NLP technologies to mine biomedical literature to support your target identification research projects
Major databases/public data sources you use for drug target identification
The use of text mined output and integrate data from different sources?

Bing Chen

Senior Principal AI Data Scientist, Genentech

Bing Chen, Ph. D., Senior Principal Data Scientist and leads the AI & Analytics Technologies team in DevSci Informatics, Development Sciences, Genentech. Bing and his team are developing and deploying cutting edge AI and analytics algorithms and models to enable translational insight and knowledge discovery. Bing has more than 20 years of data science and informatics experiences in the Biotech and Pharmaceutical Industries.

5:45-6.45 pm

Closing Address/ Canape/ Drinks Reception

Lead Generation

Time

Titles and Bullets

Facilitator

8:00 – 8:30am

Registration

8:30 – 9:00am

Opening Address & Keynote Presentation

Finding a needle in the haystack: Using AI to increase the probability of technical success in drug development

Pamela Bush

SVP, Predictive Oncology

9:05 – 10:05am

How can artificial intelligence accelerate drug discovery and development?

Massively multitask machine learning methods such as stacked models (Alchemite, pQSAR), MT-DNNs (MELLODDY), meta-learners (metaNN) and matrix factorization (Macau, IMC) can predict IC50s as accurate as 4-concentration medium-throughput-screening experiments for the majority of bioactivity models. This has many applications in drug discovery: virtual screening for hit-finding, off-target toxicity and promiscuity predictions for hit-to-lead and lead optimization, polypharmacology and selectivity prediction, mechanism-of-action prediction, etc.

How many drug discovery groups are using these powerful technologies? What are some examples of success.
What are the limitations?
Why aren’t more groups using it?

Eric Martin

Director, Computational Chemistry, Novartis

Eric Martin has a Ph.D. in physical-organic chemistry from Yale University. He has worked in computational drug design and herbicide design for over 35 years. He is currently developing novel methodologies for two areas of drug discovery:
1) developing “Profile-QSAR”, a massively multitask machine learning method that builds experimental-quality virtual screening models for over 8000 IC50 assays, and
2) “rational oral bioavailability design” during lead optimization by applying machine learning and global sensitivity analysis to physiologically-based pharmacokinetics simulations.
For the former, Eric was awarded the lifetime title of “Novartis Leading Scientist”.

10:10 – 10:40am

1-2-1 Meetings / Networking Break

10:40-11:10 am

1-2-1 Meetings / Networking Break

11:10-11:20 am

Morning Refreshments

12:20 – 1:20pm

Networking Lunch

1:20 – 1:50pm

Spotlight Presentation

Closed-loop drug discovery: Combining wet lab automation and Machine Learning for accelerated program progression from target to hit, lead, and candidate

Drug discovery is powered by the Design-Make-Test-Analyze cycle
Right now, cycle times are long, and only a fraction of drug-like chemical space is being evaluated
Combining wet lab automation with Machine Learning allows us to close the loop, with rapid data generation synergizing with a more efficient exploration of a wider chemical space
This enables an accelerated progression from target to high-quality hit, lead, and candidate

Martin-Immanuel Bittner

CEO, Arctoris

1:55-2:55 pm

Generative and predictive models for lead generation in biologics

Data generation for training predictive and generative models of biologics
Scalability for in silico design campaigns
Federated Learning
Active Learning and Bayesian Optimization

Christopher James Langmead

Director of Digital Biologics Discovery Center for Research Acceleration by Digital Innovation (CRADI) Amgen

Christopher James Langmead is the Director of Digital Biologics Discovery at Amgen. His team has developed a platform for the generative design and optimization of biologics using AI/ML to drive wet-lab experiments. Prior to joining Amgen, Dr. Langmead was a tenured professor in the School of Computer Science at Carnegie Mellon University where his research group developed a variety of methods for algorithmic experimental design and the generative modeling of proteins, including the GREMLIN algorithm which was subsequently integrated into the Rosetta ecosystem. He was also a founding faculty member of CMU’s Computational Biology Department and its associated graduate programs.

3:00-3:30 pm

1-2-1 Meetings / Networking Break

3:30-4:00 pm

1-2-1 Meetings / Networking Break

4:00-4:10 pm

Afternoon Refreshments

4:10-4:40 pm

Poster session Hit finding and lead generation with structure-guided deep generative modeling

AI and ML have enormous potential for accelerating hit discovery efforts, providing an alternative and complementary approach to library screening (both physical and virtual).
By applying our AI/ML tools to a structure-based drug design project, we have used a single PDB data point to discover novel hits comprising 3 unique scaffolds, 2 of which had sub-micromolar activity.
During hit-discovery, our partner Oncodesign only had to synthesize 12 molecules through 3 iterations, representing enormous time, effort, and cost saving for drug discovery efforts.
In this project we applied our generative AI technology for de novo design (Makya) along with our structure-based drug design pipeline to the published PIM-1 structure. Our computer-aided retrosynthesis planning tool Spaya was deployed to ensure only practical and easy-to-synthesize molecules were generated.
AI/ML tools enhance human experts, enabling them to focus on the most important aspects of their work, make better-informed decisions for their projects, and delegate work to the computer systems to save time, effort, and money. This approach has been successfully applied to our own internal projects, research collaborations with industry and academia partners, and for customers who have licensed our software tools for internal use.

Brian Atwood

Application Scientist, Iktos

Brian Atwood is a synthetic organic chemist by training. He completed his PhD in 2018 under the direction of Chris Vanderwal at UCI. His doctoral work centered around the total synthesis of two natural products: a polychlorinated marine metabolite and a pyrrole-containing alkaloid. He then moved to UCLA to conduct postdoctoral work in the lab of Mike Jung, contributing to a variety of medicinal chemistry projects. Brian joined the Iktos team in 2020 to support US operations, applying his extensive training in synthetic planning to the development and implementation of Spaya and the Spaya API.

5:45-6.45 pm

Closing Address/ Canape/ Drinks Reception

Lead Optimization

Time

Titles and Bullets

Facilitator

8:00 – 8:30am

Registration

8:30 – 9:00am

Opening Address & Keynote Presentation

Finding a needle in the haystack: Using AI to increase the probability of technical success in drug development

Pamela Bush

SVP, Predictive Oncology

10:10 – 10:40am

1-2-1 Meetings / Networking Break

10:40-11:10 am

1-2-1 Meetings / Networking Break

11:10-11:20 am

Morning Refreshments

11:20 am-12:20 pm

Collaborative Drug Discovery Data, Models, and Application

What are the areas in drug discovery where clean data is most lacking?
How do we harmonize disparate data formats from different sources?
How can data be stored and organized for maximum utility AND security?

Barry Bunin

CEO and Board Director, Collaborative Drug Discovery (CDD)

Barry A. Bunin, Ph.D. is the CEO of Collaborative Drug Discovery, and has overseen $50 million in business transactions over the last two decades. Prior to CDD, he was an Entrepreneur in Residence with Eli Lilly & Co. Dr. Bunin is on a patent for Kyprolis™ (Carfilzomib for Injection) — a selective proteasome inhibitor that received accelerated FDA approval for the treatment of patients with multiple myeloma that was widely viewed as the centerpiece of Amgen’s $10.4 Billion acquisition of Onyx Pharmaceuticals.
Dr. Bunin was the founding CEO, President, & CSO of Libraria (now Eidogen-Sertanty). At Libraria, he led a team that integrated exhaustive reaction capture with gene-family wide SAR capture. He co-authored “Chemoinformatics: Theory, Practice, and Products”, a text that overviews modern chemoinformatics technologies, and “The Combinatorial Index”, a widely used text on high-throughput chemical synthesis.
In the lab, Dr. Bunin did medicinal synthetic chemistry developing patented new chemotypes for protease inhibition at Axys Pharmaceuticals (now Celera) and RGD mimics to inhibit GP-IIbIIIa at Genentech. Dr. Bunin received his B.A. from Columbia University and his Ph.D. from UC Berkeley, where he synthesized and tested the initial 1,4-benzodiazepine libraries with Professor Jonathan Ellman.

12:20-1:20 pm

Networking Lunch

1:20 – 1:50pm

Spotlight Presentation

Closed-loop drug discovery: Combining wet lab automation and Machine Learning for accelerated program progression from target to hit, lead, and candidate

Drug discovery is powered by the Design-Make-Test-Analyze cycle
Right now, cycle times are long, and only a fraction of drug-like chemical space is being evaluated
Combining wet lab automation with Machine Learning allows us to close the loop, with rapid data generation synergizing with a more efficient exploration of a wider chemical space
This enables an accelerated progression from target to high-quality hit, lead, and candidate

Martin-Immanuel Bittner

CEO, Arctoris

1:55 – 2:55pm

Use of AI/ML in lead optimization

Impact of ML-models of phys-chem properties
Bringing structural information into AI workflows
Generative versus exhaustive compound enumeration methods

Uli Schmitz

Executive Director, Structural Chemistry, Gilead

Uli Schmitz is a member of Gilead Sciences’ Research’s Senior Leadership Team and the Executive Director in Structural Biology and Chemistry. Originally trained as an organic chemist at the RWTH Aachen, his interest in biomolecular structure drew him to UCSF, where he spent over a decade as Adjunct Faculty in the Pharmaceutical Chemistry Department working on solution structure determination and modeling of nucleic acid protein complexes. Following his desire to use structures toward discovering new drug, he joined a small biotech, Genelabs, which initially focused on nucleic acid-based drug discovery. After Genelabs was acquired by GSK, he joined Gilead where he has been heading the modeling group for over 13 years.

3:00-3:30 pm

1-2-1 Meetings / Networking Break

3:30-4:00 pm

1-2-1 Meetings / Networking Break

4:00-4:10 pm

Afternoon Refreshments

4:10-4:40 pm

Lowering the Barrier of Building Machine Learning Models for Drug Discovery Projects
with the help of Change Management Approaches

Learn how to create impactful Kp machine learning models and ensure early adoption
into your daily workflows
• We will share our experience working on a machine-learning model using data from
Reaxys database – curated data from published sources
• Find out how to optimize model development through a cross-functional/organizational
team approach and how Elsevier can supplement your efforts with data, support and
services to enable an end-to-end development and deployment of machine-learning
models

Aurora Costache

Customer Engagement Manager – Life Sciences Professional Services Group, Elsevier

Aurora is a technology and life sciences professional with over 12 years of
experience in data management and analysis software solutions for pharma
and biotech industries. A well-rounded scientist with a Ph.D. in organic
chemistry focused on cheminformatics, she interacted directly with clients
throughout her career in both scientific and business activities. With her
ProSci change management certification, Aurora supports Elsevier’s clients
and engage with them to navigate successfully through individual and
organizational digital transformations, using Elsevier’s data assets to build
AI/ML predictive models.

4:45-5:45 pm

Best practice in multiple parameter optimization by combining generative AI with physics/non-physics based approaches to optimize binding affinity, ADMET that leads to a drug candidate

Best practices for use of generative models for multiparameter optimization
Combining AI/ML approaches with physics-based methods for LO
How can we improve ADMET models?
Using deep learning in low-data situations, for both small molecules and biologics

Alan Cheng

Director, Merck & Co. research laboratories

Alan Cheng is a Director at the Merck & Co. research laboratories in South San Francisco, where he manages a group working on the discovery of small molecule and biologics therapeutics using biophysical modeling, informatics, and machine learning approaches. Previously, he was at Amgen for 11 years, and Pfizer for 5 years. He has contributed to over five clinical molecules and is an author or co-inventor on over 70 peer-reviewed publications and patents. He received his Ph.D. at UCSF in Biophysics, and his undergraduate degrees at UC Berkeley in Electrical Engineering & Computer Science, and Molecular and Cellular Biology. He also currently chairs the Bioinformatics M.S. program at Brandeis University.

5:45-6:45 pm

Closing Address & Canape/Drinks Reception

Drug Response Prediction

Time

Titles and Bullets

Facilitator

8:00 – 8:30am

Registration

8:30 – 9:00am

Opening Address & Keynote Presentation

Finding a needle in the haystack: Using AI to increase the probability of technical success in drug development

Pamela Bush

SVP, Predictive Oncology

9:05 – 10:05am

Mirroring Real Patients? – Can Machine Learning Methods Provide Insights & Predictions for Cancer Drug Response? Comparing AI techniques & ML algorithms that guide drug development

Current practice for applying machine learning in patient response prediction
Challenges for applying machine learning to predict patient response
Opportunities emerging in predicting patient response

Ning Wang

Bioinformatics Scientist Lead, Bioinformatics Lead on Immuno-Oncology Drug Development
Arcus Biosciences

Ning is a bioinformatics scientist at Arcus Biosciences, where he is responsible for drug discovery, target identification, and indication prioritization in multiple immune-oncology drug programs. Notably, Ning pioneered the 3D organoids based drug response prediction technology, which largely facilitated cancer model selection. During his PhD, he studied with Professor Alexander Hoffmann at UCLA, where he built up computational framework to identify synergy between key immune response signaling pathways in macrophage. Ning holds a PhD in Bioinformatics from UCLA.

10:10-10:40 am

1-2-1 Meetings / Networking Break

10:40 – 11:10am

1-2-1 Meetings / Networking Break

11:10-11:20 am

Morning Refreshments

1:20-1:50 pm

Networking Lunch

12:50 – 1:50pm

Spotlight Presentation

Closed-loop drug discovery: Combining wet lab automation and Machine Learning for accelerated program progression from target to hit, lead, and candidate

Drug discovery is powered by the Design-Make-Test-Analyze cycle
Right now, cycle times are long, and only a fraction of drug-like chemical space is being evaluated
Combining wet lab automation with Machine Learning allows us to close the loop, with rapid data generation synergizing with a more efficient exploration of a wider chemical space
This enables an accelerated progression from target to high-quality hit, lead, and candidate

Martin-Immanuel Bittner

CEO, Arctoris

1:55-2:55 pm

Applications of AI to patient segmentation and drug response prediction

Share examples of success stories in the applications of AI for drug development and clinical studies.
Explore opportunities for predictive sciences, clinical study design for better outcomes, and virtual trials.
Survey the state of actional data for AI in the pharma industry and discuss what we can do to power clinical decision making and improve PTS.
Discuss cultural readiness and challenges in our endeavors

Hongmei Huang

Vice President, Development Sciences Informatics, Genentech

By connecting science and technology, Hongmei Huang leads organizational drives to transform the data and digital landscape for the advancement of medicines and healthcare. She is an accomplished scientific and informatics leader with over 25 years of experience in the Pharmaceutical Biotech Industry. Currently as the Head of Development Sciences Informatics, Hongmei provides strategic leadership for the data ecosystem and AI/ML capabilities for translational sciences. She is among the key leaders for the pan Roche data FAIRification and sharing initiative to power R&D decision making.

3:00-3:30 pm

1-2-1 Meetings / Networking Break

3:30 – 4:00pm

1-2-1 Meetings / Networking Break

4:45-5:45 pm

Enhancing drug response prediction in cancer patients

Historical and novel approaches to determining patient populations
Relevant data needed for response to drug
Outlook on regulatory and clinical application of novel methods

Marvin Gee

VP, Target Discovery & Co-Founder, 3T Biosciences

Marvin Gee is VP of Target Discovery and Co-Founder at 3T Biosciences, where he is responsible for leading target discovery and computation. He received his PhD in Immunology with an additional focus in Computational Immunology at Stanford University. He published his main work on novel technology to identify the specificities of T- cell receptors for applications in oncology and further work on characterizing the structural basis of T- cell receptor recognition of immunological targets and T cell receptor cross-reactivity. He has had prior work experience engineering T cell receptors for adoptive T cell therapy. Marvin has been featured in Forbes 30-under-30 in Healthcare.

5:45-6.45 pm

Closing Address/ Canape/ Drinks Reception

West Coast Augmented Intelligence in Drug Discovery Xchange San Francisco 30 September, 2022

Data Quality

Partners

West Coast Augmented Intelligence in Drug Discovery Xchange
San Francisco
30 September, 2022