SLAS 2019 AI in Process Automation Symposium: Full Schedule

Go to symposium website → www.slas.org/events/slas-2019-ai-in-process-automation-symposium/

8:00am

Registration Open

Thursday October 3, 2019 8:00am - 5:00pm
5th Floor Corridor - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Registration

8:30am

Welcome Breakfast

Thursday October 3, 2019 8:30am - 9:00am
5th Floor Corridor - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Networking

9:00am

Opening Remarks/Welcome

Chairs

Mike Berke, MS

Director of Research and Automation Technologies, Amgen

Mike is the Director of the Research & Automation Technologies (R&AT) group at Amgen, where he has been for the last 16 years. The R&AT group focuses on developing novel devices and software tools to improve research processes.

Thursday October 3, 2019 9:00am - 9:15am
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Opening/Closing Remarks and Keynote

9:15am

Keynote Address: The Materials for Tomorrow, Today

In this talk, I argue that for materials discovery, one needs to go beyond simple computational screening approaches followed by traditional experimentation. I have been working on the design and implementation of what I call “materials acceleration platforms” (MAPs). MAPs are enabled by the confluence of three disparate fields, namely artificial intelligence (AI), high-throughput quantum chemistry (HTQC), and robotics. The integration of prediction, synthesis and characterization in an AI-driven closed-loop approach promises the acceleration of materials discovery by a factor of 10, or even a 100. I will describe our efforts under the Mission Innovation umbrella platform around this topic.

Speakers

Alán Aspuru-Guzik, University of Toronto

Professor of Chemistry and Computer Science, University of Toronto

Alán Aspuru-Guzik’s research lies at the interface of computer science with chemistry and physics. He works in the integration of robotics, machine learning and high-throughput quantum chemistry for the development of “self-driving laboratories”, which promise to accelerate... Read More →

Thursday October 3, 2019 9:15am - 10:00am
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Opening/Closing Remarks and Keynote

10:00am

Coffee Break

Thursday October 3, 2019 10:00am - 10:15am
5th Floor Corridor - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Networking

10:15am

AI in Drug Discovery Today- Introduction

Chairs

Yohann Potier, Ph.D.

Director of Data Science & Informatics, Voyager Therapeutics

Yohann was recently named Director of Data Science & Informatics at Voyager Therapeutics, after almost six years at the Novartis Institute for Biomedical Research. He studied Biotechnology and Informatics in France followed by a Ph.D. in Computational Chemistry at the University of... Read More →

Thursday October 3, 2019 10:15am - 10:20am
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Session 1: AI in Drug Discovery Today

10:20am

AI in Drug Discovery Today- Artificial and Augmented Intelligence in Early Drug Discovery

Artificial and Augmented Intelligence in Early Drug Discovery:
Drug discovery data continues to grow in size and diversity due to technological advances and automation. Correspondingly, opportunities are emerging for applying machine learning to classification, regression, clustering, prediction, and recommenders, in an effort to make each decision in the process more predictive. Examples are provided of where AI is being applied to support decision-making, ranging from imaging to medicinal chemistry to ‘omics, in addition to implications for changing our approach to data stewardship and data science as a discipline in the pharmaceutical industry.

Speakers

Jeremy Jenkins, PhD

Executive Director, Novartis Institutes for BioMedical Research

Jeremy is Executive Director and Head of Data Science in Chemical Biology & Therapeutics at the Novartis Institutes for BioMedical Research. He joined Novartis 16 years ago, following a postdoc at Harvard Medical School and a PhD in Molecular Genetics from The Ohio State University... Read More →

Chairs

Yohann Potier, Ph.D.

Director of Data Science & Informatics, Voyager Therapeutics

Thursday October 3, 2019 10:20am - 10:40am
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Session 1: AI in Drug Discovery Today

10:40am

AI in Drug Discovery Today- AI-Assisted Antibody Selection: The Application Of Machine Learning To Accelerate The Drug Discovery Process

AI-Assisted Antibody Selection: The Application Of Machine Learning To Accelerate The Drug Discovery Process:
With a 50% failure rate, inappropriate antibodies used in scientific experiments waste millions of research dollars and can delay the drug discovery process by months. Research scientists across industry and academia turn to scientific publications and related original research documents to find evidence for antibodies proven to work in their specific experimental context. However, existing publication and antibody search tools are limited in their ability to decode scientific experiments and scientists are forced to manually comb through hundreds, if not thousands of results, to find the information they need to choose the best antibody for their research.

BenchSci’s AI is trained by Ph.D. researchers in the life sciences to identify which antibodies have been successfully used in specific experimental contexts. Advances in the fields of computation and machine learning paved the way for the development of BenchSci’s proprietary image and text-based machine learning algorithms along with bioinformatics ontologies, to extract relevant experimental data from original research documents. This information is contextualized within a knowledge graph that powers an AI-assisted antibody selection platform, enabling scientists to rapidly select appropriate products, improve the efficiency of target validation experiments and drive projects forward.

Our goal in the development of this technology, is to shorten the R&D and pre-clinical phases by giving research scientists the ability to leverage the power of AI technology to streamline the experimental design process and ultimately bring treatments to market faster.

Speakers

Casandra Mangroo, PhD

Head of Science, BenchSci

Casandra is Head of Science at BenchSci. She applies research experience from her Ph.D. in Virology from the University of Toronto as the Science Team lead and product manager of BenchSci’s knowledge graph. Casandra is closely involved with developing the machine learning training... Read More →

Chairs

Yohann Potier, Ph.D.

Director of Data Science & Informatics, Voyager Therapeutics

Thursday October 3, 2019 10:40am - 11:00am
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Session 1: AI in Drug Discovery Today

11:00am

AI in Drug Discovery Today- Machine Learning Models for High Throughput Microscopy Screening and Large Scale Liability Prediction

AI in Drug Discovery Today:
AI has become a useful tool that can help with the complexity and scale of biology. This track will introduce current uses of AI and machine learning in drug discovery. Experienced speakers will present their work and how they use AI in the context of therapeutic research: different methods can assist answering diverse and complex questions or optimizing everyday research.

Machine Learning Models for High Throughput Microscopy Screening and Large Scale Liability Prediction
As Recursion, we combine AI with large-scale lab automation to discover new medical treatments. Using our automated, high throughput screening (HTS) platform, we run hundreds of thousands of mini-experiments spanning millions of microscopy images - every single week. In this talk, we’ll describe how we use machine learning analytics to make sense of all of this complex data - that is, to identify promising drug compounds while simultaneously avoiding high risk ones. This process relies on sophisticated model development, but also on engineering infrastructure that can handle petabytes of data, as well as on optimizing our HTS experiments to best enable downstream machine learning tasks. Finally, we will show how we are building on our HTS discovery platform to gain deeper insights about drug compounds of interest, for example through by applying generative machine learning models to predict likely downstream liabilities, such as heart and liver toxicities.

Speakers

Lina Nilsson

Senior Director, Data Science Product, Recursion

Lina Nilsson is Senior Director of Data Science Product at Recursion Pharmaceuticals, a company that is reimagining drug discovery through machine learning and large-scale experiment automation. Previously, she was the COO of Enlitic, a startup that uses deep learning to improve clinical... Read More →

Chairs

Yohann Potier, Ph.D.

Director of Data Science & Informatics, Voyager Therapeutics

Thursday October 3, 2019 11:00am - 11:20am
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Session 1: AI in Drug Discovery Today

11:20am

AI in Drug Discovery Today- Applications of Artificial Intelligence in Drug Discovery – Separating Hype From Utility

Applications of Artificial Intelligence in Drug Discovery – Separating Hype From Utility
Artificial intelligence and machine learning are now impacting many aspects of the drug discovery process. One factor driving the rapid adoption of machine learning in drug discovery is the availability of software tools for building machine learning models. Software that was once only available to machine learning researchers is now freely available for download. Organizations such as Facebook, Google, and Amazon are now releasing Open Source software tools for machine learning that can be applied to problems in numerous domains including drug discovery. While these new tools offer an array of opportunities, we must be adequately prepared to use them effectively. Researchers need to have a sufficient command of the underlying science to develop representations that can be processed by machine learning algorithms. Scientists applying machine learning in drug discovery must have sufficient computational skills to be able to adopt and apply these techniques. Finally, researchers must have an understanding of statistics that will enable them to assess and improve the quality of their models.

Ultimately. the success of any predictive model comes down to three factors; data, representation, and algorithms. The data being generated must be relevant, and the experimental error must be well characterized. In order to build a predictive model, we must be able to create a representation of the data, typically as some sort of vector, that can be processed by a machine learning algorithm. The algorithm can then identify relationships between the data and some observable (e.g. biological activity) and can subsequently be used to make predictions on new data.

Speakers

Pat Walters

VP Computation, Relay Therapeutics

Pat Walters heads the Computation & Informatics group at Relay Therapeutics in Cambridge, MA. His group focuses on novel applications of computational methods that integrate computer simulations and experimental data to provide insights that drive drug discovery programs. Prior to... Read More →

Chairs

Yohann Potier, Ph.D.

Director of Data Science & Informatics, Voyager Therapeutics

Thursday October 3, 2019 11:20am - 11:40am
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Session 1: AI in Drug Discovery Today

11:45am

Vendor Snapshot: Exciting New Features in Green Button Go 2019 Automation Scheduling Software

Green Button Go™ Automation Scheduling software integrates equipment from any vendor into a unified lab ecosystem for that can be tailored to your exact workflows. The Green Button Go drag-and-drop user interface allows for easy generation workflow processes to increase productivity and data quality. In addition it supports advanced data aggregation, streaming, and management platforms for your AI, IoT, and Big Data projects, including dynamic workflows that can accept real time feedback to close the loop on the design – build – test – analyze - learn process.
Presenter: David Dambman, Director of Engineering

Sponsors

Biosero

Biosero is Your Automation Software Solution Partner, Enabling Better Decisions Through Data and Advanced Analytics.

Thursday October 3, 2019 11:45am - 12:15pm
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Vendor Snapshot

12:15pm

Exhibition / Networking Lunch

Thursday October 3, 2019 12:15pm - 12:45pm
Washington Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Networking

12:45pm

Focus Groups / Roundtable Discussions

Integrating AI and ML into lab and data processes is more than developing the latest and greatest product — it's also a movement built around discussions, case studies and collaboration.

That's why we're excited to offer an additional interactive AI in Process Automation Symposium opportunity: the Lunchtime Round Table Session.

Topic 1: Applications of ML to "messy" biological problems
Discussion: How to wrangle diverse, unstructured data to best benefit – FAIR, architecture, validation, metadata, etc...

Topic 2: What does the future AI-augmented lab look like?
Discussion: What technologies still need to be developed? What’s the role of internal vs. external (SaaS or contract) research or products to realize this vision?

Thursday October 3, 2019 12:45pm - 2:00pm
Washington Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Networking

2:00pm

Lightning Session- Introduction

Lightning Session:
A series of quick presentations and Q&A designed to highlight new, innovative, real-world work being done with AI in our industry. These 10-minute talks will ignite your thinking on what can be done and how to do it.

Chairs

Mike Berke, MS

Director of Research and Automation Technologies, Amgen

Thursday October 3, 2019 2:00pm - 2:00pm
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Lightning Session

2:00pm

Lightning Session- Rapid Automated Computation, Coupling, Cleavage, Chromatography Execution (RAC4E) Platform Driving Drug Discovery

Rapid Automated Computation, Coupling, Cleavage, Chromatography Execution (RAC4E) Platform Driving Drug Discovery
Synthetic peptide therapeutics have played a notable role in medical advances over the past two decades with a more recent focus on diagnostics and personalized therapeutics, however, the field has struggled with a slow pace of discovery, optimization, and manufacturing due to limitations in the manufacturing processes – coupling, cleavage, and chromatography. Advances in laboratory automation have helped improve the productivity of expert scientists; however, these technologies have not been able to meet the demand for custom peptide sequences to enable rapid, cost-effective drug discovery, especially when compared to DNA synthesis. Inefficient synthesis techniques often take weeks, if not months, to produce the target molecule, becoming a major bottleneck in the drug discovery pipeline. Given that peptides are assembled from one reaction and a discrete number of building blocks, machine learning (ML) has the ability to drastically increase the speed of manufacturing by enabling sequence-specific optimization, significantly reducing the overall drug discovery time.

Mytide’s Rapid Automated Computation, Coupling, Cleavage, and Chromatography Execution (RAC4E) platform takes a holistic approach to peptide manufacturing starting with the use of ML models to inform sequence-specific strategies while closing the loop with data collection at every process step, which feeds back into future synthesis plans. Our solid-phase slug flow (SPSF) technology offers the opportunity to combine real-time process analytics with ML models to provide a tailored coupling process for each and every individual sequence produced. Integrating optimization strategies into RAC4E serves as a foundation for efficient library development, leading the way for direct synthesis to bioassays driving innovation with our collaborators, partners and internal drug discovery pipelines.

Authors: Dale Thomas, PhD; Justin Lummiss, PhD; Kevin Shi, PhD; Chase Olle, MEngM

Speakers

Dale Thomas, PhD

Co-Founder, Mytide Therapeutics

Dale Thomas III, Ph.D. (Co-Founder): he spanned both Mechanical Engineering and Chemical Engineering at MIT. He also completed his MEngM at MIT and BS at Maine Maritime Academy. In his research, he developed an array of flow chemistry platforms for the advanced synthesis of pharmaceuticals... Read More →

Chairs

Mike Berke, MS

Director of Research and Automation Technologies, Amgen

Thursday October 3, 2019 2:00pm - 2:10pm
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Lightning Session

2:10pm

Lightning Session- Analyzing High Content Screening Data using Neuronal Networks

AI and deep learning through neuronal networks have become a staple in today’s data analysis. Especially in image analysis, neuronal networks have become very useful with facial recognition being a prominent example. AI has several strong points over conventional image analysis methods – such as the ability to mimick ability of the human brain/vision allowing for accurate flagging of minor changes that are otherwise hard to isolate through conventional image analysis. The implementation of deep learning from scratch through existing platforms such as Kerus and Tensorflow offers a relatively simple route towards testing the potential of AI in the context of high content screening (HCS). In this talk we will review the general outline of an implementation of Kerus/Tensorflow on a local workstation using Python with a GPU platform to lend computational power. We will further review two projects where AI has been pivotal in insuring success. The first project deals with setting up a platform in C. Elegans with a HCS readout genotoxicity that was easily solvable through conventional HCS analysis like Metamorph because of the lack of ability to capture subtle features. The second project deals with a HCS screen for modulators of host factors that make the cell resistant against a bacterial toxin. Here the subtlety of the phenotype was also difficult to capture using standard image analysis. Importantly, AI identified compounds that were active against the toxin and enabled us to directly translate our findings directly into a pre-clinical model of the disease.

Speakers

Robert D. Damoiseaux, PhD

Professor, Molecular and Medical Pharmacology, UCLA

Dr. Robert Damoiseaux’s main interests are at the interface of chemistry, biology and engineering and include the development of novel assay technology platforms, High Throughput Screening, High Content Screening and nanotechnology. After having earned a Ph.D. degree at the University... Read More →

Chairs

Mike Berke, MS

Director of Research and Automation Technologies, Amgen

Thursday October 3, 2019 2:10pm - 2:20pm
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Lightning Session

2:20pm

Lightning Session- Employing Supervised Learning Methods To Optimize pH Targeting In Chemical Solutions

Employing Supervised Learning Methods To Optimize pH Targeting In Chemical Solutions
Chemical solutions are ubiquitous in research, development and production within the fields of chemistry, biology, pharmaceuticals and many others. The pH of a solution is an essential property to be able to control for a large number of experimental use cases, but that control should not come at any cost: ionic strength and other experimentally-relevant criteria also need to be controlled.

We present LabMinds’s Solution Recipe Platform (SolReP), which was developed using performance data gathered from LabMinds’s Revo (SLAS New Product Award winner, 2016). The aim of the Platform’s continual development is to optimize solution compositions in order to reliably control pH in the presence of varied solution compositions. We can extrapolate control of pH outside of training regions of parameter space, including untrained combinations of chemicals. Our product improves solution composition, bringing a robustness and accuracy that’s often lacking, and with that brings a growing preference for our solution recipes and in turn more data on which to further improve those recipes: a virtuous cycle for all.

We have targeted a core set of buffer systems with pharmaceutically relevant use cases (Acetate, Citrate, Histidine, Phosphate, Tris), across a broad range of concentrations and pHs. The uptake of these solution recipes among our customers have been great, replacing their in-house solution SOPs, where regulations allow. We target an area of pH and concentration space that is larger than simple, popular calculators are suited to and develop our platform using a growing data set that is much larger than an individual scientist can rely on, when developing solution compositions in an ad hoc manner.

Solution recipe compositions have historically been developed by making use of either simple theoretical calculators, commonly with a small region of applicability and little empirical input, or trial-and-error development, at individual points of interest. Our Platform extends the complexity and validity of the calculator approach and introduces a suite of supervised learning methodologies to ensure that continual performance data improves the power of its predictions.

The pH of a solution can be predicted by mechanistic, semi-mechanistic, empirical and model-free approaches. Many of the mechanistic and semi-mechanistic models are a century old and parameters for the few chemical species that have been published are of variable quality. Using supervised learning, we can train these models, empirical models and model-free methodologies to improve their predictive power. Characterizing the identifiability of parameters is necessary both to assess the structural suitability of the models and to aid with experimental design. Parameter identifiability for the mechanistic and semi-mechanistic models can be achieved only by training in regions of pH, ionic-strength and temperature space where the various parameters dominate the dynamics. Unidentifiable parameters do not mean that a model has no predictive power, but reinforces the importance of characterizing the sensitivity of its predictions to those parameters, which we achieved by simulating experiments sampling the posterior distribution.

LabMinds’s SolReP provides a significant step toward a data-centric approach to laboratory work.

Speakers

Ville Lehtonen, MBA, MSci

CEO, LabMinds

Founder and CEO of LabMinds Ltd. MBA from Oxford University, UK and MS Comp Sci from Aalto University, Finland.

Chairs

Mike Berke, MS

Director of Research and Automation Technologies, Amgen

Thursday October 3, 2019 2:20pm - 2:30pm
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Lightning Session

2:30pm

Lightning Session- Data-driven Prediction of Battery Cycle Life Before Capacity Degradation

Data-driven Prediction of Battery Cycle Life Before Capacity Degradation
Accurately predicting the lifetime of complex, nonlinear systems such as lithium-ion batteries is critical for accelerating technology development. However, diverse aging mechanisms, significant device variability and dynamic operating conditions have remained major challenges. We generate a comprehensive dataset consisting of 124 commercial lithium iron phosphate/ graphite cells cycled under fast-charging conditions, with widely varying cycle lives ranging from 150 to 2,300 cycles. Using discharge voltage curves from early cycles yet to exhibit capacity degradation, we apply machine-learning tools to both predict and classify cells by cycle life. Our best models achieve 9.1% test error for quantitatively predicting cycle life using the first 100 cycles (exhibiting a median increase of 0.2% from initial capacity) and 4.9% test error using the first 5 cycles for classifying cycle life into two groups. This work highlights the promise of combining deliberate data generation with data-driven modelling to predict the behavior of complex dynamical systems.

Speakers

Kristen Severson

Postdoc, IBM

Kristen is a post-doc in the Health Analytics Research Group within the Center for Computational Health at IBM Research Cambridge.Her current research focuses on the development and application of machine learning techniques to derive insight from real-world health data. Previously... Read More →

Chairs

Mike Berke, MS

Director of Research and Automation Technologies, Amgen

Thursday October 3, 2019 2:30pm - 2:40pm
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Lightning Session

2:40pm

Lightning Session- An Operational Informatics Platform To Model, Execute, and Refine Laboratory Workflows

An Operational Informatics Platform To Model, Execute, and Refine Laboratory Workflows
In silico techniques, such as cheminformatics and bioinformatics have long been used in drug discovery to help model and better understand the vast array of data that can be generated in drug discovery research, with a view to helping bring more effective drugs to market faster.

However, they have not been able to replace in vitro experiments, which must still be done on a massive scale. The pace of drug discovery research still hinges on the production and supply of various samples, reagents and consumables via automated and manual processes to perform these experiments. As new scientific space is discovered, the variety and complexity of these experiments increases dramatically, making planning of the resources required and the execution of the experiments increasingly difficult, thus creating an operational Big Data bottleneck.

In this presentation we will introduce a new, advanced, cloud-based software platform that utilizes prediction algorithms to visualize and model production laboratory environments, and then also perform the real-life execution of the chosen model, giving real time feedback to help refine it further based on Operational Informatics.

The software can help decide which hardware should be used or obtained; it can optimize the use of samples, reagents and consumables; and also provide information on the amount of human capital or outsourcing required to fulfill a production goal and removing the operational bottleneck.

Key benefits are:
•One single system for the planning and execution of all R&D and Production tasks
•Constant feedback across all levels allows for higher transparency and ability to react quickly to changes
•Integrate with existing systems in terms of horizontal integration and vertical integration
•Platform for continuous improvement of processes & initiatives
Application areas include:
•compound sample management
•high throughput screening
•medicinal chemistry
•cell line production
•clinical trials
•bioprocessing

Speakers

Ben Schenker

Director Life Sciences, Xavo

Drug discovery research is immensely complex and has to constantly adapt to new discoveries in biology and chemistry making it unlike any other industry. My passion and experience over the last 24 years has been about developing and introducing new technologies that help researchers... Read More →

Chairs

Mike Berke, MS

Director of Research and Automation Technologies, Amgen

Thursday October 3, 2019 2:40pm - 2:50pm
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Lightning Session

2:50pm

Lightning Session- Deep Learning Model Development in the AWS Ecosystem

Deep Learning Model Development in the AWS Ecosystem
Deep learning has the potential to help automate many data analysis problems within drug discovery and even more broadly scientific research. In areas such as image analysis where the previous solutions worked only moderately well at best, deep learning can now be applied to solve problems completely and with high performance. Unfortunately, the process of developing deep learning models is a highly custom one, with each use case requiring its own set of data management software and models trained on specific data. There is however quite a bit of commonality that can be abstracted out of the process of deep learning model development and reused across different problems. Amazon Web Services (AWS) is a cloud-based ecosystem of on demand computing resources that provides tools in support of this effort.

As the deep learning model development process requires the manipulation and management of large amounts of data and specialized computing resources, AWS offers an ideal environment for the entire process. We make heavy use of not only the core services inside AWS such as S3 and EC2, but also the fully managed service Amazon SageMaker, which is a complete and customizable machine learning model development tool. SageMaker allows us to collect and label data, and then train and deploy models all in one end to end workflow. This represents a large time savings versus the alternative of setting up our own custom software and infrastructure for each project. SageMaker also provides us with a system to track datasets and models, which saves time for tasks like transfer learning and helps bring order to the whole model development process.

Adopting and leveraging tools like SageMaker and AWS to develop custom models in support of scientific research, changes what was a complex and time intensive process, to one that supports more rapid and scalable implementation. This changes the value proposition in adopting deep learning for scientific research.

Speakers

Steven Van Buskirk

Engineer, Amgen

Steven Van Buskirk is an engineer with over 8 years of biotech experience. At Amgen he is focused on developing deep learning models in support of Discovery Research. Prior to Amgen Steven worked at several biotech start-ups and research labs, including QuantaLife (now Bio-Rad), InDevR... Read More →

Chairs

Mike Berke, MS

Director of Research and Automation Technologies, Amgen

Thursday October 3, 2019 2:50pm - 3:00pm
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Lightning Session

3:00pm

Exhibition & Coffee Reception

Thursday October 3, 2019 3:00pm - 3:30pm
Washington Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Networking

3:30pm

Data Automation- Introduction

Data Automation:
Data is the foundation of AI and the first job of any data scientists using AI as a solution is to build a highly structured dataset. The Data automation track will explore strategies for building new structured datasets or making use of existing data as solutions to AI approaches to drug discovery and drug screening.

Chairs

Jeff Milton

Associate Director, Ionis Pharmaceuticals

Jeff Milton has over 20 years of bioinformatics and software development experience in both academic and industry settings. He began his career at Molecular Simulations Inc (now Biovia) developing bioinformatics tools before the first draft of the Human Genome. In 2005 he moved to... Read More →

Thursday October 3, 2019 3:30pm - 3:35pm
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Session 2: Data Automation

3:35pm

Data Automation- Automatized Workflow, Augmentation And Generation As Solutions To Leverage Data

Automatized Workflow, Augmentation And Generation As Solutions To Leverage Data
For a lot of companies the term "data driven" is still a theoretical concept not always accepted and seldom properly applied. It is a big challenge for everyone to be prepared for this silent revolution. One of the first steps is to rethink our workflows and convert them into "data workflows". In this talk, we will demonstrate how artificial intelligence through augmentation and automatized workflows can help foster our ability in drug or odor discovery. In addition, we will propose a new framework to generate de novo molecules which outperforms state of the art models.

Speakers

Guillaume Godin

scientific director AI, Firmenich SA

Guillaume is Scientific Director in Artificial Intelligence at Firmenich. He joined Firmenich 13 years ago, following a postdoc at Ecole Polytechnic of Lausanne, a PhD in Medicinal Chemistry from The Orleans University and Master in chemical engineer from Mulhouse School. His broad... Read More →

Chairs

Jeff Milton

Associate Director, Ionis Pharmaceuticals

Thursday October 3, 2019 3:35pm - 3:55pm
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Session 2: Data Automation

3:55pm

Data Automation- Privacy Preserving Machine Learning and Analytics

Privacy Preserving Machine Learning and Analytics
One of the key challenges in deploying machine learning (ML) at scale is how to help data owners learn from their data while protecting their privacy. This issue has become more pressing with the advent of regulations such as the General Data Protection Regulation. It might seem as though "privacy-preserving machine learning" would be a self-contradiction: ML wants data, while privacy hides data. Researchers from academia and industry have been marrying ideas from cryptography and machine learning to provide the seemingly paradoxical ability to learn from data without seeing it, and to learn aggregate properties of populations without learning about any particular individual. In this talk we will review three privacy-preserving ML techniques--homomorphic encryption, multi-party computation, and differential privacy--and review the recent rapid progress that has been made in all three as they transition from research topics into production tools for data scientists working with sensitive data.

Speakers

Casimir Wierzynski, PhD

Senior Director AI Products Group, Intel

Casimir Wierzynski is Senior Director, Office of the CTO, in the Artificial Intelligence Product Group at Intel. He leads research efforts to identify, synthesize, and incubate emerging technologies that will enable the next generation of AI systems. Before joining Intel in 2017... Read More →

Chairs

Jeff Milton

Associate Director, Ionis Pharmaceuticals

Thursday October 3, 2019 3:55pm - 4:15pm
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Session 2: Data Automation

4:15pm

Data Automation- Increasing Sequencing Throughput By Making Robots Work Harder, But Always Checking Their Work

Increasing Sequencing Throughput By Making Robots Work Harder, But Always Checking Their Work
Next-generation sequencing cost declines and capacity increases for the first time make possible high-replicate genome-wide gene expression profiling during drug discovery. This makes library-creation, rather than sequencing, a limiting factor in data generation. The reagent and time costs of sequencing library creation, along with substantial data processing requirements, must be combated with infrastructure to process and analyze more samples. Miniaturization, multiplexing, and automation -- both mechanical and computational -- enable us to process an order of magnitude more samples than benchtop approaches, at nearly half the cost per sample. However, to guarantee robust data at scale, we require careful precautions, randomizations, and embedded controls to spot systematic and sporadic errors. We pre-process samples using Python scripts to organize complex studies with double-barcoding, allowing for pseudo-randomization and integration of controls from the very first step. Our process takes advantage of robotic plate control and both acoustic and displacement liquid handlers. Fully implemented, our process can generate over 2000 sequencing libraries per week.

Co-Author: Sagar Damle, PhD

Speakers

Steven Kuntz, PhD

Sr. Scientist, Ionis Pharmaceuticals

Steven Kuntz conducts sequencing library creation, analysis, and protocol development at Ionis Pharmaceuticals in support of Functional Genomics and Drug Discovery. He received his PhD working on the robustness of muscle differentiation networks in the labs of Barbara Wold and Paul... Read More →

Chairs

Jeff Milton

Associate Director, Ionis Pharmaceuticals

Thursday October 3, 2019 4:15pm - 4:35pm
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Session 2: Data Automation

4:35pm

Data Automation- Automated Science Education and AI Driven Closed Loop Experimentation

Automated Science Education and AI Driven Closed Loop Experimentation
Until recently, the primary mechanism for training scientists in the use of automation was by providing experience working with automated systems in research labs currently using automation technology. At Carnegie Mellon University, we have started the first Automated Science Master’s Degree program in the country. Students in this program are trained to design and implement AI-driven closed-loop experimentation processes. They receive hands-on experience using modern automation equipment to perform experiments. They are trained to use machine learning and related methods for data analysis and they are trained to use artificial intelligence methods to automatically decide what experiments to run next in a campaign. To this end, we have spent the last year identifying automation equipment supplier(s) for our Automation Teaching Lab. This effort has put us in a unique position to have surveyed the current state of a lot of hardware and software in industry from the perspective of both AI-driven automation and education. For this presentation, we will discuss our findings from the perspective of education and AI-driven experimentation. From an educational perspective, we were primarily concerned with the ability to have multiple students use the system and its software in parallel. Furthermore, we considered the ability for software to be used to simulate protocols developed by students. The ability to test in simulation is particularly crucial when there are throughput or consumables limitations. Lastly, since extensive machine learning/AI computation typically cannot be performed locally on hardware included with most integrated automation systems, we also considered the ability for remote control through an application program interface (API). Related to this, we considered to what extent we could automatically move data generated on the system to an external environment for processing. To the best of our knowledge, no single company currently offers a comprehensive package addressing all of these needs. As such, we will be discussing strengths and weaknesses of industry offerings in these areas (and more) during the presentation, but we will not be discussing the offerings of specific companies.

Co-Authors: Christopher J. Langmead, Robert F. Murphy, Ph.D.

Speakers

Joshua Kangas, PhD

Assistant Teaching Professor, Carnegie Mellon University

Joshua Kangas is an Assistant Teaching Professor at Carnegie Mellon University. The courses he teaches are focused primarily on teaching students laboratory methods through wet-lab experience. Students in his courses design their own experiments, generate their own experimental data... Read More →

Chairs

Jeff Milton

Associate Director, Ionis Pharmaceuticals

Thursday October 3, 2019 4:35pm - 4:55pm
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Session 2: Data Automation

5:00pm

Vendor Snapshot: Dynamic Data Production with Machine Learning

Sponsors

Norman Packard

CEO, daptics

Conventional design of experiments approaches are limited to exploration of just a few parameters; daptics has proven success for experimental spaces comprised of up to 20 parameters, where there are far too many experiments to explore exhaustively. daptics brings artificial... Read More →

Thursday October 3, 2019 5:00pm - 5:30pm
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Vendor Snapshot

5:30pm

Networking Reception: Food, Drinks and Prize Drawing

Relax, refresh and make new connections! Join us for open bar, heavy hors d'oeuvres (think...dinner!), games and a chance to win free registration to the 2020 SLAS AI in Process Automation Symposium to be held back here in Boston, MA next September, 2020.

Thursday October 3, 2019 5:30pm - 7:00pm
Washington Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Networking

8:00am

Registration Open

Friday October 4, 2019 8:00am - 1:00pm
5th Floor Corridor - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Registration

9:00am

Breakfast in Exhibition

Friday October 4, 2019 9:00am - 9:30am
Washington Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Networking

9:30am

AI in Screening- Introduction

AI in Screening:
This session will focus on the application of AI to the screening workflow, whether it relates to HTS data generation, analysis and QC, to activity prediction or even to “intelligent” automated screening platforms. For this inaugural symposium, this session will mostly be showcasing the use of deep learning approaches to the high content screening workflow.

Chairs

Franck Madoux, PhD

Principal Scientist, Amgen

Franck Madoux heads Amgen’s Ultra-High Throughput Screening (UHTS) group where he and his team are involved in the early phases of drug discovery for small molecules via the execution of large scale biochemical, cell-based and high content assays in miniaturized formats and the... Read More →

Friday October 4, 2019 9:30am - 9:35am
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Session 3: AI in Screening

9:35am

AI in Screening- Image-based Profiling Using Deep Learning

Image-based Profiling Using Deep Learning
Biological images have been used in research for a long time. In the past, microscopy images were used as qualitative data to display example phenotypes or for visual inspection of experiments. Now, images are used as quantitative sources of information, providing hundreds of parameters of cell state that discriminate different conditions. In this talk, I will cover the main steps of an image analysis workflow that transforms images into single-cell measurements, and will discuss computational approaches that include modern deep learning methods that we have developed in our lab. I will also present biological applications of image-based profiling, including my own research work to study genetic mutations in lung cancer.

Speakers

Juan Caicedo

Research Fellow, Broad Institute of Harvard and

Juan Caicedo is a Research Fellow at the Broad Institute of MIT and Harvard, where he investigates the use of deep learning to analyze microscopy images. Previous to this, he studied object detection problems in large scale image collections also using deep learning, at the University... Read More →

Chairs

Franck Madoux, PhD

Principal Scientist, Amgen

Friday October 4, 2019 9:35am - 9:55am
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Session 3: AI in Screening

9:55am

AI in Screening- Automating Phenotypic Screening with AI

Automating Phenotypic Screening with AI
Imaging-based phenotypic screening of cell-based disease models has become an indispensable tool for modern drug discovery. These assays are used in primary and secondary screening and can even be used to identify novel drug targets. Despite the adoption of automated microscopy-based screening, typically referred to as high-content screening (HCS), analyzing and interpreting the complex imaging data produced by these systems remains a challenging bottleneck. Although only requiring an hour or less to acquire images for each multi-well plate, analyzing the imaging data can take weeks and typically requires hands-on programming by data scientists and computer vision experts. Advances in machine learning, specifically deep learning, have enabled the development of software platforms that can automate this process and provide valuable insights to scientists within hours of completing experiments.

Here we describe a cloud-enabled end-to-end automated platform for storing, managing, analyzing, and visualizing HCS data using recent advancements in deep learning. The workflow for a typical screening experiment involves seamlessly uploading raw screening data from the HCS system to a cloud-based storage instance. From there, the data is automatically imported into a compute instance running an open-source image database and viewer developed primarily for microscopy data. The experimental metadata, including the assay plate layout, is imported simultaneously and is used to annotate all the wells in the screen.

Once the screening data is in the database, two deep learning-based workflows are launched to automatically analyze the screen. The first workflow clusters single cell phenotypes in the screen and allows researchers to explore and annotate the data using an interactive scatterplot. The workflow uses weakly supervised learning, a recently developed method in which a deep convolutional neural network (CNN) is trained to classify which unique experimental condition (i.e. well) each single cell belongs to. After this network is trained, activations from intermediate layers of the network are used as a powerful lower dimensional feature representation to cluster and visualize single cells in the screen. Researchers then use the interactive visualization tool to explore and annotate phenotypes of interest in the screen. After phenotypes and treatments of interest are identified, the second deep learning workflow is used to classify them using a segmentation-free approach. Here, a deep convolutional multiple instance learning model is trained to classify entire fields-of-view in the screen based on control treatments. This classifier is then used to score the rest of the treatments screened, typically identifying hits from a drug library.

This end-to-end system has been deployed on internal projects at Phenomic AI focused on assay optimization, including selecting informative immunofluorescent probes and cytokine or drug concentrations. It’s also been used to identify functional phenotypic hits from small scale drug and antibody screens. Additionally, it’s been used to explore 3D tumor spheroids and complex cell-cell interactions with data provided by our industry partners.

Speakers

Oren Kraus, BASc, MASc, PhD

Cofounder CTO, Phenomic AI

Oren Kraus co-founded Phenomic AI after completing his Ph.D. in Dr. Brendan Frey's lab at the University of Toronto. His research focused on applying deep learning to high-throughput microscopy screens used in drug discovery and cell biology research. Together with Jimmy Ba and collaborators... Read More →

Chairs

Franck Madoux, PhD

Principal Scientist, Amgen

Friday October 4, 2019 9:55am - 10:15am
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Session 3: AI in Screening

10:15am

AI in Screening- Application of Machine Learning Methods To Improve Hit Calling Accuracy For High Content Image Based Screens

Application of Machine Learning Methods To Improve Hit Calling Accuracy For High Content Image Based Screens
Formation of α-synuclein inclusions is linked to pathogenesis of Parkinson’s disease. A high-content imaging screen was conducted to probe Biogen’s chemogenomic set for inhibitors of α-synuclein inclusion formation in M17 neuroblastoma cell line stably expressing α-syn 3K-GFP. Confidence in hits was hindered by high hit rate and apparent unwanted mechanism of inclusion reduction by many compounds (e.g. cytotoxicity). Improved hit-calling accuracy is much needed in this high-information content space.
We generated a work flow to process complex, large number of image-based descriptors obtained from a high-content image-based screening campaign to identify inhibitors of α-synuclein inclusion formation. In this study, along with the user defined image analysis sequence in Columbus software, we applied a combination of unsupervised and supervised machine learning models to high-content image-based screening data of Biogen’s chemogenomic set of 3070 compounds. We demonstrated the value of this approach in confirming the hits in relation to current hit-calling and evaluate additional hits.

Speakers

Lakshmi Akella, PhD

Senior Scientist, Biogen

Lakshmi Akella is a computational chemist and is currently working as a Senior Scientist at Biogen in the Biotherapeutic & Medicinal Sciences Division. Prior to working at Biogen she worked at H3 Biomedicine, Broad Institute and Tripos. She holds advanced degrees in Organic Chemistry... Read More →

Chairs

Franck Madoux, PhD

Principal Scientist, Amgen

Friday October 4, 2019 10:15am - 10:35am
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Session 3: AI in Screening

10:35am

AI in Screening- Label Free Induced Pluripotent Stem Cell Counting With Deep learning For Automation

Label Free Induced Pluripotent Stem Cell Counting With Deep learning For Automation
Artificial intelligence (AI) and deep learning can build smarter and faster automated systems while eliminating the number of steps required in the process. We wanted to evaluate how well an AI could predict cell numbers of human induced pluripotent stem cells (iPSCs) from phase or bright field images for the purposes of automating iPSC culture maintenance. The shift to an automated process can result in several advantages over traditional tissue culture techniques. Current state-of-the-art in stem cell culture is 100% manual labor and is rife with operator-to-operator variation limiting the experimental scale, complexity, and precision. We have designed a fully automated method that obviates the need to conduct cell counts, reduces the number of tasks needed to passage iPSCs, increases iPSC culture consistency, enables portability of protocols from one research site to another. AI has gained the most traction in image analysis and pattern recognition. Based on the supposition iPSCs look like heads in a crowd we adapted an image-based deep learning neural network successful in crowd counting. The deep learning was conducted using a training dataset that consisted of paired bright field and Hoechst stained images, where ground truth was determined by nuclear object detection. The output from the neural network transforms an image into a topological density map, added as an image channel where the total map density is equal to the total cell count across the image. This relationship of cell number to density holds true from the entire dish down to a small user-defined region of the dish. Once trained, the AI enables spatial representation of cells across the dish and at a very wide range of accuracy and cell densities encountered with iPSC cultures without the need for cell labeling. The image-based AI algorithm can determine a precise number of iPSCs within the dish with a percent average error of 5.6%. We can visually observe model training across epochs within the neural network while it is learning to create the correct density maps from the phase contrast images. It is capable of ignoring well edges, dust particulate, and intensity effects due to the meniscus, often times superior to fluorescence labeled object detection. It enables us to measure cell density more rapidly and ‘in line’ with the automation greatly reducing the time and number of steps required for automated iPSC culturing. We are now engineering a working proof-of-concept prototype capable of making a go/no go decision for stem cell passaging and split ratios based on bright field image captures.

Speakers

Stuart Chambers

Sr. Scientist, Amgen

Stuart Chambers is a Senior Scientist in the Genome Analysis Unit at Amgen with a background in stem cells, development, and neuroscience. His group uses induced pluripotent stem cells to model aspects of disease for drug development and works to create, evaluate, and disseminate... Read More →

Chairs

Franck Madoux, PhD

Principal Scientist, Amgen

Friday October 4, 2019 10:35am - 10:55am
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Session 3: AI in Screening

11:00am

Vendor Snapshot: Improving Life Science Applications with COGNEX VisionPro ViDi Deep Learning Vision

With the largest investment in R&D and a global engineering support team, Cognex is the preferred machine vision supplier for the Life Sciences industry. Today, OEMs rely on Cognex for vision and automatic ID solutions to meet the demanding requirements of their customers and deliver accurate, reliable, and high-performance machines.
VisionPro ViDi is the first Deep Learning-based image analysis software designed specifically for a wide range of Life Sciences applications. It is a field-tested, optimized, and reliable software solution based on a state-of-the-art set of machine learning algorithms. VisionPro ViDi solves complex applications that are too difficult to program and maintain using traditional machine vision systems.

Speakers

Jozsef Nagy, B.S.

Life Science OEM Project Manager, Cognex Corporation

Jozsef Nagy is a Project Manager at Cognex Corporation with 10 years of experience in the machine vision field. At Cognex, he is focused on integrating smart vision systems into medical instruments. Most recently, he has been leading the evaluation and deployment of Cognex deep learning-based... Read More →

Sponsors

Cognex

Cognex vision helps companies improve product quality, eliminate production errors, lower manufacturing costs, and exceed consumer expectations for high quality products at an affordable price.Typical applications for machine vision include detecting defects, monitoring production lines, guiding assembly robots, and tracking, sorting and identifying parts... Read More →

Friday October 4, 2019 11:00am - 11:30am
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Vendor Snapshot

11:30am

Poster Presentations in Exhibition- #1 Automatic Translation of Workflow Descriptions into Formal Process Notations

The digitization of life sciences is based on processes implemented in software, which combine manual and automated work seamlessly. The major part of currently available process descriptions is provided in human-readable text-based formats (e.g., protocols, SOPs, clinical pathways,…), either for historical reasons or due to the lack of appropriate toolchains that formalize processes in versatile ways. Technical process descriptions, on the other hand, need to be well-defined given in a formal notation like BPMN in order for them to be executed by software and deployed on the hardware. The translation of natural-language process descriptions into formal notations requires a substantial amount of effort because technicians need to translate between actual application domains and technical domains. Human capacities limit the degree to which the translation can be sped up, but the need for translation is high: many processes are still being implemented manually, and large numbers of documented process descriptions exist.

We combine the current state-of-the-art of natural language processing (NLP) with ontological engineering and formal process modeling in order to automate the process of translation of text-based workflow descriptions into machine-readable representations. We devise a software pipeline that, firstly, preprocesses domain corpora in order to distill and identify linguistic features, which are then matched against ontological knowledge. Secondly, an online process reuses these features for rapid translation of textual data into formal process models. We demonstrate the feasibility of our approach and show current drawbacks and limitations.

Speakers

Sebastian Schoening

Group Manager, Fraunhofer IPA

Experienced group manager with a demonstrated history of working in research and development of automated systems for life-science applications. Graduated in computer science at Saarland University (Germany), skilled in the design, implementation, and analysis of discrete biotechnological... Read More →

Friday October 4, 2019 11:30am - 11:50am
Washington Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Posters

11:30am

Poster Presentations in Exhibition- #2 Automated Analysis Of Sarcomere Organization In IPSC Cardiomyocytes

Induced pluripotent stem cell-derived cardiomyocytes (iPSC-CMs), in combination with CRISPR genome editing, now offer unparalleled opportunities to study cardiac biology and disease. Mature and functional iPSC-CMs are frequently characterized by the presence of visually distinct sarcomere bands. However, few methods exist to comprehensively quantify sarcomere organization. These methods can be relatively low-throughput (requiring manual selection for regions of interest), employ Fast Fourier Transforms (requiring a minimum number of detected sarcomeres), and/or only assess well-aligned sarcomeres from mature cardiac tissues. Here we take advantage of a pixel-based image analysis method to overcome these limitations and evaluate iPSC-CM sarcomere structure. Our approach, or sarcomere organization analysis (SOA), incorporates automated cell segmentation and extracts sarcomere information from Haralick texture features. This quantification enables SOA to process any geometric shape, account for noise, and identify sarcomere persistence. These are especially important features since iPSC-CM cell shape is quite variable and sarcomere orientations and lengths can be heterogeneous. Thus, SOA allowed us to effectively distinguish levels of sarcomere organization to define CMs with highly and moderately organized sarcomeres compared to CMs with visibly disorganized sarcomeres. These differences were further apparent when comparing WT iPSC-CMs to iPSC-CMs with a genetic sarcomere mutation. This mutation resulted in more CMs with sarcomeres longer than 2 µm and a reduced organization. Our SOA method is intended to help provide a more systematic approach to examining cardiac disease biology resulting from genetic variants. Current work is aimed at incorporating deep learning for enhanced analysis and a more complete description of sarcomere organization and iPSC-CM phenotypes.

Speakers

Devin Wakefield, Ph.D.

Sr. Associate Scientist, Amgen

*Sr Associate Scientist, Amgen: 2018-present*Genome Analysis Unit imaging research*Postdoctoral Fellow, Beckman Research Institute at City of Hope: 2015-2018*Super-resolution microscopy of cancer targets*Graduate Student, Cornell University: 2010-2015*IgE receptor-mediated signaling... Read More →

Friday October 4, 2019 11:30am - 11:50am
Washington Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Posters

11:30am

Exhibition & Networking Lunch

Friday October 4, 2019 11:30am - 12:30pm
Washington Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Networking

11:50am

Poster Presentations in Exhibition- #3 Automation of a full genome arrayed library CRISPR screen

Large scale cell based phenotypic screens of RNAi libraries are well established but can be limited by incomplete and unknown levels of gene knockdown. Here we present a platform for high content screening of an arrayed lentiviral CRISPR library for the whole human and mouse genomes which has recently been established by us. The use of automation allowed us to minimize handling and any potential exposure to the viral material as well as maximize the assay throughput. Here we present the methods used and example data from the complete process.

The automated steps include culturing, inoculation, staining and imaging, all in 1536 well plates. All liquid handling is performed within an enclosed JANUS workstation with attached carrousel and incubator. Imaging is performed with an opera phenix. Assay volumes have been trialled in the range of 5 - 8 ul per well, evaporation is largely mitigated by use of a filled moat in the plate skirting. Media exchange / washing is less prone to damaging the cell layer as result of such small assay volumes.

The data presented here is representative of the platforms use in whole genome phenotypic screening experiments. This platform represents a new stage of genome screening allowing rapid identification of gene targets for novel phenotypes. By interrogating each gene individually we can discern which target or pathway is involved in producing the phenotype of interest.

Speakers

Tim Blackmore, Ph.D. Medicinal Chemistry

LIMS Specialist, Walter and Eliza Hall Institute

Completed a Bachelor of Medicinal Chemistry with honours at Monash University Melbourne Australia. Followed by a PhD with a focus on synthetic organic chemistry to develop isoform selective inhibitors of Phosphodiesterase 3A and 3B also at Monash.Worked at CSL for several years in... Read More →

Friday October 4, 2019 11:50am - 12:10pm
Washington Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Posters

11:50am

Poster Presentations in Exhibition- #4 Deep Learning for Identification of Monoclonality in Human Induced Pluripotent Stem Cells

Automated manufacturing of induced pluripotent stem cells (iPSCs) overcomes critical restrictions on scalability and technical variability that otherwise preclude the use of iPSCs in large-scale population studies. Following reprogramming from adult cells, a critical step in ensuring cell line viability is the isolation and expansion of a single stem cell, a step referred to as monoclonalization. Monoclonality is generally verified via manual analysis of microscopic images, a highly time- consuming process which relies upon human judgement, incurring a key barrier to standardization and scalability. Here we report the design of a deep learning workflow which reliably identifies monoclonality and ascribes colony viability. The workflow, termed Monoqlo, integrates multiple convolutional neural networks and, critically, leverages the time seriality of the cell culturing process. This work highlights an example of the way in which human-directed design can often overcome obstacles in machine learning engineering in cases where a paucity of training data precludes the use of “more data, better results” strategies.

Speakers

Brodie Fischbacher, M.Sc., M,Sci,

Bioinformatics Scientist, The New York Stem Cell Foundation

I am a computational biologist focussed on machine learning, working at the New York Stem Cell Foundation. I have interests primarily in deep learning for automated analysis of high content biological imaging.

Friday October 4, 2019 11:50am - 12:10pm
Washington Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Posters

12:10pm

Poster Presentations in Exhibition- #5 Deep Learning Based Image Analysis in Laboratory Automation and In Vitro Diagnostics with COGNEX VisionPro ViDi Software Suite

COGNEX Machine Vision systems are the gold standard on the Factory Automation floor and meanwhile also in Lab Automation environments. Traditional vision systems excel in gauging, measuring and precision alignment, but algorithms become challenging to program as the exceptions and defect libraries grow or different objects look similar which is often the case in Lab Automation and IVD applications.
Deep Learning-based image analysis combines the specificity and flexibility of human visual inspection with the reliability, consistency, and speed of computerized systems. With the introduction of Deep Learning we face new challenges, for example, the large number of images needed for proper training is not always available, the time to develop a highly accurate application is long, developing and maintaining the network requires a highly skilled individual or team and the black-box behavior of the system sometimes can’t earn the trust of the end-user.

Another interesting trend with the emergence of deep learning is that people start to neglect the traditional rule-based approach, but what we see is that rule-based vision and Deep Learning-based image analysis are complementing each other and enable us to solve more complex automation problems.
COGNEX VisionPro ViDi™ is a ready-to-use Deep Learning-based software suite dedicated to image analysis which can provide solutions for a wide range of applications in the life sciences field. It also provides seamless integration with our traditional rule-based vision tools as needed.
In our novel approach, we designed four specific Deep Learning tools which can be used to break down a complex problem to smaller and simpler steps to provide the final solution with a customized toolchain. Each tool is optimized for one specific task:
-Blue – Locate for feature location and verification
-Red – Analyze for segmentation and defect detection
-Green – Classify for scene and object classification
-Blue – Read for optical character recognition

This method allows us to build a solution with only a few hundred images, train and run the Deep Learning models locally on a single GPU system. It also makes it easier to localize any erroneous behavior in the system. The suite provides a graphical user interface for training and labeling with a handful of parameters to fine-tune the models. This feature can enable medical professionals without extensive Deep Learning knowledge to rapidly develop various Deep Learning-based applications where the experts can focus on optimizing, validating and deploying these solutions.
Applications where we successfully developed a solution with COGNEX VisionPro ViDi™:
-Deck inspection, Tube and Plate identification for medical instruments
-HIL Quality inspection of centrifuged blood samples
-Bacteria Classification
-Colony Counting / Classification

These examples highlight the potential of COGNEX VisionPro ViDi™ to be useful for a broad range of complex image analysis tasks within life sciences.

Speakers

Jozsef Nagy, B.S.

Life Science OEM Project Manager, Cognex Corporation

Friday October 4, 2019 12:10pm - 12:30pm
Washington Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Posters

1:00pm

AI in Chemistry-Introduction

AI In Chemistry
This session will focus on the role of AI and automation in chemistry, including the prediction of molecular properties (design), the physical realization of those molecules (synthesis), and their evaluation (testing).

Chairs

Connor Coley

MIT

Friday October 4, 2019 1:00pm - 1:05pm
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Session 4: AI in Chemistry

1:05pm

AI in Chemistry- AI Solutions for Computational Chemistry and Organic Chemistry Tasks

Speakers

Olexander Isayev, PhD

Assistant Professor, University of North Carolina

Olexandr Isayev is an Assistant Professor at UNC Eshelman School of Pharmacy, the University of North Carolina at Chapel Hill. In 2008, Olexandr received his Ph.D. in computational chemistry. He was Postdoctoral Research Fellow at the Case Western Reserve University and a scientist... Read More →

Chairs

Connor Coley

MIT

Friday October 4, 2019 1:05pm - 1:25pm
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Session 4: AI in Chemistry

1:25pm

AI in Chemistry- Creating and Deploying Self Driving Laboratories For Process Optimization

Optimizing multicomponent reactions is a challenge which lends itself well to automation due to the large number of experiments usually required. In addition to classic high throughput and Design of Experiment methodologies, the application of machine learning algorithms has recently come into focus; coupled with a robotic platform and on-line analytical tools, the ideal of a fully autonomous robotic researcher comes within reach. While historic examples of this concept have often been tailored to answer rather narrow questions, we herein present a powerful and versatile platform for interrogating a wide range of reaction systems.

Using an N9 robot by North Robotics as our central platform, we have developed a range of tools enabling us to formulate reactions, take samples, and perform on-line HPLC and MS/MS analysis, all under full automation. Results are passed on to ChemOS, a machine learning engine, which evaluates collected data and provides a new set of experimental conditions, generating a closed feedback loop enabling rapid optimization of complex reaction systems.

To showcase the power of our platform, we have deployed several variations of this autonomous toolkit to tackle a diverse range of chemical applications. In this first demonstration, these include optimization of reaction parameters for catalytic transformations and discovery of champion thin-film materials for organic photovoltaic devices. Current progress and development will be discussed.

Speakers

Sebastian Steiner

Postdoctoral Research Fell, University of British Columbia

I completed my MSc degree in Vienna, Austria, in the field of natural product synthesis, and then moved on to do my PhD in Glasgow, Scotland, in synthesis automation. I am interested in designing tools and writing software to enable lab automation, with a special focus on robotic... Read More →

Chairs

Connor Coley

MIT

Friday October 4, 2019 1:25pm - 1:45pm
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Session 4: AI in Chemistry

1:45pm

AI in Chemistry- Optimization of Chemical Reactions using Probabilistic Models

Can we accelerate the process of molecular discovery by combining automation with machine learning tools? Rapid development of new molecules with tailored properties is crucial for the chemical, petrochemical, pharmaceutical, and electronic industries, to name just a few. Our team is developing a closed-loop autonomous chemical discovery platform that generates new hypotheses, tests them, and uses those results to determine the next iterations. I will talk about how we at Kebotix employ probabilistic machine learning in efficient optimization of chemical reactions, one of the fundamental tasks in this process.

Speakers

Dennis Sheberla, PhD

CTO, Kebotix

Dennis Sheberla, chief technology officer, has a multi-disciplinary background and a passion for computer science, artificial intelligence, and robotics. His expertise lies in organic chemistry, materials characterization, computational chemistry and machine learning. Before co-founding... Read More →

Chairs

Connor Coley

MIT

Friday October 4, 2019 1:45pm - 2:05pm
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Session 4: AI in Chemistry

2:05pm

AI in Chemistry- Development of MicroCycle 1.0: A New Tool for Drug Discovery

Drug discovery requires developing a holistic understanding of the interaction between chemical and biological space. In the early phase, it is critical to develop this knowledge in a rapid and unbiased way, while benefiting from 150 years of drug hunting experience. We envisaged an iterative approach for project teams to navigate early drug discovery. Each iteration begins with a digital - human collaboration to select chemical starting points (scaffolds & BBs), leading to synthesis on a biologically relevant scale, followed by purification & characterization of these compounds, and testing in a range of integrated, automated and relevant assays. The process concludes with a machine learning based multi-parameter analysis of data in order to select next round of compounds. The first generation platform - MicroCycle 1.0 - has been developed and delivered in our Basel and Cambridge Labs. We look forward to sharing with you the story of platform development along with some key early results.

Speakers

Jonathon Grob

Investigator, Novartis Institutes of Biomedical Research

I am a chemist who is passionate about leveraging my experience inMedicinal Chemistry & technology development to instigate a transformation towardautomation & digital enabled drug hunting. 18 years at Novartis. Worked at 3 sites inmy first 4 years. Currently working with a global... Read More →

Chairs

Connor Coley

MIT

Friday October 4, 2019 2:05pm - 2:25pm
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Session 4: AI in Chemistry

2:30pm

Closing Remarks

Chairs

Yohann Potier, Ph.D.

Director of Data Science & Informatics, Voyager Therapeutics

Friday October 4, 2019 2:30pm - 2:45pm
Theater Ballroom (5th Fl) - Courtyard Boston Downtown 275 Tremont Street, Boston, MA 02116

Opening/Closing Remarks and Keynote