Vision

Using AI to rethink the science of drug development

DeepCure was founded to accelerate breakthrough science, developed by world-leading AI engineers, data scientists and biologists.

Our founding team includes some of the industry’s preeminent drug-discovery scientists and technologists.

Our vision is to use AI-driven discovery to create better molecules and faster cures for every disease-relevant protein target.

Our Investors

Leadership

Kfir Schreiber

CEO & Co-Founder

Graduate of the MIT Media Lab. Recipient of the inaugural Minsky Fellowship for prominent AI researchers. Previously a Pilot and Major in the Israeli Air Force, with a track record of managing over $100M and 20 people across major R&D projects.

Joseph Jacobson, Ph.D.

Co-Founder

Associate Professor at the MIT Media Lab. Author of over 70 peer-reviewed papers and conference proceedings. Inventor of 103 issued U.S. patents and a member of the USPTO Investors Hall of Fame. Co-Founder of several successful companies, including E-Ink, Gen9, Kovio and IgC Bio.

Thrasyvoulos (Thras) Karydis

CTO & Co-Founder

Graduate of the MIT Media Lab. Deep Learning and AI expert, with years of experience in leading hardware and software projects. Vast experience in establishing and leading collaborations with large pharma companies.

Derek Miller

VP, Head of Platform Research

Derek Miller is a machine learning engineer with thirteen years of experience and has worked in various industries, such as healthcare, genomics, and drug discovery. His work focuses on training models at scale to help provide enriched molecules for various therapeutics.

Georg Duenstl, Ph.D​.

VP of Drug Discovery

Having served on DeepCure’s Scientific Advisory Board since its inception in 2018, Georg joined the company as Vice President of Drug Discovery in 2022. He has over 16 years of drug discovery experience emphasizing pharmacology, strategy, and innovation. Before joining DeepCure, Georg was an Associate Research Fellow at LEO Pharma. He worked for more than 13 years in various positions at the company’s Danish headquarters and its Boston-based Science & Tech Hub, where he served as Chief Scientist. Georg studied in Germany and the US and holds a Ph.D. in Biochemical Pharmacology and MSc in Biology from the University of Konstanz. He also completed advanced executive education programs at the Wharton School of the University of Pennsylvania (CPD) and the MIT Sloan School of Management (ACE).

Han Lim, Ph.D.

Chief Business Officer

Dr. Han Lim is the Chief Business Officer at DeepCure. DeepCure is creating an end-to-end automated platform to accelerate and personalize small molecule drug discovery through the integration of AI, a virtual library of a quintillion synthesizable compounds, robotic synthesis, and automated assays. Before joining DeepCure, Dr. Lim was instrumental in building one of the first-generation AI drug discovery companies. His experiences are broad, from target selection and portfolio strategy for AI platforms to biopharma deals and academic collaborations. His previous roles include Chief Business Officer at Atomwise and faculty member at the University of California, Berkeley. Dr. Lim obtained a medical degree from the University of Queensland, a Ph.D. from the University of Cambridge, and postdoctoral training in the Department of Physics at MIT.

Derrick Miyao

VP of Molecular Foundry

Derrick Miyao joined DeepCure as the Vice President of Molecular Foundry. Derrick Miyao is a trailblazer in robotic synthesis and automated assays. Derrick joins DeepCure from Neurocrine, where he spent 20 years creating systems for automated drug discovery, including building two systems that can synthesize 10,000 compounds a day and successfully integrating synthesis with affinity binding for a closed discovery loop. At DeepCure, Derrick will lead the Molecular Foundry, our fully automated synthesis and screening lab in Rehovot, Israel. When asked about the lab, Derrick replied, “it is something I’ve always believed was the key to unlocking new drugs and pushing the limits of what we can discover. The impact will result in getting better drugs to market faster than traditional methods and more treatments for those who need it.”

Luca Rastelli, Ph.D​.

Chief Scientific Officer

Dr. Rastelli is the Chief Scientific Officer of Deepcure. With over 25 years of experience, he has held multiple preclinical and clinical project leadership positions. He led the development of TEPMETKO and was part of the development of BAVENCIO. Dr. Rastelli has a Ph.D. in Molecular Biology from the University of Geneva and is a named inventor on over ten issued patents, he received the American Brain Tumor Association’s 25th Anniversary Translational grant for his work on Medulloblastoma tumors at the Department of Neuro-Oncology, MD Anderson Cancer Center.

Team

Panos Terzopoulos

Senior Machine Learning Scientist

With a diverse background in mechanical engineering and robotics, Panos completed his master’s thesis on computational biology at MIT and NTUA, and he has been with DeepCure since then. He’s a machine learning scientist who works on finding practical solutions that bridge the gap between machine learning and the traditional drug discovery world.

Kelvin Chan, Ph.D.

Director of DMPK

Kelvin joined DeepCure in 2022 as Director of Drug Metabolism and Pharmacokinetics (DMPK). He has broad experience and expertise in analytical chemistry, DMPK, and CMC (Chemistry, Manufacturing, and Control) areas. Since 1984, Kelvin’s career has spanned large multinational (Syntex/Roche, Wyeth/Pfizer, Aventis/Sanofi, Alcon/Novartis), small biotech (Assembly Biosciences), and non-profit (CHDI) organizations. He contributed to the discovery or development of multiple molecular entities to successful NDAs. Kelvin received his Ph.D. in Chemistry from the University of Illinois and post-doctoral training at Cornell University.

Wasim Akhtar

IT Specialist

Wasim joined DeepCure to lead the IT and IT Security department. He has over a decade of extensive experience in Information Technology and Security, particularly in Identity and Access Management (IAM). His expertise also extends to Mobile Device Management (MDM), where he specializes in enhancing automation processes. At DeepCure, he is dedicated to constructing robust systems and implementing streamlined processes to optimize user experiences while mitigating potential threats associated with data security. This helps safeguard against the risks of data loss or theft.

Steven Ferrara, Ph.D.

Director of Medicinal Chemistry

Steven joined DeepCure in 2021 and serves as our Associate Director of Medicinal Chemistry. He has over eight years of drug discovery experience, emphasizing medicinal chemistry and chemical biology. Before joining DeepCure, Steven was a Group Leader at the Broad Institute of MIT and Harvard. He led a group of medicinal chemists who focused on developing novel therapeutic strategies for use in oncology and cardiovascular disease areas. He was essential in advancing several preclinical programs and was a key contributor and co-inventor of inhibitors targeting DHODH (BAY 2402234) and MCL1 (ANJ810). Steven received his Ph.D. in Organic Chemistry from the University of Oxford and was a postdoctoral research associate at Yale University. He also holds a Master of Chemistry from the University of Sheffield.

George Bikos

Senior Software Engineer

I am a Software Engineer with three years of experience. I have a Master’s in Computer Science and Informatics from the University of Patras, Greece. I started working as a Bioinformatics Researcher at the National Research Center of Greece and later jumped into the Health Industry, joining a company associated with Medical-Imaging. I am interested in the BioInformatics and Medical aspect of Engineering. I have lived in Athens, Greece, for the last three years.

Pegah Kolahi

Senior Scientist, Computational Chemistry

Pegah is a Computational Scientist with broad in-silico expertise and a background in computer-aided drug design and discovery. She graduated with her Masters from New York University in 2019 and has worked in the pharmaceutical and biotechnology industry since then. Throughout her work at Kadmon and Sanofi, she developed skills in advanced computational techniques such as molecular modeling, virtual library design, and molecular dynamics to support designing and optimizing drug candidates. She is passionate about applying state-of-the-art computational chemistry tools to accelerate the discovery and design of therapeutics and determine novel paths forward for drug development.

Allie Higgins

Scientific Program Manager

With six years of program management experience across companies such as Dana-Farber Cancer Institute, The Broad Institute of MIT and Harvard, and Invitae, Allie has led cross-functional teams in developing innovative solutions within genomics, product development, and clinical research spaces. Her adept management of interdisciplinary teams fosters collaboration, ensuring seamless execution and driving meaningful advancements at DeepCure. With a keen focus on streamlining the rapidly moving drug discovery process, Allie focuses on optimizing organizational strategies, facilitating efficient workflows to achieve breakthrough results.

Luke Nam

Senior Automation Engineer

Luke joined DeepCure as an automation engineer with seven years of experience in the drug discovery industry. He is passionate about leveraging software and automation to make the drug discovery process more efficient. His most recent project involved building custom enumeration software to design small molecule libraries to be synthesized on an automated chemistry platform.

Ayelet Wagner Azran

Director of People Operations

With a passion for building cultural solid foundations and identifying people’s needs for creating a thriving work environment, Ayelet joined DeepCure as People Operations Lead in 2020. Previously, she had worked at several non-profit organizations and led the HR and operations of ELAL Israel airlines in Boston. She holds a Law degree and a bachelor’s in business administration.

Carlos Borca, Ph.D.

Principal Scientist, Computational Chemistry

Carlos is a pragmatic computational chemist who enjoys innovative research, tackles real-world problems, and creates original scientific software solutions. He is passionate about creating and applying models to various chemical problems. His background centers on understanding intermolecular interactions: He earned his Ph.D. from Purdue University, focusing on evolving density functionals and ab initio-based polarizable force fields. During his postdoctoral fellowship at Georgia Tech, he developed CrystaLattE, an efficient software for computing highly accurate lattice energies of molecular crystals. At Princeton University, his postdoctoral research involved developing methodologies for machine-learning-driven robotic fabrication of polymer-enzyme hybrids. Before joining DeepCure AI, he led physics-based modeling for RNA-targeted computer-aided drug discovery at PTC Therapeutics.

Mark Schroering

Associate Director, Lead Architect

Mark is a software architect with over 20 years of experience working for companies like Boeing, Raytheon, and Genesys. He has spent the last nine years building large-scale cloud platforms that have been deployed globally in the cloud and used by millions of people. His work has been used in the avionics, medical research, and contact center industries.

Michal Segal Salto, Ph.D.

Senior Director, Biology

As an Associated research fellow, Michal joined the DeepCure drug discovery team in 2022. Michal has over 17 years of experience in cell biology, molecular biology, and biochemistry. She was awarded her Ph.D. from the Weizmann Institute of Science in Rehovot, Israel. In the past seven years, Michal led research groups and development processes in the preclinical and clinical stages. Michal has an in-depth understanding of relevant research, target, product identification, and the selection and experience designing product development programs. Michal has published peer-reviewed articles in high-impact factor journals and precipitated them at many international conferences.

Ohad Hasin, Ph.D.

Lab Operations Manager

Ohad holds a Ph.D. in organic chemistry from Tel Aviv University, where he specializes in the isolation and structure elucidation of natural products. Ohad worked in lab. managing and team lead positions in the cannabis and food tech industries before he joined Deepcure in 2022 as a lab. operations manager. Ohad uses his scientific knowledge and organizational expertise to manage all lab requirements and safety, maintain regulatory compliance, and contribute to the company’s overall success.

Ryan Ratcliff

Associate Software Architect

Ryan is an experienced software engineer with a career spanning over 20 years in various domains. He has worked on projects such as warehousing applications for Universal Studios, telephony solutions for Genesys, and genomics at LifeOmic. In the last decade, he has focused on large-scale cloud systems, emphasizing automation and large data handling. Recently, he collaborated with a Pharmacogenomics Team through LifeOmic, co-authoring two published papers clinically validating an algorithm to aid in genotype detection.

Heather L. Osswald, Ph.D.

Associate Director, Automated Chemistry

Heather joined Deepcure in 2022 as a Principal Scientist, Chemistry & Automation. She earned her Ph.D. from Purdue University and performed postdoctoral research at The Scripps Research Institute. Heather’s experience spans structure-based drug design and asymmetric organic synthesis to chemical technologies and laboratory automation. She has impacted multiple preclinical discovery projects spanning from hit ID to lead optimization and developed an automated chemical synthesis platform capable of enabling rapid exploration of chemical space and identification of lead compounds.

Chris MacNaughton

Software Architect

Chris is a software architect with over 15 years of experience working in various industries, including education, e-commerce, pharma, precision health, and wellness. He works across the software stack to build large-scale, highly-available applications and platform services. He resides in Indianapolis, IN, with his wife and three kids.

Michelle E. Fodor

Associate Director of Biophysics and Structural Biology

Michelle joined DeepCure in 2024 as Associate Director of Biophysics and Structural Biology. Before entering the pharma industry, Michelle earned her MS in Biochemistry from Colorado State University. She is coming to us now with 20 years of drug discovery experience, initially contributing to programs through expertise in Structural Biology, Biophysics, and Protein Science to eventually leading hit finding and lead optimization efforts across several disease areas. Michelle’s most noteworthy contribution has been toward the identification and development of clinical compound Batoprotafib, an allosteric inhibitor of SHP2/PTPN11, during her 13 years at Novartis. She is excited to help drive target enablement and machine learning through Biophysics and Structural Biology at DeepCure!

Matthew Tieman

Senior Machine Learning Engineer

Matt joined DeepCure in 2022 as a Senior Machine Learning Engineer. Matt is an engineer with ten years of experience developing cloud-native platforms. Much of Matt’s expertise involves leveraging distributed computing technologies in cloud environments for streaming and batch data analytics. Before coming to DeepCure, he had worked in the telecom, APM, and precision medicine spaces.

Elvira Haimov, Ph.D.

Principal Scientist, Medicinal Chemistry

Elvira joined DeepCure in 2022 as a Principal Scientist, Medicinal Chemistry. Previously, Elvira worked as a team leader in TEVA, TAPI division, developing novel synthetic methodologies for synthesizing the Active Pharmaceutical Ingredient. Then, Elvira joined the Blavatnik Center for Drug discovery, pursuing medicinal chemistry and drug discovery. Elvira led medicinal chemistry through hit selections, hit validation, SAR studies, and hit-to-lead optimization.

Ric Ogden

Director of Finance and Accounting

Ric is a seasoned finance and accounting professional bringing more than 30 years of financial leadership experience to DeepCure. He holds undergraduate degrees in Finance and Accounting as well as an MBA from Babson College and a master’s in taxation from Bentley University. Ric recently spent 4 years working as controller and CFO for a small biotech firm and is passionate about working for start-ups, particularly those that are targeting drug development for conditions that are difficult to treat.

William Kaplan, Ph.D.

Principal Scientist, Medicinal Chemistry

I will join DeepCure in 2022 as a Principal Scientist – Medicinal Chemistry. Previously, Will spent 4.5 years at Merck, where he developed his preclinical drug discovery skills, lead ID, lead optimization, design and synthesis, and program strategy/development. Will received his Ph.D. in Medicinal Chemistry from the University of Michigan (Go Blue!).

Daniel Graziano

Senior Data Scientist

Danny is a Senior Machine Learning Scientist who utilizes data-driven processes to re-imagine critical phases of the drug discovery life cycle. His primary interest is making complex biological data relatable and accessible to a broad audience to draw conclusions and base decisions. Danny brings 5+ years of in-vivo pharmacology experience from his time in the Novartis Neuroscience department. Throughout his work at Novartis and Massachusetts General Hospital, he developed skills in implementing DSP, time series, and statistical analysis pipelines for extracting translatable biomarker readouts from in-vivo electrophysiology data. He will be finishing his master’s degree in computer science from Boston University at the end of 2021.

Aayush Gupta, Ph.D.

Senior Scientist, Computational Chemistry

Aayush is an experienced computational chemist with expertise in developing AI/ML-based workflows for solving molecular properties and protein-drug modeling. Aayush earned his PhD in Chemistry from the University of Illinois at Chicago. While working on his PhD, he did an internship at Schrödinger, where he focused on small molecule crystal structure prediction pipelines. More recently, Aayush worked as an AI Research Scientist (Computational Chemistry) at Exscientia, where he developed neural network potentials for MD simulations.

Jason Deckman, Ph.D.

Senior Scientific Software Engineer

Jason joined DeepCure in 2022 as a Senior Scientific Software Engineer. Jason has a Ph.D. in theoretical/computational chemistry from U.C. Irvine. He has several years of graduate and postdoctoral experience in scientific and numerical computing, applied to biochemical simulations and algorithm development. In industry before graduate school, Jason worked in the drug discovery arena, first as a chemist and as a data analyst, enumerating and curating virtual combinatorial chemistry libraries. In the last several years, he has worked as a senior software engineer specializing in back-end infrastructure and cloud architecture, as well as full-stack development. Jason is eager to combine his chemistry knowledge and software engineering experience to deliver novel and effective software solutions for DeepCure.

Jon Kaufman, Ph.D.

Associate Director, Physics-Based Machine Learning

Jon is an Associate Director of Physics-Based Machine Learning, focusing on the intersection of machine learning and physics for drug discovery. Jon earned his Ph.D. in physics from UCSD on the controversial BICEP2 experiment, which allowed him to travel to the South Pole in Antarctica. Previously, Jon worked in applied machine learning for the healthcare, finance, energy, and hospitality industries. He loves working on challenges where machine learning and data science meet the physical world.

Jacob Gillis

Associate Director, Program Operations

Jacob is a project and program manager with over five years of scientific program management and product development experience with start-up assay development companies, working on expanding and refining product development programs and implementing quality management processes. At DeepCure, Jacob focuses on scientific program optimization and maximization of program efficiency.

MiJeong Kim, Ph.D.

Director of Immunology

With a passion for developing medicines for patients in need, MJ joined DeepCure in 2024 as a Director of Immunology. She brings years of drug discovery experience in preclinical and clinical settings, with a focus on immunology. Prior to DeepCure, MJ was a Director of Immunology at Homology Medicines inc. where she spearheaded translational immunology efforts to support clinical trials and develop the next generation of genetic medicine. MJ holds a PhD in Comparative Biomedical Sciences/Immunology from Cornell University and a postdoctoral training from Harvard Medical School.

Board of Directors

Kfir Schreiber

CEO & Co-Founder

Graduate of the MIT Media Lab. Recipient of the inaugural Minsky Fellowship for prominent AI researchers. Previously a Pilot and Major in the Israeli Air Force, with a track record of managing over $100M and 20 people across major R&D projects.

Joseph Jacobson, Ph.D.

Co-Founder

Associate Professor at the MIT Media Lab. Author of over 70 peer-reviewed papers and conference proceedings. Inventor of 103 issued U.S. patents and a member of the USPTO Investors Hall of Fame. Co-Founder of several successful companies, including E-Ink, Gen9, Kovio and IgC Bio.

Gerald Chan

Director

Gerald Chan is the co-founder of Morningside, an investment group engaged in private equity and venture capital investments. Working with academic scientists, he has started more than two dozen biotech companies across diverse therapeutic areas of oncology, inflammation, ophthalmology, autoimmunity, diabetes, neurodegeneration, rare genetic diseases, and prophylactic vaccines. Gerald is a board member of several privately held biotech companies. He is the chairman of two Nasdaq listed biotechnology companies: Apellis Pharmaceuticals and Stealth BioTherapeutics. From 2016 to 2020, he chaired the Innovation Advisory Committee of the Wellcome Trust. He is currently a trustee of the Scripps Research Institute and a member of the Dean’s Board of Advisors of the Harvard T.H. Chan School of Public Health, which was renamed in honor of his father, Mr. T.H. Chan, following a gift from the Morningside Foundation in 2014. Gerald was educated at UCLA, Harvard University, and Dana Farber Cancer Institute. He has been honored with six honorary degrees conferred by universities in the UK, Hong Kong and America. In 2017, he was elected to membership in the American Academy of Arts and Sciences. In 2019, he gave the Andrew Carnegie Lecture in University of Glasgow, Scotland and held a visiting fellowship at Trinity College, Cambridge University.

Yonatan Mandelbaum

Observer

Investing principal at TLV Partners. At the firm since 2017, he spends most of his time on fintech, bottoms-up SaaS and anything out of the ordinary, but has a true passion for working closely with humble founders whose ambitions vastly outweigh their accomplishments. Prior to joining TLVP, Yonatan was an analyst at iAngels. He holds a bachelors in finance from IDC Hertziliya, spent two years studying at Yeshivat Har Etzion and served as a commander in the Israeli Defense Force’s Haruv unit.

Shahar Tzafrir

Director

Managing Partner at TLV Partners where he focuses on seed-stage investments at the intersection of AI, enterprise, and bio. Shahar began his venture career at Magma Venture Partners as a General Partner in funds III and IV. While at Magma, Shahar led seed investments in Aidoc, Guesty, Applitools (acquired by Thoma Bravo), Argus (acquired by Continental), Cloudendure (acquired by Amazon), and Indegy (acquired by Tenable), among others. Before venture capital, Shahar spent 17 years across three enterprise software startups: Federation (acquired by Cordys), Oblicore (acquired by CA) and DigitalFuel (acquired by VMware). Prior to that, Shahar spent six years in the Israeli Defense Force’s Mamram computer division as a software developer, where he received three annual distinction awards.

Thrasyvoulos (Thras) Karydis

Director

Graduate of the MIT Media Lab. Deep Learning and AI expert, with years of experience leading hardware and software projects. Vast experience in establishing and leading collaborations with large pharma companies.

Scientific Advisory Board

John Baldoni, Ph.D.

Ex SVP, DPU Head, In-Silico Discovery, GSK Pharmaceuticals

Headed innovative drug discovery unit dedicated to explore and apply in silico methodology to drug discovery and development at GSK. This followed his role as Senior Vice President, Platform Technology and Science (PTS), GSK Pharma R&D. Joined GSK in 1989 and worked in the pharmaceutical industry for 42 years. His experience spans new chemical entity design, development and commercialization, and biopharmaceutical development. Held various positions at GSK including Senior Vice President, Preclinical Development; Vice President, Product Development; Director, Product Development; and Assistant Director, Biopharmaceutical Formulation Development, among others. Led several key cross-functional problem solving and strategic initiatives. BS in biochemistry (1974), and MS and Ph.D. degrees in chemistry (1980) from Penn State University.

Marti Head, Ph.D.

Director Joint Institute, Oak Ridge National Laboratory

Director of the Joint Institute for Biological Sciences, a collaborative research effort between Oak Ridge National Laboratory and the University of Tennessee focused on new approaches to drug development, personalized treatment, diagnosis and prediction of outcomes in health management.

Molecular Foundry

Manual synthesis dramatically stifles innovation in drug discovery for many reasons, including (i) substantial time costs, (ii) high FTE costs, (iii) low synthesis success rates (20-34%), and (iv) a bias towards known reactions.

At DeepCure, we are fixing these problems to unlock the vast chemical space that AI drug design tools want to explore, but don’t, because manually synthesizing such compounds would not be practicable.

Automated Robotic Custom Synthesis

Manual synthesis dramatically stifles innovation in drug discovery for many reasons, including (i) substantial time costs, (ii) high FTE costs, (iii) low synthesis success rates (20-34%), and (iv) a bias towards known reactions. 

 

At DeepCure, we are fixing these problems to unlock the chemical space that AI drug design tools want to explore but can’t because it is not practicably available to most chemists.

Synthetic

Steps

Reaction

Types

Reaction

Development

Industry
Standard

1

4-10

manual

91
100+2

fully 

automated

made possible with automated analytical evaluation, purification, evaporation, etc.

made practicable with automated reaction development

made feasible with miniaturization & quick turnaround (2-10 days)

Notes: 1 4+ by Q2 2024. 2 Planned to reach by end of 2024.

MolGen™

Our molecular generation tool, MolGen™, designs novel, diverse compounds. Using state-of-the-art deep reinforcement learning (RL), MolGen™ constructs synthesizable compounds with features that capture the important molecular interactions for binding and selectivity, as well as deliver the desired ADME-tox profile of the target candidate profile (TCP).

Output of PocketExpander™

MolGen™ – building & iterating compounds

Novel, potent, & selective compound

Hypothesis Generation

Unlike other AI drug discovery companies, DeepCure does not use AI to simply match a library of compounds to a known pocket. Instead, we use our patent-pending AI methods to create causal, data-driven, human-interpretable hypotheses for binding to a given protein target. This enables us to go beyond known binding sites and ligands.

Structure-Based

Our hypothesis generation starts with a rigorous analysis of available structural information. Beyond the standard steps involved in structure preparation, our proprietary protocols also include methods for repairing structures (e.g. building missing loops) and generating more robust structures leveraging molecular dynamics (MD).

PocketExpander™

For most therapeutic targets, there is no data, limited data, or biased data. PocketExpander™ allows us to generate novel hypotheses by leveraging AI/ML and computational chemistry methods to map the protein surface and identify novel binding modes (shown as colored dots). The outputs serve as the blueprints for our molecular generation tool, i.e. MolGen™.

Causal Analysis

ML methods for drug discovery typically focus on correlations, which lead to biases for the types of compounds that have previously failed in discovery. In contrast, DeepCure uses a causal ML approach to find binding interactions without the biases for fruitless binding modes to design truly novel compounds.

Medicinal chemists engage in a conversation with explainable models

DeepCure’s platform is designed to be human-interpretable. By seeing how molecules are predicted to interact with the protein, scientists can make rational design changes to the molecule and explore interesting molecular interactions – ensuring we don’t blindly follow the ML algorithm or chemists’ intuition.