Adam Riesselman is a computational biologist with experience in developing powerful, interpretable machine learning models for complex biological data. At insitro, Adam is focused on integrating high-throughput measurements with new scalable algorithms to understand disease.
Adam received a BA in Biochemistry: Cell and Molecular Biology from Drake University and his PhD in Biomedical Informatics at Harvard University with Debora Marks as a Department of Energy Computational Science Graduate Fellow. There he developed new statistical models for unsupervised mutation effect prediction from evolutionary data, de novo protein structure prediction via simulation, protein library design with improved biomolecular properties, and small molecule production optimization utilizing biosynthetic pathway engineering.
When not at the computer, Adam likes to cook and enjoy the outdoors by hiking, gardening, and biking.
Alice Starr is a software engineer, with experience designing and architecting scientific research applications. At insitro, Alice is focused on laboratory information and data architecture, making sure we make the most of our generated data. Prior to insitro, she was at Genentech, designing data solutions for the translational research and pathology organizations. She loves to tackle data challenges to advance science, which provides constant opportunities to learn.
Alice received a BS and MS in Mathematics and Computer Science from EPF, France and ITESM, Mexico.
When not working or playing with her two daughters, Alice likes to read and be outdoors as much as possible, walking or running on the beautiful California trails.
Baris works within insitro’s Data Science and Machine learning team, where he applies his dual training in medicine and convex optimization to problems in bioinformatic modeling of disease states and scalable algorithmic approaches to interpreting petabyte-scale genomic and imaging datasets.
Baris grew up in the Bay Area. In a previous life, he studied Chemical Engineering at Princeton and worked in research and development at Gilead Sciences. He then spent the majority of the last decade in an MD-PhD program at Stanford, where he worked with Lei Xing and Stephen Boyd on large-scale computing problems in radiation therapy treatment planning. His research focus was on developing high-performance convex approximations to components of the massive, nonconvex problems arising in medicine and biomedicine.
Outside of work life interests include: the ocean, reading (mostly fiction), and seeing as much live music as possible.
Carolyn is a Computer Science PhD and Masters of Medicine student at Stanford University. She received a BA and MA in mathematics at Harvard University and has interned at Microsoft Research New England.
Her research includes methods for dealing with missing or noisy data, multi-armed bandits, as well as interpretable machine learning.
In her spare time, she enjoys flying radio-controlled planes and quadcopters.
Chris Probert is a computational biologist and computer scientist with extensive experience building deep learning models for genomic data. His current work at insitro is focused on enabling large-scale deep learning on functional genomic data produced by the high throughput biology platform.
Chris is a PhD candidate in Computational Biology (Genetics) at Stanford working with Anshul Kundaje and Christina Curtis where he was an NSF Fellow and an Accel Innovation Scholar. His PhD work focused on large-scale machine learning analysis of functional genomics datasets, including imputation and superresolution of genome-wide epigenomic signals, unsupervised methods for learning differentiation lineages in single-cell RNA-seq, and tissue of origin inference from cell-free DNA fragmentation patterns. He has extensive engineering experience building scalable infrastructure and data architectures to support distributed training of deep learning models from petabyte-scale functional genomic datasets. He also holds an MS and BS in Computer Science, and experience working in both research and product focused software engineering roles at Google, Illumina, and Counsyl.
Outside of work, Chris enjoys running, cycling, backpacking, and backcountry skiing.
Daphne Koller, Board Member
Daphne Koller, Board Member
Daphne Koller is the CEO and Founder of insitro.
Daphne was the Rajeev Motwani Professor of Computer Science at Stanford University, where she served on the faculty for 18 years. She was the co-founder, co-CEO and President of Coursera for 5 years, and the Chief Computing Officer of Calico, an Alphabet company in the healthcare space. She is the author of over 200 refereed publications appearing in venues such as Science, Cell, and Nature Genetics, and has an h-index of 130. Daphne was one of TIME Magazine’s 100 most influential people and is a MacArthur Fellow, a member of the National Academy of Engineering, and a Fellow of the American Academy of Arts and Sciences and the International Society of Computational Biology.
In her spare time, Daphne enjoys spending time with her family, especially while traveling to exotic destinations (62 countries so far and counting), where they enjoy hiking, sailing, scuba diving, and eating fresh local food.
Donald is a Senior Lead Engineer, primarily working on developing strategies for internal pipelines, data provenance, and cloud infrastructure. As part of the data engineering team, Donald is working with the other teams to scale and automate internal pipelines and improve the common infrastructure to support future analyses.
Previously, he was a principal engineer at Counsyl (acquired by Myriad) working across many teams helping to develop a new LIMS system, a platform for variant curation, bioinformatics pipelines, and moving to a cloud infrastructure from on premises.
Donald received a BS and MS in Computer Science from Drexel University.
In his free time, Donald enjoys backpacking, skiing, biking, and reading.
Director of Data Science
As Director of Data Science, Eilon is leading the development of cutting edge machine learning, computational biology and statistical genetics approaches to improve drug development.
His team uses machine learning to integrate observations from large population-level studies with results from various high throughput in-vitro assays to identify potential drug targets.
Eilon has extensive experience in applying machine learning to decipher various biological questions. After completing a dual major B.Sc. in biology and computer science at Tel Aviv University, Eilon joined Rosetta genomics, where he worked on discovering miRNA genes in humans and predicting their targets. He then earned a PhD from the Weizmann Institute of Science under the supervision of Prof. Eran Segal. During his PhD, he developed synthetic biology Massively Parallel Reporter Assay (MPRA) and statistical and thermodynamic models, which he applied to decipher the encoding of transcriptional regulation in yeast. Following graduation, Eilon transitioned to a postdoc at Profs Jonathan Pritchard and Hunter Fraser labs in Stanford Medical school department of genetics. At stanford, Eilon worked on a diverse set of projects including: detection and fine mapping of genetic associations with T cell receptor V-genes expression; software for transplant health monitoring using cell-free DNA sequencing (which was commercialized by Stanford); and detection of functional genetic variants using a novel high throughput CRISPR editing. Eilon is the author of over 20 refereed publications appearing in venues such as Cell, Nature Biotechnology and Nature Genetics.
In his free time, Eilon enjoys hiking and camping outdoors with his family.
Francesco Paolo Casale
Francesco Paolo Casale
At Insitro, Paolo works within the Data Science and Machine Learning Team, where he applies his academic training in statistical genetics, computational biology and machine learning to identify and characterize functional mechanisms in human disease.
Previously, he was a postdoctoral researcher at Microsoft Research New England, working on automated machine learning and on deep learning models for imagining genetics. Before that, he obtained a PhD in statistical genetics from the University of Cambridge and the EMBL-European Bioinformatics Institute, where he developed new methods for genetic association studies and contributed to international projects such as the last phase of the 1000 Genomes Project and the Blueprint initiative. Previously, he obtained a bachelor’s and master’s degree in physics from the University of Naples, Italy.
In his spare time, Paolo enjoys playing soccer, powerlifting, motorcycling and travelling.
Gabriel grew up in Boulder, Colorado. He received his BS in Biological Engineering from Cornell University, and his MSc in Machine Learning from University College London. He completed his master’s thesis at Alzheimer’s Research UK’s Drug Discovery Institute where he studied applications of ML to High Throughput Screening.
In his free time, Gabriel competes in triathlons in addition to skiing and climbing. He also enjoys cooking and backpacking.
Haoyang Zeng is a computational biologist with extensive experience in building machine learning models for functional genomics and therapeutic design.
Haoyang grew up in Sichuan, China, home to most of the panda bears in the world. He earned his BE in Electrical Engineering at Tsinghua University, and his MS and Ph.D. in Computer Science at the Massachusetts Institute of Technology under the supervision of David Gifford. His Ph.D. research focused on developing statistical and deep learning methods for learning the regulatory function of DNA sequences, predicting the binding affinity of peptides to the Major Histocompatibility Complex (MHC) for effective neo-antigen vaccine formulation, and designing novel antibody sequences with improved binding affinity and specificity. Haoyang has co-authored 16 publications appearing in venues such as Nature Biotechnology, Nature Genetics, Cell Systems, Genome Research, and Nucleic Acid Research.
During his free time, Haoyang enjoys playing acoustic guitar, drone photography and traveling.
Hervé is a very enthusiastic applied mathematician with strong research interests in molecular and cell biology. His current work at insitro is focused on the development of new computational methods to generate and extract valuable insight from imaging experiments.
Hervé earned a Master of Machine Learning, Computer Vision and applied mathematics from the Ecole Normale Supérieure in Paris before pursuing a PhD at the Pasteur Institute, where he spearheaded the development of FISH-Quant, a software to quantify 3D microscopy images of single RNA molecules, and GRAAL, a Bayesian genome assembler using HiC data. As a postdoc in Robert Tjian’s lab at UC Berkeley, he developed computational methods to improve the quantification of high resolution microscopy data for insight into transcription regulation and spatial genomic organization.
During his free time, Hervé enjoys hiking and giving autographs pretending he is a famous NBA player.
James is a Senior Lead Data Engineer, primarily working with distributed systems and big data applications. As part of the Data Engineering team, his goal is to facilitate the development of machine learning pipelines, focusing on scalability, efficiency and repeatability.
James was previously a Ph.D. candidate at Stanford University, where he devised robot motion strategies for the Honda Asimo and Mars rover prototypes. He holds a M.Sc. in Scientific Computing from Stanford and a B.Sc. in Mathematics From Texas A&M University. Prior to joining Insitro, James worked on creating bioinformatics tools at Roche and Helix, and he co-authored a book on big data architectures.
In his free time, he chases after his dog and three cats, enjoys playing board games, travels internationally, and hacks on open-source software projects.
Jeevaa is a Computer Science masters student from University of Toronto. At insitro, Jeevaa focuses on building machine/deep learning models to improve the effectiveness of our high-resolution cellular microscopy platform.
He completed a BSc. in Applied Physics at the University of Toronto before continuing MSc. in Applied Computing at the same institution. He developed an interest in ML during his bachelors which motivated him to pursue it further. During his masters, he worked on various deep learning projects ranging from biomedical image quality enhancement to accent style transfer.
Jeevaa enjoys playing and watching soccer, traveling and spending time with friends.
Joe Marrama is a software engineer with background in heathcare data and distributed systems. At Insitro, Joe is focused on ensuring that the large amount of data we generate is effectively processed and stored.
Joe is a native of Oakland. He attended Stanford where he graduated with a BS in Symbolic Systems and a MS in Computer Science. Prior to Insitro, Joe worked at Nuna Health, where he worked with the federal Medicare program to build a system that evaluated healthcare providers on quality of service and cost-effectiveness. He loves to tackle complex engineering problems in the service of helping others.
Outside of work, Joe enjoys surfing, skiing, mountain biking, cooking, and reading.
June Jung-Eun Shin
June Jung-Eun Shin
June Jung-Eun Shin is a computational biologist with experience in developing statistical models for protein design and antibody discovery. June is a graduate student at Harvard University pursuing her PhD in Systems Biology in Debora Marks’ lab. Her graduate research is focused on developing computational models to accelerate antibody discovery: designing high fitness libraries for screening, learning sequence determinants of developability such as stability and poly-reactivity, and improving the affinity of specific antibody sequences.
In her spare time, June enjoys playing sports, taking a stroll in the park, and just being outside when the weather is nice.
Kathryn is a data engineer with a background in the microbiome and cloud computing. At insitro Kathryn is working with the data engineering, and data science and machine learning teams to build and scale data analysis pipelines in the cloud.
Before joining insitro, Kathryn worked at Second Genome building metagenomics pipelines and analyzing microbiome data. Kathryn received her Master’s in Bioinformatics from the University of Michigan and worked in Pat Schloss’ lab on projects in microbial ecology, clostridium difficile, and colorectal cancer.
In her free time, Kathryn enjoys playing and watching hockey, traveling, and scuba diving.
Matthew is a computer scientist with experience in developing and deploying machine learning models. His focus is on applying deep learning models to gain insights from imaging data.
Prior to insitro, Matthew acquired his M.S. in computer science from Stanford University. His graduate research focused on applying machine learning methods to infer diagnostic information from medical imaging, and applying natural language processing to efficiently gather data from unstructured reports. Additionally, he has extensive experience building scalable data infrastructure to support computationally intensive analysis of large datasets. He has worked in both an academic research setting and industry setting for companies such as Google and several startups.
In his free time, Matthew likes to catch up on reading, spend time with friends and family, and continue the unending quest to find a third hobby.
VP of Data Engineering
As VP of Data Engineering, Matt is responsible for leading the development of data pipelines, data storage systems, provenance tracking, and engineering infrastructure to support the high-throughput biology and Machine Learning teams at insitro.
Previously, as VP of Engineering for Myriad Genetics, Matt led engineering teams focused on software automation and genomic data pipelines to make high complexity genetic testing routine in clinical practice. During his time at Counsyl, Matt developed and scaled the software behind several successful prenatal genetic testing products.
Matt holds a Ph.D in Computer Science from MIT, where he developed efficient bioinformatic algorithms with applications in evolutionary genomics and population genetics.
In his spare time, Matt enjoys running, drawing, programming for fun and playing with his kids.
Michael is a computer scientist with a strong interest in the development and application of computational techniques for scientific discovery. His current work at insitro is focused on deriving insights from patient data to help guide disease modeling efforts.
Michael studied computer science at Stanford University, where he had the opportunity to contribute to research across machine learning and medicine.
In his free time, Michael loves to dance, run, learn new things, and joke around with friends.
Mohammad "Muneeb" Sultan
Mohammad "Muneeb" Sultan
Mohammad “Muneeb” Sultan is a computational chemist with experience working at the interface of computational biophysics, free-energy methods, machine learning, and statistical mechanics. His current work at insitro is focused on building up the machine learning platform, and designing novel methods for analyzing the outputs of various high throughput assays.
Muneeb is a native of Pakistan and grew up in the city of Rawalpindi. He got his undergraduate degree in Chemistry at Yale, and his PhD in Physical Chemistry at Stanford under Vijay Pande. At Stanford, Muneeb focused on studying oncogenic kinases using the Folding@home distributed computing platform, collecting and analysing some of the largest simulation datasets of their kind. Simultaneously, he also worked on developing new Machine learning algorithms for accelerating free-energy calculations and molecular simulations. Muneeb has co-authored 17 publications appearing in venues such as PRE, PNAS, Nature Scientific Reports, and Nature Chemistry.
During his free time, Muneeb likes to powerlift, do yoga, explore the bay area, create digital art, cook, and listen to music.
Olivia is a data engineer with a background in automating the analysis of biochemical data to enable timely, high-quality insights.
At insitro, Olivia is collaborating with the data engineering, machine learning, and process engineering teams to develop data pipelines and software to support wet lab and computational experimentation at scale.
Prior to insitro, Olivia designed and developed custom production data pipelines at Synthego Corporation, including an image processing pipeline to automate the analysis of live-cell microscopy images. She also held positions within Deloitte Consulting’s Life Sciences practice and at Medtronic Diabetes. Olivia earned her B.S. in Materials Chemistry from Harvey Mudd College, where she was a recipient of the Lewis Research Fellowship in Chemical Engineering. Her fellowship research focused on modeling membrane transport to inform the development of novel transdermal drug delivery systems.
While not at work, Olivia enjoys hiking and running in the Bay Area hills, playing her cello, analyzing NBA basketball statistics, and trying to keep her houseplants alive.
Panagiotis "Panos" Stanitsas
Panagiotis "Panos" Stanitsas
Panagiotis “Panos” Stanitsas is a computer scientist with experience in developing and deploying computer vision models in diverse application domains. At insitro, Panos focuses on the research and development of inference schemes for imaging data.
Prior to insitro, Panos worked at 3M as a Senior Data Scientist, where he focused his research and development efforts at the intersection of material science with computer vision for problems and products spanning the transportation safety space. Panos received his PhD in Computer Science and Engineering from the University of Minnesota, advised by Nikos Papanikolopoulos and Vassilios Morellas at the Center of Distributed Robotics. During his PhD, Panos derived amalgamations of deep learning models with uncertainty sampling schemes and metric learning methodologies, with emphasis on the problem of cancerous tissue recognition from hematoxylin and eosin stained tissue slides.
In his free time, Panos enjoys playing basketball, cooking, weightlifting, and feverishly trying to find the best food spots in the Bay Area.
Ralph Ma is a software engineer experienced in developing, maintaining and serving machine learning models. His current work at insitro is focused on improving experimentation and serving platforms to better accommodate the scale and uniqueness of the biological data collected.
After graduating with a B.S. in Computer Science from Stanford, Ralph worked at Google using machine learning to improve labeling of places with low impressions. Also at Google, he constructed embedding models to assist efforts in automating web actions by better understanding semantics of UI elements.
In his free time, Ralph enjoys rock climbing, fishing, and winning his fantasy football league.
Robin is passionate about working at the interface of biological and computational problems. She studied Bioinformatics as an undergraduate at UC San Diego, and recently completed her doctorate in Biophysics from Stanford, where she was a NSF and NVIDIA Fellow. Her PhD work focused on molecular dynamics simulation of protein-ligand binding, integrating computational methods development with interesting discoveries about specific proteins and drugs. During the course of her research, Robin worked on parallel algorithms, online analysis of large datasets, visualization methods, and contributed to the development of multiple related software packages, including AMBER and VMD.
In her free time, Robin likes to race bicycles, contribute to open source software, and scuba dive.
Santiago is passionate about developing computational methods to enable science. He holds a Doctorate degree in Computational Mathematical Engineering from Stanford University, where he worked with Michael Saunders and Yinyu Ye. His PhD work focused on extending interior-point methods to efficiently solve new convex problems, and was awarded the Gene Golub dissertation award for his innovations.
Before joining Insitro Santiago was a senior machine learning researcher at Apple Inc. Where, amongst other things, worked on methods to accelerate DNN training.
In his free time Santiago enjoys spending time with his family, running, trying out different cuisines and flying around in a small plane.
Chief Data Officer
Dr. Serafim Batzoglou is insitro’s Chief Data Officer (CDO).
Serafim joins insitro from Illumina, where he recently served as the company’s Vice President of Applied and Computational Biology. There, he led research and technology development of AI and molecular assays to make genomic data more interpretable in human health. His computational team developed deep learning methods for image processing across sequencing instruments, as well as for classification of patient genomic variants according to their molecular cellular effects and pathogenicity, facilitating diagnostic ability for genetic disease patients.
During his tenure at Stanford from 2001 to 2016, Serafim focused on the application of algorithms and machine learning, the study of large scale genomic and biomedical data, and the development of widely used tools in genomics. His research has spanned sequence assembly, genome alignment, identification of functional elements including gene coding regions, splice sites and transcription factor binding sites, folding of RNA structures, population genomics, cancer genomics, sequencing technologies and their use in personal genome and metagenome reconstruction, and single cell transcriptomics, among other topics.
Serafim is also the co-founder of DNAnexus, a secure cloud platform and global network for scientific collaboration and accelerated discovery, and previously served on the company’s board of directors. He has served on many scientific advisory boards, including at 23andMe, Moleculo and NextBio. He is the recipient of numerous awards, including being named one of the top 100 young innovators by MIT Technology Review, The International Society of Computational Biology’s inaugural Innovator Award and one of the top 25 voices in Precision Medicine by Insight Monk. Dr. Batzoglou holds a Ph.D. in Computer Science, a Master’s in Electrical Engineering, and a B.S. in Mathematics and Computer Science from MIT. In his Ph.D. work, he focused on computational biology and was involved in the assembly and comparative analysis of the first mammalian and human genomes.
Srinivasan is an MSc in Applied Computing candidate in the Department of Computer Science at the University of Toronto. His research interests are machine learning and image processing for computer vision and healthcare applications. His work at insitro involves developing learning models for the efficient analysis of our high-throughput microscopy platform.
During his Master’s program at the University of Toronto, he has worked on various machine learning projects, such as early prediction of sepsis onset and adversarial imitation learning by planning. Prior to this, he was a Lead Engineer in the Medical Imaging team at Samsung Research, India working on ultrasound imaging applications. Srinivasan holds a dual degree (Bachelors + Masters) in Biotechnology and Biochemical Engineering from the Indian Institute of Technology, Kharagpur.
In his free time, Srinivasan enjoys singing, hiking and reading books.
Thomas "Tom" Soare
Thomas "Tom" Soare
Tom is a statistical geneticist and data scientist excited about integrating genomic and deep
phenotypic data to impact human health.
Prior to joining insitro, Tom was a statistical geneticist and computational biologist at Goldfinch
Bio, conducting genetic association studies in large-scale sequencing cohorts to identify
common and rare variants that associate with a rare kidney disease, focal segmental
glomerulosclerosis (FSGS). To enable target identification and validation at Goldfinch, he also
analyzed scRNAseq data of human organoids and tissues, and analyzed image data for cellular
assays. Before that, he examined the effect of early-life adversity on psychopathology and DNA
methylation, as well as conducted genetic association studies of depression and cortical
thickness at the Center for Genomic Medicine at the Massachusetts General Hospital. Tom
holds a PhD in Psychology with a focus on Population Genetics from the University of
Washington where he studied the effect of satellite image-derived landscape features on
dispersal of an ant species.
In his spare time, Tom enjoys hiking, camping, sailing, and traveling with his family.
Thomas is a machine learning researcher interested in developing empirical methods to better understand when and why deep learning approaches fail.
As an intern with the machine learning team, he works on characterizing distribution shifts in imaging problems. His undergraduate research at UC Berkeley in Ben Recht’s lab focused on similar problems for deep sequence models in the context of machine translation.
Away from the keyboard, Thomas can be found in the outdoors, or at home, reading