THE CURE FOR PROTRACTED
PHARMACEUTICAL DEVELOPMENT
Standigm discovers drugs using AI, saving time and cost when compared to traditional methods.
Our AI reveals the patterns hiding in the today’s biomedical data that will lead to tomorrow’s medicines.


THE
PROBLEM

Drugs can take a decade of research and over a billion dollars' worth of development before they reach the market. Resources are wasted in the pre-discovery phase through a trial and error process that yields more error than success.

There are hidden insights in biomedical data, waiting to be discovered and to lead towards promising drug candidates.

Unfortunately, these patterns are too complex and diffuse to be detected by the human mind; this is where a more powerful solution comes in – Standigm’s latest artificial intelligence technologies.

THE
SOLUTION

Standigm removes the traditional guesswork from data analysis by using our innovative AI, automatically examining whole biomedical databases to learn what is hiding just out of sight.

By applying our state-of-the-art machine learning technology to real data, we eliminate some of the uncertainty in the drug discovery process; instead of fishing in the dark for effective treatments, we can focus on developing candidates that are primed for success.

Standigm cuts through the noise and presents data that are most pertinent to the treatment of diseases, saving time and money by shortening the development cycle.

TECHNOLOGY
ACTIVE DATA
PARSING
Standigm recognizes that the biomedical data are neither clean nor simple; we ingest various databases, established biological models, published texts, and other sources into a comprehensive corpus of information. We then do the heavy lifting of parsing the dataset to make it actionable.
AI MODELING
 
Once we have the dataset organized, we run it through our artificial intelligence system. Our AI automatically analyzes the innumerable ways the data can be combined and configured to create weight-optimized, deep learning models based on rules hidden in the data. Not only does our AI generate models, but it also provides an explanation of how these models were generated, offering necessary insight for researchers.
BIOLOGICAL
INTERPRETATION
From these AI models, we then provide biological interpretations of how the implicated drug compounds would interact with people in the real world. This information is crucial to effectively decide which drugs to assemble and test, leading to viable solutions from the promising candidates.
PROJECT
Project 1: Predicting synergetic drug combinations
The goal of the project is to predict synergetic drug combinations that effectively kill cancer cells. The disease context, the characteristics of drugs, and the interaction between drugs and diseases are described using various chemical properties of drugs, target proteins/signaling pathways of drugs, monotherapy drug response data and genomic data for cell lines, among others. Based on these data, we designed three types of input features (cell line-specific, drug-specific, and drug-cell line interaction features). With various combinations of these features and different learning parameters, we built an ensemble of gradient boosting classifiers, which ranked 3rd among 71 teams worldwide in "AstraZeneca-Sanger Drug Combination Prediction Dream Challenge (2015~2016)". The methods will be applied to precision medicine, patient stratification, and therapeutic/diagnostic design.
Status: Completed in May 2016
Project 2: Learning drug-perturbed data
The goal of the project is to predict new indications for existing drugs, called drug repositioning, from the features of drug responses and drug uses discovered via deep learning. Here, the drug responses and uses are described by the data of drug-perturbed gene expressions and of therapeutic usage labels, respectively. We have been developing various multimodal learning methods (XGBoost, Compact Bilinear Pooling, etc.) for robust feature learning. These models suggest 20 hits with new drug indications. For two of the 20 drug repositioning hits, literature has shown their experimental validations. For the remaining hits, Standigm is designing in-vivo and in-vitro experimental validations to demonstrate Standigm.AI’s prediction power. Our drug repositioning AI will discover hidden relational patterns of drugs and indications, ultimately saving the cost of drug development.
Status: Completed in January 2017
Project 3: Building & Learning biological knowledge
The goal of the project is to predict missing relationships between proteins, drugs, and diseases by learning from a biological knowledge GraphDB. We constructed the biological GraphDB consisting of nodes (32,373 proteins, 7815 drugs, 3721 diseases, etc.) and edges (55,618 drug-disease edges, 125,686 drug-protein edges, etc.) using knowledge from various open and private sources. Users can easily access and visualize the GraphDB via web browsers and navigate the DB using the Cypher query language. We are developing models to predict unknown links between the nodes (proteins, drugs, disease etc.) in the GraphDB. The models will be applied to finding new drug indications, new drug targets, and new disease biomarkers.
Status: In progress (January 2017)
TEAM

At Standigm, we’ve assembled a group of artificial intelligence, systems engineering, and systems biology experts to address one of the world’s most complex problems: the discovery of medicines.

With over 20 years of professional experience, our team is ready to accelerate your research.



Jinhan Kim
Jinhan Kim
CEO, Co-founder
Previous: Samsung Advanced Institute of Technology, NCSOFT
Education: PhD in Artificial Intelligence, The University of Edinburgh
Sangok Song
Sang Ok Song
COO, Co-founder
Previous: Samsung Advanced Institute of Technology, UPMC, Cornell University
Education: PhD in Process Systems Engineering, Seoul National University
Sojeong Yun
So Jeong Yun
CRO, Co-founder
Previous: Samsung Advanced Institute of Technology
Education: PhD in Systems Biology, POSTECH
Gaya Nadarajan
Gaya Nadarajan
Senior Scientist
Previous: Seoul National University, The University of Edinburgh, Altion Software
Education: PhD in Artificial Intelligence, The University of Edinburgh
Heejeong Koo
Hee Jeong Koo
Senior Scientist
Previous: Center for Plant Aging Research / Institute of Basic Science
Education: PhD in Systems Biology, POSTECH
Minkyu Ha
Minkyu Ha
Software Engineer
Previous: LG Electronics
Education: BSc in Computer Engineering, Pusan National University
Minkyu Shim
Minkyu Shim
Software Engineer
Previous: SKC&C
Education: MSc in Software Technology for the Web, Edinburgh Napier University
Moonhee Lee
Moon Hee Lee
Administrative Staff
Previous: Samsung Advanced Institute of Technology
Education: BA in Public Administration, Kyungpook National University
Seungkwon Cho
Sung Kweon Cho
Advisor, Clinical Pharmacology
Education: PhD, Yonsei University College of Medicine
MD, SungKyunkwan University College of Medicine
PARTNERSHIP
Investors
Collaborators
CONTACT
US
Location: Standigm, 5th Floor, 56, Nonhyeon-ro 67-gil, Gangnam-gu, Seoul, 06250, Rep. of KOREA