On February 24, 2021 Insilico Medicine announced the nomination of a preclinical candidate for a novel antifibrotic target discovered using AI, and the novel molecule designed by AI for the first time bridging biology, chemistry, and clinical trial outcome prediction with its Pharma.AI™ platform. Today, we are happy to report that the first healthy volunteers have been dosed in a first-in-human (FIH) microdose trial of ISM001-055 — a potentially first-in-class small molecule inhibitor of a novel biological target developed by Insilico Medicine for the treatment of idiopathic pulmonary fibrosis (IPF), an irreversible progressive orphan disease that affects an increasing number of people globally, with no cure currently available This small molecule showed promising efficacy for IPF and a good safety profile that led to its nomination as a preclinical drug candidate in December 2020 for IND-enabling studies. With the start of its first clinical program in Australia, Insilico Medicine has moved into a new era in the company's development.

The entire drug discovery path from an initial concept to novel target discovery and preclinical drug candidate nomination took Insilico Medicine a small fraction of cost and time for a typical preclinical program which is estimated to be around $430 million out-of-pocket expenses and above $1 billion capitalized, and takes anywhere from three to six years to finalize. The antifibrotic targets were picked using AI with two main criteria: the target must be an important regulator of pathways implicated in fibrosis and the target must be important in aging. The AI-powered target discovery tools now available in PandaOmics ™platform were used for target selection and prioritization. Once the antifibrotic targets were discovered and prioritized, Insilico utilized its Chemistry42™engine. This extraordinary drug development sprint has proved to be possible owing to Insilico Medicine's end-to-end Artificial Intelligence-powered platform Pharma.AI. The highly integrated architecture of the AI platform allowed for linking Biology and Chemistry into a smooth, well-orchestrated research workflow, resembling an industrial conveyor line.

To the best of our knowledge, this achievement sets a historical precedent for a company to be able to bring to the clinic an AI-discovered molecule based on the AI-discovered novel target -- rapidly and at a low cost. A number of other drug candidates for other indications were also designed using Pharma.AI — for Insilico's own pipeline (e.g. a recent drug candidate for kidney fibrosis), and for the company's clients — illustrating the system's ability to replicate success and generalize to other therapeutic areas.

Idiopathic Pulmonary Fibrosis is a broad medical condition that is limited to the lungs and primarily affects older adults. As the disease progresses, the health of the patient gradually deteriorates leading to potentially life-threatening pulmonary failure.. As of now, there is no cure available for patients.

To build the initial hypothesis, we used our target discovery module PandaOmics and trained it on a collection of omics and clinical datasets related to tissue Fibrosis and annotated by age and sex. PandaOmics then performed sophisticated gene and pathway scoring using a family of iPANDA algorithms previously published in Nature Communications, and came up with relevant targets via deep feature synthesis, causality inference, and de novo pathway reconstruction. The target novelty and disease association scoring was assessed by a natural language processing (NLP) engine, which analyses data from millions of data files, including patents, research publications, grants, and databases of clinical trials. As a result, PandaOmics revealed 20 targets for validation, and one novel intracellular target was prioritized for further analysis.

Next, we applied Chemistry42 — our generative chemistry module for drug discovery. This module includes an ensemble of generative and scoring engines that can "imagine" molecules from scratch using cutting-edge deep learning technologies pioneered by Insilico Medicine for pharmaceutical research applications back in 2015. Chemistry42 automatically creates drug-like molecular structures with appropriate physicochemical properties. In this case, Chemistry42 was used to design a library of small molecules that bind to the novel intracellular target revealed by PandaOmics.

The series of novel small molecules generated by Chemistry42 showed promising results on target inhibition. One particular hit ISM001 demonstrated activity with nanomolar (nM) IC50 values. When optimizing ISM001, we managed to achieve increased solubility, good ADME properties, and favourable CYP inhibition profile — with retained nanomolar potency. Interestingly, the optimized compounds also showed nanomolar potency against nine other targets related to fibrosis.

In follow-up in vivo studies, the ISM001 series of molecules showed activity improving fibrosis in a Bleomycin-induced mouse lung fibrosis model, leading to further improvement in lung function. These compounds also demonstrated a good safety profile in a 14-day repeated mouse dose range-finding (DRF) study.

The best-performing molecule of the ISM001 series was nominated as a preclinical drug candidate in December 2020 for IND-enabling studies. A final version of the drug candidate, ISM001-055, demonstrated highly promising results in multiple preclinical studies including in vitro biological studies, pharmacokinetic and safety studies. The compound improved myofibroblast activation which contributes to the development of fibrosis. ISM001-055's novel target is potentially relevant to a broad range of fibrotic indications.

After completing IND-enabling studies, we are happy to announce today that we have initiated the first-in-human exploratory microdose trial to begin characterizing the pharmacokinetic profile of ISM001-055 drug candidate in humans. The trial, administering ISM001-055 intravenously in healthy volunteers is being conducted in Australia.

The whole pre-clinical development program , from hypothesis to preclinical drug candidate, took just under 18 months to complete at a budget of around $2.6 million. This accomplishment is several orders of magnitude faster and cheaper when compared to the traditional drug discovery process. Even more importantly, with this milestone, and with other drug discovery successes, the team at Insilico Medicine demonstrated that the AI-driven approach to drug discovery is a way to increase research productivity.

With the initiation of the first-in-human trial of our drug candidate today, we have made a bold step forward towards further increased commitment to bringing hope to many people around the globe suffering from fibrosis and other diseases.

Identifying a novel pan-fibrotic target, developing a drug candidate with an unprecedented mechanism of action, and bringing it to the first-in-human clinical trial in under 2 years may seem like a miraculous leap of progress, but the path to this early success has been long and thorny. Being a pioneer in the AI-driven transformation of the pharmaceutical industry is a challenging but rewarding endeavor.

We founded Insilico Medicine in 2014 as a deep learning company from the first days, inspired by a then rising recognition of deep learning technologies as a global game changer in many industries, after a series of widely publicized successes, including famous ImageNet competition where a convolutional neural net AlexNet demonstrated outstanding performance towards image identification. In the same year, Google announced that their deep learning system managed to identify cats in YouTube videos without any previous knowledge or instructions about cats -- the model did it via unsupervised learning process. Those two, and many other achievements in the area of deep learning created excellent momentum for the AI field, and essentially catalyzed an exponential growth in both theoretical AI research, and practical applications in most industries.

In 2015, around the period of time when Deep Learning gained global recognition and rose in prominence outside pharmaceutical space, we started playing with generative adversarial networks (GANs) for drug discovery applications. GANs are a type of deep learning architecture that have one neural net inventing new stuff to match some predefined requirements (a generator), while another neural net is trying hard to prove the generator wrong. Both neural nets are tasked with learning until the generator ends up with the best result. GANs use low-dimensional formats like binary fingerprints, SMILES strings, graphs, and other light representations to generate molecules.

We described the concept of using an Adversarial Autoencoder (AAE) for the generation of novel molecules in our paper "The cornucopia of meaningful leads: Applying deep adversarial autoencoders for new molecule development in oncology," submitted for publication in Oncotarget in June 2016. This publication coincided closely with the publication of a similar idea by Alan Aspuru-Guzik's team in their ArXiv paper "Automatic chemical design using a data-driven continuous representation of molecules." During this period we started to collaborate and build a global community around generative chemistry.

Later we developed several improvements and new features to our GAN-based AI platform for drug design and started patenting our findings. In 2017 we built multiple working GAN models, including druGAN for fingerprints, ORGAN for SMILES, various recurrent neural networks (RNN) architectures with reinforcement learning and LSTM, agile temporal convolutional networks (ACTNs), and a reinforced adversarial neural computer (RANC). In 2018 we progressed towards building and validating a powerful deep generative model, generative tensorial reinforcement learning (GENTRL). GENTRL is a new AI system for drug discovery that dramatically accelerates the process of lead discovery from years to days. We made the code publicly available on GitHub to inspire a broader community of scientists to keep building on this work.

Eventually, we built an end-to-end AI platform Pharma.AI with three key components; a target discovery and multi-omics data analysis engine PandaOmics, a de novo molecular design engine Chemistry42, and a clinical trial outcomes prediction engine InClinico.

During the last several years, we have also been investing heavily in the synthesis and validation of the molecules suggested by our engine for various projects -- using a network of contract research organizations.

AI platforms that deploy virtual screening and the de novo generation of molecules have demonstrated the power of deep neural nets as tools for intelligent hit discovery. In this context, generative adversarial networks (GANs) were shown to be especially noteworthy — as we demonstrated in our pioneering work in generative chemistry with the first peer-reviewed papers published in 2016 and 2017, and many other subsequent publications.

In 2018 we published research revealing the first JAK3 inhibitor generated using the Entangled Conditional Autoencoder (ECAAE) with experimental validation. At that time, our engines could already achieve reasonable hit rates for GPCRs and other target classes.

In 2019 we reached a significant proof-of-concept milestone where we predicted a molecule for a well-known target called DDR1 in just 21 days — and successfully validated prediction in vitro and in vivo. The results were published in Nature Biotechnology and attracted attention and feedback from leading drug hunters and AI researchers. The milestone demonstrated the incredible potential of using AI to identify drug candidates and represented the first step of the overall traditional drug discovery process.

Over the years, Insilico Medicine has published more than 200 papers in peer-reviewed journals, AI conferences, and presented results at more than 200 conferences. During this time, we encountered excitement and support from the AI community and skepticism from the drug discovery and development community. Our early models used to generate molecules that were not diverse enough or easy to synthesize, and the targets that we used for public proofs of concept were well-known or druggable with known hits. With time, our improved results persuaded a number of fierce skeptics to become our supporters or even advisors and partners.

In 2020-2021 we made a significant advance with our AI platform and in February 2021 announced the nomination of a preclinical drug candidate for IPF, a small molecule inhibitor designed by Chemistry42 for a novel pan-fibrotic target discovered by PandaOmics. This was already a major practical validation for the AI platform, while just 2 month later, in April, we announced a second preclinical drug candidate — for Kidney Fibrosis, further cementing our ability to conduct drug discovery in a revolutionary new way, compared to "traditional" process. And finally, we have arrived at the first-in-human clinical trial today, marking the start of the new stage in our research validation for Pharma.AI platform, and a new level for our business — becoming a clinical-stage drug discovery company.

Throughout the history of the pharmaceutical industry development, drug discovery was, for the most part, a serendipity-driven tedious process of "trial-and-error", with poorly predictable expectations and extremely low success rates of bringing initial drug ideas to the market. This was conditioned by quite limited understanding of biology, lack of experimental data, and the absence of modeling tools and computational resources. The situation started to change for the better in the 1990s with the emergence of so-called rational drug design, pioneered by such companies utilizing structure-based computational discovery strategies.

In about the same period, the progress in a number of research-enabling technologies started to unfold rapidly, including high throughput screening, combinatorial chemistry, high throughput sequencing, and omics analytical methods — all generating massive amounts of data in the biomedical field. Simultaneously, the world has been witnessing the unfolding revolution in hardware development (high-performance computing, GPUs, and data centers of the new generation), and computational data modeling methods, including the advent of Artificial intelligence technologies.

In the early 2020s, a qualitative leap has been made in the area of Deep Learning and the underlying modeling architectures — deep neural networks. The Famous ImageNet competition in 2012 marked the rise of convolutional neural networks in prominence, and in 2014 Ian Goodfellow introduced Generative Adversarial Networks, which would later become one of the most advanced methods in generative chemistry and chemical drug design, owing to our works, and works by some of our peers.

Around the time deep learning was rising in prominence in such applications as image recognition, Insilico Medicine was founded in 2014 as the company pioneering the application of deep learning technologies for drug discovery. Those were the early days the pharmaceutical artificial intelligence and Insilico Medicine had to perform dozens of complicated pilot studies with the pharmaceutical and biotechnology companies to learn where AI can help accelerate and cost-down the process, or augment human decision making leading to the development of the creation of the first end-to-end AI-driven drug discovery platform.

The company's AI-first strategy, adopted from day zero, and a laser-sharp focus on building, validating and iteratively improving its deep learning-based generative biology and chemistry pipelines of models gradually led to the emergence of what we call "end-to-end" platform, Pharma.AI, which covers a whole spectrum of drug discovery, starting with disease modeling and target discovery — to hit discovery and various stages of preclinical optimization. The platform also includes InClinico — a specialized system for predicting outcomes of clinical trials. Today, the accumulated experience of Insilico Medicine in the application of advanced technologies to biological and chemical modeling, and possession of the most comprehensive drug discovery platform on the market, gives the company a strategic advantage in the race for discovering new first-in-class targets and molecules in record times and at low budget.

Currently, AI is widely adopted by many pharmaceutical and biotech companies for specific tasks like virtual screening or data analysis. Still, drug discovery remains the same for the most part — a cascade of poorly connected stages, without an efficient back-propagating element of learning from mistakes across different departments. With integrated end-to-end platforms like Pharma.AI, organizations can streamline their efforts and accelerate the translation of ideas into actual clinical candidates and further on. Insilico Medicine's work on building the most comprehensive AI-driven drug discovery platform over the years resulted in a new integrated research process where data and knowledge flow seamlessly from one stage of the process to another, leading to a rapid and cost-efficient workflow.

A number of companies in drug discovery were started in recent years as AI-first companies, and they already demonstrated substantial improvement of this R&D model over the industry's common practice, having achieved significant speed of research and cost reduction for bringing drug candidates to clinical trials. Those companies represent a rising trend of drug discovery industrialization. However, to the best of our knowledge, Insilico Medicine is the only company on the market which managed to bring the AI-generated molecule for the AI-discovered novel target to the clinic — within record time and at low budget.

We are proud to contribute to a transition of the pharmaceutical industry from poorly predictable serendipity-driven and organizationally disconnected drug discovery, which resembles a drug hunter's craftsmanship, towards a more predictable AI-driven process — industrialized drug discovery. This paradigm shift is the only way to sustain the industry productivity at positive levels and help maintain decent return on R&D, allowing for cheaper and better therapeutics available faster for those who need them. We hope that the results of our work and our successes will inspire a much greater shift to a new drug discovery paradigm by pharmaceutical organizations all around the globe.

To help the pharmaceutical industry expand the drug discovery and development capabilities we productized and made available for licensing our target discovery and generative chemistry system. We invite the pharmaceutical companies to join the Pharma.AI platform community by deploying PandaOmics ™ and Chemistry42 ™ systems, and piloting inClinico ™ clinical trial outcome prediction system.