AI/ML Revolutionizing Drug Discovery
AI/ML Revolutionizing Drug Discovery
Innovative TechBio Startups and Investors
“It doesn't matter how beautiful your theory is, it doesn't matter how smart you are. If it doesn't agree with experiment, it's wrong.”
Richard P. Feynman
⚙️ DeepLife
DeepLife is an early stage startup founded in 2019 in France 🥖 by Jonathan Baptista and Jean-Baptiste Morlot, developing the first SaaS platform for Digital Twin of cells, combining state-of-the-art DL algorithms on multi-omics sequencing data, public and private cell atlases, and proprietary DL-based cell engineering tools.
Their platform is an all-in-one solution offering:
DeepLife Datastore ™: the largest harmonized multi-omics database
from 30+ qualified data repositories, with continuously curated organ and disease atlases.
DeepLife Analysis ™: large scale multi-omics data analysis workflow
on 10M cells seamlessly in a flexible coding environment.
Integrate state-ot-the-art analysis tools using R & Python toolboxes.
DeepLife Virtual Cell ™: interpretable AI for System Biology, to identify & prioritize druggable targets and biomarkers, and perform comprehensive pathway analysis.
Beyond using single cell RNA sequencing data, the DeepLife’s Digital Twin is set to expand and encapsulate additional data modalities, including genomics, proteomics, and metabolomics, enabling unparalleled simulation of cellular states with each omics layer processed using their advanced LLM.
Their final goal is to supplement in vitro testing with in silico simulations and rapidly discover molecular triggers for drug discovery, for that reason they are working closely with biotech and pharmaceutical companies and collaborating actively with the academic community by publishing papers and providing open access to our platform’s features and data.
DeepLife has raised $6M.
⚙️ Synsight
Synsight is a deep tech company for developing drugs that target RNA. Founded in France 🥐 in 2013 by Cyril Bauvais and Guillaume BOLLOT, at Synsight they are developing a screening platform that benefits from AI, cellular imaging and robotization, targeting mainly protein-RNA interactions.
In particular, high-content screening allows to detect high-throughput interactions and to obtain massive and robust data by observing several thousand of cellular events, captured by a high-content imager that allows the acquisition of high-throughput and high-resolution fluorescence images (more than 60 000 images per day). The data collected and analyzed are used to train their generative models to propose new molecular entities satisfying a defined phenotype.
For this reason, they developed a specific phenotypic assay to use during high-content screening, the Microtubule Bench technology (MT bench®), that has made it possible to identify and quantify the modulations of small molecules on protein-protein interactions or between protein and nucleic acid interactions. The MT bench is a unique cellular technology for targeting RNA with small molecules, and represents the cornerstone of Synsight’s platform and opens a wide range of challenging applications such as PROTACs, downstream screening of kinases or aggregation into the cell.
In 2022 Synsight secured $1.5M.
⚙️ Biomatter
Biomatter (previously called Biomatter Designs) is a synthetic biology company founded in 2018 in Vilnius, Lithuania 🇱🇹 by Donatas Repečka, Laurynas Karpus, Rolandas Meškys and Vykintas Jauniskis, that leverages generative AI to create synthetic biologic materials, specifically new proteins and enzymes.
The company has developed the Intelligent Architecture™ platform that blends data-driven AI and physics into one seamless digital system, enabling the precise sequence and structure based design to completely redesign existing proteins or create new ones from the bottom up. In turn, it enables scientists to make extremely large steps in function and property design, with applications in:
Sustainable Manufacturing 🔩
Molecular Biology Tools 🧬
Food and Beverages 🥣🥤
Biotherapeutics 🧫 and
Agriculture 🌾
for rapid design of highly specific enzymes and proteins with unique chemistries.
Biomatter has raised €500,000 in seed funding led by Practica Capital (an early-stage VC dedicated to backing Baltic founders), accompanied by 70V (a Revenue Accelerator for B2B Startups) and angel investors, and is part of the ongoing EU grants: “High-throughput Screening System for Efficient Development of Glycosidases” and “Development of a Single Cell Analytical Platform for Archived Clinical Samples”.
Sana Currents is a research & analytics firm covering market-moving catalysts in biotech, pharma and devices.
⚙️ Abzu
Abzu founded in 2018 with offices in Copenhagen, Denmark 🇩🇰 and Barcelona, Spain 🇪🇸 and led by CEO Casper Skern Wilstrup, established itself as a global leader in explainable, rational, and safe AI in the pharmaceutical industry, contributing to new discoveries in disease understanding and RNA therapeutics.
From disease understanding to drug discovery, Abzu has introduced new methods and technology to drive discoveries and reduce R&D costs for pharmaceutical and biotech companies. Their proprietary AI, the QLattice, can be used to accelerate disease understanding, drug design and research insights in Pharma R&D.
Abzu created the QLattice to answer the “why” questions and is a symbolic AI algorithm (Cracking the Code: Hybrid AI’s Logical Edge). In contrast, traditional AI delivers “black-box” models that are good at making predictions, but they are not good at explaining the “why” behind a prediction. This lack of transparency contributes to very real problems, especially with personal information and sensitive applications.
Abzu has raised €13.3M in total funding to date and has collaborations with Roche, Dogodan Therapeutics, Contera Pharma and Checkmate Pharmaceuticals.
⚙️ TandemAI
The AI-powered preclinical drug discovery company TandemAI (China ⛩️, US 🏈) founded in 2021 scored last year $35M in Series A funding (for a total of $60M) led by Qiming Venture Partners (a China based Venture capital firm) with participation from Eight Roads Ventures (a global venture capital firm backed by Fidelity), OrbiMed (an American investment firm based in New York City) and F Prime Capital (a global venture capital firm investing in healthcare and technology).
TandemAI will use the funds to expand its platform, which integrates computational tools with medicinal chemistry, wet lab biophysics and biology to aid in drug discovery. In particular, TandemViz™ 1.0 is their proprietary web-based platform that provides drug discovery clients with a user-friendly and collaborative graphical interface to TandemAI’s suite of computational tools and is based in the synergies of their expertise in physics-based molecular simulation, AI and supercomputing infrastructure—all tightly integrated with their in-house wet lab capabilities.
For example, their iterative wet lab process enables them to repeatedly make and test compounds and provide structural and biophysical data to feed into their computational predictions, providing an accurate and efficient drug discovery solution for their clients.
⚙️ Deep Apple Therapeutics
Deep Apple Therapeutics is accelerating drug discovery with structure-based large library virtual screening and DL models. The San Francisco-based 🌉 company founded in 2021 combines cryo-EM to explore receptor conformations (GPCRs and other target classes), DL and the docking of multi-billion compound libraries generated using the company's proprietary Orchard.ai™ algorithm.
Orchard.ai™ is a virtual library expansion tool for ML enabled acceleration of hit discovery that generates project specific proprietary chemical libraries that are > 95% novel against Zinc22 (a free database of commercially-available compounds for virtual screening, that contains over 37 billion enumerated compounds in 2D), and significantly increases dock scoring against the target of interest, and increases drug likeness for hits with high synthetic tractability.
Leveraging a powerful combination of cryo-EM enabled structural biology, AI-powered pocket extraction, molecular dynamics and protein movement modeling, and ultra-high-volume virtual screening of massive, internally generated virtual libraries, Deep Apple’s DL approach can quickly identify and advance novel candidates addressing well-validated biological targets for a broad range of diseases.
Created by the life sciences venture capital Apple Tree Partners (ATP) with academic co-founders Georgios Skiniotis (at Stanford University, a world leader in cryo-EM and GPCR structural biology), Brian Shoichet (at University of California San Francisco, a pioneer of virtual screening), and John Irwin (at University of California San Francisco, the computational library authority who created the widely used ZINC free virtual library of more than 10 billion synthesizable compounds), Deep Apple emerged from stealth with a Series A commitment of $52M from ATP. Spiros Liras, Ph.D., is the founding CEO of Deep Apple and a Venture Partner at ATP.
⚙️ DeepCell
Deepcell founded by Maddison Masaeli and Mahyar Salek—spun out of Stanford University 🎓 in 2017—leverages microfluidics, optics and AI to examine and classify cells by using its REM-I Platform released on May 17, 2023, that is a cell morphology analysis and sorting platform which comprises the REM-I benchtop instrument with the Human Foundation Model (HFM) and Axon data suite, bringing together single cell imaging, sorting and high-dimensional analysis.
In particular, HFM characterizes each cell in real-time by combining self-supervised learning and morphometrics (computer vision) to extract a 115-dimensional embedding vector representing cell morphology. Then the embeddings representing each cell’s unique morphology are projected onto a morphology UMAP (or Uniform Manifold Approximation and Projection, that is a dimension reduction technique that can be used for visualization) in real-time, and clustered by morphology so that in the Axon data suite users can view, compare and sort morphologically distinct cell populations.
Interestingly, the REM-I platform is offering high-resolution images of single cells completely label-free—that is increasing cell viability and keeping the cells unperturbed— that are captured at high speed, while the AI characterisation of captured cell images happens in real-time.
Just a month ago, Deepcell and NVIDIA announced a collaboration to develop Generative AI Models for Single Cell Morphology, and Deepcell has raised so far a total of $98M in funding over 4 rounds.
⚙️ SyntheticGestalt and Enamine
SyntheticGestalt in Tokyo, Japan 🗾 is a company developing ML models for drug discovery and software for facilitating and automating research in the life-sciences industry. Its AI platform has a cloud-based, scalable structure and can make predictions on large libraries, making it possible to predict physicochemical and ADME/ Tox properties and early toxicity, as well as enzyme functions.
On January 12, 2024, SyntheticGestalt and Enamine announced the start of a joint effort to create a suite of AI models that will enable the generation of synthetically accessible biologically active compounds with optimized physicochemical and ADME/ Tox properties. Enamine has developed the world’s largest reputable collection of chemical compounds, carefully designed and produced for Life Science industries.
For this collaboration, Enamine will give access to SyntheticGestalt to its Enamine REAL database, which has 38 billion molecules in its current edition. SyntheticGestalt will add the REAL database to its Drug Discovery Service, which uses proprietary AI models to provide predictions on physicochemical and ADME/ Tox properties of compounds. Then, Enamine will synthesize the selected compounds within just 3-4 weeks and provide quality pharmacological in vitro profiling data through the in-house tests to streamline and shorten the discovery cycle.
Furthermore, SyntheticGestalt will enhance its pre-trained AI model using the data provided by Enamine. It is expected to become the largest pre-trained model in the world based on the 3D structures of the compounds, to improve the predictive accuracy of SyntheticGestalt’s ML models. The resulting models will be offered on a joint research basis to certain interested parties. Finally, the pre-trained AI model and its performance will be presented at NVIDIA’s annual event, NVIDIA GTC Japan AI Day, in March of 2024.
SyntheticGestalt founded in 2018 by Atsuhiro Hagiwara has raised a total of $11M so far.
AMPED PCR in the UK 🇬🇧 (founded in 2022 by
) provides molecular diagnostics solutions for researchers in Life Sciences AndApplied Markets. They manufacture gold standard PCR products via innovative manufacturing methods: Distributed Manufacturing, Integrated Automation and Modular Solutions.
⚙️ Peptris
Peptris has developed a platform technology to enhance efficiencies across the drug discovery/development cascade using AI/ML. Their neural network models aid researchers to rationalize and provide insights to experimental data in molecular biology and make predictions to generate hypotheses for newer experiments to be done. Peptris that plays tetris with proteins, has curated millions of data points including structure, annotations and properties data of Proteins, Molecules and Interactions from public data sources:
The learned representations of Proteins and Molecules from their pre-trained multi-task networks enable them to predict binding affinities of protein-small molecule and protein-protein interactions. This fundamental tool makes it possible to accelerate the drug discovery process.
Petris, a Bengaluru-based company 🇮🇳, was founded in 2019 by Narayanan Venkatasubramanian, Anand Budni and Amit Mahajan who are computational experts, and Shridhar Narayanan who has contributed to the discovery and development of several clinical candidate drugs, including Enmetazobactam. The company is working on oncology, inflammation and rare diseases and has raised $1M in pre-seed funding led by Speciale Invest (an early-stage venture capital firm based in India).
⚙️ Aqemia
Aqemia is an in silico drug discovery start-up using quantum physics and AI to transform the drug discovery process. The company started in France 🇫🇷 in 2019, as a deeptech spin-off from École normale supérieure, and was founded by Maximilien Levesque, Co-founder and CEO and Emmanuelle Rolland-Martiano, Co-Founder and COO of Aqemia.
Aqemia addresses drug discovery projects from their earliest stage by generating its own data using unique quantum physics algorithms derived from 12 years of research at Cambridge and Oxford (UK) universities, and École Normale Supérieure and CNRS, and has built an innovation engine it calls the Aqemia’s Launchpad.
The company is generating one of the world's fastest-growing drug discovery pipelines and in 2022 raised €30M in a Series A funding round led by
Eurazeo (a French private equity firm and investment group with a diversified portfolio of €35 billion in assets under management, including €23 billion from third parties, invested in more than 600 companies),
Bpifrance (a French public sector investment bank, a joint venture of two state owned enterprises: the Caisse des dépôts et consignations and EPIC BPI-Groupe) through its Large Venture fund,
with the participation of Elaia its historic investor (a French venture capital firm focused on European digital and deep tech startups, from early stage to growth development).
Moreover, in 2023 Aqemia announced a multi-year research collaboration with the global pharmaceutical company Sanofi. As part of the agreement, Aqemia will be eligible to potentially receive up to $140M based on an upfront payment and the successful completion of research and development milestones on a number of specific therapeutic targets.
And just this week Aqemia raised additional €30M Series A funding, thanks to their partners Wendel (one of Europe's leading listed investment firms, operating at the crossroads of industry and finance), Bpifrance Large Venture, Eurazeo, and Elaia.
Clear Vector is an identity-driven cloud security company that was launched in 2021 in US 🥞, in order to give organizations the tools to proactively fight cyberattackers as the world moves into a cloud-native and cloud-first future.
⚙️ Black Diamond Ventures
Black Diamond Ventures (California US, 1998) is a venture capital firm specializing in investments in early to mid-stage companies. The firm invests in biotechnology, medical devices, semiconductor design, data analytics and mobile platforms.
Invests into ➡️
Strateos: a pioneer in the development of remote access laboratories and lab control software for life science discovery. In 2013 Strateos started a collaboration with Eli Lilly.
Prellis Biologics: with a technology in advanced bioprinting and tissue engineering for printed lymph nodes to replicate the immune system as an accessible, scalable platform to discover novel targets & therapeutic antibodies. Prellis Bio’s funding to date is $64.5M.
Atonarp: works at the intersection of emerging digital technology and molecular sciences to unlock insights that improve our quality of life and advance our understanding of the world. And
Alveo: developing cutting-edge molecular testing and cloud-based data analytics for rapid diagnosis and management of infectious diseases. On December 13, 2023, Alveo announced 19 new distributor partnerships across Europe, Africa and the Middle East.
For more:
Until next time 👋,