TechBio: Latest Trends 🛸
TechBio: Latest Trends 🛸
MetaphysicalCells: A newsletter about Science, Technology and AI Drug Discovery
“Most people use statistics like a drunk man uses a lamppost; more for support than illumination”.
By Andrew Lang
News ☄️
Insilico Medicine's leadership to address key challenges in AI drug discovery at BIO Convention
Syntekabio to Showcase Advanced AI Drug Discovery Technologies at BIO International Convention 2024
Sanofi, Formation Bio, OpenAI Partner on AI-Powered Drug Discovery
LabGenius raises £35m for AI-powered drug discovery
Accenture Invests in Turbine to Accelerate Use of AI-Powered Cell Simulations for Biopharma Research and Development
From black holes to AI driven drug discovery – collaboration wins the day
Artificial Intelligence (ai) In Drug Discovery Market to be Worth $7.1 Bn by 2030 - Report by Vantage Market Research
Rakovina Therapeutics 💠
Rakovina Therapeutics (TSX.V: RKV) is using cutting edge Deep Docking™ AI to target DNA-damage response (DDR) mechanisms and create innovative precision medicines with the potential to improve patient outcomes across multiple tumor types. DDR is a collection of processes that identify and correct DNA damage in our cells millions of times every day, and many cancers harbor a defect in natural DDR mechanisms.
Deep Docking is a novel DL platform that is suitable for docking billions of molecular structures in a rapid and accurate way by utilizing quantitative structure–activity relationship (QSAR) deep models trained on docking scores of subsets of a chemical library, to approximate the docking outcome for yet unprocessed entries and, therefore, to remove unfavorable molecules in an iterative manner. The use of DD methodology in conjunction with the FRED docking program allowed rapid and accurate calculation of docking scores for 1.36 billion molecules from the ZINC15 library against 12 prominent target proteins and demonstrated up to 100-fold data reduction and 6000-fold enrichment of high scoring molecules, without notable loss of favorably docked entities (Deep Docking: A Deep Learning Platform for Augmentation of Structure Based Drug Discovery).
By employing their proprietary Deep Docking AI Platform they have identified the following promising targets for cancer treatment:
kt-2000AI against PARP (PARP inhibitors are an attractive option for anticancer drugs targeting DDR pathways) and
other novel DDR targets to generate best-in-class drug candidates that can be advanced to human trials or developed in collaboration with pharmaceutical partners.
On May 9, 2024, Rakovina has expanded its research collaboration with Pharma Inventor and the University of British Columbia to identify novel drug candidates. In particular,
Pharma Inventor Inc—a British Columbia-based chemistry R&D and analytical services company serving pharmaceutical and biotech industries, as well as research institutes and academic research groups across North America—will provide medicinal chemistry support to rapidly synthesize novel lead drug candidates identified by the Deep Docking AI platform for further validation. And
Regarding the University of British Columbia (UBC), Rakovina established a lead optimization research infrastructure at the University’s Vancouver Prostate Center and will provide rapid validation of novel drug candidates identified through the Deep Docking AI platform.
Based in Vancouver, Canada, Rakovina Therapeutics was founded in 2021 by Jeffrey Bacha, a serial entrepreneur with startups and companies operating in the biotechnology and life sciences fields. Rakovina Therapeutics has raised a total of $5.1M in funding over 2 rounds and on 23 May 2024 announced plans to raise $1.5M to support AI-related research. This includes lead orders totalling $1.25M from two new investors.
IMM investment, 인베스트먼트 ✴️
Established in September 1999 by Timothy Chang, IMM Investment Corp. is a leading investment firm in Seoul Korea, focusing on venture capital and mezzanine funds. Since its inception, IMM Investment has evolved into a multi-asset alternative investment company with 6.4 trillion won (approximately $4.8 billion) of assets under management. IMM Investment provides multi-stage investments ranging from $1M of seed capital to over $1 billion growth equity / infrastructure capital. In recent years, IMM Investment has shifted its focus to bio, healthcare and electric vehicle (EV) batteries. In the Bio/Healthcare space they invest into:
Lunit Inc. (KRX:328130) is a leading provider of AI-powered solutions for cancer diagnostics and therapeutics offering:
AI Radiology Solutions:
Lunit INSIGHT CXR for Chest X-ray, Lunit INSIGHT CXR Triage for Chest X-ray Triage-FDA cleared, Lunit INSIGHT MMG for Mammography-FDA cleared, Lunit INSIGHT DBT for Digital Breast Tomosynthesis-FDA cleared and
AI Oncology Solutions:
Lunit SCOPE IO for AI-Powered Biomarker for Immune Phenotyping and Lunit SCOPE PD-L1 for AI-Powered PD-L1 Quantification for Immunotherapy.
On Mar 18, 2024, Lunit Expanded its Presence in Europe: to Deliver AI-powered Cancer Screening Solution to France and Portugal.
On May 20, 2024, Lunit Achieved Historic Milestone since 100 Peer-Reviewed Papers Published on Its AI Medical Imaging Suite.
On May 22, 2024, Lunit Completed Acquisition of Volpara: Pioneering Next-Level of AI-Driven Cancer Care. With this acquisition, Lunit integrates Volpara’s advanced breast health platform—the breast density assessment, Scorecard, and screening workflow enhancement—with its AI-powered solutions for breast cancer detection, and becomes strategically positioned for a robust entry into the American market.
On May 24, 2024, Lunit to Showcase 7 Studies at ASCO 2024, including AI Innovations in HER2 Quantification, and Multimodal Predictive Models for Immunotherapy Response.
Lunit has raised a total of $561.1M in funding over 11 rounds. They have offices in Seoul HQ, Boston, USA, Amsterdam, The Netherlands and Shanghai, China.
Geninus Inc. (KOSDAQ: 389030) is a bioinformatics analysis business providing Tissue Based Cancer Genomics analysis (CancerSCAN in collaboration with Samsung Genome Research Center), Single Cell analysis (Celinus for ultra-precise genome analysis), NGS/Next-Generation Sequencing Based Liquid Biopsy analysis (LiquidScan) and R&D analysis. In addition, they developed the OncoSTATION which encompasses the entire range from automated experimentation and analysis data quality management system to data processing, QC, mutation detection, annotation and report generation, and providing related services in association with CancerSCAN. They also provide a genetic test service, the HealthSCAN, through hospitals. The company was incorporated in 2018 and is based in Seoul, South Korea.
Deepnoid Inc. in Seoul (KOSDAQ: 315640) is offering Medical AI solutions (DEEP:NEURO for brain MRA and CT imaging, DEEP:CHEST applied to chest X-ray images, DEEP:LUNG applied to low-dose CT and chest CT images, DEEP:SPINE applied to X-ray of the spine), Industrial AI (DEEP:SEED collects, purifies and manages X-ray image data, DEEP:SECURITY is an AI-based automatic X-ray hazardous article reading solution jointly developed by Deepnoid and Korea Airports Corporation, DEEP:FACTORY is a DL-based machine vision solution developed by Deepnoid for factory automation) and an AI Platform (DEEP:PHI is a platform where you can experience AI model planning and solution development by simply assembling modules if you are interested in AI without high-performance equipment or programming knowledge).
In 2024, DEEPNOID Expects Increased Sales as Its DEEP:NEURO Is Available in Hospitals.
In 2024, Deepnoid and an Indonesia hospital collaborated on medical AI clinical study.
Pharos iΒio Co Ltd (KOSDAQ: 388870) is a Korean clinical stage biotech transforming drug development for rare and refractory diseases utilizing AI. Their AI-based Chemiverse Platform assists them from Search, Virtual Screening, Drug Generation, ADMET and QM to LBD, Network Analysis, Drug Affinity and Target Efficacy Recommendation.
Currently, PHI-101 is in phase I for two clinical trials for Acute Myelogenous Leukemia (relapsed or refractory acute myelogenous leukemia) and Ovarian Cancer (platinum-resistance/refractory ovarian, fallopian tubal and primary peritoneal cancer). PHI-1 is the first oral Chk2 selective inhibitor identified by the Chemiverse platform. PHI-101-TNBC is also being developed as a drug to treat metastatic triple-negative breast cancer (TNBC) through an indication expansion analysis using Pharos iBio's big data & AI-based drug development platform.
In May 2024, Pharos iBio said it has signed a MoU with MEDiC Life Sciences, a Silicon Valley-based company that has established a gene-scissor technology (CRISPR) based cancer target and biomarker discovery platform. Through this agreement, the two companies will utilize Pharos iBio's Chemiverse and MEDiC's CRISPR-based cancer gene discovery platform MCATTM during drug discovery.
Pharos iBio has raised a total funding of $35.41M.
NGeneBio Co Ltd (KOSDAQ: 354200) is a leading company in molecular diagnostics and companion diagnostics, offering NGS in vitro Diagnostics, Clinical Analysis Software and Genomics Data Analysis. For example, ML based pathogenicity prediction helps interpret rare missense variants of BRCA1 and BRCA2, which are associated with hereditary cancers. Recent studies have shown that classifiers trained using variants of a specific gene or a set of genes related to a particular disease perform better than those trained using all variants, due to their higher specificity, despite the smaller training dataset size. At NGeneBIo in Seoul they further investigated the advantages of “gene-specific” ML compared to “disease-specific” ML by using 1068 rare (gnomAD minor allele frequency (MAF) < 0.005) missense variants of 28 genes associated with hereditary cancers for their investigation. Popular ML classifiers were employed: regularized logistic regression, extreme gradient boosting, random forests, support vector machines and deep neural networks. They used MAFs from multiple populations, functional prediction and conservation scores and positions of variants. The disease-specific training dataset included the gene-specific training dataset and was > 7 × larger. However, they observed that gene-specific training variants were sufficient to produce the optimal pathogenicity predictor if a suitable ML classifier was employed. So, they recommended gene-specific over disease-specific ML as an efficient and effective method for predicting the pathogenicity of rare BRCA1 and BRCA2 missense variants.
NGeneBio raised a total of $23.17M and on April 30, 2024 announced that it signed a contract with the United Arab Emirates-based medical company Euro Alliance to transfer its NGS-based precision diagnostic medical device manufacturing technology.
Genedit Inc has a proprietary technology platform, the NanoGalaxy®, that contains a library spanning thousands of unique non-viral, non-lipid, polymer nanoparticles. By using their iterative screening process, they are able to identify polymer nanoparticles that can deliver the needed genetic medicine payload to the needed tissue to treat disease.
On January 23, 2024, GenEdit announced a multiyear collaboration (up to $644M) and license agreement with Genentech, a member of the Roche Group, to employ GenEdit’s NanoGalaxy platform to discover and develop novel nanoparticles to deliver Genentech’s nucleic acid-based medicines for treatment of autoimmune disease.
Headquartered in San Francisco, CA the company has a total funding of $58.5M.
and many more.
For more about Korea: Republic of Korea and AI Drug Discovery.
Hummingbird VC 🔷
Hummingbird VC is a global generalist seed investment fund, investing in outlier founders at the earliest stage of their journey. Founded in 2010, Hummingbird Ventures is a venture capital firm based in London, UK investing in IT and online services (digital media, social media, e-commerce, cloud computing, infrastructure software, enterprise software, gaming and mobile applications).
with over $500M in assets under management invests intoSerna Bio (previously Ladder Therapeutics) is utilizing an AI enabled, data-first approach to write the rules that define RNA-small molecule interactions, mapping the druggable transcriptome. Serna was founded by Dr. Rabia Khan from Pakistan—ex Managing Director of Discovery Sciences at Sensyne Health Plc (now: Arcturis)—and its scientific officer is Dr. Danny Incarnato with a PhD in molecular biotechnologies from the University of Siena (Italy) and an expert in RNA structure and computational biology. Dr. Incarnato is also leading research in RNA structure at the University of Groningen, the Netherlands (INCARNATO lab). The Serna Bio platform operates at the intersection of synthetic biology, ML and high-throughput experimentation:
Pheiron in Berlin founded in 2023 is the GPS for drug development. Their platform uses AI and large-scale human genetics (thousands of proprietary disease signatures capturing disease onset and progression in high-resolution) to infer causal insights on targets and populations.
Using Pheiron’s platform to assess the safety of Lp(a) lowering therapy, they found no indication of prominent safety signals in line with results from early Phase I and II trials. Pheiron’s platform supports that therapeutic lowering of Lp(a) will be safe in humans (AI-enabled Target Safety Assessment).
Using Pheiron’s platform to assess the efficacy of Lp(a) lowering therapy, they confirmed prior studies and identify novel therapeutic opportunities (AI-enabled Target Efficacy Assessment).
Waypoint Bio in New York is optimizing cell therapy using spatial biology. Their platform is leveraging advances in computer vision, in silico protein design and pooled screening, to achieve groundbreaking deep phenotyping across a multitude of cell therapy designs, using spatial biology profiling to rank order and select the most optimized cell therapies. In particular they offer,
Novel pooled testing and spatial biology leverage the advances in cell therapy for solid tumor and autoimmune treatment
Cell therapy designs faster with more rigorous analysis and testing - compressing years of work into single experiment
Tests 1000s of potential therapies in a single mouse, enabling new ways to optimize therapy selection for development
Novel AI/ML to rationally design better cells
Exploring uncharted protein space to discover and develop new cell therapies with proprietary ML.
Hummingbird VC invests also into: Enveda Biosciences, Billion TO One, Amber Bio, Kaleidoscope, Latch Bio, Basecamp Research and Kernal Biologics.
CGG 🔵
CGG, a global technology and a high-performance computing (HPC) leader, announced on May 15, 2024 the launch of its AI Cloud solution, designed to meet the needs of data-intensive industries, including life sciences (early diagnosis of cancer, biological and chemical process simulation or implementing computer vision techniques), digital media, manufacturing and geoscience. CGG AI Cloud combines high-performance architecture, including cutting-edge GPUs (NVIDIA H100's) fully configured for AI fine-tuning and inference, and a software environment preinstalled with your preferred AI stack, all with exceptional support at every step from our HPC & Cloud solutions experts (CGG Launches AI Cloud Solution Powered by NVIDIA for Optimized AI and HPC Workloads). With the latest GPU and AI software stacks you can empower your digital twin efforts with high-performance architecture, tackle all challenges of efficiently processing and analyzing data of NGS workloads and gain a competitive edge with computational simulation and modeling during drug discovery.
Novalix 💮
NovAliX in France, is a world-leading Drug Discovery CRO company, offering Chemistry Services (Custom Synthesis, Chemical Process Research and Medicinal Chemistry), Biophysics and Biology Services (Protein Production, Structural Biology and Biophysical Characterization), Pharmacology & DMPK (In vitro pharmacology, In vivo pharmacology, Translational Science & Histology and ADME-DMPK) and Drug Discovery (Hit identification, Hit to lead and Lead optimization).
On January 16, 2023, Chemical.AI announced that the collaboration with NovAliX has reached a milestone after almost two years. In particular, ChemAIRS (a retrosynthesis tool) developed by Chemical.AI, has enabled NovAliX to achieve cost savings and efficiency improvement on its research projects. ChemAIRS offers synthetic predictions by combining big data with continuous-learning chemical rules and optimizing algorithms, and is capable of supporting the integration of millions of internal Electronic Lab Notebook (ELN) data. ChemAIRS can reduce the total route steps by 20-70% by integrating tens of millions of enterprise BB (Building Block) data, thus helping chemists to find shorter and more valuable potential routes for synthesis. On March 5, 2024, NovAliX announced its long-term strategic partnership with the Max Planck Institute (MPI) for Multidisciplinary Sciences in Göttingen.