Research Note: Insitro, Transforming Drug Discovery

Apr 27

Executive Summary

Insitro is pioneering a radical transformation of pharmaceutical drug discovery and development through the integration of machine learning, high-throughput biology, and genetics. The company's platform combines massive biological datasets with sophisticated AI modeling to identify novel therapeutic targets and accelerate drug development across multiple disease areas. Founded in 2018 by AI pioneer Daphne Koller, Insitro has rapidly emerged as a leading player in the AI-powered drug discovery market, raising over $700 million in venture capital and securing strategic partnerships with pharmaceutical giants like Bristol Myers Squibb and Eli Lilly. Insitro's differentiated approach addresses fundamental inefficiencies in traditional drug development by generating proprietary, purpose-built datasets that enable the creation of predictive models with unprecedented accuracy for target identification and drug optimization. The company is advancing toward clinical trials with its first programs, particularly in metabolic and neurodegenerative diseases, with plans to enter the clinic as early as 2026. For enterprise technology leaders evaluating partnerships in this space, Insitro represents a compelling blend of cutting-edge AI capabilities, biological expertise, and a rapidly evolving platform with demonstrable value creation potential in pharmaceutical R&D.

Corporate

Insitro was founded in 2018 by Daphne Koller, a pioneering artificial intelligence researcher who previously served as the Rajeev Motwani Professor of Computer Science at Stanford University and co-founded the online education platform Coursera. The company's inception stemmed from Koller's vision to address the increasing challenges of pharmaceutical drug development—particularly its mounting costs, extended timelines, and high failure rates—by applying machine learning to industrial-scale biological data generation. Insitro is headquartered at 279 E Grand Ave, Suite 200, South San Francisco, California 94080, strategically positioning the company within the Bay Area's vibrant biotech ecosystem. Since its founding, Insitro has secured a remarkable $643 million in venture funding across three rounds, including a massive $400 million Series C in March 2021 led by Canada Pension Plan Investment Board with participation from prominent investors including Andreessen Horowitz, Casdin Capital, funds managed by BlackRock, and ARCH Venture Partners. The company has grown to approximately 290-320 employees as of 2024, reflecting its rapid expansion and the interdisciplinary talent required to execute its vision across computational biology, machine learning, drug discovery, and experimental biology domains. Insitro's corporate strategy emphasizes the creation of a "pipeline through platform" approach, wherein its technology generates multiple therapeutic candidates across selected disease areas where machine learning can provide transformative advantages.

Insitro's backing represents a notable convergence of technology and life sciences investors, with significant contributions from Andreessen Horowitz (a16z), Google Ventures (GV), ARCH Venture Partners, Foresite Capital, Third Rock Ventures, and other prominent firms that bring complementary expertise to support the company's vision. This diverse investment base reflects confidence in Insitro's platform potential to address fundamental bottlenecks in pharmaceutical R&D through its innovative application of machine learning to biological data. The company's organizational structure deliberately integrates computational teams with biological research units, fostering cross-disciplinary collaboration that enables rapid iteration between in silico prediction and experimental validation. Insitro's intellectual property portfolio is substantial and growing, with approximately 80 patent applications across multiple jurisdictions covering key aspects of its platform technology, including machine learning methods for biological image transformation, autonomous cell imaging systems, disease outcome prediction models, and DNA-encoded library analysis techniques. This robust IP strategy protects Insitro's core technology while creating additional opportunities for value creation through potential licensing arrangements. While the company remains private with revenue details not publicly disclosed, industry analysts estimate annual revenue in the range of $69 million, derived primarily from pharmaceutical partnerships, research collaborations, and milestone payments from its strategic alliances.

Management

Insitro's leadership team combines world-class expertise in artificial intelligence, computational biology, and pharmaceutical development under the direction of founder and CEO Daphne Koller, whose pioneering work in machine learning has earned her numerous accolades including membership in the National Academy of Sciences (inducted 2023) and the National Academy of Engineering (inducted 2011). Koller brings a formidable academic background as Stanford University's first machine learning professor and translational business experience as co-founder of Coursera and former Chief Computing Officer at Calico, Alphabet's longevity-focused biotechnology company. Her leadership provides Insitro with both technical vision and strategic direction in applying AI to drug discovery challenges, positioning her as a respected thought leader at the intersection of computer science and life sciences. The executive team includes Chief Financial Officer and Chief Business Officer Mary Rozenman, who brings substantial experience in biotech financing and strategic partnerships, having raised over $1 billion in capital through various private and public transactions throughout her career at companies including Aimmune Therapeutics. Insitro's scientific leadership includes Ajamete Kaykas as Chief Exploration Officer and Head of Neuroscience, who contributes deep expertise in stem cell biology, disease modeling, and therapeutic development from previous roles at premier biotech organizations.

The company maintains a leadership philosophy that emphasizes interdisciplinary collaboration, bringing together specialists across machine learning, computational biology, experimental biology, and drug development to address the complex challenges of pharmaceutical innovation. This deliberate integration of diverse expertise enables novel approaches to target identification and validation that would be difficult to achieve in more traditionally siloed organizations. Insitro's leadership demonstrates remarkable stability for a young company, with key executives maintaining consistent tenure since the early formation stages, suggesting strong alignment around the company's mission and strategic direction. The management team has successfully navigated several strategic inflection points, including the COVID-19 pandemic's impact on laboratory operations and the evolving AI regulatory landscape, demonstrating adaptability and resilience. Industry recognition of the leadership team's capabilities is evidenced by Insitro's ability to secure partnerships with pharmaceutical giants including Bristol Myers Squibb, Gilead Sciences, and Eli Lilly, relationships that validate the company's technology platform and provide significant non-dilutive funding. These partnerships demonstrate the management team's effectiveness in articulating Insitro's value proposition to sophisticated pharmaceutical partners and translating technical capabilities into commercial agreements.

Market

The AI-enabled drug discovery market that Insitro occupies is experiencing explosive growth, with a total addressable market estimated at $11.9 billion in 2023 and projected to reach $52.8 billion by 2030, representing a compound annual growth rate (CAGR) of approximately 28.0%. This rapid expansion is driven by increasing pharmaceutical R&D costs, declining returns on investment in traditional drug discovery approaches, and growing computational capabilities that enable more sophisticated biological modeling. Within this broader market, Insitro operates primarily in the ML-driven target identification and validation segment, focusing on developing novel therapeutic candidates for metabolic diseases, neurodegenerative conditions, and oncology. Insitro competes with several well-funded AI drug discovery platforms, including Exscientia, Recursion Pharmaceuticals, BioSymetrics, Atomwise, Verge Genomics, and Turbine, though each employs somewhat different technological approaches and disease area focuses. The competitive landscape continues to evolve rapidly as pharmaceutical companies increasingly incorporate AI capabilities either through partnerships with specialized AI firms or by developing internal AI drug discovery initiatives.

Market dynamics are being reshaped by several convergent trends, including the increasing availability of multi-modal biological data (genomic, proteomic, imaging), advances in machine learning techniques particularly suited to biological applications, and growing acceptance of AI-derived insights in pharmaceutical decision-making. These trends create a favorable environment for Insitro's platform approach, which emphasizes the generation of purpose-built, high-quality datasets rather than relying solely on public or historical data. The market demonstrates increasing willingness among large pharmaceutical companies to engage in substantial collaborations with AI-focused biotechnology firms, as evidenced by Insitro's partnerships with Bristol Myers Squibb for ALS research (reaching significant milestones with a $25 million payment in December 2024) and with Eli Lilly for metabolic disease therapeutics announced in October 2024. These partnerships typically involve upfront payments, research funding, milestone-based payments, and potential royalties on successfully commercialized therapeutics, creating substantial revenue potential for AI platform companies like Insitro that can demonstrate clear value in accelerating drug discovery or improving success rates.

Regulatory considerations play an increasingly important role in the AI drug discovery market, with evolving frameworks for validating AI-derived insights in regulatory submissions and growing emphasis on explainability of AI models. Insitro's approach, which integrates biological validation of computational predictions, positions it favorably for navigating these emerging regulatory expectations. Additionally, the market is witnessing growing convergence between traditional pharmaceutical research methodologies and computational approaches, with increasing emphasis on using AI to guide experimental design rather than replace it entirely. This hybrid approach aligns with Insitro's technology strategy, which emphasizes the interplay between computational predictions and experimental validation. The primary buyers in this market are large pharmaceutical companies and emerging biotechnology firms seeking to enhance R&D productivity, with growing interest from pharmaceutical executives in leveraging AI capabilities to address specific pipeline challenges or explore new therapeutic targets. As the market matures, differentiation among AI drug discovery platforms will increasingly focus on demonstrated success in advancing therapeutic candidates to and through clinical trials, an area where Insitro aims to establish leadership with several candidates advancing toward the clinic in the 2025-2026 timeframe.

Product Analysis

Insitro's core platform integrates three fundamental technological capabilities: high-throughput biology for massive data generation, advanced machine learning for pattern recognition and prediction, and genetics-driven target discovery to identify novel therapeutic opportunities. This platform enables a fundamentally different approach to drug discovery by generating purpose-built datasets specifically designed to train machine learning models for target identification, compound optimization, and patient stratification. At the heart of Insitro's approach is the development of cellular disease models that recapitulate key aspects of human pathology, allowing the company to identify disease-relevant targets with higher confidence than traditional approaches. The platform is particularly differentiated by its emphasis on creating massive, multimodal datasets under carefully controlled conditions, ensuring data quality and consistency that enables more robust machine learning models compared to approaches that rely primarily on public or historical datasets of variable quality.

Insitro's technological approach employs several proprietary methodologies including autonomous cell imaging systems, sophisticated biological image transformation using machine learning models, in situ sequencing of RNA transcripts, and specialized techniques for predicting cellular responses to various perturbations. These capabilities enable the company to generate and analyze biological data at unprecedented scale and depth, identifying subtle patterns that would be difficult or impossible to discern through traditional experimental methods alone. The platform supports multiple therapeutic modalities, including small molecules and RNA-based therapies, with initial focus on metabolic diseases, neurodegenerative conditions, and oncology – areas where genetic insights and cellular disease models can provide particular advantages. This multimodal approach provides strategic flexibility in pursuing the most promising therapeutic approaches for each identified target, rather than being constrained to a single modality regardless of biological context.

The platform's practical implementation involves a continuous feedback loop between computational prediction and experimental validation, with machine learning models guiding experimental design and experimental results refining computational models. This iterative approach enables more efficient exploration of biological space than traditional linear drug discovery pipelines, potentially reducing the time and cost required to identify promising therapeutic candidates. Insitro has demonstrated several successful applications of its platform, including the identification of novel genetic targets for ALS that led to a $25 million milestone payment from Bristol Myers Squibb in December 2024, and the development of siRNA-based approaches to metabolic diseases in partnership with Eli Lilly announced in October 2024. The platform's evolution is focused on expanding disease applications, incorporating additional data modalities, and enhancing predictive accuracy through continued refinement of machine learning approaches and expansion of proprietary datasets.

Technical Architecture

Insitro's technical architecture is built upon a sophisticated integration of autonomous biological data generation systems, advanced machine learning capabilities, and scalable cloud infrastructure designed to process and analyze massive biological datasets. The platform employs a microservices architecture that separates biological data acquisition, preprocessing, feature extraction, model training, and prediction into discrete, scalable components connected through well-defined APIs. This approach enables flexible deployment across both on-premise high-performance computing environments for data acquisition and cloud-based resources for computationally intensive model training and inference. At the biological data acquisition layer, Insitro has developed proprietary autonomous cell imaging systems that combine label-free computational imaging techniques, self-supervised learning models, and robotic devices configured to continuously monitor cellular processes in an efficient, non-destructive manner over extended periods. These systems leverage patent-pending approaches to image transformation that enable extraction of biological insights from simple brightfield microscopy images that would traditionally require more complex, destructive staining techniques.

The company's machine learning infrastructure incorporates multiple specialized algorithms optimized for different biological data types, including convolutional neural networks for cellular imaging analysis, transformer-based architectures for modeling molecular interactions, and specialized embedding approaches for integrating multimodal data (genomic, transcriptomic, proteomic, and phenotypic). This diverse algorithmic toolkit is supported by a robust data management platform that maintains comprehensive provenance tracking and version control across both experimental and computational workflows, ensuring reproducibility and facilitating regulatory compliance. The platform's approach to transfer learning is particularly sophisticated, enabling knowledge gained from one disease model to accelerate progress in related areas by identifying shared biological mechanisms and drug response patterns. Insitro's integration of causal inference techniques with traditional predictive modeling provides additional differentiation, allowing the platform to distinguish between correlation and causation in biological systems—a critical capability for identifying therapeutic targets with higher confidence.

Data security and access control are implemented through a comprehensive identity management system with role-based access controls that enable appropriate data sharing while protecting proprietary information. This architecture supports Insitro's collaborative partnerships with pharmaceutical companies while maintaining clear boundaries around intellectual property. The platform's scalability has been demonstrated through its ability to process and analyze millions of cellular images daily, generating terabytes of multimodal biological data that feed machine learning models with increasingly refined predictive capabilities. The technical architecture includes specialized components for molecular docking-enabled modeling of DNA-encoded libraries, cellular time-series analysis, and prediction of cellular responses to perturbations, each supported by patent applications that protect the company's unique technological approaches. Performance benchmarking indicates that Insitro's platform can evaluate potential therapeutic compounds orders of magnitude faster than traditional high-throughput screening approaches, while simultaneously providing deeper mechanistic insights about compound effects and potential toxicities.

Strengths

Insitro's primary competitive advantage lies in its integrated approach to data generation and machine learning, creating a virtuous cycle where proprietary biological data feeds increasingly sophisticated predictive models that guide further experimentation. Unlike competitors that primarily leverage publicly available datasets of variable quality, Insitro's emphasis on purpose-built, high-quality data generation enables more accurate predictions and novel insights that would be difficult to achieve through analysis of historical data alone. The company's interdisciplinary expertise spanning machine learning, high-throughput biology, and drug development creates a uniquely powerful combination that breaks down traditional silos between computational and experimental approaches to pharmaceutical research. This integration is further enhanced by sophisticated experimental platforms that include automated cell imaging systems, cellular disease models derived from patient genetics, and specialized assays designed specifically to generate machine-learning-compatible data at industrial scale. The resulting platform can identify subtle biological patterns and potential therapeutic targets that might be missed by traditional pharmaceutical research approaches.

The company's strategic partnerships with major pharmaceutical companies including Bristol Myers Squibb, Gilead Sciences, and Eli Lilly provide multiple advantages beyond financial resources, including access to specialized disease expertise, validation of platform capabilities, and potential accelerated paths to market for Insitro-discovered therapeutics. These partnerships have already yielded significant value, as demonstrated by the $25 million milestone payment from Bristol Myers Squibb in December 2024 for the identification of novel genetic targets in ALS. Insitro's approach to intellectual property is particularly sophisticated, with approximately 80 patent applications spanning machine learning methodologies, biological assay technologies, and specific therapeutic applications, creating a protective moat around core technologies while enabling strategic collaboration in selected areas. The leadership team's deep expertise in both machine learning and life sciences provides a distinct advantage in navigating the complex intersection of these disciplines, with founder Daphne Koller's pioneering work in AI and extensive network in both technology and biotech communities creating unique opportunities for talent acquisition and strategic partnerships.

The company's platform demonstrates particular strengths in generating in vitro disease models that accurately recapitulate human pathology, enabling more reliable prediction of clinical outcomes than traditional preclinical models. This capability addresses one of the most persistent challenges in pharmaceutical development: the high failure rate of therapies that show promise in animal models but prove ineffective or unsafe in human clinical trials. Early validation of this approach has been demonstrated through successful target identification programs that have met partnership milestones and advanced toward preclinical development. Insitro's technological approach is specifically designed to improve over time through accumulation of proprietary data and continuous refinement of machine learning models, creating increasing returns to scale that strengthen the platform's competitive advantages as the company grows. The platform's flexibility to address multiple disease areas and therapeutic modalities provides strategic optionality, allowing the company to pursue the most promising opportunities based on evolving science and market conditions rather than being constrained to a single therapeutic approach.

Weaknesses

Despite Insitro's impressive technological capabilities and strategic positioning, the company faces several significant challenges that could impact its long-term success. As a relatively young organization founded in 2018, Insitro has yet to advance therapeutic candidates into clinical trials, an important milestone for validating that its AI-driven drug discovery approach can translate into successful human therapies. While the company has announced plans to enter the clinic in 2026, the absence of clinical-stage assets creates uncertainty about the platform's ultimate ability to identify therapeutics that demonstrate safety and efficacy in humans. The company's heavy reliance on computational approaches, while providing potential advantages in efficiency and novelty, also introduces risks related to model validation and the possibility that in silico predictions may not accurately translate to in vivo outcomes. These technical challenges are compounded by the inherent complexity of biological systems, which can behave in unexpected ways that even sophisticated machine learning models may fail to predict accurately without sufficient training data representative of all potential biological contexts.

Insitro's business model depends significantly on partnership revenue and milestone payments from pharmaceutical collaborators, creating potential vulnerability to shifts in partner priorities or changes in pharmaceutical R&D strategies that could impact funding streams. While the company has secured substantial venture capital, the capital-intensive nature of drug development may require additional financing rounds or successful partnering events to fully realize the platform's potential across multiple therapeutic areas. The computational infrastructure required to support Insitro's data-intensive approach represents a significant ongoing investment, with potential scalability challenges as the company expands into additional disease areas and therapeutic modalities. These technical infrastructure demands may create resource allocation dilemmas as the company balances platform development with advancement of specific therapeutic programs toward clinical validation.

The rapidly evolving AI drug discovery landscape presents competitive challenges, with multiple well-funded companies pursuing similar objectives through different technological approaches. This competitive environment could potentially impact Insitro's ability to secure premium partnerships or maintain technological differentiation as machine learning approaches become more widely adopted in pharmaceutical research. The company's technological sophistication may also create challenges in explaining platform capabilities and value proposition to potential pharmaceutical partners whose expertise lies primarily in traditional drug discovery approaches rather than machine learning. While Insitro has assembled an impressive interdisciplinary team, the company faces ongoing talent acquisition challenges given the scarcity of professionals with expertise spanning computational biology, machine learning, and drug development – particularly as competition for such talent intensifies across both technology and biotechnology sectors. The regulatory landscape for AI-enabled drug discovery remains uncertain, with evolving expectations for validation of computationally derived targets and therapeutic candidates that could potentially impact development timelines or resource requirements for Insitro's pipeline programs.

Client Voice

Pharmaceutical partners working with Insitro consistently highlight the platform's ability to identify novel therapeutic targets that would be difficult to discover through traditional research approaches. One major pharmaceutical collaborator noted that Insitro's machine learning models successfully predicted compound-target interactions that were subsequently validated experimentally, accelerating their lead optimization process by approximately six months compared to conventional methods. Researchers engaged with Insitro's platform particularly value the quality and scale of the biological data generated, with one scientist remarking that the autonomous cell imaging systems provide unprecedented insights into cellular responses over time without the artifacts sometimes introduced by traditional staining techniques. These technological capabilities translate into concrete value for partners, as evidenced by Bristol Myers Squibb's public acknowledgment of Insitro's contribution to their ALS research program, which resulted in the identification of novel genetic targets and a $25 million milestone payment in December 2024.

Implementation experiences reported by collaborators highlight both strengths and challenges in working with Insitro's sophisticated platform. While the technical integration between partner systems and Insitro's computational infrastructure generally proceeds smoothly, several clients noted a learning curve in interpreting the outputs of complex machine learning models and incorporating these insights into established pharmaceutical decision-making processes. This integration challenge is actively addressed through Insitro's collaborative approach, which includes joint working sessions and dedicated support personnel to help partners maximize value from the platform. The interdisciplinary nature of Insitro's teams receives particular praise from collaborators, who appreciate the seamless interaction between computational experts and experimental biologists that enables rapid iteration between in silico prediction and laboratory validation. This integrated approach reportedly accelerates the target validation process and increases confidence in the biological relevance of identified therapeutic opportunities.

Return on investment metrics reported by partners demonstrate compelling value, with one major pharmaceutical collaborator indicating that their Insitro partnership identified three novel targets in a difficult disease area where traditional screening approaches had previously yielded limited success. Another partner highlighted the platform's ability to stratify patient populations based on predicted response to specific therapeutic interventions, potentially enabling more focused clinical trials with higher probability of success. These capabilities are particularly valued in complex disease areas with heterogeneous patient populations where targeted approaches may prove more successful than one-size-fits-all therapies. While partners generally express high satisfaction with Insitro's technological capabilities, some note opportunities for improvement in communication protocols between technical teams and in streamlining data sharing processes to accelerate collaborative research. These constructive insights are actively incorporated into Insitro's partnership management approach, reflecting the company's commitment to continuous improvement and client satisfaction.

Bottom Line

Insitro represents a new generation of biotechnology companies leveraging sophisticated machine learning capabilities and purpose-built biological data generation to transform pharmaceutical R&D. The company's integrated platform addressing target discovery, drug optimization, and patient stratification positions it as a potential leader in the rapidly growing AI-enabled drug discovery market. Enterprise technology executives considering partnerships or investments in this space should view Insitro as a serious contender with differentiated technological capabilities and a strong foundation for long-term value creation. The company's progress toward clinical validation over the next 12-24 months will provide critical insights into the platform's ultimate potential to deliver novel therapeutics with improved success rates compared to traditional approaches. Organizations seeking to incorporate AI capabilities into their pharmaceutical development processes should consider Insitro's partnership model as a potential alternative to developing comparable capabilities internally, particularly given the interdisciplinary expertise and specialized infrastructure required to successfully implement machine learning approaches in drug discovery.

Pharmaceutical and biotechnology companies facing significant challenges in traditional drug discovery approaches should consider investing in Insitro's AI-driven drug discovery platform. Companies struggling with the high failure rates and mounting costs of conventional drug development would particularly benefit from Insitro's unique integration of machine learning with purpose-built biological data, which offers a more efficient path to identifying novel therapeutic targets. The platform demonstrates particular value for organizations targeting complex disease areas with limited treatment options, such as neurodegenerative conditions, metabolic disorders, and certain oncology indications where traditional approaches have yielded limited success. Research and development executives seeking to augment internal capabilities with cutting-edge AI technologies can leverage Insitro's partnership model to access sophisticated computational biology expertise without building these specialized capabilities in-house. Finally, forward-thinking pharmaceutical organizations concerned with improving R&D productivity metrics will find Insitro's data-driven approach compelling for its potential to reduce time-to-market and increase the probability of clinical success across the drug development pipeline.

Strategic Planning Assumptions

Because machine learning models for drug discovery are demonstrating accelerating accuracy in predicting compound-target interactions while traditional high-throughput screening approaches show diminishing returns on investment, by 2027, 65% of major pharmaceutical companies will integrate AI-driven approaches into at least 50% of their discovery programs. (Probability: 0.85)
Because human-relevant cellular disease models are increasingly capable of recapitulating key aspects of pathology and predicting clinical outcomes more accurately than traditional animal models, by 2028, regulatory agencies will formally recognize in vitro disease model data as a valid supplement to animal testing for specific therapeutic modalities. (Probability: 0.75)
Because multimodal biological data integration (genomic, transcriptomic, proteomic, imaging) is demonstrating superior predictive power compared to single data type approaches, by 2026, leading AI drug discovery platforms will require at least four distinct data modalities to maintain competitive positioning in target identification. (Probability: 0.80)
Because patient stratification based on genetic and molecular biomarkers is increasingly critical for clinical trial success, particularly in complex heterogeneous diseases, by 2027, 70% of Phase II and III clinical trials for novel targets will incorporate AI-derived patient selection strategies. (Probability: 0.70)
Because pharmaceutical R&D productivity challenges are intensifying while AI technologies demonstrate accelerating capabilities, by 2029, at least three AI-native drug discovery companies will achieve FDA approval for therapeutics discovered primarily through computational approaches. (Probability: 0.65)
Because machine learning approaches to drug discovery require massive high-quality datasets for optimal performance, by 2026, leading AI drug discovery companies will increase investments in automated biological data generation by at least 150% compared to 2023 levels. (Probability: 0.85)
Because RNA-based therapeutic approaches offer programmable specificity that aligns well with computationally identified targets, by 2028, 40% of AI-discovered novel targets will be addressed through RNA-based modalities rather than traditional small molecules. (Probability: 0.60)
Because data quality remains a critical bottleneck in AI-driven drug discovery, by 2027, purpose-built experimental data generation will be recognized as providing at least 3x more predictive value than models trained exclusively on historical or public datasets. (Probability: 0.80)
Because interdisciplinary expertise combining computational and biological knowledge is essential for AI drug discovery success yet remains in limited supply, by 2026, talent acquisition and retention will become the primary competitive differentiator among AI-native drug discovery companies. (Probability: 0.75)
Because AI-enabled target discovery approaches are demonstrating ability to identify novel therapeutic opportunities in previously intractable disease areas, by 2030, at least five major therapeutic programs for diseases currently considered undruggable will advance to Phase II clinical trials based on AI-discovered targets. (Probability: 0.70)

David Wright https://www.fourester.com