Pharmacelera Archives - Pharmacelera | Pushing the limits of computational chemistry

Freedom Space 5.0 Integrates with exaScreen® to Enable 3D Ultra-Large Virtual Screening

Enric Herrero — Tue, 03 Mar 2026 09:06:23 +0000

Barcelona, Spain, and Kyiv, Ukraine – March 3, 2026 – Pharmacelera, the deeptech company pushing the limits of computational technologies for drug discovery, and Chemspace, a global provider of small molecules and drug discovery services, today announced the launch of a powerful new joint solution that integrates the Chemspace Freedom Space 5.0 with Pharmacelera’s flagship virtual screening platform, exaScreen®. This launch provides researchers with unprecedented access to synthetically tractable chemical space combined with cutting-edge computational methods for hit discovery.

As the pharmaceutical industry increasingly turns to ultra-large libraries to identify novel hits, the challenge lies in navigating chemical diversity accurately while ensuring synthetic feasibility. The new joint solution directly addresses this challenge by combining Pharmacelera’s advanced 3D Quantum-Mechanics (QM) and Machine Learning (ML)-driven algorithms with the Chemspace Freedom Space, a curated collection of 296 billion chemically diverse and highly synthesizable compounds.

With this launch, researchers will be able to:

Conduct accurate and efficient virtual screening across the Chemspace Freedom Space.
Rapidly source and synthesize compounds for experimental validation.
Expand opportunities to generate novel Intellectual Property (IP) through unexplored chemical space.
Streamline the path from virtual prediction to real-world testing.

"Freedom Space 5.0 was built to give researchers access to unprecedented chemical diversity while solving one of virtual screening's most persistent challenges — synthetic accessibility. Integrating Freedom Space 5.0 with exaScreen® combines the scale of 296 billion synthesizable compounds with Pharmacelera's algorithms, enabling accurate virtual screening across an ultra-large yet tractable chemical space. This combination gives researchers a truly powerful tool to identify novel, high-quality hits that would remain undiscovered with conventional libraries and screening approaches"

Olga Tarkhanova, PhD, CEO at Chemspace

“Leveraging the information contained in ultra-large chemical spaces through highly accurate 3D algorithms is key to accelerating and strengthening intellectual property in modern drug discovery. We are thrilled to collaborate with Chemspace to apply our accurate 3D QM- and ML-based algorithms to Freedom Space 5.0 , giving researchers access to a truly tractable and innovative chemical space”

Enric Gibert, PhD, CEO of Pharmacelera

About Chemspace

Chemspace is a global platform for discovering, designing, and delivering small molecules, providing integrated solutions for early-stage drug discovery through both online and offline platforms. The Chemspace online platform offers a comprehensive solution for molecule discovery, purchasing, and procurement, enabling exploration of trillions of small molecules. With customizable catalog access, flexible purchasing options, and advanced compound management tools, the platform delivers a streamlined experience from search to synthesis. The Chemspace offline platform provides end-to-end discovery services, including AI/ML-driven design, virtual screening, cheminformatics, chemistry, and biology services. This integrated approach supports hit identification, optimization, and biological validation within a coordinated workflow.

For more information, visit https://chem-space.com/search

About Pharmacelera

Pharmacelera is a deep-tech science-first company founded by experienced drug hunters, high-performance computing engineers, and leading academic researchers. The company has developed a proprietary in-silico platform that integrates accurate 3D Quantum-Mechanics (QM) models with advanced Artificial Intelligence (AI) algorithms to design novel, diverse, and high-quality molecules from ultra-large and previously untapped chemical spaces. Pharmacelera solutions provide access to its cutting-edge technology for HitID, H2L and LO.

Founded in 2015 and headquartered in Barcelona, Spain, Pharmacelera collaborates with leading pharmaceutical and biotech organizations across Europe and the United States.

Contact:

Chemspace
Olga Tarkhanova, Ph.D., CEO
o.tarkhanova@chem-space.com

Pharmacelera
Enric Gibert, Ph.D., CEO
contact@pharmacelera.com

The post Freedom Space 5.0 Integrates with exaScreen® to Enable 3D Ultra-Large Virtual Screening appeared first on Pharmacelera | Pushing the limits of computational chemistry.

Pharmacelera Appoints Dr. Cynthia Tingle as Head of U.S. Operations and Business Development

Enric Herrero — Mon, 23 Feb 2026 22:35:16 +0000

Boston and Barcelona — February 23, 2026 — Pharmacelera, a deep-tech company developing and applying high-accuracy Quantum Mechanics and Artificial Intelligence (“deep physics”) algorithms to design therapies for unmet medical needs, today announced the appointment of Dr. Cynthia White Tingle as Head of U.S. Operations and Business Development.

Dr. Tingle holds a PhD in Organic Chemistry from Brown University and brings more than two decades of corporate and business development and customer success experience delivering advanced computing solutions to biopharma R&D and intellectual property teams. She has held senior leadership, commercial, and customer-facing roles at CambridgeSoft, CAS, Chemaxon, and Optibrium.

“Cynthia will play a pivotal role in advancing Pharmacelera’s growth strategy in the United States,” said Dr. Enric Gibert, CEO and Co-founder of Pharmacelera. “Her experience and leadership will be instrumental in building a strong US-based scientific team and expanding our collaborations with pharmaceutical companies, biotech firms, and research institutions across North America, always with a science-first and customer-focused approach”, he added.

“The integration of accurate Quantum Mechanics algorithms to model 3D molecular interactions with Artificial Intelligence methods capable of exploring ultra-large chemical spaces represents a meaningful step forward in strengthening intellectual property in drug discovery,” said Dr. Tingle. “Identifying novel and diverse active starting points is essential — but equally critical is the ability to progress them and design differentiated drug candidates”, she added.

The post Pharmacelera Appoints Dr. Cynthia Tingle as Head of U.S. Operations and Business Development appeared first on Pharmacelera | Pushing the limits of computational chemistry.

Pharmacelera raises €6M to expand in U.S. and build out its high speed, high accuracy, deep tech drug discovery platform

Enric Herrero — Wed, 18 Feb 2026 09:00:00 +0000

Round led by Heran Partners and joined by Clave Capital, Inveready and Bio&Tech Smart Capital
Financing will enable Pharmacelera to build ongoing relationships with major pharm and biotech customers in the US
Pharmacelera’s platform scours vast chemical ‘exaSpace’ accurately for novel molecules

Barcelona, Spain, February 18, 2026 – Pharmacelera, a deep tech company applying Quantum Mechanics and Artificial Intelligence to revolutionize drug discovery, has closed a €6 million investment round to accelerate its expansion in the United States and grow the capabilities of its proprietary platform.

Utilizing its proprietary Quantum Mechanics and Artificial Intelligence (“QaiM”) algorithms, Pharmacelera is revolutionizing drug discovery by finding novel and diverse molecular candidates across the vast chemical “exaSpace” with unprecedented speed, efficiency and accuracy. It can generate molecules that are up to 10 times better, 75,000 times faster, than traditional AI-led drug discovery approaches. Its technology can be applied to small molecules and small peptides in all stages of drug discovery – from hit identification, through hit-to-lead, to lead optimization.

This investment round will help Pharmacelera grow further and faster – firstly, by establishing a permanent team in the U.S., and secondly, by enabling the Company to expand the technical capabilities of its unique QaiM drug discovery engine in key growth areas.

The round was led by Heran Partners, a leading life sciences investor, and joined by Clave Capital, a long-standing tech transfer investor; Inveready, a Spanish alternative asset manager with a dedicated life sciences strategy; and Bio&Tech Smart Capital, a specialist investor in healthtech and science-based innovation.

Pharmacelera, accelerated by The Collider program at Barcelona Mobile World Capital, has already participated in more than 100 projects to date, including several notable successes in GPCRs. It has won repeat business from customers in both Europe and the U.S., including three big pharma companies and numerous highly-regarded biotechs.

Enric Gibert, Chief Executive Officer of Pharmacelera, said: “The first wave of AI-powered drug discovery promised a lot but delivered comparatively little. Pharmacelera is changing the picture, by coupling AI with quantum-based simulations to leverage the exaSpace – the vast, undiscovered universe of trillions of molecules – to find highly novel drug candidates that are up to 10 times better, using a process that’s up to 75,000 times faster than traditional AI-led approaches.”

He continued: “The backing of these leading investors, who have a deep understanding of drug discovery, is a strong validation of our revolutionary technology. The funding will enable us to establish a team in the U.S. – a natural next step to continue strengthening our relationships with large pharmaceutical and biotech companies on both the East and West coasts. It will also help us to greatly widen the capabilities of our QaiM engine.”

Raf Roelands, Partner at Heran Partners and new member of Pharmacelera’s Board of Directors, said: “By combining physics-based algorithms with machine learning, Pharmacelera enables the design of molecular candidates for novel targets and modes of action with a higher probability of success. We have a high conviction in this company, which was reinforced through direct discussions with its customers, including leading pharmaceutical companies, who have already experienced the significant impact of its technology.”

The funding round follows the signing of a strategic alliance between Pharmacelera and Silicon Valley company igniter General Inception (GI) in 2023, in which Pharmacelera became GI’s AI drug discovery strategic partner. Venkat Reddy, GI’s Chief Scientific Officer, sits on Pharmacelera’s Board of Directors. Since then, Pharmacelera’s technology has strengthened the intellectual property of several of GI’s portfolio companies.

For more information, please contact:

contact@pharmacelera.com

Notes to Editors

About Pharmacelera

Pharmacelera is a deep tech computational drug discovery company applying its advanced 3D Quantum Mechanics and Artificial Intelligence (“QaiM”) engine to explore the vast chemical “exaspace” – which potentially comprises trillions of molecules – with unprecedented speed, efficiency and accuracy. This engine can significantly outperform traditional methods in its ability to identify structurally diverse, novel, and synthesizable compounds. Using this technology, the Company’s world class, cross-disciplinary team has already participated in more than 100 projects. Pharmacelera’s diversified and scalable business model has attracted recurrent customers including several big pharma firms and many prominent biotechs. Founded by AI engineers, drug hunters from industry and top academic profiles, its founders have co-authored more than 500 publications and hold more than 50 patents on technology and drug discovery. It is backed by Heran Partners, Clave Capital, Inveready and Bio&Tech Smart Capital and based at the Parc Científic de Barcelona, one of Europe’s premiere life science hubs. For more information, please visit https://pharmacelera.com/

About Heran Partners

Heran Partners is a specialist venture capital investor committed to creating transformative impact within the life sciences and healthcare industry. It is a Belgium-based investment fund driven by a dedicated team with strong scientific and entrepreneurial backgrounds. It provides venture and growth capital accompanied by a strong network, expertise and mentorship to start-ups and scale-ups with a solid technology platform and strong market potential.

Heran’s investment philosophy centers on addressing emerging health challenges such as an ageing population, the surge in chronic diseases, and associated increases in healthcare costs. Heran believes in harnessing the revolutionary potential of technology, science, and data to meet these challenges head-on. It focusses on solutions for unmet needs in the market. For more information, please visit https://www.heranpartners.com/

About Clave Capital

Clave Capital is an independent alternative asset management firm specialized in innovative projects and industrial SMEs. The firm has extensive experience in creating business value from scientific research results, with more than 20 years of expertise in investing, building, and supporting technology projects from their early stages, with a clear focus on technology transfer. Currently, the firm manages €173 million, with a highlight being Clave Innohealth F.C.R., a €50 million fund specialized in medical technologies and promoted with the support of CDTI Innvierte and several private investors linked to the healthcare sector. For more information, please visit https://clave.capital/

About Inveready

Inveready is a leading financial services firm specialized in Alternative Assets, Wealth Management, and Investment Funds. Founded in 2008 as a venture capital fund, Inveready has evolved into one of the most active investment firms for small and medium-sized enterprises in Spain, currently managing over €2.4 billion.

The financial group organizes its services into three main business lines: Alternative Assets, which includes various direct investment strategies (Venture Capital, Life Sciences Venture Debt, Strategic Public Equity, Private Equity, and Infrastructure); Wealth Management, which advises clients across a range of high-value products and services; and Investment Funds, investing in small-cap equities with a value investing approach through its management company True Value.

With a team of 60 employees, Inveready is headquartered in San Sebastián, with offices in Barcelona and Madrid. The firm has been recognized as “Best Venture Capital Firm” by SpainCap in 2017 and “Best European Venture Debt Fund” by Preqin in 2023, among other awards. For more information, please visit https://inveready.com/

About Bio&Tech Smart Capital

Bio&Tech Smart Capital, FCRE is an early-stage venture capital fund based in Santiago de Compostela, Spain, focused on investing in life sciences, healthtech and science-driven technology companies. The fund is managed by Noso Capital and is deeply connected to Galicia’s growing innovation ecosystem, combining strong regional roots with an active investment focus across Spain.

The fund was created with the mission of translating scientific knowledge into scalable, high-potential businesses, supporting founders at Seed and Series A stages. Bio&Tech Smart Capital is led by a team combining venture capital experience, scientific research and entrepreneurship, backing differentiated technologies with clear and meaningful applications in healthcare. For more information, please visit https://biotechsmartcapital.com/ , https://nosocapital.com/es-es/index

About General Inception

General Inception (GI) is pioneering company creation as an Igniter company. General Inception partners with extraordinary scientific founders at the inception of their journey to efficiently translate their groundbreaking innovations into transformational companies that address humanity’s grand challenges. As a business co-founder, GI brings together domain and functional expertise, executive talent, infrastructure and development resources, and capital to ignite, nurture and scale the company journey. GI is backed by leading venture capital firms Genoa Ventures, Hughes Ventures, Northpond Ventures, OMX Ventures, Paladin Capital Group, and Vertical Venture Partners. For more information, please visit https://www.generalinception.com/

The post Pharmacelera raises €6M to expand in U.S. and build out its high speed, high accuracy, deep tech drug discovery platform appeared first on Pharmacelera | Pushing the limits of computational chemistry.

Pharmacelera extends the current partnership with Enamine for the screening of ultra-large chemical libraries

Fernando Martín — Tue, 07 May 2024 08:06:19 +0000

Barcelona, Spain, and Kyiv, Ukraine, 07 May 2024. Pharmacelera, the leading provider of computational tools for hit discovery, and Enamine, the developer of the world’s largest and most reputable virtual space: REAL, have announced the extension of their current partnership to explore an extraordinary magnitude of compounds, that has been extended by a 10 fold factor – when compared to the early version -. Ultra-large chemical libraries constitute a key paradigm to tap into new and still unexplored chemical spaces, increasing the probability for the researcher to find new and chemically diverse potent hits for Discovery Programs. Efficient handling of the ultra-large compound libraries still remains the main challenge.

In 2022, Pharmacelera and Enamine started their collaboration with the plug-in of Enamine Real Database – over 165 well-validated parallel synthesis protocols applied to over 138,000 qualified reagents and building blocks at this stage- to the new version of Pharmacelera’s virtual screening flagship tool. The resulting software product was named exaScreen® . exaScreen® is harnessing the power of Artificial Intelligence (AI) and Quantum-Mechanics (QM) algorithms. The success of this initial phase prompted both partners to create an efficient approach to give their customers an access to more REAL Compounds to find new diverse starting points for drug discovery by allowing the screening of Enamine’s REAL Space consisting today of 48 billion compounds. The resulting hits can be synthesized by Enamine within only a 3-4 weeks period with an 80% success rate. More analogues for hit follow-up activities are accessible for Pharmacelera’s customers,with Enamine offering an access to several trillions of REAL Compounds, and an even of make-on-demand (“MADE”) Building Blocks.

As part of this extended partnership, Enamine will receive a license to use exaScreen® for their internal library research work.

“Screening of ultra-large virtual chemical libraries has shown to be a powerful approach that can give a quick access to potent IP-free hits for a wide variety of targets. We are really delighted to count on Pharmacelera among our armada of talented deep -tech partners, and to extend our current collaboration with Pharmacelera to use their exaScreen® technology to extract the needles from our exciting expandable 3D space environment, but also being glad to use it in-house for our own screening library development work.», said Michael Bossert, Head of Strategic Alliances at Enamine.

“This agreement is fully aligned with Pharmacelera’s strategy to work with leading institutions in the field of Drug Discovery that have complementary technology and expertise”, says Rémy Hoffmann, Chief Business Development Officer at Pharmacelera. “We are thrilled to expand the current collaboration started on December 2022 with Enamine, the prominent compound provider, to apply our accurate Quantum-Mechanics (QM) and Machine Learning (ML) algorithms to mine the Enamine’s REAL Space and deliver synthesizable compounds that can be further evaluated in biological assays”, said Enric Gibert, Pharmacelera’s CEO.

About Enamine

Enamine is a scientifically driven integrated discovery Contract Research Organisation with unique partnering opportunities in exploring new chemical space. The company combines access to the inhouse produced screening compounds (4.2M in stock) and building blocks (300K in stock) with a comprehensive platform of integrated discovery services to advance and accelerate the efforts in Drug Discovery. For more information visit: https://enamine.net

About Enamine REAL Space

Enamine REAL Space contains 48 billion make-on-demand molecules that can be synthesized at Enamine extremely fast (3-4 weeks), with high feasibility (over 80%), and inexpensive. The REAL compounds are created by parallel chemistry through the compilation of 424,490 building blocks via more than 164 well-validated parallel synthesis protocols, underlying Enamine’s approach to design make-on-demand compounds to maximize synthesis success rate.

About Pharmacelera

Pharmacelera develops advanced computational tools for the discovery of novel hits using accurate Quantum-Mechanics (QM), Artificial Intelligence (AI), and High-Performance Computing (HPC). The company’s products PharmScreen®, exaScreen® and PharmQSAR® use 3D molecular descriptors derived from Quantum-Mechanics (QM) calculations to mine an unexplored chemical space and to identify diverse hits uncovered by traditional algorithms. Pharmacelera is a private company founded in 2015 and based in Barcelona, Spain. The company works with several big pharma and biotech organizations across Europe and the United States.

The post Pharmacelera extends the current partnership with Enamine for the screening of ultra-large chemical libraries appeared first on Pharmacelera | Pushing the limits of computational chemistry.

Pharmacelera and MODSIM Pharma AB announce a partnership on providing an extended portfolio of in-silico services

Enric Herrero — Thu, 02 Mar 2023 08:00:00 +0000

Barcelona and Uppsala, March 2nd, 2023 – Pharmacelera, the leading provider of computational tools for hit discovery, and MODSIM Pharma AB, the leading provider of physics-based biomolecular simulations tools, have announced a technology and business partnership to jointly provide an efficient in-silico platform from Hit Finding up to Lead Optimization of new bio-active chemical entities.

Through this collaborative platform the two companies will be able to combine the expertise in virtual screening with the Free Energy Perturbation (FEP) technology for both performing in silico mutagenesis in proteins and ranking ligands, to find and prioritize compounds within chemical series and ultimately facilitate the identification of pre-clinical development candidates.

The collaboration will provide integrated resources, expertise, and capabilities for speeding up new discoveries, and development opportunities to research groups from academia, biotech, or pharmaceutical industry.

Enric Gibert (Pharmacelera CEO and co-founder): “MODSIM Pharma has developed a unique and accurate physics-based Free Energy Perturbation (FEP) technology that scales much better than current offerings. We are thrilled to engage with this team to deliver an increased value to our customers by a thorough analysis methodology of proteins (analysis of mutations) and with a clear step forward into the Lead Optimization stage programs.”

Hugo Gutierrez de Teran (MODSIM Pharma CEO and co-founder): “Pharmacelera has established one of the strongest ligand-based computational pipelines to screen millions of compounds virtually and filter large chemical libraries. This provides the best starting point for hit to lead and optimization processes of candidate molecules typical of our projects. We look forward to start working on more ambitious ventures that cover the full workflow from initial screening to optimization, combining Pharmacelera ligand-based and MODSIM structure-based complementary technologies”.

About Pharmacelera

Pharmacelera develops advanced computational tools for the discovery of novel hits using accurate Quantum-Mechanics (QM), Artificial Intelligence (AI), and High-Performance Computing (HPC). The company’s products PharmScreen® and PharmQSAR® use 3D molecular descriptors derived from Quantum-Mechanics (QM) calculations to mine an unexplored chemical space and to identify hits uncovered by traditional algorithms. Pharmacelera is a private company founded in 2015 and based in Barcelona, Spain. The company works with several big pharma and biotech organizations across Europe and the United States.

About MODSIM Pharma AB

MODSIM Pharma develops computational software and pipelines to increase the performance of structure-based drug discovery. The company has developed highly computationally efficient Free Energy Perturbation simulations protocols adapted for high-performance computing (HPC). The QresFEP module allows for systematic in-silico mutagenesis applicable to assess site-directed mutagenesis experiments or protein stability studies. With QligFEP, MODSIM Pharma can perform ligand optimization, scaffold hopping, linker length adjustment or postscoring pose ranking, based on accurate and systematic FEP simulations of ligand series. Initially focused on G protein-coupled receptors (GPCRs), the company has recently evolved the GPCR-Modsim web server, a one-stop shop for the 3D modeling and molecular dynamics (MD) simulations of GPCRs, into a generic membrane protein modeling and simulation package optimized for HPC.

MODSIM Pharma is a private company founded in 2018 and based in Uppsala, Sweden. The company offers the optimized combination of either module to address problems related to target characterization of structure-based ligand optimization, and has agreements or contracts with different biotech and pharma companies.

Media Contacts

Pharmacelera

Rémy Hoffmann, CBDO (remy.hoffmann@pharmacelera.com)

MODSIM Pharma

Marc Willuhn, CBDO (marc@modsim-pharma.com )

The post Pharmacelera and MODSIM Pharma AB announce a partnership on providing an extended portfolio of in-silico services appeared first on Pharmacelera | Pushing the limits of computational chemistry.

Pharmacelera and Welab Barcelona are announcing a research collaboration on providing drug discovery services

Enric Herrero — Fri, 27 Jan 2023 08:12:32 +0000

Barcelona, January 27th, 2023 – Pharmacelera, the leading provider of computational tools for hit discovery, and Welab, the leading drug discovery and development platform is Spain, have announced a partnership to jointly provide an efficient solution from hit finding up to pre-clinical development of new chemical entities.

Through this collaborative platform aiming to foster and encourage the discovery of new medicines for tomorrow, the two companies will be able to combine the expertise in virtual screening with the capability to synthesize and test the predicted molecules, both under the roof of their facilities at the Parc Científic of Barcelona.

The collaboration will provide integrated resources, expertise, and capabilities for speeding up new discoveries, and therapeutic opportunities to research groups from academy, biotech, or pharmaceutical industry.

Enric Gibert (Pharmacelera CEO and co-founder): “Through this partnership with a team of experienced drug discovery researchers from the Pharma industry, Pharmacelera will be able to offer an integrated service to its customers that will extend the in-silico design and identification of potential hits to their validation through synthesis, ADME profiling, and testing. Being the two companies located within the Parc Científic of Barcelona, the interactions during projects will be facilitated and our respective customers should get more value in getting results faster.”

Jose Miguel Vela (Welab CSO): “This collaboration with Pharmacelera will boost our capacity to provide new drug discovery programs to our customers. Beyond leveraging hit finding capabilities, the deep and complementary knowledge and expertise of both companies add high value to this partnership, for us, and for our clients”.

About Pharmacelera

Pharmacelera develops advanced computational tools for the discovery of novel hits using accurate Quantum-Mechanics (QM), Artificial Intelligence (AI), and High-Performance Computing (HPC). The company’s products PharmScreen® and PharmQSAR use 3D molecular descriptors derived from Quantum-Mechanics (QM) calculations to mine an unexplored chemical space and to identify hits uncovered by traditional algorithms. Pharmacelera is a private company founded in 2015 and based in Barcelona, Spain. The company works with several big pharma and biotech organizations across Europe and the United States.

About WeLab Barcelona

https://www.welabbarcelona.com/

Founded in 2020 through the acquisition of the Drug Discovery & Preclinical Development center from Esteve Pharmaceuticals S.A., Welab Barcelona is formed by experienced scientists with cutting-edge equipment and technologies, and a proven track record across the entire drug discovery and development cycle, successfully translating new discoveries into medicines. Welab’s R&D site, located in the Parc Científic of Barcelona, is the largest integrated Drug Discovery Center in Spain, and provides Pharma R&D services and scientific solutions.

Media Contacts

Pharmacelera

Rémy Hoffmann, CBDO (remy.hoffmann@pharmacelera.com)

Welab Barcelona

Xavier Codony (xcodony@welab.barcelona)

The post Pharmacelera and Welab Barcelona are announcing a research collaboration on providing drug discovery services appeared first on Pharmacelera | Pushing the limits of computational chemistry.

Pharmacelera to partner with Enamine for the screening of ultra-large chemical libraries

Fernando Martín — Thu, 15 Dec 2022 09:28:44 +0000

Barcelona, Spain, and Kyiv, Ukraine, 15 December 2022. Pharmacelera, the leading provider of computational tools for hit discovery, and Enamine, the developer of REAL Database – the world’s largest virtual library of highly feasible compounds, have announced a partnership to jointly provide an efficient solution for hit finding. Ultra-large chemical libraries are observed as one of the key paradigms to access an unexplored chemical space. How to traverse these enormous spaces accurately is a research area that has raised the interest of the pharmaceutical industry, since finding novel hits with chemical diversity is a fundamental pillar in drug discovery.

In this context, Pharmacelera and Enamine have reached an agreement to plug the Enamine Real Database – over 5.5 billion highly feasible compounds – into the new version of Pharmacelera’s virtual screening flagship tool PharmScreen®. The resulting joint solution will allow the accurate screening of the ultra-large chemical library, providing its users not only with access to the physical compounds for testing from Enamine but also with new Intellectual Property (IP) for their targets of interest.

“Pharmacelera offers an original, scientifically sound, and meaningful way of reading and interpreting the molecules, with excellent further applicability for virtual screening in Drug Discovery programs. We are happy to partner with Pharmacelera, to enable a more straightforward connection of PharmScreen® to the real test compounds”, said Michael Bossert, Head of Strategic Alliances at Enamine.

“This agreement is extremely aligned with Pharmacelera’s strategy to work with leading institutions in the fields of Drug Discovery that have complementary technology and expertise”, says Rémy Hoffmann, Chief Business Development Officer at Pharmacelera. “We are thrilled to start this collaboration with Enamine, the prominent compound provider, as it will allow us to apply our accurate Quantum-Mechanics (QM) and Machine Learning (ML) algorithms to mine the Enamine’s REAL Database”, said Enric Gibert, Pharmacelera’s CEO.

ENDS

About Enamine

Enamine is a global leading designer and the largest producer of building blocks (280,000+ compounds in stock) and screening libraries (3M+ compounds in stock). REAL® Database is a collection of currently 5.5 billion enumerated compounds that can be synthesized within only 3 weeks with more than 80% success rate. This database is complemented with REAL® Space providing access to over 32 billion REAL Compounds through the compilation of 137,000 building blocks used in 167 different synthesis protocols. Enamine offers integrated drug discovery services with seamless and efficient hit follow-up support.

About Pharmacelera

Pharmacelera develops advanced computational tools for the discovery of novel hits using accurate Quantum-Mechanics (QM), Artificial Intelligence (AI), and High-Performance Computing (HPC). The company’s products PharmScreen® and PharmQSAR use 3D molecular descriptors derived from Quantum-Mechanics (QM) calculations to mine an unexplored chemical space and to identify hits uncovered by traditional algorithms. Pharmacelera is a private company founded in 2015 and based in Barcelona, Spain. The company works with several big pharma and biotech organizations across Europe and the United States.

Media Contacts

Pharmacelera

Rémy Hoffmann, CBDO (remy.hoffmann@pharmacelera.com)

Enamine Ltd.

Michael Bossert, Head of Strategic Alliances (m.bossert@enamine.net)

The post Pharmacelera to partner with Enamine for the screening of ultra-large chemical libraries appeared first on Pharmacelera | Pushing the limits of computational chemistry.

Clustering methods for large molecular library screening

Fernando Martín — Thu, 01 Aug 2019 07:36:47 +0000

Today, the amount of data generated in many fields such as engineering, social sciences or medicine is suffering a tremendous scale-up. Extraction of relevant information is hence becoming increasingly challenging, and methods of data analysis such as clustering are now crucial. Clustering consists on the identification of homogeneous subgroups among a set of heterogeneous items. In the context of computer-aided drug discovery, where the chemical space is estimated to be 10⁶³ compounds, we can use it to select promising subgroups inside a large chemical library, getting rid of the bulk of the dataset with either no medical interest or redundancy a priori.

Non-hierarchical methods

Clustering algorithms vary largely on their efficiency, so some methods are more practical than others for their application on libraries of different size (Downs & Barnard, 2002). For large datasets, the most suitable are non-hierarchical algorithms, that are based in a single partition of the data. From them, probably the most widely used is K-means (Forgy, 1965), that efficiently generates a user-defined number of clusters that are iteratively updated until an optimal classification is found. Compared with the family of nearest-neighbor algorithms such as the one developed by Darko Butina (Butina, 1999), K-means produces groups with a homogeneous size, although this sometimes comes at a cost of a higher internal heterogeneity (Walters, 2019). A faster implementation of K-means, called Mini Batch K-means (Sculley, 2010) uses just a small portion of the data to update the clusters in each iteration.

Hierarchical vs non-hierarchical clustering

Our approach

To assess the utility of Mini Batch K-means, we generated a dataset by combining all sets of the Directory of Useful Decoys with the library from Specs, considered as decoys. In total, the dataset contained more than 300K structures from which just 2,2K were active compounds. Applying our proposed multistep protocol that combines clustering with 3D hydrophobic fields overlays, we were able retrieve a significant number of hits, screening less than a 5% of all compounds, and more importantly with high chemical diversity.

Combination of Mini Batch K-means with hydrophobic descriptors.

Although applying clustering methods might hide interesting structures compared to the integral screening of all compounds in a dataset, it also enables exploring a much larger chemical space that, otherwise, would be intractable. Future steps should be focused on finding the optimal number of clusters to generate, as well as increasing the quality of the chosen representative molecules.

Which is your experience with clustering large chemical libraries? How do you think we should cope with these large datasets?

Butina, D. (1999). Unsupervised data base clustering based on daylight’s fingerprint and Tanimoto similarity: A fast and automated way to cluster small and large data sets. Journal of Chemical Information and Computer Sciences, 39(4), 747–750. https://doi.org/10.1021/ci9803381
Downs, G. M., & Barnard, J. M. (2002). Clustering Methods and Their Uses in Computational Chemistry. In Reviews in Computational Chemistry, Volume 18 (pp. 1–40). Hoboken, New Jersey, USA: John Wiley & Sons, Inc. https://doi.org/10.1002/0471433519.ch1
Forgy, E. (1965). Cluster analysis of multivariate data : efficiency versus interpretability of classifications. Biometrics, 21, 768–769.
Sculley, D. (2010). Web-Scale K-Means Clustering. Proceedings of the 19th International Conference on World Wide Web, 1177–1178.
Walters, W. P. (2019). K-means Clustering. Retrieved from http://practicalcheminformatics.blogspot.com/2019/01/k-means-clustering.html

The post Clustering methods for large molecular library screening appeared first on Pharmacelera | Pushing the limits of computational chemistry.

Bosch i Gimpera Foundation Award

Enric Gibert — Fri, 15 Dec 2017 10:32:59 +0000

Professor Javier Luque (h-index of 66), Pharmacelera’s Scientific Director, has received the 10th edition award from the Boschi Gimpera Foundation for his technology transfer efforts from the University of Barcelona to Pharmacelera.

Professor Luque has supervised the use of molecular models based on Quantum-Mechanics (QM) computations derived from more than 20 years of research for molecular alignment, virtual screening and 3D Quantitative Structure-Activity Relationship (QSAR) studies.

These models represent molecules by a combination of the steric, electrostatic and hydrophobic interaction fields entirely in 3D, exploring larger chemical diversity than traditional algorithms based on shape or other simplifications.

The post Bosch i Gimpera Foundation Award appeared first on Pharmacelera | Pushing the limits of computational chemistry.

PharmScreen field-based alignment outperforms traditional solutions

Enric Gibert — Sat, 05 Aug 2017 15:54:38 +0000

PharmScreen field-based alignment outperforms traditional solutions by taking into account relevant ligand characteristics related with ligand-receptor interaction.PharmScreen superior alignment allows finding better leads in a drug discovery project.

In this figure, we can see how two cdk2 inhibitors are aligned by PharmScreen in comparison with traditional shape-based tools.

The hydrophobic fields of the two ligands are shown as a lipophilic potential (a). PharmScreen alignments (c) emphasize the optimal hydrophilic/hydrophobic overlap while the alignment based on traditional descriptors (b) misses completely the necessary balance between hydrophobic and hydrophilic properties.

The post PharmScreen field-based alignment outperforms traditional solutions appeared first on Pharmacelera | Pushing the limits of computational chemistry.