Computational chemistry, CADD (Computer-Aided Drug Design), cheminformatics, and data analysis are key components of any science-led drug discovery project. These approaches have been demonstrated to reduce R&D costs and timelines while adding valuable scientific insights. They are applied at all stages of the drug discovery process to focus effort, impact projects, and rapidly move compounds towards the clinic.
BioAscent’s computational drug designers work with you to support your drug discovery projects, applying the right computational methodologies to help solve the challenges inevitably encountered during the discovery process.
“BioAscent computational chemists worked on a structure-based drug design project where there was a Cryo-EM structure of the target. Working on Cryo-EM models is challenging and BioAscent generated valid docking hypothesis and design concepts which resulted in a series of compounds which showed good activity and enabled us to establish new IP position. The BioAscent team is collaborative and professional. Their extensive experience in structure-based drug design allowed them to make a significant impact on the progress of the project. We would happily recommend the BioAscent In Silico Discovery team for computational projects.”
Director of Medicinal Chemistry, US Biotech
Our In Silico Discovery and AI scientists have years of knowledge and success applying multiple ligand-based and structure-based computational methodologies at all stages of the drug discovery workflow.
To support the implementation of AI and machine learning across projects, BioAscent has developed the In Silico Workbench, an industrial-strength, high-performance drug discovery environment purpose-built for CRO workflows. The workbench encompasses structure-based design, matched molecular pair analysis, proximity and selectivity profiling, generative chemistry, and AI-assisted co-folding within a single environment, enabling seamless transitions between workflows without loss of project context.
Understanding targets, structures, and molecular mechanics.
Finding starting points and expanding chemical opportunity.
Improving potency, selectivity, developability, and decision-making.
Specialised approaches supporting next-generation therapeutics and portfolio decision-making.
Proximity design - PROTAC linker design and optimisation, molecular glues, and ternary-complex modelling.
Mimetics - Mapping peptide binders into drug-like small molecules via pharmacophoric hotspot alignment.
Biologics - Generative backbone diffusion and sequence design for de novo protein binders.
Biophysical Kinetics - ODE simulation of binding kinetics (kon, koff, residence time tau) to project in vivo receptor occupancy.
Drug discovery is a cross-functional process. Our computational chemists work in concert with you and our medicinal chemistry and biosciences groups, navigating and avoiding the common pitfalls associated with the discovery process, and taking your project from concept to candidate in the most timely and efficient way.
“The BioAscent in silico discovery team developed a QSAR model based on non-standard activity data that required adaptability and creativity from the BioAscent team. The QSAR model was then used to generate novel compounds and to enumerate focused arrays. Throughout the project, the BioAscent in silico team has been responsive and flexible, which helped us reach a successful conclusion.”
CTO, Tay Therapeutics
BioAscent continues to invest in computational infrastructure and methodology to keep pace with the rapidly evolving AI drug design landscape. Current areas of active development include:
Integrated generative chemistry within the DMTA cycle, enabling AI-driven de novo design constrained by synthetic accessibility and multi-parameter optimisation objectives.
AI-assisted co-folding for structure prediction in the absence of experimental data, supporting SBDD on challenging targets including intrinsically disordered proteins and novel binding sites.
Matched molecular pair analysis with selectivity profiling across target families, enabling systematic identification of transformation vectors that modulate activity and off-target liabilities in parallel.
Accelerating CNS drug discovery — read more on the dedicated CNS page.
Fast, reliable and secure delivery of computationally intensive projects is delivered by our scalable, enterprise-grade computing environment built on Dell Xeon server architecture:
Hybrid CPU/GPU architecture, combining multi-core Intel Xeon CPUs with state-of-the-art NVIDIA GPUs to support both traditional molecular modelling workflows and modern AI-driven applications.
Dedicated on-premises AI infrastructure, with high-tier GPU hardware clusters reserved for local AI inference, enabling secure deployment of:
Generative chemistry
Deep learning-based docking models
Biomolecular structure prediction
Advanced machine learning workflows
Hardware-isolated processing architecture separates AI inference from computational chemistry and structural simulation workloads ensuring:
Consistent performance
Maximum throughput
High system availability
No resource contention during intensive campaigns
Integrated software ecosystem combining leading commercial and open-source molecular modelling platforms, databases, and workflow automation tools. These technologies are tailored, combined, and extended as required to deliver the most effective solution for each project.
Ultra-large virtual screening capability supporting:
Billions of compounds in ligand-based screening workflows
Millions of compounds in structure-based screening campaigns
"The Centre for Virus Research Translational Hub (CTH), based at the University of Glasgow, is focused on identifying novel antiviral and immunotherapeutic targets. In collaboration with the In Silico Discovery team at BioAscent, we have advanced our high-throughput drug screening platform through the identification of carefully curated compound libraries tailored to our antiviral research.
The BioAscent team's expertise and guidance have been instrumental to the development of our platforms, and the collaboration has been highly effective. The partnership has been notably integrated and flexible, responding well to evolving project demands and funding priorities. Their professionalism and solution-oriented approach have made the collaboration feel like a seamless extension of our own team."
Business Development & Liaison Manager, CVR Translational Hub, University of Glasgow
“We have been working with the In Silico Discovery team at BioAscent for over a year.
The first target we collaborated on was very challenging because the activity data were unusual. BioAscent proposed a machine learning approach to model that non-linear activity and predict the activity of a set of new compounds.
We then began collaborating on a second target. BioAscent performed MD simulations, docking studies, focused-library design, structure-based and ligand-based virtual screening. Homology modelling was also carried out for series of proteins to understand the potential selectivity issues among isoforms.
Overall, the BioAscent computational chemistry team has been innovative, reliable, and collaborative. Their work has resulted in meaningful scientific insights and idea generation and made a significant impact on the direction and progress of several of our small molecule drug discovery projects. ”
Director Medicinal Chemistry, Global Pharmaceutical Company
Discovery and characterization of novel TRPML1 agonists. X. Peng, C.J. Holler, A-M.F. Alves, M.G. Oliviera, M. Speake, A. Pugliese, M.R. Oskouei, I.D de Freitas, A.Y.-P. Chen, R. Gallegos, S.M. McTighe, G. Koenig, R.S. Hurst, J-F. Blain, J.C. Lanter, D.A. Burnett. View paper.
Implementation of an AI-assisted fragment-generator in an open-source platform. A. E. Bilsland, A. Pugliese, J. Bower. View paper.
Automated Generation of Novel Fragments Using Screening Data, a Dual SMILES Autoencoder, Transfer Learning and Syntax Correction. A. Bilsland, K. McAulay, R. West, A. Pugliese (corresponding author), J. Bower. View paper.
The identification and characterisation of autophagy inhibitors from the published kinase inhibitor sets. M. Zachari, J. Rainard, G. Pandarakalam, L. Robinson, J. Gillespie; M. Rajamanickam; V. Hamon; A. Morrison; I. Ganley; S. McElroy. View paper.
Synthesis and structure–activity relationships of N-(4-benzamidino)-oxazolidinones–potent and selective inhibitors of kallikrein-related peptidase 6; chemRxiv DOI: 10.26434/chemrxiv.9788276, 2019. E. De Vita, N. Smits, H. van den Hurk, E. Beck, J. Hewitt, G. Baillie, E. Russell, A. Pannifer, V. Hamon, A.Morrison, S. McElroy, P. Jones, N. Ignatenko, N. Gunkel and A. Miller. View paper.
Deep generative molecular design – AI at the service of the drug designer. Pharmacology Matters, British Pharmacological Society's online magazine, 2019. A. Pugliese and J. Bower. View paper.
Structure-based design, synthesis and biological evaluation of a novel series of isoquinolone and pyrazolo[4,3-c]pyridine inhibitors of fascin 1 as potential anti-metastatic agents. Bioorg Med Chem Lett. 2019; 29: 1023-9. S. Francis, et al. View paper.
Strategies for Fragment Library Design. In: Erlanson, D.A. and Jahnke W. eds. Fragment-based Drug Discovery: Lessons and Outlook. Wiley,pp. 101-117 2016. J. Bower, A. Pugliese, and M. Drysdale.
Identification of a selective G1-phase benzimidazolone inhibitor by a senescence-targeted virtual screen using artificial neural networks. Neoplasia. 2015 Sep; 17(9):704-15. A. Bilsland, A. Pugliese, et al. View paper.
Fragment-Based Hit Identification – Thinking in 3D. Drug Discov Today. 2013 Dec; 18 (23-24):1221-7. AD. Morley, A. Pugliese, et al. View paper.
Computational tools and resources for metabolism-related property predictions. 2. Application to prediction of half-life time in human liver microsomes. Future Med Chem. 2012 Oct; 4(15):1933-44. AV. Zakharov, ML. Peach, M. Sitzmann, IV. Filippov, HJ. McCartney, LH. Smith, A. Pugliese, MC Nicklaus. View paper.
Software and Resources for Computational Medicinal Chemistry. Future Med Chem. 2011 Jun; 3(8):1057-85. C. Liao, M. Sitzmann, A. Pugliese, M. Nicklaus. View paper.
"We found the collaboration to be highly collaborative throughout, from the initial VS to the analogue-by-catalogue stage. The initial VS was well designed, with the assumptions and choices for methods well explained and agreed with us. There was excellent sharing of outputs, and the team was very responsive to adapting the hit selection strategy as the results evolved."
Enedra Therapeutics
