David F. Nippa
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
David F. Nippa has a total of 72 co-authors. Here are the top co-authors by number of shared publications:
- Uwe Grether
Roche Pharma Research & Early Development, Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd, 4070 Basel, Switzerland
10 shared publications - Gisbert Schneider
ETH Zurich
9 shared publications - Kenneth Atz
Roche Pharma Research and Early Development (pRED), F. Hoffmann-La Roche Ltd., Grenzacherstrasse 124, Basel, Switzerland, 4070
8 shared publications - Rainer E. Martin
Roche Pharma Research and Early Development (pRED), Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd., Basel, Switzerland
8 shared publications - Alex T. Müller
Roche Pharma Research and Early Development (pRED), Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd., Basel, Switzerland
7 shared publications - Jens Wolfard
Roche Pharma Research and Early Development (pRED), Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd., Basel, Switzerland
5 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by American Chemical Society (ACS) in ChemRxiv
Orchestrating literature landscaping in drug discovery by coupling citation expansion with large language models
Systematic literature reviews guide decisions in drug discovery, yet keyword-based retrieval misses relevant work hidden behind synonyms, compound codes and cross-disciplinary vocabulary. Manual screening of large literature pools is slow and costly. Large language models (LLMs) could relieve this bottleneck, but existing tools address either citation-based retrieval or LLM screening, and rarely validate how well the combination performs. We present CESAR (Citation Expansion for Systematic Academic Reviewing), an open-source workflow that assembles domain corpora by following references and citing works through OpenAlex. It screens titles and abstracts with LLMs calibrated against human-annotated reference sets. We demonstrate CESAR on a broad methodological field, total synthesis, and on a narrow drug target, monoacylglycerol lipase (MAGL). For total synthesis, the collected corpus contained 78% of an independently curated reference collection published 2000–2023. The classifier retained 99.3% of those that reached screening, and inexpensive models performed close to the most expensive ones. For MAGL, an open-weight model reduced more than 20,000 records to 893 at no cost, with an estimated 79% of them relevant, while extracting target selectivity, evidence level and compound names in the same step. Run on a single local GPU, the same model matched cloud performance, enabling screening of confidential material without external data transfer. CESAR turns screening of tens of thousands of abstracts into a task of hours to days, at costs from zero to about one US dollar per thousand papers, and keeps expert attention for the decisions that require it.
- 9 November 2026
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessOrchestrating literature landscaping in drug discovery by coupling citation expansion with large language models
Systematic literature reviews guide decisions in drug discovery, yet keyword-based retrieval misses relevant work hidden behind synonyms, compound codes and cross-disciplinary vocabulary. Manual screening of large literature pools is slow and costly. Large language models (LLMs) could relieve this bottleneck, but existing tools address either citation-based retrieval or LLM screening, and rarely validate how well the combination performs. We present CESAR (Citation Expansion for Systematic Academic Reviewing), an open-source workflow that assembles domain corpora by following references and citing works through OpenAlex. It screens titles and abstracts with LLMs calibrated against human-annotated reference sets. We demonstrate CESAR on a broad methodological field, total synthesis, and on a narrow drug target, monoacylglycerol lipase (MAGL). For total synthesis, the collected corpus contained 78% of an independently curated reference collection published 2000–2023. The classifier retained 99.3% of those that reached screening, and inexpensive models performed close to the most expensive ones. For MAGL, an open-weight model reduced more than 20,000 records to 893 at no cost, with an estimated 79% of them relevant, while extracting target selectivity, evidence level and compound names in the same step. Run on a single local GPU, the same model matched cloud performance, enabling screening of confidential material without external data transfer. CESAR turns screening of tens of thousands of abstracts into a task of hours to days, at costs from zero to about one US dollar per thousand papers, and keeps expert attention for the decisions that require it.
- Open Access
- 9 October 2026
- Published by Springer Nature in Nature Computational Science
- p. 1-17
Advancing chemical reaction prediction in data-scarce drug discovery with active and geometric deep learning
The success of generative molecular design depends on the synthetic accessibility of the molecules it creates. While computational models can help predict chemical reactions, their current effectiveness is limited by a lack of reference data and the difficulty of accurately predicting reaction regioselectivity. Here, to address this, we present an integrated closed-loop workflow that combines efficient reaction data acquisition with high-accuracy deep learning. We developed an active learning strategy, driven by a tree-based ensemble, to guide the acquisition of the most informative laboratory experiments. This experimental campaign yielded a diverse benchmark for C–H borylation. The bespoke dataset allowed us to train and evaluate geometric graph neural networks. We demonstrate that augmenting these symmetry-aware models with self-supervised auxiliary tasks consistently improves performance for both reaction outcome prediction and regioselectivity prediction. Prospective tests on unseen substrates, featuring challenging N -heteroaryl motifs, pinpointed the correct borylation positions in all cases, illustrating the practical utility of our workflow for efficient drug optimization.
- 9 October 2026
- Published by Springer Nature in Nature Computational Science
- p. 1-17
Open AccessAdvancing chemical reaction prediction in data-scarce drug discovery with active and geometric deep learning
The success of generative molecular design depends on the synthetic accessibility of the molecules it creates. While computational models can help predict chemical reactions, their current effectiveness is limited by a lack of reference data and the difficulty of accurately predicting reaction regioselectivity. Here, to address this, we present an integrated closed-loop workflow that combines efficient reaction data acquisition with high-accuracy deep learning. We developed an active learning strategy, driven by a tree-based ensemble, to guide the acquisition of the most informative laboratory experiments. This experimental campaign yielded a diverse benchmark for C–H borylation. The bespoke dataset allowed us to train and evaluate geometric graph neural networks. We demonstrate that augmenting these symmetry-aware models with self-supervised auxiliary tasks consistently improves performance for both reaction outcome prediction and regioselectivity prediction. Prospective tests on unseen substrates, featuring challenging N -heteroaryl motifs, pinpointed the correct borylation positions in all cases, illustrating the practical utility of our workflow for efficient drug optimization.
- Open Access
- 26 November 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1)
Expediting hit-to-lead progression in drug discovery through reaction prediction and multi-dimensional optimization
The rapid and economical synthesis of novel bioactive compounds remains a hurdle in drug discovery efforts. This study demonstrates an integrated medicinal chemistry workflow that effectively diversifies hit and lead structures, enabling an acceleration of the critical hit-to-lead optimization phase. Employing high-throughput experimentation (HTE), we generated a comprehensive data set encompassing 13,490 novel Minisci-type C-H alkylation reactions. These data served as the foundation for training deep graph neural networks to accurately predict reaction outcomes. Scaffold-based enumeration of potential Minisci reaction products, starting from moderate inhibitors of monoacylglycerol lipase (MAGL), yielded a virtual library containing 26,375 molecules. This virtual chemical library was evaluated using reaction prediction, physicochemical property assessment, and structure-based scoring, identifying 212 MAGL inhibitor candidates. Of these, 14 compounds were synthesized and exhibited subnanomolar activity, representing a potency improvement of up to 4500 times over the original hit compound. These ligands also showed favorable pharmacological profiles. Co-crystallization of three computationally designed ligands with the MAGL protein provided structural insights into their binding modes. This study demonstrates the potential of combining miniaturized HTE with deep learning and optimization of molecular properties to reduce cycle times in hit-to-lead progression.
- 26 November 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1)
Open AccessExpediting hit-to-lead progression in drug discovery through reaction prediction and multi-dimensional optimization
The rapid and economical synthesis of novel bioactive compounds remains a hurdle in drug discovery efforts. This study demonstrates an integrated medicinal chemistry workflow that effectively diversifies hit and lead structures, enabling an acceleration of the critical hit-to-lead optimization phase. Employing high-throughput experimentation (HTE), we generated a comprehensive data set encompassing 13,490 novel Minisci-type C-H alkylation reactions. These data served as the foundation for training deep graph neural networks to accurately predict reaction outcomes. Scaffold-based enumeration of potential Minisci reaction products, starting from moderate inhibitors of monoacylglycerol lipase (MAGL), yielded a virtual library containing 26,375 molecules. This virtual chemical library was evaluated using reaction prediction, physicochemical property assessment, and structure-based scoring, identifying 212 MAGL inhibitor candidates. Of these, 14 compounds were synthesized and exhibited subnanomolar activity, representing a potency improvement of up to 4500 times over the original hit compound. These ligands also showed favorable pharmacological profiles. Co-crystallization of three computationally designed ligands with the MAGL protein provided structural insights into their binding modes. This study demonstrates the potential of combining miniaturized HTE with deep learning and optimization of molecular properties to reduce cycle times in hit-to-lead progression.
- 15 October 2025
- Published by Royal Society of Chemistry (RSC) in RSC Medicinal Chemistry
- Vol. 16 (12) , 5753-5764
Accelerating compound synthesis in drug discovery: the role of digitalisation and automation
This opinion addresses how digitalisation and automation can reduce the synthesis bottleneck in the DMTA cycle. Current automated synthesis & planning, future data-rich integrated platforms, and the medicinal chemist's evolving role are reviewed.
- 15 October 2025
- Published by Royal Society of Chemistry (RSC) in RSC Medicinal Chemistry
- Vol. 16 (12) , 5753-5764
Accelerating compound synthesis in drug discovery: the role of digitalisation and automation
This opinion addresses how digitalisation and automation can reduce the synthesis bottleneck in the DMTA cycle. Current automated synthesis & planning, future data-rich integrated platforms, and the medicinal chemist's evolving role are reviewed.
- Open Access
- 28 January 2025
- Published by American Chemical Society (ACS) in ChemRxiv
Expediting hit-to-lead progression in drug discovery through reaction prediction and multi-objective molecular optimization
The rapid and economical synthesis of novel bioactive compounds remains a significant hurdle in drug discovery efforts. This study demonstrates an integrated medicinal chemistry workflow that effectively diversifies hit and lead structures, enabling an efficient acceleration of the critical hit-to-lead optimization phase. Employing high-throughput experimentation (HTE), we generated a comprehensive data set encompassing 13,490 novel Minisci-type C-H alkylation reactions. This data set served as the foundation for training deep graph neural networks to accurately predict reaction outcomes. Scaffold-based enumeration of potential Minisci reaction products, starting from moderate inhibitors of monoacylglycerol lipase (MAGL), yielded a virtual library containing 26,375 molecules. This virtual chemical library was evaluated using reaction prediction, physicochemical property assessment, and structure-based scoring, identifying 212 potential MAGL inhibitor candidates. Of these, 14 ligands were synthesized and exhibited subnanomolar activity, representing a potency improvement of up to 4500 times over the original hit compound. These compounds also displayed favorable pharmacological profiles. Co-crystallization of three computationally designed ligands with the MAGL protein provided valuable structural insights into their preferred binding poses. This study demonstrates the potential of combining miniaturized HTE with deep learning and molecular property optimization to reduce cycle times in drug discovery.
- 28 January 2025
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessExpediting hit-to-lead progression in drug discovery through reaction prediction and multi-objective molecular optimization
The rapid and economical synthesis of novel bioactive compounds remains a significant hurdle in drug discovery efforts. This study demonstrates an integrated medicinal chemistry workflow that effectively diversifies hit and lead structures, enabling an efficient acceleration of the critical hit-to-lead optimization phase. Employing high-throughput experimentation (HTE), we generated a comprehensive data set encompassing 13,490 novel Minisci-type C-H alkylation reactions. This data set served as the foundation for training deep graph neural networks to accurately predict reaction outcomes. Scaffold-based enumeration of potential Minisci reaction products, starting from moderate inhibitors of monoacylglycerol lipase (MAGL), yielded a virtual library containing 26,375 molecules. This virtual chemical library was evaluated using reaction prediction, physicochemical property assessment, and structure-based scoring, identifying 212 potential MAGL inhibitor candidates. Of these, 14 ligands were synthesized and exhibited subnanomolar activity, representing a potency improvement of up to 4500 times over the original hit compound. These compounds also displayed favorable pharmacological profiles. Co-crystallization of three computationally designed ligands with the MAGL protein provided valuable structural insights into their preferred binding poses. This study demonstrates the potential of combining miniaturized HTE with deep learning and molecular property optimization to reduce cycle times in drug discovery.
- Open Access
- 23 January 2025
- Published by Wiley in Molecular Informatics
- Vol. 44 (1) , e202400361
Simple User‐Friendly Reaction Format
Utilizing the growing wealth of chemical reaction data can boost synthesis planning and increase success rates. Yet, the effectiveness of machine learning tools for retrosynthesis planning and forward reaction prediction relies on accessible, well‐curated data presented in a structured format. Although some public and licensed reaction databases exist, they often lack essential information about reaction conditions. To address this issue and promote the principles of findable, accessible, interoperable, and reusable (FAIR) data reporting and sharing, we introduce the Simple User‐Friendly Reaction Format (SURF). SURF standardizes the documentation of reaction data through a structured tabular format, requiring only a basic understanding of spreadsheets. This format enables chemists to record the synthesis of molecules in a format that is understandable by both humans and machines, which facilitates seamless sharing and integration directly into machine learning pipelines. SURF files are designed to be interoperable, easily imported into relational databases, and convertible into other formats. This complements existing initiatives like the Open Reaction Database (ORD) and Unified Data Model (UDM). At Roche, SURF plays a crucial role in democratizing FAIR reaction data sharing and expediting the chemical synthesis process.
- 23 January 2025
- Published by Wiley in Molecular Informatics
- Vol. 44 (1) , e202400361
Open AccessSimple User‐Friendly Reaction Format
Utilizing the growing wealth of chemical reaction data can boost synthesis planning and increase success rates. Yet, the effectiveness of machine learning tools for retrosynthesis planning and forward reaction prediction relies on accessible, well‐curated data presented in a structured format. Although some public and licensed reaction databases exist, they often lack essential information about reaction conditions. To address this issue and promote the principles of findable, accessible, interoperable, and reusable (FAIR) data reporting and sharing, we introduce the Simple User‐Friendly Reaction Format (SURF). SURF standardizes the documentation of reaction data through a structured tabular format, requiring only a basic understanding of spreadsheets. This format enables chemists to record the synthesis of molecules in a format that is understandable by both humans and machines, which facilitates seamless sharing and integration directly into machine learning pipelines. SURF files are designed to be interoperable, easily imported into relational databases, and convertible into other formats. This complements existing initiatives like the Open Reaction Database (ORD) and Unified Data Model (UDM). At Roche, SURF plays a crucial role in democratizing FAIR reaction data sharing and expediting the chemical synthesis process.
- Open Access
- 17 January 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1
Author Correction: Prospective de novo drug design with deep interactome learning
- 17 January 2025
- Published by Springer Nature in Nature Communications
- Vol. 16 (1) , 1
Open AccessAuthor Correction: Prospective de novo drug design with deep interactome learning
- Open Access
- 4 January 2025
- Published by Adjacent Digital Politics Ltd in Open Access Government
- Vol. 46 (1) , 76-77
AI-driven innovations in GPCR ligand synthesis for treating inflammatory diseases
AI-driven innovations in GPCR ligand synthesis for treating inflammatory diseases: This article explores the significance of G Protein-Coupled Receptors (GPCRs) in therapeutic drug development and strategies for advancing GPCR-targeted therapies, including the use of agonists, antagonists, biased agonism, and allosteric modulators. G Protein-Coupled Receptors (GPCRs) are a large and diverse group of membrane proteins that play a crucial role in cellular communication and signal transduction. (1) Characterized by their seven transmembrane domains, GPCRs activate intracellular G proteins in response to extracellular signals such as hormones, neurotransmitters, and other signaling molecules. The GPCR superfamily consists of approximately 800 membrane proteins, sharing a common evolutionary origin and coupling primarily to intracellular transducers like G proteins and arrestins. These receptors are integral to complex signaling systems that modulate a wide array of physiological and pathophysiological processes. (2)
- 4 January 2025
- Published by Adjacent Digital Politics Ltd in Open Access Government
- Vol. 46 (1) , 76-77
Open AccessAI-driven innovations in GPCR ligand synthesis for treating inflammatory diseases
AI-driven innovations in GPCR ligand synthesis for treating inflammatory diseases: This article explores the significance of G Protein-Coupled Receptors (GPCRs) in therapeutic drug development and strategies for advancing GPCR-targeted therapies, including the use of agonists, antagonists, biased agonism, and allosteric modulators. G Protein-Coupled Receptors (GPCRs) are a large and diverse group of membrane proteins that play a crucial role in cellular communication and signal transduction. (1) Characterized by their seven transmembrane domains, GPCRs activate intracellular G proteins in response to extracellular signals such as hormones, neurotransmitters, and other signaling molecules. The GPCR superfamily consists of approximately 800 membrane proteins, sharing a common evolutionary origin and coupling primarily to intracellular transducers like G proteins and arrestins. These receptors are integral to complex signaling systems that modulate a wide array of physiological and pathophysiological processes. (2)
- 31 May 2024
- Published by Royal Society of Chemistry (RSC) in RSC Medicinal Chemistry
- Vol. 15 (7) , 2310-2321
Geometric deep learning-guided Suzuki reaction conditions assessment for applications in medicinal chemistry
Suzuki cross-coupling reactions are considered a valuable tool for constructing carbon–carbon bonds in small molecule drug discovery. However, the synthesis of chemical matter often represents a time-consuming and labour-intensive bottleneck. We demonstrate how machine learning methods trained on high-throughput experimentation (HTE) data can be leveraged to enable fast reaction condition selection for novel coupling partners. We show that the trained models support chemists in determining suitable catalyst-solvent-base combinations for individual transformations including an evaluation of the need for HTE screening. We introduce an algorithm for designing 96-well plates optimized towards reaction yields and discuss the model performance of zero- and few-shot machine learning. The best-performing machine learning model achieved a three-category classification accuracy of 76.3% (±0.2%) and an F1-score for a binary classification of 79.1% (±0.9%). Validation on eight reactions revealed a receiver operating characteristic (ROC) curve (AUC) value of 0.82 (±0.07) for few-shot machine learning. On the other hand, zero-shot machine learning models achieved a mean ROC-AUC value of 0.63 (±0.16). This study positively advocates the application of few-shot machine learning-guided reaction condition selection for HTE campaigns in medicinal chemistry and highlights practical applications as well as challenges associated with zero-shot machine learning.
- 31 May 2024
- Published by Royal Society of Chemistry (RSC) in RSC Medicinal Chemistry
- Vol. 15 (7) , 2310-2321
Geometric deep learning-guided Suzuki reaction conditions assessment for applications in medicinal chemistry
Suzuki cross-coupling reactions are considered a valuable tool for constructing carbon–carbon bonds in small molecule drug discovery. However, the synthesis of chemical matter often represents a time-consuming and labour-intensive bottleneck. We demonstrate how machine learning methods trained on high-throughput experimentation (HTE) data can be leveraged to enable fast reaction condition selection for novel coupling partners. We show that the trained models support chemists in determining suitable catalyst-solvent-base combinations for individual transformations including an evaluation of the need for HTE screening. We introduce an algorithm for designing 96-well plates optimized towards reaction yields and discuss the model performance of zero- and few-shot machine learning. The best-performing machine learning model achieved a three-category classification accuracy of 76.3% (±0.2%) and an F1-score for a binary classification of 79.1% (±0.9%). Validation on eight reactions revealed a receiver operating characteristic (ROC) curve (AUC) value of 0.82 (±0.07) for few-shot machine learning. On the other hand, zero-shot machine learning models achieved a mean ROC-AUC value of 0.63 (±0.16). This study positively advocates the application of few-shot machine learning-guided reaction condition selection for HTE campaigns in medicinal chemistry and highlights practical applications as well as challenges associated with zero-shot machine learning.
- Top Cited PapersOpen Access
- 22 April 2024
- Published by Springer Nature in Nature Communications
- Vol. 15 (1) , 1-18
Prospective de novo drug design with deep interactome learning
De novo drug design aims to generate molecules from scratch that possess specific chemical and pharmacological properties. We present a computational approach utilizing interactome-based deep learning for ligand- and structure-based generation of drug-like molecules. This method capitalizes on the unique strengths of both graph neural networks and chemical language models, offering an alternative to the need for application-specific reinforcement, transfer, or few-shot learning. It enables the “zero-shot" construction of compound libraries tailored to possess specific bioactivity, synthesizability, and structural novelty. In order to proactively evaluate the deep interactome learning framework for protein structure-based drug design, potential new ligands targeting the binding site of the human peroxisome proliferator-activated receptor (PPAR) subtype gamma are generated. The top-ranking designs are chemically synthesized and computationally, biophysically, and biochemically characterized. Potent PPAR partial agonists are identified, demonstrating favorable activity and the desired selectivity profiles for both nuclear receptors and off-target interactions. Crystal structure determination of the ligand-receptor complex confirms the anticipated binding mode. This successful outcome positively advocates interactome-based de novo design for application in bioorganic and medicinal chemistry, enabling the creation of innovative bioactive molecules.
- 22 April 2024
- Published by Springer Nature in Nature Communications
- Vol. 15 (1) , 1-18
Top Cited PapersOpen AccessProspective de novo drug design with deep interactome learning
De novo drug design aims to generate molecules from scratch that possess specific chemical and pharmacological properties. We present a computational approach utilizing interactome-based deep learning for ligand- and structure-based generation of drug-like molecules. This method capitalizes on the unique strengths of both graph neural networks and chemical language models, offering an alternative to the need for application-specific reinforcement, transfer, or few-shot learning. It enables the “zero-shot" construction of compound libraries tailored to possess specific bioactivity, synthesizability, and structural novelty. In order to proactively evaluate the deep interactome learning framework for protein structure-based drug design, potential new ligands targeting the binding site of the human peroxisome proliferator-activated receptor (PPAR) subtype gamma are generated. The top-ranking designs are chemically synthesized and computationally, biophysically, and biochemically characterized. Potent PPAR partial agonists are identified, demonstrating favorable activity and the desired selectivity profiles for both nuclear receptors and off-target interactions. Crystal structure determination of the ligand-receptor complex confirms the anticipated binding mode. This successful outcome positively advocates interactome-based de novo design for application in bioorganic and medicinal chemistry, enabling the creation of innovative bioactive molecules.