Nil Adell Mill
Nil Adell Mill has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
Alexei Ossadtchi
Center for Bioelectric Interfaces of the Institute for Cognitive Neuroscience of the National Research University Higher School of Economics, Moscow, Russia
1 shared publicationAntonio Cardinale
1 shared publication- Bruno Fant
MyNEO
1 shared publication - Cedric Bogaert
MyNEO
1 shared publication - Greta Markert
Laboratorium für Organische Chemie ETH 8093 Zurich Switzerland
1 shared publication - Jannis Born
IBM Research Europe, Rüschlikon, Switzerland
1 shared publication
Latest Publications
- Open Access
neoMS: Attention-based Prediction of MHC-I Epitope Presentation
Personalised immunotherapy aims to (re-)activate the immune system of a given patient against its tumour. It relies extensively on the ability of tumour-derived neoantigens to trigger a T-cell immune reaction able to recognise and kill the tumour cells expressing them. Since only peptides presented on the cell surface can be immunogenic, the prediction of neoantigen presentation is a crucial step of any discovery pipeline. Limiting neoantigen presentation to MHC binding fails to take into account all other steps of the presentation machinery and therefore to assess the true potential clinical benefit of a given epitope. Indeed, research has uncovered that merely 5% of predicted tumour-derived MHC-bound peptides is actually presented on the cell surface, demonstrating that affinity-based approaches fall short from isolating truly actionable neoantigens. Here, we present neoMS, a MHC-I presentation prediction algorithm leveraging mass spectrometry-derived MHC ligandomic data to better isolate presented antigens from potentially very large sets. The neoMS model is a transformer-based, peptide-sequence-to-HLA-sequence neural network algorithm, trained on 386,647 epitopes detected in the ligandomes of 92 HLA-monoallelic datasets and 66 patient-derived HLA-multiallelic datasets. It leverages attention mechanisms in which the most relevant parts of both putative epitope and HLA alleles are isolated. This results in a positive predictive value of 0.61 at a recall of 40% on its patient-derived test dataset, considerably outperforming current alternatives. Predictions made by neoMS correlate with peptide identification confidence in mass spectrometry experiments and reliably identify binding motif preferences of individual HLA alleles thereby further consolidating the biological relevance of the model. Additionally, neoMS displays extrapolation capabilities, showing good predictive power for presentation by HLA alleles not present in its training dataset. Finally, it was found that neoMS results can help refine predictions of response to immune checkpoint inhibitor treatment in certain cancer indications. Taken together, these results establish neoMS as a considerable step forward in high-specificity isolation of clinically actionable antigens for immunotherapies.
Open AccessneoMS: Attention-based Prediction of MHC-I Epitope Presentation
Personalised immunotherapy aims to (re-)activate the immune system of a given patient against its tumour. It relies extensively on the ability of tumour-derived neoantigens to trigger a T-cell immune reaction able to recognise and kill the tumour cells expressing them. Since only peptides presented on the cell surface can be immunogenic, the prediction of neoantigen presentation is a crucial step of any discovery pipeline. Limiting neoantigen presentation to MHC binding fails to take into account all other steps of the presentation machinery and therefore to assess the true potential clinical benefit of a given epitope. Indeed, research has uncovered that merely 5% of predicted tumour-derived MHC-bound peptides is actually presented on the cell surface, demonstrating that affinity-based approaches fall short from isolating truly actionable neoantigens. Here, we present neoMS, a MHC-I presentation prediction algorithm leveraging mass spectrometry-derived MHC ligandomic data to better isolate presented antigens from potentially very large sets. The neoMS model is a transformer-based, peptide-sequence-to-HLA-sequence neural network algorithm, trained on 386,647 epitopes detected in the ligandomes of 92 HLA-monoallelic datasets and 66 patient-derived HLA-multiallelic datasets. It leverages attention mechanisms in which the most relevant parts of both putative epitope and HLA alleles are isolated. This results in a positive predictive value of 0.61 at a recall of 40% on its patient-derived test dataset, considerably outperforming current alternatives. Predictions made by neoMS correlate with peptide identification confidence in mass spectrometry experiments and reliably identify binding motif preferences of individual HLA alleles thereby further consolidating the biological relevance of the model. Additionally, neoMS displays extrapolation capabilities, showing good predictive power for presentation by HLA alleles not present in its training dataset. Finally, it was found that neoMS results can help refine predictions of response to immune checkpoint inhibitor treatment in certain cancer indications. Taken together, these results establish neoMS as a considerable step forward in high-specificity isolation of clinically actionable antigens for immunotherapies.
- Open Access
- 25 March 2021
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 2 (2) , 025024
Data-driven molecular design for discovery and synthesis of novel ligands: a case study on SARS-CoV-2
Bridging systems biology and drug design, we propose a deep learning framework for de novo discovery of molecules tailored to bind with given protein targets. Our methodology is exemplified by the task of designing antiviral candidates to target SARS-CoV-2 related proteins. Crucially, our framework does not require fine-tuning for specific proteins but is demonstrated to generalize in proposing ligands with high predicted binding affinities against unseen targets. Coupling our framework with the automatic retrosynthesis prediction of IBM RXN for Chemistry, we demonstrate the feasibility of swift chemical synthesis of molecules with potential antiviral properties that were designed against a specific protein target. In particular, we synthesize an antiviral candidate designed against the host protein angiotensin converting enzyme 2 (ACE2); a surface receptor on human respiratory epithelial cells that facilitates SARS-CoV-2 cell entry through its spike glycoprotein. This is achieved as follows. First, we train a multimodal ligand–protein binding affinity model on predicting affinities of bioactive compounds to target proteins and couple this model with pharmacological toxicity predictors. Exploiting this multi-objective as a reward function of a conditional molecular generator that consists of two variational autoencoders (VAE), our framework steers the generation toward regions of the chemical space with high-reward molecules. Specifically, we explore a challenging setting of generating ligands against unseen protein targets by performing a leave-one-out-cross-validation on 41 SARS-CoV-2-related target proteins. Using deep reinforcement learning, it is demonstrated that in 35 out of 41 cases, the generation is biased towards sampling binding ligands, with an average increase of 83% comparing to an unbiased VAE. The generated molecules exhibit favorable properties in terms of target binding affinity, selectivity and drug-likeness. We use molecular retrosynthetic models to provide a synthetic accessibility assessment of the best generated hit molecules. Finally, with this end-to-end framework, we synthesize 3-Bromobenzylamine, a potential inhibitor of the host ACE2 protein, solely based on the recommendations of a molecular retrosynthesis model and a synthesis protocol prediction model. We hope that our framework can contribute towards swift discovery of de novo molecules with desired pharmacological properties.
- 25 March 2021
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 2 (2) , 025024
Open AccessData-driven molecular design for discovery and synthesis of novel ligands: a case study on SARS-CoV-2
Bridging systems biology and drug design, we propose a deep learning framework for de novo discovery of molecules tailored to bind with given protein targets. Our methodology is exemplified by the task of designing antiviral candidates to target SARS-CoV-2 related proteins. Crucially, our framework does not require fine-tuning for specific proteins but is demonstrated to generalize in proposing ligands with high predicted binding affinities against unseen targets. Coupling our framework with the automatic retrosynthesis prediction of IBM RXN for Chemistry, we demonstrate the feasibility of swift chemical synthesis of molecules with potential antiviral properties that were designed against a specific protein target. In particular, we synthesize an antiviral candidate designed against the host protein angiotensin converting enzyme 2 (ACE2); a surface receptor on human respiratory epithelial cells that facilitates SARS-CoV-2 cell entry through its spike glycoprotein. This is achieved as follows. First, we train a multimodal ligand–protein binding affinity model on predicting affinities of bioactive compounds to target proteins and couple this model with pharmacological toxicity predictors. Exploiting this multi-objective as a reward function of a conditional molecular generator that consists of two variational autoencoders (VAE), our framework steers the generation toward regions of the chemical space with high-reward molecules. Specifically, we explore a challenging setting of generating ligands against unseen protein targets by performing a leave-one-out-cross-validation on 41 SARS-CoV-2-related target proteins. Using deep reinforcement learning, it is demonstrated that in 35 out of 41 cases, the generation is biased towards sampling binding ligands, with an average increase of 83% comparing to an unbiased VAE. The generated molecules exhibit favorable properties in terms of target binding affinity, selectivity and drug-likeness. We use molecular retrosynthetic models to provide a synthetic accessibility assessment of the best generated hit molecules. Finally, with this end-to-end framework, we synthesize 3-Bromobenzylamine, a potential inhibitor of the host ACE2 protein, solely based on the recommendations of a molecular retrosynthesis model and a synthesis protocol prediction model. We hope that our framework can contribute towards swift discovery of de novo molecules with desired pharmacological properties.
- Open Access
- 12 December 2019
- Published by Springer Nature in Scientific Reports
- Vol. 9 (1) , 1-14
Analysis of neuronal ensemble activity reveals the pitfalls and shortcomings of rotation dynamics
Back in 2012, Churchland and his colleagues proposed that “rotational dynamics”, uncovered through linear transformations of multidimensional neuronal data, represent a fundamental type of neuronal population processing in a variety of organisms, from the isolated leech central nervous system to the primate motor cortex. Here, we evaluated this claim using Churchland’s own data and simple simulations of neuronal responses. We observed that rotational patterns occurred in neuronal populations when (1) there was a temporal sequence in peak firing rates exhibited by individual neurons, and (2) this sequence remained consistent across different experimental conditions. Provided that such a temporal order of peak firing rates existed, rotational patterns could be easily obtained using a rather arbitrary computer simulation of neural activity; modeling of any realistic properties of motor cortical responses was not needed. Additionally, arbitrary traces, such as Lissajous curves, could be easily obtained from Churchland’s data with multiple linear regression. While these observations suggest that temporal sequences of neuronal responses could be visualized as rotations with various methods, we express doubt about Churchlandet al.’s bold assessment that such rotations are related to “an unexpected yet surprisingly simple structure in the population response”, which “explains many of the confusing features of individual neural responses”. Instead, we argue that their approach provides little, if any, insight on the underlying neuronal mechanisms employed by neuronal ensembles to encode motor behaviors in any species.
- 12 December 2019
- Published by Springer Nature in Scientific Reports
- Vol. 9 (1) , 1-14
Open AccessAnalysis of neuronal ensemble activity reveals the pitfalls and shortcomings of rotation dynamics
Back in 2012, Churchland and his colleagues proposed that “rotational dynamics”, uncovered through linear transformations of multidimensional neuronal data, represent a fundamental type of neuronal population processing in a variety of organisms, from the isolated leech central nervous system to the primate motor cortex. Here, we evaluated this claim using Churchland’s own data and simple simulations of neuronal responses. We observed that rotational patterns occurred in neuronal populations when (1) there was a temporal sequence in peak firing rates exhibited by individual neurons, and (2) this sequence remained consistent across different experimental conditions. Provided that such a temporal order of peak firing rates existed, rotational patterns could be easily obtained using a rather arbitrary computer simulation of neural activity; modeling of any realistic properties of motor cortical responses was not needed. Additionally, arbitrary traces, such as Lissajous curves, could be easily obtained from Churchland’s data with multiple linear regression. While these observations suggest that temporal sequences of neuronal responses could be visualized as rotations with various methods, we express doubt about Churchlandet al.’s bold assessment that such rotations are related to “an unexpected yet surprisingly simple structure in the population response”, which “explains many of the confusing features of individual neural responses”. Instead, we argue that their approach provides little, if any, insight on the underlying neuronal mechanisms employed by neuronal ensembles to encode motor behaviors in any species.