Search Results for author: Philippe Schwaller

Found 21 papers, 13 papers with code

Molecular Hypergraph Neural Networks

1 code implementation20 Dec 2023 Junwu Chen, Philippe Schwaller

To tackle this challenge, we introduce molecular hypergraphs and propose Molecular Hypergraph Neural Networks (MHNN) to predict the optoelectronic properties of organic semiconductors, where hyperedges represent conjugated structures.

Property Prediction

FSscore: A Machine Learning-based Synthetic Feasibility Score Leveraging Human Expertise

no code implementations20 Dec 2023 Rebecca M. Neeser, Bruno Correia, Philippe Schwaller

The FSscore showcases how human expert feedback can be utilized to optimize the assessment of synthetic feasibility for a variety of applications.

Drug Discovery Graph Attention

Holistic chemical evaluation reveals pitfalls in reaction prediction models

1 code implementation14 Dec 2023 Victor Sabanza Gil, Andres M. Bran, Malte Franke, Remi Schlama, Jeremy S. Luterbacher, Philippe Schwaller

The prediction of chemical reactions has gained significant interest within the machine learning community in recent years, owing to its complexity and crucial applications in chemistry.

Out-of-Distribution Generalization

Transformers and Large Language Models for Chemistry and Drug Discovery

no code implementations9 Oct 2023 Andres M Bran, Philippe Schwaller

Language modeling has seen impressive progress over the last years, mainly prompted by the invention of the Transformer architecture, sparking a revolution in many fields of machine learning, with breakthroughs in chemistry and biology.

Drug Discovery Language Modelling

ODEFormer: Symbolic Regression of Dynamical Systems with Transformers

1 code implementation9 Oct 2023 Stéphane d'Ascoli, Sören Becker, Alexander Mathis, Philippe Schwaller, Niki Kilbertus

We introduce ODEFormer, the first transformer able to infer multidimensional ordinary differential equation (ODE) systems in symbolic form from the observation of a single solution trajectory.

regression Symbolic Regression

Beam Enumeration: Probabilistic Explainability For Sample Efficient Self-conditioned Molecular Design

1 code implementation25 Sep 2023 Jeff Guo, Philippe Schwaller

Generative molecular design has moved from proof-of-concept to real-world applicability, as marked by the surge in very recent papers reporting experimental validation.

Augmented Memory: Capitalizing on Experience Replay to Accelerate De Novo Molecular Design

no code implementations10 May 2023 Jeff Guo, Philippe Schwaller

Molecular generative models have shown remarkable sample efficiency when coupled with reinforcement learning, as demonstrated in the Practical Molecular Optimization (PMO) benchmark.

Data Augmentation Drug Discovery

ChemCrow: Augmenting large-language models with chemistry tools

2 code implementations11 Apr 2023 Andres M Bran, Sam Cox, Oliver Schilter, Carlo Baldassari, Andrew D White, Philippe Schwaller

Our agent autonomously planned and executed the syntheses of an insect repellent, three organocatalysts, and guided the discovery of a novel chromophore.

Drug Discovery

Identification of Enzymatic Active Sites with Unsupervised Language Modeling

no code implementations NeurIPS Workshop AI4Scien 2021 Loïc Kwate Dassi, Matteo Manica, Daniel Probst, Philippe Schwaller, Yves Gaetan Nana Teukam, Teodoro Laino

Herein, we apply a Transformer architecture to a language representation of bio-catalyzed chemical reactions to learn the signal at the base of the substrate-active site atomic interactions.

Language Modelling

Dataset Bias in the Natural Sciences: A Case Study in Chemical Reaction Prediction and Synthesis Design

no code implementations6 May 2021 Ryan-Rhys Griffiths, Philippe Schwaller, Alpha A. Lee

Datasets in the Natural Sciences are often curated with the goal of aiding scientific understanding and hence may not always be in a form that facilitates the application of machine learning.

BIG-bench Machine Learning Chemical Reaction Prediction +1

Unassisted Noise Reduction of Chemical Reaction Data Sets

1 code implementation2 Feb 2021 Alessandra Toniato, Philippe Schwaller, Antonio Cardinale, Joppe Geluykens, Teodoro Laino

Existing deep learning models applied to reaction prediction in organic chemistry can reach high levels of accuracy (> 90% for Natural Language Processing-based ones).

Exploring Chemical Space using Natural Language Processing Methodologies for Drug Discovery

no code implementations10 Feb 2020 Hakime Öztürk, Arzucan Özgür, Philippe Schwaller, Teodoro Laino, Elif Ozkirimli

Text-based representations of chemicals and proteins can be thought of as unstructured languages codified by humans to describe domain-specific knowledge.

Drug Discovery

Predicting retrosynthetic pathways using a combined linguistic model and hyper-graph exploration strategy

no code implementations17 Oct 2019 Philippe Schwaller, Riccardo Petraglia, Valerio Zullo, Vishnu H Nair, Rico Andreas Haeuselmann, Riccardo Pisoni, Costas Bekas, Anna Iuliano, Teodoro Laino

We present an extension of our Molecular Transformer architecture combined with a hyper-graph exploration strategy for automatic retrosynthesis route planning without human intervention.

Retrosynthesis

"Found in Translation": Predicting Outcomes of Complex Organic Chemistry Reactions using Neural Sequence-to-Sequence Models

1 code implementation13 Nov 2017 Philippe Schwaller, Theophile Gaudin, David Lanyi, Costas Bekas, Teodoro Laino

With this approach, we demonstrate results superior to the state-of-the-art solution by a significant margin on the top-1 accuracy.

Translation

Cannot find the paper you are looking for? You can Submit a new open access paper.