MIA: Wouter Boomsma & Jes Frellsen, Convolutional models of molecular structure
May 23, 2018
MIA Meeting: https://www.youtube.com/watch?v=-UKL3kOlOds&list=PLlMMtlgw6qNjROoMNTBQjAcdx53kV50cS&index=43m15s
Wouter Boomsma and Jes Frellsen
Departments of Computer Science
University of Copenhagen and IT University of Copenhagen
Convolutional models of molecular structure
Abstract: Although originally devised in the field of image analysis, convolutional neural networks (CNNs) are increasingly finding applications outside the image domain. In particular, a number of studies over the last year have made a convincing case for the use of CNNs within the field of molecular modelling. As an example of these recent developments, we will present our work on using convolutions to predict mutation-induced changes-of-stability (ddgs) in proteins. We will demonstrate how a simple convolutional model using a purely data-driven approach achieves performance comparable to that of state-of-the-art methods in the field. Finally, we will discuss current theoretical developments in the area of convolutions, including the quest for rotational equivariance.
Primer: Learning from molecular structure
Abstract: Purely data-driven modelling techniques have had a fundamental impact on the analysis of biological sequences. In particular, neural networks have been used extensively, with successful applications in for instance the prediction of secondary structure, aggregation propensities, and disorder. In contrast, the 3D structure of molecules has been modelled almost exclusively with carefully parameterised physical force fields, which are notoriously difficult to optimise from data. Recent developments in Machine Learning are changing this picture, making it possible to learn structure-sequence relationships directly from raw molecular structures. In this primer, we will briefly review these developments, and introduce the concept of convolutional neural networks, which form the basis for many of the current activities, including the work we will present as our main talk.
For more information on the Broad Institute and MIA visit: http://www.broadinstitute.org/MIA
Copyright Broad Institute, 2018. All rights reserved.
Видео MIA: Wouter Boomsma & Jes Frellsen, Convolutional models of molecular structure канала Broad Institute
MIA Meeting: https://www.youtube.com/watch?v=-UKL3kOlOds&list=PLlMMtlgw6qNjROoMNTBQjAcdx53kV50cS&index=43m15s
Wouter Boomsma and Jes Frellsen
Departments of Computer Science
University of Copenhagen and IT University of Copenhagen
Convolutional models of molecular structure
Abstract: Although originally devised in the field of image analysis, convolutional neural networks (CNNs) are increasingly finding applications outside the image domain. In particular, a number of studies over the last year have made a convincing case for the use of CNNs within the field of molecular modelling. As an example of these recent developments, we will present our work on using convolutions to predict mutation-induced changes-of-stability (ddgs) in proteins. We will demonstrate how a simple convolutional model using a purely data-driven approach achieves performance comparable to that of state-of-the-art methods in the field. Finally, we will discuss current theoretical developments in the area of convolutions, including the quest for rotational equivariance.
Primer: Learning from molecular structure
Abstract: Purely data-driven modelling techniques have had a fundamental impact on the analysis of biological sequences. In particular, neural networks have been used extensively, with successful applications in for instance the prediction of secondary structure, aggregation propensities, and disorder. In contrast, the 3D structure of molecules has been modelled almost exclusively with carefully parameterised physical force fields, which are notoriously difficult to optimise from data. Recent developments in Machine Learning are changing this picture, making it possible to learn structure-sequence relationships directly from raw molecular structures. In this primer, we will briefly review these developments, and introduce the concept of convolutional neural networks, which form the basis for many of the current activities, including the work we will present as our main talk.
For more information on the Broad Institute and MIA visit: http://www.broadinstitute.org/MIA
Copyright Broad Institute, 2018. All rights reserved.
Видео MIA: Wouter Boomsma & Jes Frellsen, Convolutional models of molecular structure канала Broad Institute
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Screening Applications - Julia JoungBroad Discovery Series: Moving from "hit-or-miss" toward a brighter future for psychiatric careMPG Primer: Challenges and opportunities for developing more generalizable polygenic risk scoresMPG Primer: Harmonization of deeply sequenced genomes (2023)Broad Fellow: Ahmed BadranMIA: Travis Gibson, The dysbiotic microbiome as a dynamical system; Younhun Kim, Dirichlet processesThe Drug Repurposing Hub at the Broad InstituteBroad Institute: Genomics platform surpasses 10 Million COVID-19 testsMIA: Bo Xia, In silico screening for genome structure; Ruochi Zhang, graph representation learningMPG Primer: Chronos: a dynamic model for CRISPR data (2022)Broad Institute Artist-In-Residence - Lucy Kim3. How to link genetic constraint score from gene of interest to protein structure using G2P PortalElinor Karlsson on the genetics of unusual traitsBroad Discovery Series: Biomedical science and machine learning: A two-way street (2023)Broad Institute: The Rare Cancer Dependency MapMPG Primer: Sparse dictionary learning recovers pleiotropy from human cell fitness screens (2022)Field Work - Kevin EsveltEWSC: Machine Learning about Sudden Cardiac Death from ECG Waveforms, Ziad ObermeyerMPG Primer: The Lipid Droplet Knowledge Portal (2022)MPG Primer: Detecting & tracking contamination in SARS-CoV-2 sequencing w/spike-in controls (2022)Broad Institute Artist-In-Residence - Naoe Suzuki