Workshop
Sat Jul 24 05:43 AM -- 02:20 PM (PDT)
ICML 2021 Workshop on Computational Biology
The ICML Workshop on Computational Biology will highlight how machine learning approaches can be tailored to making discoveries with biological data. Practitioners at the intersection of computation, machine learning, and biology are in a unique position to frame problems in biomedicine, from drug discovery to vaccination risk scores, and the Workshop will showcase such recent research. Commodity lab techniques lead to the proliferation of large complex datasets, and require new methods to interpret these collections of high-dimensional biological data, such as genetic sequences, cellular features or protein structures, and imaging datasets. These data can be used to make new predictions towards clinical response, to uncover new biology, or to aid in drug discovery.
This workshop aims to bring together interdisciplinary machine learning researchers working at the intersection of machine learning and biology that includes areas such as computational genomics; neuroscience; metabolomics; proteomics; bioinformatics; cheminformatics; pathology; radiology; evolutionary biology; population genomics; phenomics; ecology, cancer biology; causality; representation learning and disentanglement to present recent advances and open questions to the machine learning community.
The workshop is a sequel to the WCB workshops we organized in the last five years at ICML, which had excellent line-ups of talks and were well-received by the community. Every year, we received 60+ submissions. After multiple rounds of rigorous reviewing, around 50 submissions were selected from which the best set of papers were chosen for Contributed talks and Spotlights and the rest were invited for Poster presentations. We have a steadfast and growing base of reviewers making up the Program Committee. For two of the previous editions, a special issue of Journal of Computational Biology has been released with extended versions of a selected set of accepted papers.
| Opening Remarks | |
| Invited talk 1 - Lessons from the Pandemic for Machine Learning and Medical Imaging (Talk) | |
| Invited Talk 1 Q&A (Q&A) | |
| Contributed Talk 1 - Multigrate: single-cell multi-omic data integration (Contributed Talk) | |
| Contributed Talk 1 Q&A (Q&A) | |
| Spotlight Set 1-1 | Statistical correction of input gradients for black box models trained with categorical input features (Spotlight) | |
| Spotlight Set 1-2 | Opportunities and Challenges in Designing Genomic Sequences (Spotlight) | |
| Spotlight Set 1-3 | pmVAE: Learning Interpretable Single-Cell Representations with Pathway Modules (Spotlight) | |
| Spotlight Set 1-5 | Deep Contextual Learners for Protein Networks (Spotlight) | |
| Spotlight Set 1-4 | Multimodal data visualization, denoising and clustering with integrated diffusion (Spotlight) | |
| Break 1 (Break) | |
| Introduction for Session 2 (Introduction) | |
| Invited talk 2 - Anomaly detection to find rare phenotypes (Talk) | |
| Invited Talk 2 Q&A (Q&A) | |
| Contributed Talk 2 - Light Attention Predicts Protein Location from the Language of Life (Contributed Talk) | |
| Contributed Talk 2 Q&A (Q&A) | |
| Highlight 1 | Representation of Features as Images with Neighborhood Dependencies forCompatibility with Convolutional Neural Networks (Paper Highlight) | |
| Highlight 2 | VoroCNN: Deep Convolutional Neural Network Built on 3D Voronoi Tessellation of Protein Structures (Paper Highlight) | |
| Highlight 3 | DIVERSE: Bayesian Data IntegratiVE learning for precise drug ResponSE prediction (Paper Highlight) | |
| Highlight 4 | Spherical Convolutions on Molecular Graphs for Protein Model Quality Assessment (Paper Highlight) | |
| Highlight 5 | Data-driven Experimental Prioritization via Imputation and Submodular Optimization (Paper Highlight) | |
| Highlight 6 | Data Inequality, Machine Learning and Health Disparity (Paper Highlight) | |
| Highlight 7 | Deep neural networks identify sequence context features predictive of transcription factor binding (Paper Highlight) | |
| Poster Session 1 and Break (Poster session and lunch break) | |
| Poster Session 2 and Break (Poster session and lunch break) | |
| Introduction for Session 3 (Introduction) | |
| Invited talk 3 - Every Patient Deserves Their Own Equation (Talk) | |
| Invited Talk 3 Q&A (Q&A) | |
| Contributed Talk 3 - Reconstructing unobserved cellular states from paired single-cell lineage tracing and transcriptomics data (Contributed Talk) | |
| Contributed Talk 3 Q&A (Q&A) | |
| Spotlight Set 2-1 | Equivariant Graph Neural Networks for 3D Macromolecular Structure (Spotlight) | |
| Spotlight Set 2-2 | Viral Evolution and Antibody Escape Mutations using Deep Generative Models (Spotlight) | |
| Spotlight Set 2-3 | Multi-Scale Representation Learning on Proteins (Spotlight) | |
| Spotlight Set 2-4 | Immuno-mimetic Deep Neural Networks (Immuno-Net) (Spotlight) | |
| Spotlight Set 2-5 | Gene expression evolution across species, organs and sexes in Drosophila (Spotlight) | |
| Poster Session 3 and Break (Poster session and break) | |
| Introduction for Session 4 (Introduction) | |
| Invited talk 4 - Learning from evolution (Talk) | |
| Invited Talk 4 Q&A (Q&A) | |
| Contributed Talk 4 - A Bayesian Mutation-Selection Model of Evolutionary Constraints on Coding Sequences (Contributed Talk) | |
| Contributed Talk 4 Q&A (Q&A) | |
| Closing Remarks & Awards Ceremony (Closing Remarks) | |
| Multigrate: single-cell multi-omic data integration (Workshop Poster) | |
| Deconvolution of the T cell immune response using multi-modal learning (Workshop Poster) | |
| Deep Contextual Learners for Protein Networks (Workshop Poster) | |
| Integrating unpaired scRNA-seq and scATAC-seq with unequal cell type compositions (Workshop Poster) | |
| Fingerprint VAE (Workshop Poster) | |
| Viral Evolution and Antibody Escape Mutations using Deep Generative Models (Workshop Poster) | |
| Light Attention Predicts Protein Location from the Language of Life (Workshop Poster) | |
| Data Inequality, Machine Learning and Health Disparity (Workshop Poster) | |
| VEGN: variant effect prediction with graph neural network (Workshop Poster) | |
| pmVAE: Learning Interpretable Single-Cell Representations with Pathway Modules (Workshop Poster) | |
| Opportunities and Challenges in Designing Genomic Sequences (Workshop Poster) | |
| Distance-Enhanced Graph Neural Network for Link Prediction (Workshop Poster) | |
| MultImp: Multiomics Generative Models for Data Imputation (Workshop Poster) | |
| NeuRL: Closed-form Inverse Reinforcement Learning for Neural Decoding (Workshop Poster) | |
| Prediction of RNA-protein Interactions Using a Nucleotide Language Model (Workshop Poster) | |
| Equivariant Graph Neural Networks for 3D Macromolecular Structure (Workshop Poster) | |
| Reference-free cell type annotation and phenotype characterisation in single cell RNA sequencing by learning geneset representations (Workshop Poster) | |
| Graph Representation Learning on Tissue-Specific Multi-Omics (Workshop Poster) | |
| Neural message passing for joint paratope-epitope prediction (Workshop Poster) | |
| Designing Interpretable Convolution-Based Hybrid Networks for Genomics (Workshop Poster) | |
| Reconstructing unobserved cellular states from paired single-cell lineage tracing and transcriptomics data (Workshop Poster) | |
| Gene expression evolution across species, organs and sexes in Drosophila (Workshop Poster) | |
| Effective Surrogate Models for Protein Design with Bayesian Optimization (Workshop Poster) | |
| Exploring the latent space of deep generative models: Applications to G-protein coupled receptors (Workshop Poster) | |
| MultiMAP: Dimensionality Reduction and Integration of Multimodal Data (Workshop Poster) | |
| Towards better understanding of developmental disorders from integration of spatial single-cell transcriptomics and epigenomics (Workshop Poster) | |
| DynaMorph: self-supervised learning of morphodynamic states of live cells (Workshop Poster) | |
| Identifying systematic variation in gene-gene interactions at the single-cell level by leveraging low-resolution population-level data (Workshop Poster) | |
| Graph attribution methods applied to understanding immunogenicity in glycans (Workshop Poster) | |
| Representation of Features as Images with Neighborhood Dependencies forCompatibility with Convolutional Neural Networks (Workshop Poster) | |
| Representation learning of genomic sequence motifs via information maximization (Workshop Poster) | |
| TCR-epitope binding affinity prediction using multi-head self attention model (Workshop Poster) | |
| Multi-target optimization for drug discovery using generative models (Workshop Poster) | |
| Multimodal data visualization, denoising and clustering with integrated diffusion (Workshop Poster) | |
| VoroCNN: Deep Convolutional Neural Network Built on 3D Voronoi Tessellation of Protein Structures (Workshop Poster) | |
| Prot-A-GAN: Automatic Protein Function Annotation using GAN-inspired Knowledge Graph Embedding (Workshop Poster) | |
| APObind: A Dataset of Ligand Unbound Protein Conformations for Machine Learning Applications in De Novo Drug Design (Workshop Poster) | |
| Simultaneous Selection of Multiple Important Single Nucleotide Polymorphisms in Familial Genome Wide Association Studies Data (Workshop Poster) | |
| Deep neural networks identify sequence context features predictive of transcription factor binding (Workshop Poster) | |
| Synthetic COVID-19 Chest X-ray Dataset for Computer-Aided Diagnosis (Workshop Poster) | |
| Data-driven Experimental Prioritization via Imputation and Submodular Optimization (Workshop Poster) | |
| Spherical Convolutions on Molecular Graphs for Protein Model Quality Assessment (Workshop Poster) | |
| Statistical correction of input gradients for black box models trained with categorical input features (Workshop Poster) | |
| Epiphany: Predicting the Hi-C Contact Map from 1D Epigenomic Data (Workshop Poster) | |
| Semi-supervised Deconvolution of Spatial Transcriptomics in Breast Tumors (Workshop Poster) | |
| Improving confident peptide identifications across mass spectrometry runs by learning deep representations of TIMS-MS1 features (Workshop Poster) | |
| Immuno-mimetic Deep Neural Networks (Immuno-Net) (Workshop Poster) | |
| Drug Repurposing using Link Prediction on Knowledge Graphs (Workshop Poster) | |