Machine Learning in Computational Biology: Daily Digest

Carlos Oliver
  • 0.0 (0)
  • LIFE SCIENCES
  • UPDATED DAILY

Daily summaries of preprints in machine learning and computational biology. Source code: https://github.com/OliverLaboratory/arxivreader

Episodes

  1. 1D AGO

    10.11.2025: Peptide Mimic Generation, SE(3) Diffusion Docking, and Target-Aware Graph Augmentation for Molecular Design

    This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 SPECTRA: Spectral Target-Aware Graph Augmentation for Imbalanced Molecular Property Regression (https://arxiv.org/pdf/2511.04838.pdf) 3:49 SigmaDock: Untwisting Molecular Docking With Fragment-Based SE(3) Diffusion (https://arxiv.org/pdf/2511.04854.pdf) 9:03 Peptide2Mol: A Diffusion Model for Generating Small Molecules as Peptide Mimics for Targeted Protein Binding (https://arxiv.org/pdf/2511.04984.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

    14 min

  2. 4D AGO

    07.11.2025: Advances in Protein Function Prediction, Multimodal Learning, and Disease-Related Protein Aggregation

    This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 Enhancing Multimodal Protein Function Prediction Through Dual-Branch Dynamic Selection with Reconstructive Pre-Training (https://arxiv.org/pdf/2511.04040.pdf) 4:16 Protein aggregation in Huntington's disease (https://arxiv.org/pdf/2511.04174.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

    9 min

  3. 6D AGO

    05.11.2025: Scalable Molecular Generation, Latent Variable Transformers, and Advances in RNA Structure Prediction

    This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 Machine Learning for RNA Secondary Structure Prediction: a review of current methods and challenges (https://arxiv.org/pdf/2511.02622.pdf) 5:32 STAR-VAE: Latent Variable Transformers for Scalable and Controllable Molecular Generation (https://arxiv.org/pdf/2511.02769.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

    10 min

  4. NOV 4

    04.11.2025: Deep Learning Capture Phases, Transfer Learning for Molecular Discovery, and Generative Structure Retrieval

    This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 Generative Modeling Enables Molecular Structure Retrieval from Coulomb Explosion Imaging (https://arxiv.org/pdf/2511.00179.pdf) 4:57 Transfer learning discovery of molecular modulators for perovskite solar cells (https://arxiv.org/pdf/2511.00204.pdf) 9:23 STELLAR-koff: A Transfer Learning Model for Protein-Ligand Dissociation Rate Constant Prediction Based on Interaction Landscape (https://arxiv.org/pdf/2511.01171.pdf) 13:58 Identification of Capture Phases in Nanopore Protein Sequencing Data Using a Deep Learning Model (https://arxiv.org/pdf/2511.01277.pdf) 18:22 Split-Flows: Measure Transport and Information Loss Across Molecular Resolutions (https://arxiv.org/pdf/2511.01464.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

    23 min

  5. NOV 3

    03.11.2025: Autoregressive Molecule Generation, Geometry-Aware Protein Modeling, and Ultra-Efficient Biological Information Processing

    This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 Molecular glues stabilize water-mediated hydrogen bonds in ternary complexes (https://arxiv.org/pdf/2510.26806.pdf) 4:34 GeoPep: A geometry-aware masked language model for protein-peptide binding site prediction (https://arxiv.org/pdf/2510.27040.pdf) 8:57 The Demon Hidden Behind Life's Ultra-Energy-Efficient Information Processing -- Demonstrated by Biological Molecular Motors (https://arxiv.org/pdf/2510.27212.pdf) 12:50 InertialAR: Autoregressive 3D Molecule Generation with Inertial Frames (https://arxiv.org/pdf/2510.27497.pdf) 17:17 MolChord: Structure-Sequence Alignment for Protein-Guided Drug Design (https://arxiv.org/pdf/2510.27671.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

    22 min

  6. OCT 31

    31.10.2025: Substructure-aware Alignment, Image Denoising, and Interpretable Biological Concepts in Molecular and Genomic Models

    This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 Discovering Interpretable Biological Concepts in Single-cell RNA-seq Foundation Models (https://arxiv.org/pdf/2510.25807.pdf) 4:13 Enabling Fast and Accurate Neutral Atom Readout through Image Denoising (https://arxiv.org/pdf/2510.25982.pdf) 9:05 Bridging the Gap Between Molecule and Textual Descriptions via Substructure-aware Alignment (https://arxiv.org/pdf/2510.26157.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

    13 min

  7. OCT 30

    30.10.2025: Sample Efficiency, Rectified Flows, and Protein Design in Molecular Generation

    This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 Re-evaluating sample efficiency in de novo molecule generation (https://arxiv.org/pdf/2212.01385.pdf) 4:41 Flows, straight but not so fast: Exploring the design space of Rectified Flows in Protein Design (https://arxiv.org/pdf/2510.24732.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

    9 min

  8. OCT 29

    29.10.2025: Atom Placement,Foundation Model, Protein Optimization,Activity Optimization, Sequence Sampling,Protein Design, Structure Fusion,Molecular Representation, Test-Time Tuning,Molecular Generation

    This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 Structure-Aware Fusion with Progressive Injection for Multimodal Molecular Representation Learning (https://arxiv.org/pdf/2510.23640.pdf) 4:28 Test-Time Tuned Language Models Enable End-to-end De Novo Molecular Structure Generation from MS/MS Spectra (https://arxiv.org/pdf/2510.23746.pdf) 8:26 Relaxed Sequence Sampling for Diverse Protein Design (https://arxiv.org/pdf/2510.23786.pdf) 13:05 Low-N Protein Activity Optimization with FolDE (https://arxiv.org/pdf/2510.24053.pdf) 17:40 Pearl: A Foundation Model for Placing Every Atom in the Right Location (https://arxiv.org/pdf/2510.24670.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

    22 min

  9. OCT 28

    28.10.2025: Graph Featurisation,Ensemble Models, Multi-Modal,Protein Representation, Anisotropic Noise,Force Field Modeling, Protein Embeddings,Database, Quantum Phase,Classification, Knowledge Graphs,LLMs, Algebra Prediction,Binding Affinities

    This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 A Multimodal Human Protein Embeddings Database: DeepDrug Protein Embeddings Bank (DPEB) (https://arxiv.org/pdf/2510.22008.pdf) 4:47 Learning 3D Anisotropic Noise Distributions Improves Molecular Force Field Modeling (https://arxiv.org/pdf/2510.22123.pdf) 9:44 CAP: Commutative Algebra Prediction of Protein-Nucleic Acid Binding Affinities (https://arxiv.org/pdf/2510.22130.pdf) 14:20 ATOM: AdapTive and OptiMized dynamic temporal knowledge graph construction using LLMs (https://arxiv.org/pdf/2510.22590.pdf) 19:21 A Novel Framework for Multi-Modal Protein Representation Learning (https://arxiv.org/pdf/2510.23273.pdf) 23:42 Improving Predictions of Molecular Properties with Graph Featurisation and Heterogeneous Ensemble Models (https://arxiv.org/pdf/2510.23428.pdf) 28:14 Quantum Phase Classification of Rydberg Atom Systems Using Resource-Efficient Variational Quantum Circuits and Classical Shadows (https://arxiv.org/pdf/2510.23489.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

    33 min

  10. OCT 27

    27.10.2025: 2025-10-27 Advances in Machine Learning for Molecular and Biomolecular Design

    This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 Meta-Learning for Cross-Task Generalization in Protein Mutation Property Prediction (https://arxiv.org/pdf/2510.20943.pdf) 4:55 M-GLC: Motif-Driven Global-Local Context Graphs for Few-shot Molecular Property Prediction (https://arxiv.org/pdf/2510.21088.pdf) 8:39 Uncertainty-Aware Multi-Objective Reinforcement Learning-Guided Diffusion Models for 3D De Novo Molecular Design (https://arxiv.org/pdf/2510.21153.pdf) 13:37 RiboPO: Preference Optimization for Structure- and Stability-Aware RNA Design (https://arxiv.org/pdf/2510.21161.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

    18 min

  11. OCT 22

    22.10.2025: 2025-10-22 Advances in Molecular Data Analysis and Generative Neural Methods

    This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 Speak to a Protein: An Interactive Multimodal Co-Scientist for Protein Analysis (https://arxiv.org/pdf/2510.17826.pdf) 5:17 Atomic Literary Styling: Mechanistic Manipulation of Prose Generation in Neural Language Models (https://arxiv.org/pdf/2510.17909.pdf) 9:50 HyperDiffusionFields (HyDiF): Diffusion-Guided Hypernetworks for Learning Implicit Molecular Neural Fields (https://arxiv.org/pdf/2510.18122.pdf) 14:20 Protein generation with embedding learning for motif diversification (https://arxiv.org/pdf/2510.18790.pdf) 19:06 SO(3)-invariant PCA with application to molecular data (https://arxiv.org/pdf/2510.18827.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

    23 min

  12. OCT 21

    21.10.2025: 2025-10-21 Advances in Machine Learning for Molecular and Structural Biology

    This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 Interpretable RNA-Seq Clustering with an LLM-Based Agentic Evidence-Grounded Framework (https://arxiv.org/pdf/2510.16082.pdf) 5:02 AtomBench: A Benchmark for Generative Atomic Structure Models using GPT, Diffusion, and Flow Architectures (https://arxiv.org/pdf/2510.16165.pdf) 9:17 Protein Folding with Neural Ordinary Differential Equations (https://arxiv.org/pdf/2510.16253.pdf) 14:03 Parameter Identifiability of RNA Dynamics in PDE Transport Models of Fluorescence Recovery After Photobleaching (https://arxiv.org/pdf/2510.16304.pdf) 18:10 CryoDyna: Multiscale end-to-end modeling of cryo-EM macromolecule dynamics with physics-aware neural network (https://arxiv.org/pdf/2510.16510.pdf) 23:23 Atom-anchored LLMs speak Chemistry: A Retrosynthesis Demonstration (https://arxiv.org/pdf/2510.16590.pdf) 27:57 Evaluating protein binding interfaces with PUMBA (https://arxiv.org/pdf/2510.16674.pdf) 32:26 3D-GSRD: 3D Molecular Graph Auto-Encoder with Selective Re-mask Decoding (https://arxiv.org/pdf/2510.16780.pdf) 37:09 ProtoMol: Enhancing Molecular Property Prediction via Prototype-Guided Multimodal Learning (https://arxiv.org/pdf/2510.16824.pdf) 41:22 DeepChem Equivariant: SE(3)-Equivariant Support in an Open-Source Molecular Machine Learning Library (https://arxiv.org/pdf/2510.16897.pdf) 45:24 The Atomic Instruction Gap: Instruction-Tuned LLMs Struggle with Simple, Self-Contained Directives (https://arxiv.org/pdf/2510.17388.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

    50 min
  • 12 Episodes

About

Daily summaries of preprints in machine learning and computational biology. Source code: https://github.com/OliverLaboratory/arxivreader

Information