Machine Learning in Computational Biology: Daily Digest

48 Episodes

Reverse

09.01.2026: Multi-Modal Molecular Design, Semi-Supervised Learning, and Activity Cliff Estimation

2026-01-0908:30

This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 Surface-based Molecular Design with Multi-modal Flow Matching (https://arxiv.org/pdf/2601.04506.pdf) 4:42 A Semi-supervised Molecular Learning Framework for Activity Cliff Estimation (https://arxiv.org/pdf/2601.04507.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

08.01.2026: Knowledge Distillation, Deep Learning for Cancer Subtyping, and Protein Function Reasoning

2026-01-0812:59

This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 Inferring Clinically Relevant Molecular Subtypes of Pancreatic Cancer from Routine Histopathology Using Deep Learning (https://arxiv.org/pdf/2601.03410.pdf) 4:21 Interleaved Tool-Call Reasoning for Protein Function Understanding (https://arxiv.org/pdf/2601.03604.pdf) 8:50 Investigating Knowledge Distillation Through Neural Networks for Protein Binding Affinity Prediction (https://arxiv.org/pdf/2601.03704.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

07.01.2026: Molecular Property Prediction, Learnable DNA Tokenization, and Multi-Scale Graph Autoregressive Modeling

2026-01-0708:34

This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 Multi-scale Graph Autoregressive Modeling: Molecular Property Prediction via Next Token Prediction (https://arxiv.org/pdf/2601.02530.pdf) 4:35 DNACHUNKER: Learnable Tokenization for DNA Language Models (https://arxiv.org/pdf/2601.03019.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

06.01.2026: Equivariant Models, Protein and RNA Structure Prediction, and Large Language Models for Molecular Applications

2026-01-0618:51

This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 Deep Learning Framework for RNA Inverse Folding with Geometric Structure Potentials (https://arxiv.org/pdf/2601.00895.pdf) 4:56 MDAgent2: Large Language Model for Code Generation and Knowledge Q&A in Molecular Dynamics (https://arxiv.org/pdf/2601.02075.pdf) 10:05 Edge-aware GAT-based protein binding site prediction (https://arxiv.org/pdf/2601.02138.pdf) 14:23 Quantized SO(3)-Equivariant Graph Neural Networks for Efficient Molecular Property Prediction (https://arxiv.org/pdf/2601.02213.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

05.01.2026: Uncertainty Quantification, Protein Energy Alignment, and Quantum Simulation in Molecular Modeling

2026-01-0517:34

This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 Rule-Based Approaches to Atomic Sentence Extraction (https://arxiv.org/pdf/2601.00506.pdf) 3:44 Quantifying the uncertainty of molecular dynamics simulations : Good-Turing statistics revisited (https://arxiv.org/pdf/2601.00618.pdf) 8:23 Physio-DPO: Aligning Large Language Models with the Protein Energy Landscape to Eliminate Structural Hallucinations (https://arxiv.org/pdf/2601.00647.pdf) 13:03 Quantum Simulation of Protein Fragment Electronic Structure Using Moment-based Adaptive Variational Quantum Algorithms (https://arxiv.org/pdf/2601.00656.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

30.12.2025: Design Archetypes, Interpretable Machine Learning, and Benchmarking in Molecular and Protein Science

2025-12-3020:03

This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 On the comparison of models and experiments in the study of DNA open states: the problem of degrees of freedom (https://arxiv.org/pdf/2512.22160.pdf) 4:32 LiveProteinBench: A Contamination-Free Benchmark for Assessing Models' Specialized Capabilities in Protein Science (https://arxiv.org/pdf/2512.22257.pdf) 9:51 INSIGHT: Spatially resolved survival modelling from routine histology crosslinked with molecular profiling reveals prognostic epithelial-immune axes in stage II/III colorectal cancer (https://arxiv.org/pdf/2512.22262.pdf) 14:43 Revealing design archetypes and flexibility in e-molecule import pathways using Modeling to Generate Alternatives and interpretable machine learning (https://arxiv.org/pdf/2512.23284.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

29.12.2025: Molecule Generative Models, In Vitro Evaluation, and Hit Generation

2025-12-2905:09

This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 From In Silico to In Vitro: Evaluating Molecule Generative Models for Hit Generation (https://arxiv.org/pdf/2512.22031.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

24.12.2025: Multi-Modal Molecular Elucidation, Agentic Optimization, and Advanced RNA Structure Analysis

2025-12-2424:32

This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 NMIRacle: Multi-modal Generative Molecular Elucidation from IR and NMR Spectra (https://arxiv.org/pdf/2512.19733.pdf) 4:51 Methods for Analyzing RNA Pseudoknots via Chord Diagrams and Intersection Graphs (https://arxiv.org/pdf/2512.19939.pdf) 9:14 MolAct: An Agentic RL Framework for Molecular Editing and Property Optimization (https://arxiv.org/pdf/2512.20135.pdf) 14:26 SynCraft: Guiding Large Language Models to Predict Edit Sequences for Molecular Synthesizability Optimization (https://arxiv.org/pdf/2512.20333.pdf) 19:44 MERGE-RNA: a physics-based model to predict RNA secondary structure ensembles with chemical probing (https://arxiv.org/pdf/2512.20581.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

23.12.2025: Advances in Out-of-Distribution Detection, Substructure-Aware Protein Encoding, and Diffusion Models for Molecular Graphs

2025-12-2304:23

This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 Greater than the Sum of Its Parts: Building Substructure into Protein Encoding Models (https://arxiv.org/pdf/2512.18114.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

22.12.2025: Homology-Clustering, Modular On-Device Pipelines, and Generative Multi-Objective Optimization for Molecular and Protein Design

2025-12-2214:52

This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 Atom: Efficient On-Device Video-Language Pipelines Through Modular Reuse (https://arxiv.org/pdf/2512.17108.pdf) 5:34 SafeBench-Seq: A Homology-Clustered, CPU-Only Baseline for Protein Hazard Screening with Physicochemical/Composition Features and Cluster-Aware Confidence Intervals (https://arxiv.org/pdf/2512.17527.pdf) 10:07 Generative Multi-Objective Bayesian Optimization with Scalable Batch Evaluations for Sample-Efficient De Novo Molecular Design (https://arxiv.org/pdf/2512.17659.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

18.12.2025: Protein Language Models, Cross-Modal Molecular Mapping, and Machine Learning for RNA-Targeting Drug Design

2025-12-1809:56

This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 Multiscale Cross-Modal Mapping of Molecular, Pathologic, and Radiologic Phenotypes in Lipid-Deficient Clear Cell Renal CellCarcinoma (https://arxiv.org/pdf/2512.14750.pdf) 5:00 HD-Prot: A Protein Language Model for Joint Sequence-Structure Modeling with Continuous Structure Tokens (https://arxiv.org/pdf/2512.15133.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

16.12.2025: Molecular Property Prediction, Conditional Generation Strategies, and Multi-Omics Fusion with Graph Networks

2025-12-1614:03

This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 Modeling Dabrafenib Response Using Multi-Omics Modality Fusion and Protein Network Embeddings Based on Graph Convolutional Networks (https://arxiv.org/pdf/2512.12134.pdf) 5:01 MolGuidance: Advanced Guidance Strategies for Conditional Molecular Generation with Flow Matching (https://arxiv.org/pdf/2512.12198.pdf) 9:20 GoMS: Graph of Molecule Substructure Network for Molecule Property Prediction (https://arxiv.org/pdf/2512.12489.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

15.12.2025: Planner-Aligned Actions, 3D Molecular Sculpting, and Sparse Feature Masks for Chemical Language Models

2025-12-1512:22

This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 MolSculpt: Sculpting 3D Molecular Geometries from Chemical Syntax (https://arxiv.org/pdf/2512.10991.pdf) 4:09 Task-Specific Sparse Feature Masks for Molecular Toxicity Prediction with Chemical Language Models (https://arxiv.org/pdf/2512.11412.pdf) 8:02 Atomic Action Slicing: Planner-Aligned Options for Generalist VLA Agents (https://arxiv.org/pdf/2512.11584.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

12.12.2025: Optimal Transport, Autonomous Molecular Dynamics, and Atom-Level Diffusion for Protein Modeling

2025-12-1214:07

This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 DynaMate: An Autonomous Agent for Protein-Ligand Molecular Dynamics Simulations (https://arxiv.org/pdf/2512.10034.pdf) 4:54 UNAAGI: Atom-Level Diffusion for Generating Non-Canonical Amino Acid Substitutions (https://arxiv.org/pdf/2512.10515.pdf) 9:37 Optimal transport unlocks end-to-end learning for single-molecule localization (https://arxiv.org/pdf/2512.10683.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

11.12.2025: Protein Language Models, Molecular Transformers, and Knowledge Graphs for Improved Molecular Discovery

2025-12-1122:06

This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 Self Distillation Fine-Tuning of Protein Language Models Improves Versatility in Protein Design (https://arxiv.org/pdf/2512.09329.pdf) 3:55 KGOT: Unified Knowledge Graph and Optimal Transport Pseudo-Labeling for Molecule-Protein Interaction Prediction (https://arxiv.org/pdf/2512.09365.pdf) 8:46 Toward Closed-loop Molecular Discovery via Language Model, Property Alignment and Strategic Search (https://arxiv.org/pdf/2512.09566.pdf) 13:31 Circuits, Features, and Heuristics in Molecular Transformers (https://arxiv.org/pdf/2512.09757.pdf) 18:07 Exploring Protein Language Model Architecture-Induced Biases for Antibody Comprehension (https://arxiv.org/pdf/2512.09894.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

10.12.2025: Transformer-Based Protein Embeddings, Secondary Structure Prediction, and Deep Learning Advances

2025-12-1004:34

This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 Protein Secondary Structure Prediction Using Transformers (https://arxiv.org/pdf/2512.08613.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

09.12.2025: Advances in Hierarchical Molecular Representations, Diffusion Models, and Self-Supervised Learning for Structural Prediction

2025-12-0923:34

This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 Chemistry Integrated Language Model using Hierarchical Molecular Representation for Polymer Informatics (https://arxiv.org/pdf/2512.06301.pdf) 4:29 Hierarchical geometric deep learning enables scalable analysis of molecular dynamics (https://arxiv.org/pdf/2512.06520.pdf) 9:35 On fine-tuning Boltz-2 for protein-protein affinity prediction (https://arxiv.org/pdf/2512.06592.pdf) 14:33 Multi-Scale Protein Structure Modelling with Geometric Graph U-Nets (https://arxiv.org/pdf/2512.06752.pdf) 18:33 Self-Supervised Learning on Molecular Graphs: A Systematic Investigation of Masking Design (https://arxiv.org/pdf/2512.07064.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

08.12.2025: Efficient Molecular Generation, Equivariant Models, and Improved Protein Function Prediction

2025-12-0827:31

This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 Mitigating the Antigenic Data Bottleneck: Semi-supervised Learning with Protein Language Models for Influenza A Surveillance (https://arxiv.org/pdf/2512.05222.pdf) 4:40 STAR-GO: Improving Protein Function Prediction by Learning to Hierarchically Integrate Ontology-Informed Semantic Embeddings (https://arxiv.org/pdf/2512.05245.pdf) 9:43 DMAGT: Unveiling miRNA-Drug Associations by Integrating SMILES and RNA Sequence Structures through Graph Transformer Models (https://arxiv.org/pdf/2512.05287.pdf) 14:13 Generalization Beyond Benchmarks: Evaluating Learnable Protein-Ligand Scoring Functions on Unseen Targets (https://arxiv.org/pdf/2512.05386.pdf) 18:26 PERM EQ x GRAPH EQ: Equivariant Neural Networks for Quantum Molecular Learning (https://arxiv.org/pdf/2512.05475.pdf) 23:27 NEAT: Neighborhood-Guided, Efficient, Autoregressive Set Transformer for 3D Molecular Generation (https://arxiv.org/pdf/2512.05844.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

05.12.2025: Gene Elimination, Multi-Task Molecular Learning, and Graph-Based Cancer Detection

2025-12-0509:00

This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 RGE-GCN: Recursive Gene Elimination with Graph Convolutional Networks for RNA-seq based Early Cancer Detection (https://arxiv.org/pdf/2512.04333.pdf) 4:27 BioMedGPT-Mol: Multi-task Learning for Molecular Understanding and Generation (https://arxiv.org/pdf/2512.04629.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

04.12.2025: Atomic Diffusion Models, Atom-Level Tokenization, and Structure–Property Associations in Molecular Analysis

2025-12-0404:20

This podcast is brought to you by the Oliver Laboratory at Vanderbilt University. ---------------------------------------- 0:00 Atomic Diffusion Models for Small Molecule Structure Elucidation from NMR Spectra (https://arxiv.org/pdf/2512.03127.pdf) ---------------------------------------- Source code: https://github.com/OliverLaboratory/arxivreader Contact: oliverlaboratory.com Source code: https://github.com/OliverLaboratory/arxivreader

#box-pro-ellipsis-177227735317796{-webkit-line-clamp:2;}Machine Learning in Computational Biology: Daily Digest

Machine Learning in Computational Biology: Daily Digest