Weekly BioML Digest [October 20, 2025]

Machine Learning × Computational Biology compilation from arXiv + bioRxiv

Hey! It's your weekly digest of machine learning papers in CompBio and Drug Discovery. Here is how it was created:

• Both arXiv and bioRxiv queried for new papers published in the past week [October 13, 2025 - October 19, 2025].
• Found 4873 new arXiv papers and 1513 new bioRxiv papers.
• 20 arXiv papers and 108 bioRxiv papers matched keyword filters.
• 30 papers are included in this digest after deduplication and ChatGPT relevance+novelty reranking.

These are your top 30 papers:

🧬 = bioRxiv paper | 📄 = arXiv paper

• 🧬 Odyssey: reconstructing evolution through emergent consensus in the global proteome
  Singhal, A.; Venkatasubramanian, S.; Moushegian, S.; Strutt, S.; Lin, M.; Lee, C. — bioRxiv:synthetic biology, 2025-10-15
  abs · pdf

• 🧬 All-atom protein design via SE(3) flow matching with ProteinZen
  Li, A. J.; Kortemme, T. — bioRxiv:bioengineering, 2025-10-18
  abs · pdf

• 🧬 Constrained Diffusion for Protein Design with Hard Structural Constraints
  Christopher, J. K.; Seamann, A.; Cui, J.; Khare, S.; Fioretto, F. — bioRxiv:molecular biology, 2025-10-15
  abs · pdf

• 🧬 GhostFold: Accurate protein structure prediction using structure-constrained synthetic coevolutionary signals
  Mishra, N.; Briney, B. — bioRxiv:bioinformatics, 2025-10-14
  abs · pdf

• 🧬 FKSFold: Improving AlphaFold3-Type Predictions of Molecular Glue-Induced Ternary Complexes with Feynman-Kac-Steered Diffusion
  Shen, J.; Zhou, S.; Che, X. — bioRxiv:biophysics, 2025-10-14
  abs · pdf

• 🧬 ConforFold Recovers Alternative Protein Conformations Beyond MSA Subsampling
  Syrlybaeva, R.; Strauch, E.-M. — bioRxiv:biochemistry, 2025-10-14
  abs · pdf

• 🧬 SLOGEN: A Structure-based Lead Optimization Model Unifying Fragment Generation and Screening
  Yang, B.; Xu, Y.; Xiang, C.; Zhu, Y.; Li, T.; Sinitskiy, A.; Li, J. — bioRxiv:bioinformatics, 2025-10-15
  abs · pdf

• 📄 Matcha: Multi-Stage Riemannian Flow Matching for Accurate and Physically Valid Molecular Docking
  Daria Frolova, Talgat Daulbaev, Egor Sevryugov, Sergei A. Nikolenko, Dmitry N. Ivankov, Ivan Oseledets, Marina A. Pak — cs.LG, 2025-10-16
  abs · pdf

• 🧬 A Genomic Language Model for Zero-Shot Prediction of PromoterVariant Effects
  Shearer, C.; Orenbuch, R.; Teufel, F.; Ritter, D.; Steinmetz, C. J.; Xie, E.; Gazizov, A.; Spinner, A.; Frazer, J.; Dias, M.; Notin, P.; Marks, D. — bioRxiv:genomics, 2025-10-14
  abs · pdf

• 🧬 Protein-protein interaction priors shape biologically coherent latent spaces for causally concordant cross-omic translation
  Martinez-Enguita, D.; Hillerton, T.; Akesson, J.; Jörnsten, R.; Gustafsson, M. — bioRxiv:bioinformatics, 2025-10-14
  abs · pdf

• 🧬 Advancing Protein Ensemble Predictions Across the Order-Disorder Continuum
  Invernizzi, M.; Bottaro, S.; Streit, J. O.; Trentini, B.; Venanzi, N. A.; Reidenbach, D.; Lee, Y.; Lindorff-Larsen, K.; Jing, B.; Airoldi, F.; Sirelkhatim, H.; Dallago, C.; Fisicaro, C.; Tamiola, K. — bioRxiv:biophysics, 2025-10-18
  abs · pdf

• 🧬 AbTune: Layer-wise selective fine-tuning of protein language models for antibodies
  Xu, X.; Bonvin, A. M. J. J. — bioRxiv:bioinformatics, 2025-10-17
  abs · pdf

• 🧬 peleke-1: A Suite of Protein Language Models Fine-Tuned for Targeted Antibody Sequence Generation
  Santolla, N.; Pridgen, T.; Nigam, P.; Ford, C. T. — bioRxiv:immunology, 2025-10-16
  abs · pdf

• 🧬 Decoding protein-membrane binding interfaces from surface-fingerprint-based geometric deep learning and molecular dynamics simulations
  Park, B.; Van Lehn, R. C. — bioRxiv:bioinformatics, 2025-10-15
  abs · pdf

• 🧬 Fine-Tuning Protein Language Models on Human Spatial Constraint Yields State-of-the-Art Variant Effect Prediction
  Bajracharya, G.; Capra, J. A. — bioRxiv:genetics, 2025-10-16
  abs · pdf

• 🧬 Designing molecular RNA switches with Restricted Boltzmann machines
  FERNANDEZ-DE-COSSIO-DIAZ, J.; Hardouin, P.; Lyonnet du Moutier, F.-X.; Di Gioacchino, A.; Marchand, B.; Ponty, Y.; Sargueil, B.; Monasson, R.; Cocco, S. — bioRxiv:bioinformatics, 2025-10-19
  abs · pdf

• 📄 Coder as Editor: Code-driven Interpretable Molecular Optimization
  Wenyu Zhu, Chengzhu Li, Xiaohe Tian, Yifan Wang, Yinjun Jia, Jianhui Wang, Bowen Gao, Ya-Qin Zhang, Wei-Ying Ma, Yanyan Lan — cs.LG, 2025-10-16
  abs · pdf

• 📄 MoRA: On-the-fly Molecule-aware Low-Rank Adaptation Framework for LLM-based Multi-Modal Molecular Assistant
  Tao Yin, Xiaohong Zhang, Jiacheng Zhang, Li Huang, Zhibin Zhang, Yuansong Zeng, Jin Xie, Meng Yan — cs.LG, 2025-10-14
  abs · pdf

• 🧬 Phenotypic AI-based design of cell-specific small molecule cytotoxics
  Rojas-Granado, G.; Sanchez-Soto, M.; Calahorra, J.; Caballero, M.; Ramos, I.; Bertoni, M.; Aloy, P. — bioRxiv:bioinformatics, 2025-10-15
  abs · pdf

• 🧬 Integrative machine learning predicts activating kinase mutations for precision oncology
  Wang, Y.; Wan, F.; Chen, Z.; Nukpexzah, J.; Pan, I. T.; Stebe, K. J.; de la Fuente-Nunez, C.; Radhakrishnan, R. — bioRxiv:cancer biology, 2025-10-15
  abs · pdf

• 🧬 Protein large language model assisted one-to-one gene homology mapping in cross-species single-cell transcriptome integration
  Kuang, Z.-Y.; Sun, Y.-C.; Wei, N.-N.; Wu, H.-J. — bioRxiv:bioinformatics, 2025-10-18
  abs · pdf

• 🧬 Spatially varying cell-specific gene regulation network inference
  Li, Y.; Chen, J.; Wang, H. — bioRxiv:bioinformatics, 2025-10-19
  abs · pdf

• 🧬 Robust footprinting with sample-specific Tn5 bias correction for bulk and single cell ATAC-seq
  Lin, Y.; Wang, H.; WIlson, P.; Zhang, N. — bioRxiv:genomics, 2025-10-18
  abs · pdf

• 📄 Biology-informed neural networks learn nonlinear representations from omics data to improve genomic prediction and interpretability
  Katiana Kontolati, Rini Jasmine Gladstone, Ian Davis, Ethan Pickering — cs.LG, 2025-10-16
  abs · pdf

• 🧬 Robust prediction of drug combination side effects in realistic settings
  Jimenez, R.; Paccanaro, A. — bioRxiv:bioinformatics, 2025-10-16
  abs · pdf

• 🧬 DeepVul: A Multi-Task Transformer Model for Joint Prediction of Gene Essentiality and Drug Response
  Jararweh, A.; Bach, M. N.; Arredondo, D.; Macaulay, O.; Dicome, M.; Tafoya, L.; Hu, Y.; Virupakshappa, K.; Boland, G.; Flaherty, K.; Sahu, A. — bioRxiv:bioinformatics, 2025-10-15
  abs · pdf

• 🧬 Multiple instance learning with spatial transcriptomics for interpretable patient-level predictions: application in glioblastoma
  Grouard, S.; Esposito, C.; El Khoury, J.; Ducret, V.; Thiriez, C.; Herpin, L.; Chossegros, A.; Hoffmann, C.; Bayard, Q.; Robin, G.; Tay, N.; Baena, E.; MOSAIC consortium, ; Durand, E. Y.; Espin Perez, A.; Fidon, L. — bioRxiv:cancer biology, 2025-10-15
  abs · pdf

• 🧬 Structured Chemical Reaction Modeling with Multitask Graph Neural Networks
  Astero, M.; Li, A.; Casiraghi, E.; Rousu, J. — bioRxiv:bioinformatics, 2025-10-14
  abs · pdf

• 📄 Inferred global dense residue transition graphs from primary structure sequences enable protein interaction prediction via directed graph convolutional neural networks
  Islam Akef Ebeid, Haoteng Tang, Pengfei Gu — cs.LG, 2025-10-15
  abs · pdf

• 🧬 Learning the Language of Phylogeny with MSA Transformer
  Chen, R.; Foley, G.; Boden, M. — bioRxiv:bioinformatics, 2025-10-14
  abs · pdf