arXiv Machine Learning September 29, 2026 By Jie Li, Kathryn E. Kirchoff, Dante A. Pertusi, Zhizhuo Zhang

Improving Molecular-Morphology Contrastive Pretraining using Deep-Learning-based Morphology Profiles

Read the original on arXiv Machine Learning →

The paper presents MoCoP v2, an enhanced contrastive pretraining method that aligns small molecule embeddings with deep‑learning‑derived cell morphology profiles. By replacing CellProfiler fingerprints with richer image‑encoded features, the new embeddings better capture how molecules alter cell morphology, leading to improved QSAR, toxicity, ADME, and activity predictions. Performance scales log‑linearly with training data size, indicating further gains with larger datasets.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Aug 18

Deep Learning for BioImaging: What Are We Really Learning?

arXiv:2603. 13377v2 Announce Type: replace-cross Abstract: Representation learning has driven major advances in natural image analysis by enabling models to acquire high-level semantic features.

By Ivan Svatko, Maxime Sanchez, Ihab Bendidi, Gilles Cottrell, Auguste Genovesio

benchmarks

arXiv Machine Learning

Aug 17

Conditional Neural Optimal Transport for Predicting Cellular Phenotypes from Molecular Structure

arXiv:2608. 14293v1 Announce Type: cross Abstract: High-content microscopy enables systematic profiling of cellular responses to chemical perturbations, but the scale of the chemical space makes exhaustive phenotypic characterization experimentally infeasible.

By Gauthier Avit\'e, Maxime Sanchez-Renauld, Nicolas Bourriez, Auguste Genovesio

arXiv Computer Vision

Sep 1

JUMP-lite: Compact, reproducible benchmarking of cell representations

arXiv:2608.07632v2 Announce Type: replace-cross Abstract: Image-based profiling captures rich phenotypic signatures for drug discovery and functional genomics. Large public datasets like JUMP Cell Pa...

By Al\'an F. Mu\~noz, Johan Fredin Haslum, Runxi Shen, Anne E. Carpenter, Shantanu Singh

benchmarks

arXiv Machine Learning

Jun 9

Advancing Ligand-based Virtual Screening and Molecular Generation with Pretrained Molecular Embedding Distance

arXiv:2604. 24474v2 Announce Type: replace Abstract: Molecular similarity plays a central role in ligand-based drug discovery, such as virtual screening, analog searching, and goal-directed molecular generation.

By Shiyun Wa, Yifei Wang, Simone Sciabola, Ye Wang

rag

arXiv Computer Vision

Sep 4

Using Deep Learning Models Pretrained by Self-Supervised Learning for Protein Localization

The study evaluates self‑supervised learning (SSL) models pretrained on ImageNet‑1k and the Human Protein Atlas (HPA) Field‑of‑View (FOV) for protein localization in microscopy images. DINO‑based Vision Transformer backbones pretrained on either dataset transfer well to the OpenCell dataset, achieving strong performance even without fine‑tuning and improving further when fine‑tuned (0.704 ± 0.027 macro F1 on 17 classes). At the single‑cell level, the HPA‑pretrained model outperforms others in k‑nearest‑neighbor classification across all neighborhood sizes (macro F1 ≥ 0.515).

By Ben Isselmann, Dilara G\"oksu, Heinz Neumann, Andreas Weinmann

rag fine-tuning

arXiv AI

Aug 5

Learning Molecular Representations from Cellular Phenotypes with Structure Preservation

arXiv:2608. 02688v1 Announce Type: cross Abstract: Phenotypic drug discovery enables the discovery of functional relationships between molecular structures and cellular responses.

By Xuan Lin, Jingyu Sheng, Tengfei Ma, Li Sun, Dapeng Xiong

rag multimodal safety

One email a morning, machine-written

Related stories

Deep Learning for BioImaging: What Are We Really Learning?

Conditional Neural Optimal Transport for Predicting Cellular Phenotypes from Molecular Structure

JUMP-lite: Compact, reproducible benchmarking of cell representations

Advancing Ligand-based Virtual Screening and Molecular Generation with Pretrained Molecular Embedding Distance

Using Deep Learning Models Pretrained by Self-Supervised Learning for Protein Localization

Learning Molecular Representations from Cellular Phenotypes with Structure Preservation