Chem-PerturBridge: a harmonized compendium of small molecule perturbation transcriptomic effects

• URL: http://arxiv.org/abs/2605.31522v1
• Date: Fri, 29 May 2026 16:38:30 GMT
• Title: Chem-PerturBridge: a harmonized compendium of small molecule perturbation transcriptomic effects
• Abstract summary: Chem-PerturBridge is a harmonized multi-dataset resource comprising over 37k compounds, 136 cellular contexts, and 1.25M transcriptomic samples.<n>We use the resource to evaluate matched-condition agreement across datasets and replicate agreement within datasets.
• Score: 4.860649440823431
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large perturbation models require training data encompassing chemical, cellular, and assay diversity. Current transcriptomic resources for small-molecule modeling, however, are fragmented across technologies, metadata conventions, controls, doses, and preprocessing pipelines. We introduce Chem-PerturBridge, a harmonized multi-dataset resource comprising over 37k compounds, 136 cellular contexts, and 1.25M transcriptomic samples across eight assay types, with standardized identifiers, metadata, and replicate-aware condition-level effects. We use the resource to evaluate matched-condition agreement across datasets and replicate agreement within datasets. Matched same-compound conditions generally show weak agreement in fine-grained logFC rankings and magnitudes across most dataset pairs, often falling below same-context different-compound baselines. In contrast, logFC direction agreement is substantially more stable and usually exceeds these baselines. We further evaluate Chem-PerturBridge as a pretraining resource for compound representation learning. Under a compound-held-out OP3 evaluation split, embeddings pretrained on Chem-PerturBridge improve over L1000-only embeddings, Morgan fingerprints, and the descriptor-free OP3 baseline across metrics. An extensive molecule-holdout evaluation across 11 datasets further shows that models trained on Chem-PerturBridge outperform or match those that are not. Chem-PerturBridge therefore supports both diagnostic evaluation of cross-dataset signature agreement and model-oriented reuse of heterogeneous perturbation transcriptomic data.

Related papers

• DegradeQuery: Counterfactual Tuple Pretraining for Context-Aware PROTAC Degradation Prediction [18.81893983662407]
  We introduce DegradeQuery, a context-aware prediction framework.<n>It converts label-missing records into a pre-training signal.<n>On the official PROTAC-8K benchmark, DegradeQuery achieves an area under the receiver operating characteristic curve of 0.9065 and an accuracy of 0.8500.
  arXiv  Detail & Related papers  (2026-08-11T07:25:41Z)
• Beyond Predictive Accuracy: A Reliability-Aware Audit of Molecular Representations for Human Olfaction [0.0]
  We present a reliability-aware audit of generic molecular representations for human olfaction across four claims.<n>Human three-attribute rating geometry, based on intensity, pleasantness, and familiarity, is reproducible across participant splits.<n>MoLFormer provides no clear incremental predictive value beyond a combined RDKit-Morgan baseline in either single-molecule dataset.
  arXiv  Detail & Related papers  (2026-07-25T03:38:14Z)
• Generative Augmentation of Raman Spectra for Glioma Classification [0.0]
  We develop a conditional variational autoencoder capable of generating class-conditioned synthetic Raman spectra.<n>The generated data are evaluated in Train-on-Synthetic, Test-on-Real (TS/TR) and Train-on-Synthetic+Real, Test-on-Real (TSR/TR) settings.<n> augmenting the real training data with synthetic spectra consistently improves classification performance across multiple models.
  arXiv  Detail & Related papers  (2026-07-11T08:19:51Z)
• MSAlign: Aligning Molecule and Mass Spectra Foundation Models for Metabolite Identification [11.133897813950789]
  We address the Molecule Retrieval task, which consists in recovering the chemical structure of a metabolite from its MS/MS spectrum given a set of candidate molecules.<n>We propose a unified framework encompassing recent approaches based on representation alignment and contrastive learning.<n>MSAlign is simple to implement, fast to train and consistently outperforms existing approaches across all benchmarks.
  arXiv  Detail & Related papers  (2026-05-19T12:19:35Z)
• A Systematic Survey and Benchmark of Deep Learning for Molecular Property Prediction in the Foundation Model Era [57.5440098776759]
  Molecular property prediction integrates quantum chemistry, cheminformatics, and deep learning to connect molecular structure with biological behavior.<n>This survey traces four complementary paradigms, including Quantum, Descriptor Machine Learning, Geometric Deep Learning, and Foundation Models.<n> Benchmark analyses integrate evidence from both widely used datasets and datasets reflecting industry perspectives.
  arXiv  Detail & Related papers  (2026-04-17T15:16:33Z)
• Learning Continuous Solvent Effects from Transient Flow Data: A Graph Neural Network Benchmark on Catechol Rearrangement [0.0]
  This work introduces the textbfCatechol Benchmark, a high- throughput transient flow chemistry dataset.<n>We evaluate various architectures under rigorous leave-one-solvent-out and leave-one-mixture-out protocols to test generalization to unseen chemical environments.<n>We propose a hybrid GNN-based architecture that integrates Graph Attention Networks (GATs) with Differential Reaction Fingerprints (D RFP) and learned mixture-aware encodings.
  arXiv  Detail & Related papers  (2025-12-22T16:19:01Z)
• Rep3Net: An Approach Exploiting Multimodal Representation for Molecular Bioactivity Prediction [0.8049701904919515]
  In early stage drug discovery, bioactivity prediction of molecules against target proteins plays a crucial role.<n>We propose Rep3Net, a unified deep learning architecture that not only incorporates descriptor data but also includes spatial and relational information.<n>Our model employing multimodald features produce reliable bioactivity prediction on Poly [ADP-ribose] polymerase 1 dataset.
  arXiv  Detail & Related papers  (2025-11-29T15:39:48Z)
• Composable Score-based Graph Diffusion Model for Multi-Conditional Molecular Generation [85.58520120011269]
  We propose Composable Score-based Graph Diffusion model (CSGD), which extends score matching to discrete graphs via concrete scores.<n>We show that CSGD achieves state-of-the-art performance with a 15.3% average improvement in controllability over prior methods.<n>Our findings highlight the practical advantages of score-based modeling for discrete graph generation and its capacity for flexible, multi-property molecular design.
  arXiv  Detail & Related papers  (2025-09-11T13:37:56Z)
• Aligned Manifold Property and Topology Point Clouds for Learning Molecular Properties [55.2480439325792]
  This work introduces AMPTCR, a molecular surface representation that combines local quantum-derived scalar fields and custom topological descriptors within an aligned point cloud format.<n>For molecular weight, results confirm that AMPTCR encodes physically meaningful data, with a validation R2 of 0.87.<n>In the bacterial inhibition task, AMPTCR enables both classification and direct regression of E. coli inhibition values.
  arXiv  Detail & Related papers  (2025-07-22T04:35:50Z)
• Robust Molecular Property Prediction via Densifying Scarce Labeled Data [53.24886143129006]
  In drug discovery, compounds most critical for advancing research often lie beyond the training set.<n>We propose a novel bilevel optimization approach that leverages unlabeled data to interpolate between in-distribution (ID) and out-of-distribution (OOD) data.
  arXiv  Detail & Related papers  (2025-06-13T15:27:40Z)
• Chemical knowledge-informed framework for privacy-aware retrosynthesis learning [72.39098405805318]
  Current machine learning-based retrosynthesis gathers reaction data from multiple sources into one single edge to train prediction models.<n>This paradigm poses considerable privacy risks as it necessitates broad data availability across organizational boundaries.<n>In the present study, we introduce the chemical knowledge-informed framework (CKIF), a privacy-preserving approach for learning retrosynthesis models.
  arXiv  Detail & Related papers  (2025-02-26T13:13:24Z)
• BAPULM: Binding Affinity Prediction using Language Models [7.136205674624813]
  We introduce BAPULM, an innovative sequence-based framework that leverages the chemical latent representations of proteins via ProtT5-XL-U50 and through MolFormer. Our approach was validated extensively on benchmark datasets, achieving sequential scoring power (R) values of 0.925 $pm$ 0.043, 0.914 $pm$ 0.004, and 0.8132 $pm$ 0.001 on benchmark1k2101, Test2016_290, and CSAR-HiQ_36, respectively.
  arXiv  Detail & Related papers  (2024-11-06T04:35:30Z)
• ScholarChemQA: Unveiling the Power of Language Models in Chemical Research Question Answering [54.80411755871931]
  Question Answering (QA) effectively evaluates language models' reasoning and knowledge depth. Chemical QA plays a crucial role in both education and research by effectively translating complex chemical information into readily understandable format. This dataset reflects typical real-world challenges, including an imbalanced data distribution and a substantial amount of unlabeled data that can be potentially useful. We introduce a QAMatch model, specifically designed to effectively answer chemical questions by fully leveraging our collected data.
  arXiv  Detail & Related papers  (2024-07-24T01:46:55Z)
• MoleculeCLA: Rethinking Molecular Benchmark via Computational Ligand-Target Binding Analysis [18.940529282539842]
  We construct a large-scale and precise molecular representation dataset of approximately 140,000 small molecules. Our dataset offers significant physicochemical interpretability to guide model development and design. We believe this dataset will serve as a more accurate and reliable benchmark for molecular representation learning.
  arXiv  Detail & Related papers  (2024-06-13T02:50:23Z)
• A Systematic Approach to Featurization for Cancer Drug Sensitivity Predictions with Deep Learning [49.86828302591469]
  We train >35,000 neural network models, sweeping over common featurization techniques. We found the RNA-seq to be highly redundant and informative even with subsets larger than 128 features.
  arXiv  Detail & Related papers  (2020-04-30T20:42:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.