Papers for

biotech companies

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Pathology models predict gene activity patterns from tissue images

Predicting Single-Cell Spatial Gene Expression from H&E using Pathology Foundation Models

Abstract: Predicting gene expression directly from hematoxylin and eosin (H&E) images offers a scalable and cost-effective approach to deriving spatial molecular insights from routine histology. Pathology foundation models, typically pretrained using tile-level objectives, may not adequately capture the fine-grained cellular features required for single-cell molecular prediction. In this work, we systematically evaluate and establish domain-informed and task-specific strategies for adapting pathology foundation models to single-cell spatial gene expression prediction. Using paired H&E and Xenium 5K data, our approach improves mean gene-wise Pearson correlation by 2.67x over the standard zero-shot baseline and achieves state-of-the-art performance on this task. We demonstrate strong gene-detection performance across the full gene panel (AUROC = 0.800) and importantly identify that predictive performance varies substantially across biological contexts, with our model achieving its highest Pearson correlation for spatially variable genes (r = 0.643). Our findings demonstrate that, despite the challenges of sparse single-cell measurements, H&E-derived representations can recover biologically meaningful spatial expression patterns, highlighting both the opportunities and limitations of morphology-based molecular inference at cellular resolution.

Tue 10 NovComputer Vision and Pattern Recognition
The gist
Predicting gene activity in individual cells usually requires costly and complex tests. This paper shows that computer models can estimate gene expression from standard microscope images of tissue stained with common dyes. The authors improved existing models so they better capture detailed cell features, achieving stronger correlation with actual gene data. Their method works best for genes that vary a lot in space, revealing how tissue appearance relates to molecular activity.
Open → 2611.13649v1

Attention U-Net improves nucleus segmentation in pathology images

Automated Nucleus Segmentation in Histology Images: An Attention U-Net Approach with Comprehensive Preprocessing and Inference Pipelines

Abstract: Objectives: In the area of digital pathology, nucleus segmentation is an essential step for quantitative analysis; however, high nuclear density and staining heterogeneity in histology images pose a great challenge. Methods: This study implements a lightweight Attention U-Net model on the MoNuSeg 2018 dataset to overcome these challenges. The proposed pipeline integrates comprehensive image and mask preprocessing, including stain deconvolution and multi-pass mask smoothing, with a high-fidelity overlapping patch-stitching strategy during inference on high-resolution images. Results: The model achieved an Intersection over Union (IoU) score of 0.8745 on full-resolution, unseen test images. This result demonstrates the effectiveness of attention mechanisms in enhancing feature localization and validates the stitching methodology for generating seamless and accurate segmentation maps. Conclusion: Attention U-Net is an effective and competitive method for automated, scalable nucleus delineation in challenging clinical contexts.

Thu 22 OctComputer Vision and Pattern Recognition
The gist
Identifying cell nuclei in microscope images of tissue is important for medical analysis but can be difficult because cells are crowded and look different due to staining. The authors built a computer program using a special type of neural network called Attention U-Net, which helps detect nuclei more accurately by focusing on important image features. They also include careful image processing steps and a method to combine small image patches into a full picture. Their method achieved a high score on a public test set, showing it can segment nuclei reliably.
Open → 2610.31902v1

ImmuneAgent AI system speeds antibody discovery across viruses

Multimodal reasoning for broadly neutralizing antibody discovery from label-free human B cell repertoires across virus families

Abstract: Discovering broadly neutralizing antibodies (bnAbs) from human natural immune repertoires remains a fundamental challenge in immunology, hindered by: the extreme rarity of bnAb, incomplete understanding of their cellular origins across pathogens, and the inability of existing computational tools to generalize across emerging viral threats. Here we present ImmuneAgent, a closed-loop AI system that integrates multimodal reasoning with continual meta-learning and wet-lab feedback to overcome these barriers. Applied to screen the natural BCR repertoires from vaccinated or infected cohorts, the system achieves a ~55% neutralization antibody discovery rate (60 of 110 cloned candidates) and a ~11% bnAb yield (12 of 110), substantially outperforming a state-of-the-art sequence-based neutralization predictor or cofolding models evaluated at the same cloning budget. Five ImmuneAgent-discovered antibodies conferred 100% in vivo protection against lethal influenza challenge, comparable to the clinical-stage therapeutic MEDI8852. The system recovered the cellular and structural determinants of bnAb activity and identified FCRL5+CD27+ atypical memory B cells as a conserved bnAb reservoir and hydrophobic interface enrichment as a cross-viral structural signature, which generalized to unseen antigens, discovering human metapneumovirus (hMPV) cross-neutralizing and human papillomavirus (HPV)-neutralizing antibodies without antigen-specific sorting. These results validate that ImmuneAgent is a generalizable framework for rapid therapeutic antibody discovery against emerging viral threats.

Fri 2 OctArtificial IntelligenceComputational Engineering, Finance, and Science
The gist
Finding rare antibodies that can fight many viruses is very hard because they are so rare and hard to identify. The authors created ImmuneAgent, an AI system that learns continuously and uses lab feedback to find these rare antibodies in human immune cells. It found many effective antibodies, some protecting mice from deadly flu, and even worked on viruses it hadn’t seen before. This system could help quickly find new treatments for emerging viral infections.
Open → 2610.03160v1

Simple methods improve gene expression prediction from H&E images

Is H&E Image-to-Spatial Transcriptomics Simpler Than It Looks?

Abstract: Predicting spatial gene expression from routine H&E histology offers a scalable route toward spatial molecular profiling. Recent work has pursued increasingly sophisticated architectures to capture spatial context and richer expression structure. At the same time, simple estimators have shown strong performance in several studies, but what they already solve and where additional complexity is needed remain unclear. We study this behavior through the structure of prediction error under the mean-squared error (MSE) objective. Differences in average expression across genes can account for a substantial part of aggregate prediction performance, while a key unresolved error lies in recovering variation within each slide. Decomposing MSE into slide-level and within-slide components, we find that the within-slide component has lower residual-normalized parameter sensitivity in controlled neural experiments. This motivates Component-Guided Loss (CGL), which increases supervision of the within-slide component. CGL-Linear is a closed-form affine instantiation that achieves overall state-of-the-art performance across HEST-1k cohorts and gene-panel sizes. The same within-slide supervision improves existing neural models. These results suggest that substantial gains can come from aligning the training objective with prediction-error structure rather than increasing model complexity.

Sat 26 SeptComputer Vision and Pattern RecognitionMachine Learning
The gist
Predicting gene activity in tissue samples usually requires complex AI models, but the authors found that simpler methods can perform just as well by focusing on specific errors within each sample. They show that understanding the types of mistakes made during prediction leads to better training methods. This means that models can be improved not by being more complicated but by using better ways to learn from the data.
Open → 2609.32857v1

GyroNovo improves peptide sequencing by focusing on key missing fragments

GyroNovo: Error-Guided Fragment Imputation with Mass-Aware Attention for \textit{De Novo} Peptide Sequencing

Abstract: De novo peptide sequencing from tandem mass spectra is essential for identifying peptides without relying on reference databases. Despite advances in deep learning, accurate sequencing remains challenging because experimental spectra are often sparse, noisy, and incomplete, leaving informative b- and y-ion fragments unobserved. Existing methods attempt to recover this missing evidence via latent-space imputation before autoregressive decoding. However, they typically treat imputation as a fixed reconstruction task, without considering which missing fragments are most relevant to decoder errors. Moreover, existing peak representations do not explicitly model mass differences between peaks, despite their fundamental importance. We introduce GyroNovo, a framework with two main contributions. First, we use decoder errors observed during training to adapt the imputation objective, prioritizing fragments associated with frequent decoding errors. We further use the decoder error distribution to construct easy and hard augmented views of each spectrum, enabling the decoder to learn under varying degrees of spectral corruption and missing-fragment severity. Second, we introduce a mass-aware inductive bias into self-attention by using rotary embeddings to encode pairwise mass differences between spectral peaks. Together, these components align missing-fragment recovery with decoder behavior while explicitly incorporating the mass relationships that underlie peptide fragmentation. At inference time, GyroNovo retains a standard encoder-imputer-decoder architecture and requires neither additional inputs nor auxiliary search procedures. Experiments on NovoBench show gains of about 9 percentage points in peptide-level precision and 7 percentage points in amino-acid-level precision over the state-of-the-art baseline. Code: https://github.com/UBC-NLP/gyronovo.

Thu 24 SeptMachine Learning
The gist
Peptide sequencing helps identify small protein pieces by analyzing their patterns in mass spectrometry data, but this data is often noisy and incomplete. The researchers created GyroNovo, a system that better guesses the missing pieces by focusing on parts most tied to errors during learning and by understanding the mass differences between fragments. Their approach helps the system learn even when data is messy and improves the accuracy of identifying peptides without needing a reference database. Testing showed GyroNovo performs significantly better than previous methods.
Open → 2609.30542v1