Biology subjects

Harb, H.

Publications and source records attributed to Harb, H..

3 recordsLinked to original sources

bioRxiv2026

Hierarchical Temporal Transformer for Cancer Grade Prediction and Cross-Cancer Transfer Learning from Pathology Reports

Background: Language models for cancer reports usually read one document at a time and are tested on tumour types seen in training. Continuous-time sequence models address the first gap, but whether they use visit timing, not just order, is seldom tested. Methods: We developed the Hierarchical Temporal Transformer (HTT), which encodes reports with adapted BiomedBERT and reads the sequence with a cancer-type-conditioned temporal transformer. We evaluated it against best-possible AUROC ceilings on two synthetic benchmarks, one with the label stated in the text and one recoverable only from tumour sizes and visit intervals (ten seeds). Diagnostics led to an interval-aware time code (HTT-IA). On 4,786 TCGA pathology reports in 14 types, three types were withheld, and a text-only HTT was compared with a survival model. Results: On the phrase benchmark HTT reached AUROC 0.931 +/- 0.012 against 0.913 +/- 0.007 for a last-report baseline (+0.018, 95% CI -0.009 to +0.050); dates cannot raise the ceiling there. On the growth benchmark the initial time code scored 0.790, equal to a no-time model (0.787), whereas HTT-IA reached 0.843 (+0.053, 0.026 to 0.082) against ceilings of 0.894 without and 0.979 with dates. On unseen tumour types HTT reached 0.925 +/- 0.007, equal to in-distribution performance and to a single-report baseline. Text-only macro C-index was 0.592 (CALM 0.626-0.652). Conclusion: Cross-type transfer is carried by the pre-trained encoder. Visit timing is used only when the data make it identifiable and the time code is on a clinical scale. Ceilings, order-only ablations and re-dating probes are inexpensive checks for such models.

bioinformatics↗

bioRxiv2026

Hierarchical temporal transformer for cancer grade prediction and cross cancer transfer learning from pathology reports

Language models for cancer clinical reports carry two blind spots. They read each report in isolation, ignoring how a patients disease changes across visits, and they are evaluated only on cancer types present in their training data. We present the Hierarchical Temporal Transformer (HTT), a two-level architecture that addresses both. Level 1 encodes each report with BiomedBERT adapted by low-rank adaptation (LoRA). Level 2 is a temporal transformer that reads a patients full report sequence using a continuous-time positional encoding built from the measured number of days between visits, with learnable cancer-type embeddings supplying per-family conditioning. Two experiments test the two capabilities separately, since no fully open corpus contains longitudinal reports for many cancer types. On a controlled synthetic corpus of sequential radiology reports, in which progression phrases are inserted from templated trajectories, HTT reaches a validation AUROC of 0.942 against 0.881 for a single-report baseline and transfers to held-out pancreatic cancer at 0.995 against 0.949 while the two models are indistinguishable on a 60-patient test set. On 4,786 real pathology reports from the TCGA-Reports corpus spanning 14 cancer types HTT predicts tumor grade for three types withheld entirely from training, reaching AUROC 1.000 on thyroid carcinoma, 0.960 on sarcoma and 0.808 on lung squamous cell carcinoma. The mean held-out AUROC of 0.923 equals the in-distribution test AUROC of 0.923, so transfer to unseen cancer families incurred no measurable penalty. Ablation on the real corpus shows that the transfer is carried by the pre-trained encoder rather than by the temporal components, which, with one report per patient, contribute 0.39 AUROC points. Grade-related pathological language therefore appears to be learnable in a cancer-type agnostic way, which points toward unified cancer NLP systems that require no per-type retraining.

bioinformatics↗

bioRxiv2019

Untargeted Metabolomic Profiling Identifies Disease-specific Profiles in Food Allergy

BackgroundFood allergy (FA) affects an increasing proportion of children for reasons that remain obscure. Identification of pathogenic mechanisms involved in FA using untargeted metabolomic approaches may provide much needed diagnostic and prognostic disease biomarkers and improved treatment options.\n\nMethodsMass spectrometry-based untargeted metabolomic profiling was performed on serum samples of children with either FA alone, asthma alone or both FA and asthma as well as healthy pediatric controls.\n\nResultsFA subjects exhibited a disease-specific metabolomic signature as compared to both control subjects and asthmatics. In particular, FA was uniquely associated with a marked decrease in sphingolipids, as well as a number of other lipid metabolites, in the face of normal frequencies of circulating natural killer T (NKT) cells. Specific comparison of FA and asthmatic subjects revealed differences in the microbiota-sensitive aromatic amino acid and secondary bile acid metabolism. Children with both FA and asthma exhibited a metabolomic profile that aligned with that of FA alone but not asthma. Among children with FA, distinct profiles were associated with history of severe reactions and presence of multiple FA.\n\nConclusionsChildren with FA display a disease-specific metabolomic profile that is informative of disease mechanisms and severity, and which dominates in the presence of asthma. Lower levels of sphingolipids and ceramides and other metabolomic alterations observed in FA children may reflect the interplay between an altered microbiota and immune cell subsets in the gut.

immunology↗