Skip to main content
Search

Boston University

5 related articles

Subscribe to updates
  1. bioRxiv

    scCont turns single-cell time courses into readable gene modules: nearest-neighbor pairing plus Shapley attribution splits EMT into interpretable transition units

    scCont breaks cell-state transitions in time-course single-cell RNA data into interpretable functional transition units: instead of explicit time labels or clustering priors, it selects positive pairs with a k-nearest-neighbor graph in expression space for contrastive learning, then uses Shapley attribution to map latent dimensions back to gene programs. Across four SERGIO simulated datasets and 13 epithelial-to-mesenchymal transition time-course datasets, its gene modules carry statistical filtering and GO enrichment annotation; on simulated data at k=10, background genes make up 7.0% of the 100 highest-attributed genes per latent, against a 73.3% chance level.

  2. Enzyme kinetics prediction learns pairwise differences: kcat R² of 0.71 under cold start, zero-shot PCC of 0.40 on external adenylate kinase data

    Enzyme kinetics prediction has relied on absolute regression over heterogeneous data, where the same enzyme-substrate system can differ by orders of magnitude across studies and models drift toward the mean. DeltaKcat recasts the task as pairwise relative learning: within one study it fixes either the enzyme or the substrate and a siamese network predicts the kinetic difference between two enzyme-substrate complexes, after which an experimentally characterized reference complex restores absolute values. Under a cold-start split, absolute kcat prediction reaches R² 0.71 and PCC 0.85, against R² 0.14 to 0.48 for DLKcat, CataPro and UniKP; on external adenylate kinase data excluded from training, zero-shot PCC is 0.40.

  3. Sampled on outcome, still predictable: a weighted gradient boosting machine matches Cox on uranium miner cancer data

    In outcome-dependent sampling, covariates are collected for only part of the cohort, so standard survival models trained on the sampled data target a distribution that differs from the cohort. A gradient boosting machine carries the sampling weights into training and tuning, selecting iterations by a weighted integrated Brier score, and the weighted empirical risk is shown to converge to the corresponding integrated Brier risk. In simulations it outperformed the Cox model in high-dimensional and nonlinear settings, and on uranium miner cancer data the test C-index was 0.803 versus 0.801 for Cox.

  4. arXiv

    Sequence models stop squeezing history into one state: semantic similarity picks the lag, 95.35% on IMDB

    A sequence-modeling framework written as a nonlinear time-delay system lets the current input's semantic similarity to past inputs set how far back the model looks, reaching 95.35% accuracy on IMDB sentiment classification with 2.6M parameters, above the 89.90% of LSTM and 83.00% of Mamba in the same table.

  5. How Generative AI Video Models Depict Depression: A Mixed Methods Study of OpenAI's Sora 2

    Using the single-word prompt "Depression," this study generated 100 videos across two access points of Sora 2 (consumer app, n=50; developer API, n=50), had two trained coders independently code narrative structure, visual environments, objects, figure demographics, and figure states, and extracted computational features (visual aesthetics, audio, semantic content, temporal dynamics) for comparison, finding a pronounced recovery bias in app-generated videos (78%, 39/50, featured arcs progressing from depressive states toward resolution versus 14%, 7/50, of API outputs), with app videos brightening over time (mean slope 2.90, SD 2.43 per second vs -0.18, SD 1.24 per second for the API; Cohen d=1.59; q<.001) and containing three times more motion (Cohen d=2.07; q<.

You’re all caught up