cs.CLOct 28, 2026

Learning Scientific Trajectories to Predict Future Biomedical Discoveries

Authors: Chia-Hsuan Chang, Brian Ondov, Jiang Lv, Lan Jiang, Yunmai Wang, Haerin Song, Xueqing Peng, Qiaozhu Mei, 

Organizations: Department of Biomedical Informatics and Data Science, Yale School of Medicine, New Haven, CT 06510, USA · Department of Cell Biology, Yale School of Medicine, New Haven, CT 06520, USA · Interdisciplinary Program in Artificial Intelligence, Seoul National University, 1 Gwanak-ro, Gwanak-gu, Seoul 08826, Republic of Korea · School of Information, University of Michigan, Ann Arbor, MI 48109, USA

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

AI co-scientists have expanded the use of large language models for generating scientific hypotheses and guiding experimental investigation. Here we investigate whether temporal patterns in the semantic representations of complete biomedical conclusions can guide hypothesis generation. We introduce ForeSCITE, a framework that identifies thematic clusters of published conclusions, estimates a direction separating earlier from more recent findings within each cluster, and projects existing conclusion embeddings along these directions. An embedding language model trained to reconstruct conclusions decodes the projected coordinates into natural-language hypotheses. Across 407 clusters derived from approximately three million pre-cutoff conclusions, we identify temporal structure and illustrate its retention after decoding. In retrospective, time-sliced evaluations, ForeSCITE increases semantic coverage beyond the historical corpus, biomedical entity-pair novelty and post-cutoff pair re-observation relative to five prompt-based and retrieval-augmented baselines. Expert review of prioritized CAR-T hypotheses identified 37 candidates as both novel and biologically plausible, and expert justifications for five selected hypotheses illustrate their biological rationale and subsequent literature support where available. These findings support temporal guidance in semantic space as a scalable mechanism for proposing biomedical hypotheses for subsequent scientific evaluation.

Figures & tables

Figure 1: Temporal extrapolation of biomedical findings for hypothesis generation. Published conclusions in natural-language space are encoded as points in a shared semantic representation space. A temporal direction learned from historical findings guides extrapolation from a reference conclusion toward a candidate representation, which an embedding language model decodes into a natural-language hypothesis. Red and blue regions distinguish historical findings and candidate future findings, respectively, separated by the knowledge cutoff. The CAR-T example illustrates how prior findings can inform a new disease-specific hypothesis. The surface and temporal arrow are conceptual illustrations of the embedding space and learned extrapolation direction.
Figure 2: ForeSCITE workflow from historical literature to candidate biomedical hypotheses. Left, Conclusions extracted from PubMed abstracts are filtered for biological relations, partitioned by the knowledge cutoff and encoded as semantic vectors. Upper middle, Thematic clustering and early–late classification identify research trend directions. Lower middle, Alignment of paired conclusion texts and embeddings produces an ELM that serves as a representation-to-text decoder. Right, Reference conclusions selected by recency or citation impact are extrapolated along the corresponding temporal directions and decoded into candidate hypotheses. Bottom, ELM alignment reconstructs the original conclusion text from its embedding through an adapter and language model. Snowflakes and flames denote frozen and trainable components, respectively. FFN, feed-forward network. Implementation and training details are provided in Methods.
Figure 3: Publication-time structure, decoded temporal movement and early–late classification of biomedical conclusions. a, Publication-time structure and decoded temporal movement across three illustrative thematic clusters. Columns show Molecular Hematologic Malignancy Research (left), Diabetic Vascular and Renal Complications (middle), and Rare Monogenic Disease Genetics (right). Top row, Distributions of publication years predicted by linear regression on 1,024-dimensional conclusion embeddings, grouped by actual publication period. Blue and orange denote pre- and post-cutoff conclusions, respectively. The separate red “Extrapolated” group shows predictions for decoded, re-embedded hypotheses generated from the most recent 5% of pre-cutoff conclusions in each cluster; the parenthetical years identify the source period, not publication dates of the generated hypotheses. Bottom row, Two-dimensional bottleneck coordinates of a publication-year-predicting MLP, with hexagonal bins colored by publication year according to the shared color bar. Light-blue markers denote ten sampled recent pre-cutoff reference conclusions per cluster, red markers denote re-embedded ELM-decoded hypotheses after extrapolation along the cluster-specific research trend direction with α=0.25\alpha=0.25 , and gray lines connect matched pairs. Both endpoints are mapped by the same fitted MLP without refitting. The paired movements generally follow the early-to-late gradient.
Figure 4: Publication-time structure, decoded temporal movement and early–late classification of biomedical conclusions (continued). b, Distribution of five-fold cross-validation accuracy for linear classifiers distinguishing early from recent conclusions across the 407 thematic clusters (mean =0.847=0.847 , s.d. =0.048=0.048 ; median =0.857=0.857 ). c, Accuracy versus cluster size, defined here as the combined number of early- and late-period conclusions used to train the classifier. Each point denotes one cluster. The red line shows a regression on log-transformed cluster size and the shaded region its 95% confidence interval (slope =0.0421=0.0421 , intercept =0.7043=0.7043 , r=0.364r=0.364 , P=3.69×10−14P=3.69\times 10^{-14} ).
Figure 5: ForeSCITE expands semantic coverage and generates novel entity pairs that align with future literature under two reference-selection strategies. a,b, Semantic space growth, ΔCov\Delta\text{Cov} , measured by the #Circles metric at radius r=0.7r=0.7 for recency-based and impact-based reference conclusions, respectively. Coverage is reported as a fraction of the coverage achieved by the 236,057 human-authored post-cutoff conclusions; error bars denote s.d. Labels above the points report the corresponding absolute coverage values. c,d, Bootstrap distributions of the Entity Novelty Ratio and Future Validation Ratio calculated from co-occurring biomedical entity pairs for the recency-based and impact-based reference conclusions, respectively. For each method and selection strategy, hypotheses were resampled with replacement 1,000 times and both ratios were recomputed for every sample (9,000 bootstrap samples per panel). Each point represents one bootstrap resample. The vertical dashed line marks the human-written post-cutoff Entity Novelty Ratio of 25.72%, calculated from 161,625 novel pairs among 628,434 pairs extracted from 236,057 conclusions. The horizontal dotted line marks the degree-weighted sampling baseline for the Future Validation Ratio (0.689%); the vertical axis is broken to display this baseline alongside the generation results. Both the recency-based and impact-based sets contain 236,057 pre-cutoff conclusions (Appendix Table A1 ). Across both analyses, ForeSCITE generations show a tradeoff between increasing entity novelty and maintaining alignment with future literature.
Figure 6: Expert assessment and temporal evidence for ForeSCITE-generated CAR-T hypotheses. a, ForeSCITE generated 1,465 CAR-T hypotheses with α=0.25\alpha=0.25 . GPT-5 assessed novelty on an ordinal scale from 0 (very low) to 5 (very high); counts and percentages are shown for each score, with scores 4 and 5 highlighted. Two immunology cell biologists reviewed all 240 hypotheses with scores of 4 or 5 (16.4% of all generated hypotheses) for novelty and biological plausibility. Expert assessment identified 37 hypotheses as both novel and plausible: 15.4% of the reviewed subset and 2.5% of all generated hypotheses. b, Temporal evidence for the NKG2D-based CAR-T hypothesis in synovial sarcoma. Pre-cutoff studies supported NKG2D-directed activity in other tumors and engineered T-cell approaches in synovial sarcoma. White, green and peach boxes denote pre-cutoff literature, the ForeSCITE-generated hypothesis and post-cutoff literature, respectively. The later preclinical study provides direct support for the disease-specific hypothesis. The timeline marks the March 31, 2023 knowledge cutoff and a buffer period ending January 1, 2024.
Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

YearRecency-based selectionImpact-based selection
202337,59110,235
2022141,50227,605
202156,96424,269
2020—21,715
2019—19,223
2018—17,431
Appendix
Table A1: Year-wise distribution of pre-cutoff reference conclusions under recency-based and impact-based selection. Impact-based references satisfy RCR >2>2 ; the listed counts total 236,057.
Figure B1: Sensitivity analysis for the HDBSCAN minimum cluster size. Density-based clustering validation (DBCV) score and the number of points assigned to noise across candidate minimum cluster sizes. A minimum cluster size of 500 retains a strong DBCV score while assigning fewer points to noise than a minimum cluster size of 250.
Figure C2: Extrapolation step size controls the tradeoff between semantic displacement and embedding diversity. a, Average cosine similarity between 236,057 paired reference and ForeSCITE-generated conclusion embeddings (left axis) and effective-rank loss of the generated embedding matrix relative to the reference matrix (right axis) across temporal step sizes α\alpha . The horizontal line and band show the mean within-cluster cosine similarity and ±1\pm 1 s.d.; the vertical line marks the estimated crossover at α∗=1.17\alpha^{*}=1.17 . Increasing α\alpha produces more distant embeddings but greater rank loss. b, Joint UMAP projection fitted to all training embeddings and ForeSCITE-generated embeddings at α∈{0.05,0.2,0.4,0.8,1.2}\alpha\in\{0.05,0.2,0.4,0.8,1.2\} . Generated embeddings broadly follow the training manifold at small α\alpha but become progressively concentrated as α\alpha increases, illustrating space collapse.
More in this topic

Scientific Hypothesis Generation

Scientific hypothesis generation develops methods for proposing testable explanations and research directions from literature, data, and experiments.

See all 91 papers

Explore similar work

CardsList

  1. Continuous Knowledge Metabolism: Generating Scientific Hypotheses from Evolving Literature

    Apr 14, 2026Jinkai Tao, Yubo Wang, Xiaoyu Liu +1Scientific DiscoveryScientific Hypothesis Generation

    TsingyuAI, Beijing, China · School of Information, Central University of Finance and Economics, Beijing, China · Thrust of Artificial Intelligence, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China +1

  2. GIANTS: Generative Insight Anticipation from Scientific Literature

    Apr 10, 2026Joy He-Yueya, Anikait Singh, Ge Gao +5Large Language Model-Guided Scientific DiscoveryResearch Idea Generation

    Stanford University · New York University

  3. DN-Hypo-Pipeline: An AI-Driven Workflow for Generating Hypotheses using Large Language Models and Scientific Explanations

    Jun 7, 2026Lei Lin, Ronghao Wang, Chunbao Zhou +2Scientific ReasoningScientific Hypothesis Generation

    Computer Network Information Center, Chinese Academy of Sciences, China