# Long Short-Term Memory

Coarse-grained molecular dynamics gives short membrane-protein trajectories, but long-time diffusion statistics are costly to obtain. A neural stochastic model combines a transformer encoding of protein configurations, recurrent memory at multiple time scales and a stochastic latent process with learned memory to generate correlated displacements autoregressively. In the seven-PIEZO system it yields a mean anomalous diffusion exponent of 1.048±0.012 against 1.049±0.022 for MD, where the earlier VAR-SDE model gives 1.563±0.016, and its trajectories extend to 40,000 frames.

Coarse-grained molecular dynamics gives short membrane-protein trajectories, but long-time diffusion statistics are costly to obtain. A neural stochastic model combines a transformer encoding of protein configurations, recurrent memory at multiple time scales and a stochastic latent process with learned memory to generate correlated displacements autoregressively. In the seven-PIEZO system it yields a mean anomalous diffusion exponent of 1.048±0.012 against 1.049±0.022 for MD, where the earlier VAR-SDE model gives 1.563±0.016, and its trajectories extend to 40,000 frames.

A real-time OD demand calibration framework couples a data-driven demand-prediction network with a black-box microscopic traffic simulator in both directions, using an analytically tractable metamodel to carry gradients back so network parameters and demand estimates update together at each time step. In a 3×3 grid network, after link B1C1 closed at hour 4 on day 10, density MSE was 21.6 [veh/km]² versus 57.9 [veh/km]² for LimEKF, a 63% reduction; on the Tokyo expressway corridor during the 2021 Games travel-demand-management day, the online-updated version reached 0.66 [veh/km]² against 1.15 [veh/km]² for LimEKF.

A real-time OD demand calibration framework couples a data-driven demand-prediction network with a black-box microscopic traffic simulator in both directions, using an analytically tractable metamodel to carry gradients back so network parameters and demand estimates update together at each time step. In a 3×3 grid network, after link B1C1 closed at hour 4 on day 10, density MSE was 21.6 [veh/km]² versus 57.9 [veh/km]² for LimEKF, a 63% reduction; on the Tokyo expressway corridor during the 2021 Games travel-demand-management day, the online-updated version reached 0.66 [veh/km]² against 1.15 [veh/km]² for LimEKF.

Using MAWS observations, this study evaluated the bias in BMKG Ina-Flows sea surface temperature forecasts and compared three machine-learning bias-correction algorithms (SVR, LSTM, Bi-LSTM) at Karimun Jawa and Bira, finding a warm bias at both sites, with LSTM best at Karimun Jawa (RMSE 0.207, MAE 0.182, MBE -0.171, a 29.83% RMSE reduction) and Bi-LSTM best at Bira (RMSE 0.218, MAE 0.173, MBE 0.011, a 26.10% RMSE reduction), indicating that correction effectiveness is location-dependent and algorithm choice should rest on local validation.

Using MAWS observations, this study evaluated the bias in BMKG Ina-Flows sea surface temperature forecasts and compared three machine-learning bias-correction algorithms (SVR, LSTM, Bi-LSTM) at Karimun Jawa and Bira, finding a warm bias at both sites, with LSTM best at Karimun Jawa (RMSE 0.207, MAE 0.182, MBE -0.171, a 29.83% RMSE reduction) and Bi-LSTM best at Bira (RMSE 0.218, MAE 0.173, MBE 0.011, a 26.10% RMSE reduction), indicating that correction effectiveness is location-dependent and algorithm choice should rest on local validation.

The study presents a sparsely supervised AI framework in which frozen ultrasound foundation model (USFM, ViT-B) embeddings of 768 dimensions per frame are passed to a lightweight bidirectional LSTM temporal head that outputs a 0–1 frame-quality score, trained with Gaussian soft labels that peak at expert-marked key frames and decay smoothly with frame distance (width σ = 5 frames); in subject-level five-fold cross-validation on 18 subjects and 323 ultrasound videos spanning nine controlled acquisition sweep types (about 45,500 frames), it selected a usable frame in 82.2% of sweeps containing key frames with a mean minimum distance of 3.07 frames, exceeding the strongest training-free baseline (USFM feature cosine similarity, 49.2%) and a hard-label model (71.9%).

The study presents a sparsely supervised AI framework in which frozen ultrasound foundation model (USFM, ViT-B) embeddings of 768 dimensions per frame are passed to a lightweight bidirectional LSTM temporal head that outputs a 0–1 frame-quality score, trained with Gaussian soft labels that peak at expert-marked key frames and decay smoothly with frame distance (width σ = 5 frames); in subject-level five-fold cross-validation on 18 subjects and 323 ultrasound videos spanning nine controlled acquisition sweep types (about 45,500 frames), it selected a usable frame in 82.2% of sweeps containing key frames with a mean minimum distance of 3.07 frames, exceeding the strongest training-free baseline (USFM feature cosine similarity, 49.2%) and a hard-label model (71.9%).

This work generates new EGFR inhibitor candidates by fine-tuning a GPT-2 model on roughly 500,000 molecules from the ChEMBL database and benchmarking it against an LSTM network trained on the same dataset, evaluating generated compounds for validity, distinctiveness, and novelty, filtering them by Lipinski's rule of five, synthetic accessibility, and drug-likeness scores, and docking selected candidates against EGFR (PDB ID: 1M17) to assess binding affinity, finding that GPT-2 excels at producing structurally varied molecules while the LSTM generates a larger fraction of chemically valid compounds, with many candidates showing good binding interactions with EGFR.

This work generates new EGFR inhibitor candidates by fine-tuning a GPT-2 model on roughly 500,000 molecules from the ChEMBL database and benchmarking it against an LSTM network trained on the same dataset, evaluating generated compounds for validity, distinctiveness, and novelty, filtering them by Lipinski's rule of five, synthetic accessibility, and drug-likeness scores, and docking selected candidates against EGFR (PDB ID: 1M17) to assess binding affinity, finding that GPT-2 excels at producing structurally varied molecules while the LSTM generates a larger fraction of chemically valid compounds, with many candidates showing good binding interactions with EGFR.