Papers › Integrating convolutional layers and biformer network with forward-forward and...

Integrating convolutional layers and biformer network with forward-forward and backpropagation training

28 Feb 2025Scientific Reports 2025 2archive 2025-07-28

Ali Kianfar, Parvin Razzaghi, Zahra Asgari

Accurate molecular property prediction is crucial for drug discovery and computational chemistry, facilitating the identification of promising compounds and accelerating therapeutic development. Traditional machine learning falters with high-dimensional data and manual feature engineering, while existing deep learning approaches may not capture complex molecular structures, leaving a research gap. We introduce Deep-CBN, a novel framework designed to enhance molecular property prediction by capturing intricate molecular representations directly from raw data, thus improving accuracy and efficiency. Our methodology combines convolutional neural networks (CNNs) with a BiFormer attention mechanism, employing both the forward-forward algorithm and backpropagation. The model operates in three stages: (1) feature learning, extracting local features from SMILES strings using CNNs; (2) attention refinement, capturing global context with a BiFormer module enhanced by the forward-forward algorithm; and (3) prediction subnetwork tuning, fine-tuning via backpropagation. Evaluations on benchmark datasets—including Tox21, BBBP, SIDER, ClinTox, BACE, HIV, and MUV—show that Deep-CBN achieves near-perfect ROC-AUC scores, significantly outperforming state-of-the-art methods. These findings demonstrate its effectiveness in capturing complex molecular patterns, offering a robust tool to accelerate drug discovery processes.

Paper PDF Code

Code

akianfar/Deep-CBN mentioned in papertf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Computational chemistry Drug Discovery Feature Engineering Molecular Property Prediction Prediction Property Prediction

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Molecular Property Prediction	BACE	Deep-CBN	ROC-AUC	83.6	#7 of 20	Archive leaderboard	report
Molecular Property Prediction	BBBP	Deep-CBN	ROC-AUC	75.8	#12 of 29	Archive leaderboard	report
Molecular Property Prediction	HIV	Deep-CBN	ROC-AUC	97.3	#1 of 4	Archive leaderboard	report
Molecular Property Prediction	MUV	Deep-CBN	ROC-AUC	99.8	#1 of 5	Archive leaderboard	report
Molecular Property Prediction	SIDER	Deep-CBN	ROC-AUC	78.2	#2 of 19	Archive leaderboard	report
Molecular Property Prediction	Tox21	Deep-CBN	ROC-AUC	92.4	#1 of 20	Archive leaderboard	report
Molecular Property Prediction	clintox	Deep-CBN	ROC-AUC	99.2	#1 of 20	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Attention Softmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections