P279 Bridging In Vitro and In Vivo Neural Data for Ethical and Efficient Neuroscience Research
Masanori Shimono1
[1] Graduate School of Information Science and Technology, Osaka University, Osaka, Japan
E:m-shimono@ist.osaka-u.ac.jp@font-face {font-family:"Cambria Math"; panose-1:2 4 5 3 5 4 6 3 2 4; mso-font-charset:0; mso-generic-font-family:roman; mso-font-pitch:variable; mso-font-signature:-536870145 1107305727 0 0 415 0;}@font-face {font-family:游明朝; panose-1:2 2 4 0 0 0 0 0 0 0; mso-font-charset:128; mso-generic-font-family:roman; mso-font-pitch:variable; mso-font-signature:-2147482905 717749503 18 0 131231 0;}@font-face {font-family:AdvOTf23bb480; panose-1:2 11 6 4 2 2 2 2 2 4; mso-font-alt:Calibri; mso-font-charset:0; mso-generic-font-family:swiss; mso-font-pitch:auto; mso-font-signature:3 0 0 0 1 0;}@font-face {font-family:"\@游明朝"; mso-font-charset:128; mso-generic-font-family:roman; mso-font-pitch:variable; mso-font-signature:-2147482905 717749503 18 0 131231 0;}p.MsoNormal, li.MsoNormal, div.MsoNormal {mso-style-unhide:no; mso-style-qformat:yes; mso-style-parent:""; margin:0mm; text-align:justify; text-justify:inter-ideograph; mso-pagination:none; font-size:10.5pt; mso-bidi-font-size:12.0pt; font-family:"游明朝",serif; mso-ascii-font-family:游明朝; mso-ascii-theme-font:minor-latin; mso-fareast-font-family:游明朝; mso-fareast-theme-font:minor-fareast; mso-hansi-font-family:游明朝; mso-hansi-theme-font:minor-latin; mso-bidi-font-family:"Times New Roman"; mso-bidi-theme-font:minor-bidi; mso-font-kerning:1.0pt; mso-ligatures:standardcontextual;}a:link, span.MsoHyperlink {mso-style-priority:99; color:#0563C1; mso-themecolor:hyperlink; text-decoration:underline; text-underline:single;}a:visited, span.MsoHyperlinkFollowed {mso-style-noshow:yes; mso-style-priority:99; color:#954F72; mso-themecolor:followedhyperlink; text-decoration:underline; text-underline:single;}.MsoChpDefault {mso-style-type:export-only; mso-default-props:yes; font-family:"游明朝",serif; mso-bidi-font-family:"Times New Roman"; mso-bidi-theme-font:minor-bidi;}div.WordSection1 {page:WordSection1;}
Introduction
Neural activity transmits information via binary spike signals, enabling complex brain computations. While this principle is well established, accurately predicting large-scale neural activity patterns remains challenging. Integrating findings from in vitro and in vivo experiments remains unresolved, yet is crucial for advancing neuroscience and establishing ethical, efficient research methodologies.Methods
We propose a machine learning-basedmutual generationframework to enhance neural activity prediction across experimental paradigms by refining previous methodologies [1]. Specifically, we trained a model using in vitro neural data to predict in vivo activity and vice versa (Fig.1). The model, built with multi-region neural recordings, employs deep learning architectures optimized for spatiotemporal pattern recognition (Fig.1-c). The method details are related to a patent and will be explained at the venue.Results
Our results demonstrate accurate prediction of in vivo neural activity from in vitro data and vice versa (Fig.1-e). We also found that data from specific brain regions reliably predict neural activity across multiple areas, suggesting universal principles in brain information processing. These findings have implications for neural modeling, experimental design, and translational neuroscience. Furthermore, high-precision in vivo prediction from in vitro data could reduce animal experimentation, supporting the3R principles(Replacement, Reduction, Refinement).Discussion
This study sets a new standard for ethical, reproducible neuroscience research, bridging fundamental neuroscience and clinical applications.
Figure 1. Fig. 1) This figure illustrates the time duration of extracted data and data partitioning for training and testing. (a,b) In vitro (top) and in vivo (bottom) setups. (c,d) 5-minute training and 2.5-minute test segments are used for prediction. Four conditions are tested: in vitro→in vitro, in vivo→in vivo, in vitro→in vivo, and in vivo→in vitro. (e) ROC AUC scores evaluate prediction performance.
Acknowledgements
MS is supported by several MEXT fundings (21H01352, 23K18493).
@font-face {font-family:"Cambria Math"; panose-1:2 4 5 3 5 4 6 3 2 4; mso-font-charset:0; mso-generic-font-family:roman; mso-font-pitch:variable; mso-font-signature:-536870145 1107305727 0 0 415 0;}@font-face {font-family:"Yu Gothic"; panose-1:2 11 4 0 0 0 0 0 0 0; mso-font-alt:游ゴシック; mso-font-charset:128; mso-generic-font-family:swiss; mso-font-pitch:variable; mso-font-signature:-536870145 717749759 22 0 131231 0;}@font-face {font-family:"ＭＳ Ｐゴシック"; panose-1:2 11 6 0 7 2 5 8 2 4; mso-font-alt:"MS PGothic"; mso-font-charset:128; mso-generic-font-family:swiss; mso-font-pitch:variable; mso-font-signature:-536870145 1791491579 134217746 0 131231 0;}@font-face {font-family:"\@游ゴシック"; panose-1:2 11 4 0 0 0 0 0 0 0; mso-font-alt:"\@Yu Gothic"; mso-font-charset:128; mso-generic-font-family:swiss; mso-font-pitch:variable; mso-font-signature:-536870145 717749759 22 0 131231 0;}@font-face {font-family:"\@ＭＳ Ｐゴシック"; mso-font-charset:128; mso-generic-font-family:swiss; mso-font-pitch:variable; mso-font-signature:-536870145 1791491579 134217746 0 131231 0;}p.MsoNormal, li.MsoNormal, div.MsoNormal {mso-style-unhide:no; mso-style-qformat:yes; mso-style-parent:""; margin:0mm; mso-pagination:widow-orphan; font-size:12.0pt; font-family:"ＭＳ Ｐゴシック",sans-serif; mso-bidi-font-family:"ＭＳ Ｐゴシック";}.MsoChpDefault {mso-style-type:export-only; mso-default-props:yes; font-family:"游明朝",serif; mso-bidi-font-family:"Times New Roman"; mso-bidi-theme-font:minor-bidi;}div.WordSection1 {page:WordSection1;}
References
[1] Nakajima, R., Shirakami, A., Tsumura, H., Matsuda, K., Nakamura, E., & Shimono, M. (2023). Mutual generation in neuronal activity across the brain via deep neural approach, and its network interpretation.Communications Biology,6(1), 1105.
@font-face {font-family:"Cambria Math"; panose-1:2 4 5 3 5 4 6 3 2 4; mso-font-charset:0; mso-generic-font-family:roman; mso-font-pitch:variable; mso-font-signature:-536870145 1107305727 0 0 415 0;}@font-face {font-family:"Yu Gothic"; panose-1:2 11 4 0 0 0 0 0 0 0; mso-font-alt:游ゴシック; mso-font-charset:128; mso-generic-font-family:swiss; mso-font-pitch:variable; mso-font-signature:-536870145 717749759 22 0 131231 0;}@font-face {font-family:游明朝; panose-1:2 2 4 0 0 0 0 0 0 0; mso-font-charset:128; mso-generic-font-family:roman; mso-font-pitch:variable; mso-font-signature:-2147482905 717749503 18 0 131231 0;}@font-face {font-family:"\@游ゴシック"; panose-1:2 11 4 0 0 0 0 0 0 0; mso-font-alt:"\@Yu Gothic"; mso-font-charset:128; mso-generic-font-family:swiss; mso-font-pitch:variable; mso-font-signature:-536870145 717749759 22 0 131231 0;}@font-face {font-family:"\@游明朝"; mso-font-charset:128; mso-generic-font-family:roman; mso-font-pitch:variable; mso-font-signature:-2147482905 717749503 18 0 131231 0;}p.MsoNormal, li.MsoNormal, div.MsoNormal {mso-style-unhide:no; mso-style-qformat:yes; mso-style-parent:""; margin:0mm; text-align:justify; text-justify:inter-ideograph; mso-pagination:none; font-size:10.5pt; mso-bidi-font-size:12.0pt; font-family:"游明朝",serif; mso-ascii-font-family:游明朝; mso-ascii-theme-font:minor-latin; mso-fareast-font-family:游明朝; mso-fareast-theme-font:minor-fareast; mso-hansi-font-family:游明朝; mso-hansi-theme-font:minor-latin; mso-bidi-font-family:"Times New Roman"; mso-bidi-theme-font:minor-bidi; mso-font-kerning:1.0pt; mso-ligatures:standardcontextual;}.MsoChpDefault {mso-style-type:export-only; mso-default-props:yes; font-family:"游明朝",serif; mso-bidi-font-family:"Times New Roman"; mso-bidi-theme-font:minor-bidi;}div.
