NLS segment recommended by NLSExplorer

Position Prediction type NLS indicates Nuclear Localization Signals, NIA means potential Nuclear Important Area in protein sequence. Length Recommendation score Entropy score Rcommended NLS segment
130-141 NLS 120.990212.9183TGTKRKLDEYLD
144-163 NLS 200.95533.44145QGVVGQFNKIKLRPKYKKST



Segment Similarity Information

For each NLS, we present the top 5 predicted segments from the NLS candidate library based on their similarity. The NLS candidate library was constructed by running NLSExplorer on nuclear proteins from Swiss-Prot, it contains a large number of known and potential NLSs.
NLS Similar NLS Uni ID Species Probability Position
TGTKRKLDEYLD SKKRKSP O13911 Schizosaccharomyces pombe (strain 972 / ATCC 24843) 0.9855445027351379 2-8
AMKRKL Q0UZ59 Phaeosphaeria nodorum (strain SN15 / ATCC MYA-4574 / FGSC 10173) 0.9783025979995728 1-6
RGTKRRR Q9U1Y5 Caenorhabditis elegans 0.9877992868423462 2-8
KKRAR Q4HZK7 Gibberella zeae (strain ATCC MYA-4620 / CBS 123657 / FGSC 9075 / NRRL 31084 / PH-1) 0.9893062710762024 2-6
ATKRKA Q4WRC2 Aspergillus fumigatus (strain ATCC MYA-4609 / CBS 101355 / FGSC A1100 / Af293) 0.9835029244422913 1-6
QGVVGQFNKIKLRPKYKKST PKRVLKG Q5AR44 Emericella nidulans (strain FGSC A4 / ATCC 38163 / CBS 112.46 / NRRL 194 / M139) 0.9051908254623413 1-7
QLRKRKRV Q02749 Saccharomyces cerevisiae (strain ATCC 204508 / S288c) 0.9466467499732971 3-10
KKLKGKRSKI P39529 Saccharomyces cerevisiae (strain ATCC 204508 / S288c) 0.9561310410499573 14-23
KKRGVL Q68F54 Xenopus laevis 0.9105245471000671 1-6
ASGKKPGTKGTKRHRKIT Q09922 Schizosaccharomyces pombe (strain 972 / ATCC 24843) 0.9869093298912048 2-19



Potential segment important for nuclear transport

In addition to predicting NLSs, our model also identifies other motifs or domains that may influence nuclear transport by using the exploration module-A2KA. These segments could represent novel types of NLSs that has not included in the training dataset of recommendation system or nuclear transport-related elements, such as NES.

Position Type NLS indicates Nuclear Localization Signals, NIA means potential Nuclear Important Area in protein sequence. Length Recommendation score Entropy score Segment
455-460 NIA 60.014611.25163KKVKKE
531-538 NIA 80.013872.5VIGKVNRR
226-235 NIA 100.012692.37095FVVKKSEVKP
564-579 NIA 160.010943.25AITFAEQKLNCKYKKF
418-423 NIA 60.010482.25163VNKKST
406-411 NIA 60.009152.25163PNKYVV
518-526 NIA 90.008792.9477VIQKYNRFK
555-562 NIA 80.00732.40564LQGLVPLS
540-552 NIA 130.006812.4997STTLHNNLLKLLA
259-264 NIA 60.006672.25163DNRVFV
13-22 NIA 100.006562.64644ASTPSRASFD
389-394 NIA 60.00632.58496VSQILK
508-513 NIA 60.006282.58496GEIKDV
25-36 NIA 120.005813.25163YSEFCDKQPNDY
211-216 NIA 60.005682.25163SNRFSD
170-175 NIA 60.005612.58496LEQTIN
301-310 NIA 100.005312.72193NCKKCHFVDV
489-503 NIA 150.005152.92323KNEERLTIAKKNKEF



Attention distribution along the sequence

The distribution of attention highlights the focus of our computational model on the sequence, with higher attention points indicating a greater likelihood of influencing the sequence's ability to localize to the nucleus.





Sequence visualization according to the attention map

NLSExplorer's inference focus is automatically presented intuitively in the prediction result. It provides a detailed profile of the nuclear localization relevance for each amino acid site, demonstrating both the inherent reliability of the learning model and the potential biological meaningful sites.





The structure statistical of recommended segment

Regarding the large-scale recommended segments, we compile the structural composition of each segment.





The recommended segment visualization on 3d structure

The green, blue, and yellow regions refer to the top three recommended NLS, while the red region represents other regions important for nuclear transport(top-5)